update on regression analysis
This commit is contained in:
mhjensen
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -222,7 +251,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Aug 24, 2018</h4></center> <!-- date -->
|
||||
<center><h4>Sep 6, 2018</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
|
||||
@@ -246,7 +275,7 @@ MathJax.Hub.Config({
|
||||
<li><a href="._Regression-bs008.html">9</a></li>
|
||||
<li><a href="._Regression-bs009.html">10</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs001.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -243,7 +272,7 @@ A regression model aims at finding a likelihood function \( p(y\vert \hat{x}) \)
|
||||
<li><a href="._Regression-bs009.html">10</a></li>
|
||||
<li><a href="._Regression-bs010.html">11</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs002.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,19 +232,29 @@ MathJax.Hub.Config({
|
||||
<a name="part0002"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec1" class="anchor">General linear models </h2>
|
||||
<h2 id="___sec1" class="anchor">Regression analysis, overarching aims II </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
Before we proceed let us study a case from linear algebra where we aim at fitting a set of data \( \hat{y}=[y_0,y_1,\dots,y_{n-1}] \). We could think of these data as a result of an experiment or a complicated numerical experiment. These data are functions of a series of variables \( \hat{x}=[x_0,x_1,\dots,x_{n-1}] \), that is \( y_i = y(x_i) \) with \( i=0,1,2,\dots,n-1 \). The variables \( x_i \) could represent physical quantities like time, temperature, position etc. We assume that \( y(x) \) is a smooth function.
|
||||
|
||||
<p>
|
||||
Since obtaining these data points may not be trivial, we want to use these data to fit a function which can allow us to make predictions for values of \( y \) which are not in the present set. The perhaps simplest approach is to assume we can parametrize our function in terms of a polynomial of degree \( n-1 \) with \( n \) points, that is
|
||||
$$
|
||||
y=y(x) \rightarrow y(x_i)=\tilde{y}_i+\epsilon_i=\sum_{j=0}^{n-1} \beta_i x_i^j+\epsilon_i,
|
||||
$$
|
||||
|
||||
where \( \epsilon_i \) is the error in our approximation.
|
||||
Consider an experiment in which \( p \) characteristics of \( n \) samples are
|
||||
measured. The data from this experiment are denoted \( \mathbf{X} \), with
|
||||
\( \mathbf{X} \) as above. The matrix \( \mathbf{X} \) is called the <em>design
|
||||
matrix</em>. Additional information of the samples is available in the
|
||||
form of \( \mathbf{Y} \) (also as above). The variable \( \mathbf{Y} \) is
|
||||
generally referred to as the <em>response variable</em>. The aim of
|
||||
regression analysis is to explain \( \mathbf{Y} \) in terms of
|
||||
\( \mathbf{X} \) through a functional relationship like \( Y_i =
|
||||
f(\mathbf{X}_{i,\ast}) \). When no prior knowledge on the form of
|
||||
\( f(\cdot) \) is available, it is common to assume a linear relationship
|
||||
between \( \mathbf{X} \) and \( \mathbf{Y} \). This assumption gives rise to
|
||||
the <em>linear regression model</em> where \( \beta = (\beta_1, \ldots,
|
||||
\beta_p)^{\top} \) is the <em>regression parameter</em>. The parameter
|
||||
\( \beta_j \), \( j=1, \ldots, p \), represents the effect size of covariate
|
||||
\( j \) on the response. That is, for each unit change in covariate \( j \)
|
||||
(while keeping the other covariates fixed) the observed change in the
|
||||
response is equal to \( \beta_j \).
|
||||
|
||||
<p>
|
||||
</div>
|
||||
@@ -240,7 +279,7 @@ where \( \epsilon_i \) is the error in our approximation.
|
||||
<li><a href="._Regression-bs010.html">11</a></li>
|
||||
<li><a href="._Regression-bs011.html">12</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs003.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,20 +232,21 @@ MathJax.Hub.Config({
|
||||
<a name="part0003"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec2" class="anchor">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec2" class="anchor">General linear models </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
For every set of values \( y_i,x_i \) we have thus the corresponding set of equations
|
||||
Before we proceed let us study a case from linear algebra where we aim at fitting a set of data \( \hat{y}=[y_0,y_1,\dots,y_{n-1}] \). We could think of these data as a result of an experiment or a complicated numerical experiment. These data are functions of a series of variables \( \hat{x}=[x_0,x_1,\dots,x_{n-1}] \), that is \( y_i = y(x_i) \) with \( i=0,1,2,\dots,n-1 \). The variables \( x_i \) could represent physical quantities like time, temperature, position etc. We assume that \( y(x) \) is a smooth function.
|
||||
|
||||
<p>
|
||||
Since obtaining these data points may not be trivial, we want to use these data to fit a function which can allow us to make predictions for values of \( y \) which are not in the present set. The perhaps simplest approach is to assume we can parametrize our function in terms of a polynomial of degree \( n-1 \) with \( n \) points, that is
|
||||
$$
|
||||
\begin{align*}
|
||||
y_0&=\beta_0+\beta_1x_0^1+\beta_2x_0^2+\dots+\beta_{n-1}x_0^{n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0+\beta_1x_1^1+\beta_2x_1^2+\dots+\beta_{n-1}x_1^{n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0+\beta_1x_2^1+\beta_2x_2^2+\dots+\beta_{n-1}x_2^{n-1}+\epsilon_2\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0+\beta_1x_{n-1}^1+\beta_2x_{n-1}^2+\dots+\beta_1x_{n-1}^{n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
y=y(x) \rightarrow y(x_i)=\tilde{y}_i+\epsilon_i=\sum_{j=0}^{n-1} \beta_i x_i^j+\epsilon_i,
|
||||
$$
|
||||
|
||||
where \( \epsilon_i \) is the error in our approximation.
|
||||
|
||||
<p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -240,7 +270,7 @@ $$
|
||||
<li><a href="._Regression-bs011.html">12</a></li>
|
||||
<li><a href="._Regression-bs012.html">13</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs004.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,40 +232,19 @@ MathJax.Hub.Config({
|
||||
<a name="part0004"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec3" class="anchor">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<h2 id="___sec3" class="anchor">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
Defining the vectors
|
||||
For every set of values \( y_i,x_i \) we have thus the corresponding set of equations
|
||||
$$
|
||||
\hat{y} = [y_0,y_1, y_2,\dots, y_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and
|
||||
$$
|
||||
\hat{\beta} = [\beta_0,\beta_1, \beta_2,\dots, \beta_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and
|
||||
$$
|
||||
\hat{\epsilon} = [\epsilon_0,\epsilon_1, \epsilon_2,\dots, \epsilon_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and the matrix
|
||||
$$
|
||||
\hat{X}=
|
||||
\begin{bmatrix}
|
||||
1& x_{0}^1 &x_{0}^2& \dots & \dots &x_{0}^{n-1}\\
|
||||
1& x_{1}^1 &x_{1}^2& \dots & \dots &x_{1}^{n-1}\\
|
||||
1& x_{2}^1 &x_{2}^2& \dots & \dots &x_{2}^{n-1}\\
|
||||
\dots& \dots &\dots& \dots & \dots &\dots\\
|
||||
1& x_{n-1}^1 &x_{n-1}^2& \dots & \dots &x_{n-1}^{n-1}\\
|
||||
\end{bmatrix}
|
||||
$$
|
||||
|
||||
we can rewrite our equations as
|
||||
$$
|
||||
\hat{y} = \hat{X}\hat{\beta}+\hat{\epsilon}.
|
||||
\begin{align*}
|
||||
y_0&=\beta_0+\beta_1x_0^1+\beta_2x_0^2+\dots+\beta_{n-1}x_0^{n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0+\beta_1x_1^1+\beta_2x_1^2+\dots+\beta_{n-1}x_1^{n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0+\beta_1x_2^1+\beta_2x_2^2+\dots+\beta_{n-1}x_2^{n-1}+\epsilon_2\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0+\beta_1x_{n-1}^1+\beta_2x_{n-1}^2+\dots+\beta_1x_{n-1}^{n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
@@ -262,7 +270,7 @@ $$
|
||||
<li><a href="._Regression-bs012.html">13</a></li>
|
||||
<li><a href="._Regression-bs013.html">14</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs005.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,22 +232,40 @@ MathJax.Hub.Config({
|
||||
<a name="part0005"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec4" class="anchor">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec4" class="anchor">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
We are obviously not limited to the above polynomial. We could replace the various powers of \( x \) with elements of Fourier series, that is, instead of \( x_i^j \) we could have \( \cos{(j x_i)} \) or \( \sin{(j x_i)} \), or time series or other orthogonal functions.
|
||||
For every set of values \( y_i,x_i \) we can then generalize the equations to
|
||||
Defining the vectors
|
||||
$$
|
||||
\begin{align*}
|
||||
y_0&=\beta_0x_{00}+\beta_1x_{01}+\beta_2x_{02}+\dots+\beta_{n-1}x_{0n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0x_{10}+\beta_1x_{11}+\beta_2x_{12}+\dots+\beta_{n-1}x_{1n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0x_{20}+\beta_1x_{21}+\beta_2x_{22}+\dots+\beta_{n-1}x_{2n-1}+\epsilon_2\\
|
||||
\dots & \dots \\
|
||||
y_{i}&=\beta_0x_{i0}+\beta_1x_{i1}+\beta_2x_{i2}+\dots+\beta_{n-1}x_{in-1}+\epsilon_i\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0x_{n-1,0}+\beta_1x_{n-1,2}+\beta_2x_{n-1,2}+\dots+\beta_1x_{n-1,n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
\hat{y} = [y_0,y_1, y_2,\dots, y_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and
|
||||
$$
|
||||
\hat{\beta} = [\beta_0,\beta_1, \beta_2,\dots, \beta_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and
|
||||
$$
|
||||
\hat{\epsilon} = [\epsilon_0,\epsilon_1, \epsilon_2,\dots, \epsilon_{n-1}]^T,
|
||||
$$
|
||||
|
||||
and the matrix
|
||||
$$
|
||||
\hat{X}=
|
||||
\begin{bmatrix}
|
||||
1& x_{0}^1 &x_{0}^2& \dots & \dots &x_{0}^{n-1}\\
|
||||
1& x_{1}^1 &x_{1}^2& \dots & \dots &x_{1}^{n-1}\\
|
||||
1& x_{2}^1 &x_{2}^2& \dots & \dots &x_{2}^{n-1}\\
|
||||
\dots& \dots &\dots& \dots & \dots &\dots\\
|
||||
1& x_{n-1}^1 &x_{n-1}^2& \dots & \dots &x_{n-1}^{n-1}\\
|
||||
\end{bmatrix}
|
||||
$$
|
||||
|
||||
we can rewrite our equations as
|
||||
$$
|
||||
\hat{y} = \hat{X}\hat{\beta}+\hat{\epsilon}.
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
@@ -245,7 +292,7 @@ $$
|
||||
<li><a href="._Regression-bs013.html">14</a></li>
|
||||
<li><a href="._Regression-bs014.html">15</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs006.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,24 +236,19 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
We redefine in turn the matrix \( \hat{X} \) as
|
||||
We are obviously not limited to the above polynomial. We could replace the various powers of \( x \) with elements of Fourier series, that is, instead of \( x_i^j \) we could have \( \cos{(j x_i)} \) or \( \sin{(j x_i)} \), or time series or other orthogonal functions.
|
||||
For every set of values \( y_i,x_i \) we can then generalize the equations to
|
||||
$$
|
||||
\hat{X}=
|
||||
\begin{bmatrix}
|
||||
x_{00}& x_{01} &x_{02}& \dots & \dots &x_{0,n-1}\\
|
||||
x_{10}& x_{11} &x_{12}& \dots & \dots &x_{1,n-1}\\
|
||||
x_{20}& x_{21} &x_{22}& \dots & \dots &x_{2,n-1}\\
|
||||
\dots& \dots &\dots& \dots & \dots &\dots\\
|
||||
x_{n-1,0}& x_{n-1,1} &x_{n-1,2}& \dots & \dots &x_{n-1,n-1}\\
|
||||
\end{bmatrix}
|
||||
\begin{align*}
|
||||
y_0&=\beta_0x_{00}+\beta_1x_{01}+\beta_2x_{02}+\dots+\beta_{n-1}x_{0n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0x_{10}+\beta_1x_{11}+\beta_2x_{12}+\dots+\beta_{n-1}x_{1n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0x_{20}+\beta_1x_{21}+\beta_2x_{22}+\dots+\beta_{n-1}x_{2n-1}+\epsilon_2\\
|
||||
\dots & \dots \\
|
||||
y_{i}&=\beta_0x_{i0}+\beta_1x_{i1}+\beta_2x_{i2}+\dots+\beta_{n-1}x_{in-1}+\epsilon_i\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0x_{n-1,0}+\beta_1x_{n-1,2}+\beta_2x_{n-1,2}+\dots+\beta_1x_{n-1,n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
and without loss of generality we rewrite again our equations as
|
||||
$$
|
||||
\hat{y} = \hat{X}\hat{\beta}+\hat{\epsilon}.
|
||||
$$
|
||||
|
||||
The left-hand side of this equation forms know. Our error vector \( \hat{\epsilon} \) and the parameter vector \( \hat{\beta} \) are our unknow quantities. How can we obtain the optimal set of \( \beta_i \) values?
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -251,7 +275,7 @@ The left-hand side of this equation forms know. Our error vector \( \hat{\epsilo
|
||||
<li><a href="._Regression-bs014.html">15</a></li>
|
||||
<li><a href="._Regression-bs015.html">16</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs007.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,22 +232,28 @@ MathJax.Hub.Config({
|
||||
<a name="part0007"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec6" class="anchor">Optimizing our parameters </h2>
|
||||
<h2 id="___sec6" class="anchor">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
We have defined the matrix \( \hat{X} \)
|
||||
We redefine in turn the matrix \( \hat{X} \) as
|
||||
$$
|
||||
\begin{align*}
|
||||
y_0&=\beta_0x_{00}+\beta_1x_{01}+\beta_2x_{02}+\dots+\beta_{n-1}x_{0n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0x_{10}+\beta_1x_{11}+\beta_2x_{12}+\dots+\beta_{n-1}x_{1n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0x_{20}+\beta_1x_{21}+\beta_2x_{22}+\dots+\beta_{n-1}x_{2n-1}+\epsilon_1\\
|
||||
\dots & \dots \\
|
||||
y_{i}&=\beta_0x_{i0}+\beta_1x_{i1}+\beta_2x_{i2}+\dots+\beta_{n-1}x_{in-1}+\epsilon_1\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0x_{n-1,0}+\beta_1x_{n-1,2}+\beta_2x_{n-1,2}+\dots+\beta_1x_{n-1,n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
\hat{X}=
|
||||
\begin{bmatrix}
|
||||
x_{00}& x_{01} &x_{02}& \dots & \dots &x_{0,n-1}\\
|
||||
x_{10}& x_{11} &x_{12}& \dots & \dots &x_{1,n-1}\\
|
||||
x_{20}& x_{21} &x_{22}& \dots & \dots &x_{2,n-1}\\
|
||||
\dots& \dots &\dots& \dots & \dots &\dots\\
|
||||
x_{n-1,0}& x_{n-1,1} &x_{n-1,2}& \dots & \dots &x_{n-1,n-1}\\
|
||||
\end{bmatrix}
|
||||
$$
|
||||
|
||||
and without loss of generality we rewrite again our equations as
|
||||
$$
|
||||
\hat{y} = \hat{X}\hat{\beta}+\hat{\epsilon}.
|
||||
$$
|
||||
|
||||
The left-hand side of this equation forms know. Our error vector \( \hat{\epsilon} \) and the parameter vector \( \hat{\beta} \) are our unknow quantities. How can we obtain the optimal set of \( \beta_i \) values?
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -246,7 +281,7 @@ $$
|
||||
<li><a href="._Regression-bs015.html">16</a></li>
|
||||
<li><a href="._Regression-bs016.html">17</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs008.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,23 +232,21 @@ MathJax.Hub.Config({
|
||||
<a name="part0008"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec7" class="anchor">Optimizing our parameters, more details </h2>
|
||||
<h2 id="___sec7" class="anchor">Optimizing our parameters </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
We well use this matrix to define the approximation \( \hat{\tilde{y}} \) via the unknown quantity \( \hat{\beta} \) as
|
||||
We have defined the matrix \( \hat{X} \)
|
||||
$$
|
||||
\hat{\tilde{y}}= \hat{X}\hat{\beta},
|
||||
$$
|
||||
|
||||
and in order to find the optimal parameters \( \beta_i \) instead of solving the above linear algebra problem, we define a function which gives a measure of the spread between the values \( y_i \) (which represent hopefully the exact values) and the parametrized values \( \tilde{y}_i \), namely
|
||||
$$
|
||||
Q(\hat{\beta})=\sum_{i=0}^{n-1}\left(y_i-\tilde{y}_i\right)^2=\left(\hat{y}-\hat{\tilde{y}}\right)^T\left(\hat{y}-\hat{\tilde{y}}\right),
|
||||
$$
|
||||
|
||||
or using the matrix \( \hat{X} \) as
|
||||
$$
|
||||
Q(\hat{\beta})=\left(\hat{y}-\hat{X}\hat{\beta}\right)^T\left(\hat{y}-\hat{X}\hat{\beta}\right).
|
||||
\begin{align*}
|
||||
y_0&=\beta_0x_{00}+\beta_1x_{01}+\beta_2x_{02}+\dots+\beta_{n-1}x_{0n-1}+\epsilon_0\\
|
||||
y_1&=\beta_0x_{10}+\beta_1x_{11}+\beta_2x_{12}+\dots+\beta_{n-1}x_{1n-1}+\epsilon_1\\
|
||||
y_2&=\beta_0x_{20}+\beta_1x_{21}+\beta_2x_{22}+\dots+\beta_{n-1}x_{2n-1}+\epsilon_1\\
|
||||
\dots & \dots \\
|
||||
y_{i}&=\beta_0x_{i0}+\beta_1x_{i1}+\beta_2x_{i2}+\dots+\beta_{n-1}x_{in-1}+\epsilon_1\\
|
||||
\dots & \dots \\
|
||||
y_{n-1}&=\beta_0x_{n-1,0}+\beta_1x_{n-1,2}+\beta_2x_{n-1,2}+\dots+\beta_1x_{n-1,n-1}+\epsilon_{n-1}.\\
|
||||
\end{align*}
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
@@ -249,7 +276,7 @@ $$
|
||||
<li><a href="._Regression-bs016.html">17</a></li>
|
||||
<li><a href="._Regression-bs017.html">18</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs009.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,39 +232,24 @@ MathJax.Hub.Config({
|
||||
<a name="part0009"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec8" class="anchor">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec8" class="anchor">Optimizing our parameters, more details </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
The function
|
||||
We well use this matrix to define the approximation \( \hat{\tilde{y}} \) via the unknown quantity \( \hat{\beta} \) as
|
||||
$$
|
||||
Q(\hat{\beta})=\left(\hat{y}-\hat{X}\hat{\beta}\right)^T\left(\hat{y}-\hat{X}\hat{\beta}\right),
|
||||
\hat{\tilde{y}}= \hat{X}\hat{\beta},
|
||||
$$
|
||||
|
||||
can be linked to the variance of the quantity \( y_i \) if we interpret the latter as the mean value of for example a numerical experiment. When linking below with the maximum likelihood approach below, we will indeed interpret \( y_i \) as a mean value
|
||||
and in order to find the optimal parameters \( \beta_i \) instead of solving the above linear algebra problem, we define a function which gives a measure of the spread between the values \( y_i \) (which represent hopefully the exact values) and the parametrized values \( \tilde{y}_i \), namely
|
||||
$$
|
||||
y_{i}=\langle y_i \rangle = \beta_0x_{i,0}+\beta_1x_{i,1}+\beta_2x_{i,2}+\dots+\beta_{n-1}x_{i,n-1}+\epsilon_i,
|
||||
Q(\hat{\beta})=\sum_{i=0}^{n-1}\left(y_i-\tilde{y}_i\right)^2=\left(\hat{y}-\hat{\tilde{y}}\right)^T\left(\hat{y}-\hat{\tilde{y}}\right),
|
||||
$$
|
||||
|
||||
where \( \langle y_i \rangle \) is the mean value. Keep in mind also that till now we have treated \( y_i \) as the exact value. Normally, the response (dependent or outcome) variable \( y_i \) the outcome of a numerical experiment or another type of experiment and is thus only an approximation to the true value. It is then always accompanied by an error estimate, often limited to a statistical error estimate given by the standard deviation discussed earlier. In the discussion here we will treat \( y_i \) as our exact value for the response variable.
|
||||
|
||||
<p>
|
||||
In order to find the parameters \( \beta_i \) we will then minimize the spread of \( Q(\hat{\beta}) \) by requiring
|
||||
or using the matrix \( \hat{X} \) as
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \beta_j} = \frac{\partial }{\partial \beta_j}\left[ \sum_{i=0}^{n-1}\left(y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}\right)^2\right]=0,
|
||||
Q(\hat{\beta})=\left(\hat{y}-\hat{X}\hat{\beta}\right)^T\left(\hat{y}-\hat{X}\hat{\beta}\right).
|
||||
$$
|
||||
|
||||
which results in
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \beta_j} = -2\left[ \sum_{i=0}^{n-1}x_{ij}\left(y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}\right)\right]=0,
|
||||
$$
|
||||
|
||||
or in a matrix-vector form as
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right).
|
||||
$$
|
||||
|
||||
<p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -265,7 +279,7 @@ $$
|
||||
<li><a href="._Regression-bs017.html">18</a></li>
|
||||
<li><a href="._Regression-bs018.html">19</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs010.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,19 +236,32 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
We can rewrite
|
||||
The function
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right),
|
||||
Q(\hat{\beta})=\left(\hat{y}-\hat{X}\hat{\beta}\right)^T\left(\hat{y}-\hat{X}\hat{\beta}\right),
|
||||
$$
|
||||
|
||||
as
|
||||
can be linked to the variance of the quantity \( y_i \) if we interpret the latter as the mean value of for example a numerical experiment. When linking below with the maximum likelihood approach below, we will indeed interpret \( y_i \) as a mean value
|
||||
$$
|
||||
\hat{X}^T\hat{y} = \hat{X}^T\hat{X}\hat{\beta},
|
||||
y_{i}=\langle y_i \rangle = \beta_0x_{i,0}+\beta_1x_{i,1}+\beta_2x_{i,2}+\dots+\beta_{n-1}x_{i,n-1}+\epsilon_i,
|
||||
$$
|
||||
|
||||
and if the matrix \( \hat{X}^T\hat{X} \) is invertible we have the solution
|
||||
where \( \langle y_i \rangle \) is the mean value. Keep in mind also that till now we have treated \( y_i \) as the exact value. Normally, the response (dependent or outcome) variable \( y_i \) the outcome of a numerical experiment or another type of experiment and is thus only an approximation to the true value. It is then always accompanied by an error estimate, often limited to a statistical error estimate given by the standard deviation discussed earlier. In the discussion here we will treat \( y_i \) as our exact value for the response variable.
|
||||
|
||||
<p>
|
||||
In order to find the parameters \( \beta_i \) we will then minimize the spread of \( Q(\hat{\beta}) \) by requiring
|
||||
$$
|
||||
\hat{\beta} =\left(\hat{X}^T\hat{X}\right)^{-1}\hat{X}^T\hat{y}.
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \beta_j} = \frac{\partial }{\partial \beta_j}\left[ \sum_{i=0}^{n-1}\left(y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}\right)^2\right]=0,
|
||||
$$
|
||||
|
||||
which results in
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \beta_j} = -2\left[ \sum_{i=0}^{n-1}x_{ij}\left(y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}\right)\right]=0,
|
||||
$$
|
||||
|
||||
or in a matrix-vector form as
|
||||
$$
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right).
|
||||
$$
|
||||
|
||||
<p>
|
||||
@@ -253,7 +295,7 @@ $$
|
||||
<li><a href="._Regression-bs018.html">19</a></li>
|
||||
<li><a href="._Regression-bs019.html">20</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs011.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,23 +236,21 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
The residuals \( \hat{\epsilon} \) are in turn given by
|
||||
We can rewrite
|
||||
$$
|
||||
\hat{\epsilon} = \hat{y}-\hat{\tilde{y}} = \hat{y}-\hat{X}\hat{\beta},
|
||||
\frac{\partial Q(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right),
|
||||
$$
|
||||
|
||||
and with
|
||||
as
|
||||
$$
|
||||
\hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right)= 0,
|
||||
\hat{X}^T\hat{y} = \hat{X}^T\hat{X}\hat{\beta},
|
||||
$$
|
||||
|
||||
we have
|
||||
and if the matrix \( \hat{X}^T\hat{X} \) is invertible we have the solution
|
||||
$$
|
||||
\hat{X}^T\hat{\epsilon}=\hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right)= 0,
|
||||
\hat{\beta} =\left(\hat{X}^T\hat{X}\right)^{-1}\hat{X}^T\hat{y}.
|
||||
$$
|
||||
|
||||
meaning that the solution for \( \hat{\beta} \) is the one which minimizes the residuals. Later we will link this with the maximum likelihood approach.
|
||||
|
||||
<p>
|
||||
</div>
|
||||
</div>
|
||||
@@ -255,7 +282,7 @@ meaning that the solution for \( \hat{\beta} \) is the one which minimizes the r
|
||||
<li><a href="._Regression-bs019.html">20</a></li>
|
||||
<li><a href="._Regression-bs020.html">21</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs012.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,21 +232,26 @@ MathJax.Hub.Config({
|
||||
<a name="part0012"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec11" class="anchor">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec11" class="anchor">Interpretations and optimizing our parameters </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
Normally, the response (dependent or outcome) variable \( y_i \) the outcome of a numerical experiment or another type of experiment and is thus only an approximation to the true value. It is then always accompanied by an error estimate, often limited to a statistical error estimate given by the standard deviation discussed earlier. In the discussion here we will treat \( y_i \) as our exact value for the response variable.
|
||||
|
||||
<p>
|
||||
Introducing the standard deviation \( \sigma_i \) for each measurement \( y_i \), we define now the \( \chi^2 \) function as
|
||||
The residuals \( \hat{\epsilon} \) are in turn given by
|
||||
$$
|
||||
\chi^2(\hat{\beta})=\sum_{i=0}^{n-1}\frac{\left(y_i-\tilde{y}_i\right)^2}{\sigma_i^2}=\left(\hat{y}-\hat{\tilde{y}}\right)^T\frac{1}{\hat{\Sigma^2}}\left(\hat{y}-\hat{\tilde{y}}\right),
|
||||
\hat{\epsilon} = \hat{y}-\hat{\tilde{y}} = \hat{y}-\hat{X}\hat{\beta},
|
||||
$$
|
||||
|
||||
where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as matrix elements.
|
||||
and with
|
||||
$$
|
||||
\hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right)= 0,
|
||||
$$
|
||||
|
||||
we have
|
||||
$$
|
||||
\hat{X}^T\hat{\epsilon}=\hat{X}^T\left( \hat{y}-\hat{X}\hat{\beta}\right)= 0,
|
||||
$$
|
||||
|
||||
meaning that the solution for \( \hat{\beta} \) is the one which minimizes the residuals. Later we will link this with the maximum likelihood approach.
|
||||
|
||||
<p>
|
||||
</div>
|
||||
@@ -250,7 +284,7 @@ where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as
|
||||
<li><a href="._Regression-bs020.html">21</a></li>
|
||||
<li><a href="._Regression-bs021.html">22</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs013.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -209,22 +238,17 @@ MathJax.Hub.Config({
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
In order to find the parameters \( \beta_i \) we will then minimize the spread of \( \chi^2(\hat{\beta}) \) by requiring
|
||||
Normally, the response (dependent or outcome) variable \( y_i \) the outcome of a numerical experiment or another type of experiment and is thus only an approximation to the true value. It is then always accompanied by an error estimate, often limited to a statistical error estimate given by the standard deviation discussed earlier. In the discussion here we will treat \( y_i \) as our exact value for the response variable.
|
||||
|
||||
<p>
|
||||
Introducing the standard deviation \( \sigma_i \) for each measurement \( y_i \), we define now the \( \chi^2 \) function as
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_j} = \frac{\partial }{\partial \beta_j}\left[ \sum_{i=0}^{n-1}\left(\frac{y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}}{\sigma_i}\right)^2\right]=0,
|
||||
\chi^2(\hat{\beta})=\sum_{i=0}^{n-1}\frac{\left(y_i-\tilde{y}_i\right)^2}{\sigma_i^2}=\left(\hat{y}-\hat{\tilde{y}}\right)^T\frac{1}{\hat{\Sigma^2}}\left(\hat{y}-\hat{\tilde{y}}\right),
|
||||
$$
|
||||
|
||||
which results in
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_j} = -2\left[ \sum_{i=0}^{n-1}\frac{x_{ij}}{\sigma_i}\left(\frac{y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}}{\sigma_i}\right)\right]=0,
|
||||
$$
|
||||
where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as matrix elements.
|
||||
|
||||
or in a matrix-vector form as
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{A}^T\left( \hat{b}-\hat{A}\hat{\beta}\right).
|
||||
$$
|
||||
|
||||
where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix elements \( a_{ij} = x_{ij}/\sigma_i \) and the vector \( \hat{b} \) with elements \( b_i = y_i/\sigma_i \).
|
||||
<p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -255,7 +279,7 @@ where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix
|
||||
<li><a href="._Regression-bs021.html">22</a></li>
|
||||
<li><a href="._Regression-bs022.html">23</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs014.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -209,20 +238,22 @@ MathJax.Hub.Config({
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
We can rewrite
|
||||
In order to find the parameters \( \beta_i \) we will then minimize the spread of \( \chi^2(\hat{\beta}) \) by requiring
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{A}^T\left( \hat{b}-\hat{A}\hat{\beta}\right),
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_j} = \frac{\partial }{\partial \beta_j}\left[ \sum_{i=0}^{n-1}\left(\frac{y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}}{\sigma_i}\right)^2\right]=0,
|
||||
$$
|
||||
|
||||
as
|
||||
which results in
|
||||
$$
|
||||
\hat{A}^T\hat{b} = \hat{A}^T\hat{A}\hat{\beta},
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_j} = -2\left[ \sum_{i=0}^{n-1}\frac{x_{ij}}{\sigma_i}\left(\frac{y_i-\beta_0x_{i,0}-\beta_1x_{i,1}-\beta_2x_{i,2}-\dots-\beta_{n-1}x_{i,n-1}}{\sigma_i}\right)\right]=0,
|
||||
$$
|
||||
|
||||
and if the matrix \( \hat{A}^T\hat{A} \) is invertible we have the solution
|
||||
or in a matrix-vector form as
|
||||
$$
|
||||
\hat{\beta} =\left(\hat{A}^T\hat{A}\right)^{-1}\hat{A}^T\hat{b}.
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{A}^T\left( \hat{b}-\hat{A}\hat{\beta}\right).
|
||||
$$
|
||||
|
||||
where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix elements \( a_{ij} = x_{ij}/\sigma_i \) and the vector \( \hat{b} \) with elements \( b_i = y_i/\sigma_i \).
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -253,7 +284,7 @@ $$
|
||||
<li><a href="._Regression-bs022.html">23</a></li>
|
||||
<li><a href="._Regression-bs023.html">24</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs015.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -209,24 +238,19 @@ MathJax.Hub.Config({
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
If we then introduce the matrix
|
||||
We can rewrite
|
||||
$$
|
||||
\hat{H} = \left(\hat{A}^T\hat{A}\right)^{-1},
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \hat{\beta}} = 0 = \hat{A}^T\left( \hat{b}-\hat{A}\hat{\beta}\right),
|
||||
$$
|
||||
|
||||
we have then the following expression for the parameters \( \beta_j \) (the matrix elements of \( \hat{H} \) are \( h_{ij} \))
|
||||
as
|
||||
$$
|
||||
\beta_j = \sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}\frac{y_i}{\sigma_i}\frac{x_{ik}}{\sigma_i} = \sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}b_ia_{ik}
|
||||
\hat{A}^T\hat{b} = \hat{A}^T\hat{A}\hat{\beta},
|
||||
$$
|
||||
|
||||
We state without proof the expression for the uncertainty in the parameters \( \beta_j \) as (we leave this as an exercise)
|
||||
and if the matrix \( \hat{A}^T\hat{A} \) is invertible we have the solution
|
||||
$$
|
||||
\sigma^2(\beta_j) = \sum_{i=0}^{n-1}\sigma_i^2\left( \frac{\partial \beta_j}{\partial y_i}\right)^2,
|
||||
$$
|
||||
|
||||
resulting in
|
||||
$$
|
||||
\sigma^2(\beta_j) = \left(\sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}a_{ik}\right)\left(\sum_{l=0}^{p-1}h_{jl}\sum_{m=0}^{n-1}a_{ml}\right) = h_{jj}!
|
||||
\hat{\beta} =\left(\hat{A}^T\hat{A}\right)^{-1}\hat{A}^T\hat{b}.
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
@@ -258,7 +282,7 @@ $$
|
||||
<li><a href="._Regression-bs023.html">24</a></li>
|
||||
<li><a href="._Regression-bs024.html">25</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs016.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,19 +236,26 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
The first step here is to approximate the function \( y \) with a first-order polynomial, that is we write
|
||||
|
||||
<p>
|
||||
If we then introduce the matrix
|
||||
$$
|
||||
y=y(x) \rightarrow y(x_i) \approx \beta_0+\beta_1 x_i.
|
||||
\hat{H} = \left(\hat{A}^T\hat{A}\right)^{-1},
|
||||
$$
|
||||
|
||||
By computing the derivatives of \( \chi^2 \) with respect to \( \beta_0 \) and \( \beta_1 \) show that these are given by
|
||||
we have then the following expression for the parameters \( \beta_j \) (the matrix elements of \( \hat{H} \) are \( h_{ij} \))
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_0} = -2\left[ \sum_{i=0}^{n-1}\left(\frac{y_i-\beta_0-\beta_1x_{i}}{\sigma_i^2}\right)\right]=0,
|
||||
\beta_j = \sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}\frac{y_i}{\sigma_i}\frac{x_{ik}}{\sigma_i} = \sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}b_ia_{ik}
|
||||
$$
|
||||
|
||||
and
|
||||
We state without proof the expression for the uncertainty in the parameters \( \beta_j \) as (we leave this as an exercise)
|
||||
$$
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_0} = -2\left[ \sum_{i=0}^{n-1}x_i\left(\frac{y_i-\beta_0-\beta_1x_{i}}{\sigma_i^2}\right)\right]=0.
|
||||
\sigma^2(\beta_j) = \sum_{i=0}^{n-1}\sigma_i^2\left( \frac{\partial \beta_j}{\partial y_i}\right)^2,
|
||||
$$
|
||||
|
||||
resulting in
|
||||
$$
|
||||
\sigma^2(\beta_j) = \left(\sum_{k=0}^{p-1}h_{jk}\sum_{i=0}^{n-1}a_{ik}\right)\left(\sum_{l=0}^{p-1}h_{jl}\sum_{m=0}^{n-1}a_{ml}\right) = h_{jj}!
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
@@ -251,7 +287,7 @@ $$
|
||||
<li><a href="._Regression-bs024.html">25</a></li>
|
||||
<li><a href="._Regression-bs025.html">26</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs017.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,42 +236,20 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
For a linear fit we don't need to invert a matrix!!
|
||||
Defining
|
||||
The first step here is to approximate the function \( y \) with a first-order polynomial, that is we write
|
||||
$$
|
||||
\gamma = \sum_{i=0}^{n-1}\frac{1}{\sigma_i^2},
|
||||
y=y(x) \rightarrow y(x_i) \approx \beta_0+\beta_1 x_i.
|
||||
$$
|
||||
|
||||
|
||||
By computing the derivatives of \( \chi^2 \) with respect to \( \beta_0 \) and \( \beta_1 \) show that these are given by
|
||||
$$
|
||||
\gamma_x = \sum_{i=0}^{n-1}\frac{x_{i}}{\sigma_i^2},
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_0} = -2\left[ \sum_{i=0}^{n-1}\left(\frac{y_i-\beta_0-\beta_1x_{i}}{\sigma_i^2}\right)\right]=0,
|
||||
$$
|
||||
|
||||
and
|
||||
$$
|
||||
\gamma_y = \sum_{i=0}^{n-1}\left(\frac{y_i}{\sigma_i^2}\right),
|
||||
\frac{\partial \chi^2(\hat{\beta})}{\partial \beta_0} = -2\left[ \sum_{i=0}^{n-1}x_i\left(\frac{y_i-\beta_0-\beta_1x_{i}}{\sigma_i^2}\right)\right]=0.
|
||||
$$
|
||||
|
||||
$$
|
||||
\gamma_{xx} = \sum_{i=0}^{n-1}\frac{x_ix_{i}}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
$$
|
||||
\gamma_{xy} = \sum_{i=0}^{n-1}\frac{y_ix_{i}}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
we obtain
|
||||
$$
|
||||
\beta_0 = \frac{\gamma_{xx}\gamma_y-\gamma_x\gamma_y}{\gamma\gamma_{xx}-\gamma_x^2},
|
||||
$$
|
||||
|
||||
$$
|
||||
\beta_1 = \frac{\gamma_{xy}\gamma-\gamma_x\gamma_y}{\gamma\gamma_{xx}-\gamma_x^2}.
|
||||
$$
|
||||
|
||||
<p>
|
||||
This approach (different linear and non-linear regression) suffers often from both being underdetermined and overdetermined in the unknown coefficients \( \beta_i \). A better approach is to use the Singular Value Decomposition (SVD) method discussed below. Or using Lasso and Ridge regression. See below.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -273,7 +280,7 @@ This approach (different linear and non-linear regression) suffers often from bo
|
||||
<li><a href="._Regression-bs025.html">26</a></li>
|
||||
<li><a href="._Regression-bs026.html">27</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs018.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,42 +232,49 @@ MathJax.Hub.Config({
|
||||
<a name="part0018"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec17" class="anchor">Simple regression model </h2>
|
||||
We are now ready to write our first program which aims at solving the above linear regression equations. We start with data we have produced ourselves, in this case normally distributed random numbers along the \( x \)-axis. These numbers define then the value of a function \( y(x)=4+3x+N(0,1) \). Thereafter we order the \( x \) values and employ our linear regression algorithm to set up the best fit. Here we find it useful to use the numpy function \( c\_ \) arrays where arrays are stacked along their last axis after being upgraded to at least two dimensions with ones post-pended to the shape. The following examples help in understanding what happens
|
||||
<h2 id="___sec17" class="anchor">The \( \chi^2 \) function </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
For a linear fit we don't need to invert a matrix!!
|
||||
Defining
|
||||
$$
|
||||
\gamma = \sum_{i=0}^{n-1}\frac{1}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
|
||||
$$
|
||||
\gamma_x = \sum_{i=0}^{n-1}\frac{x_{i}}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
$$
|
||||
\gamma_y = \sum_{i=0}^{n-1}\left(\frac{y_i}{\sigma_i^2}\right),
|
||||
$$
|
||||
|
||||
$$
|
||||
\gamma_{xx} = \sum_{i=0}^{n-1}\frac{x_ix_{i}}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
$$
|
||||
\gamma_{xy} = \sum_{i=0}^{n-1}\frac{y_ix_{i}}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
we obtain
|
||||
$$
|
||||
\beta_0 = \frac{\gamma_{xx}\gamma_y-\gamma_x\gamma_y}{\gamma\gamma_{xx}-\gamma_x^2},
|
||||
$$
|
||||
|
||||
$$
|
||||
\beta_1 = \frac{\gamma_{xy}\gamma-\gamma_x\gamma_y}{\gamma\gamma_{xx}-\gamma_x^2}.
|
||||
$$
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>array([<span style="color: #666666">1</span>,<span style="color: #666666">2</span>,<span style="color: #666666">3</span>]), np<span style="color: #666666">.</span>array([<span style="color: #666666">4</span>,<span style="color: #666666">5</span>,<span style="color: #666666">6</span>])])
|
||||
<span style="color: #008000; font-weight: bold">print</span>(np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>array([[<span style="color: #666666">1</span>,<span style="color: #666666">2</span>,<span style="color: #666666">3</span>]]), <span style="color: #666666">0</span>, <span style="color: #666666">0</span>, np<span style="color: #666666">.</span>array([[<span style="color: #666666">4</span>,<span style="color: #666666">5</span>,<span style="color: #666666">6</span>]])])
|
||||
</pre></div>
|
||||
<p>
|
||||
This approach (different linear and non-linear regression) suffers often from both being underdetermined and overdetermined in the unknown coefficients \( \beta_i \). A better approach is to use the Singular Value Decomposition (SVD) method discussed below. Or using Lasso and Ridge regression. See below.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
beta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(beta)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Linear Regression'</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
We see that, as expected, a linear fit gives a seemingly (from the graph) good representation of the data.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -266,7 +302,7 @@ We see that, as expected, a linear fit gives a seemingly (from the graph) good r
|
||||
<li><a href="._Regression-bs026.html">27</a></li>
|
||||
<li><a href="._Regression-bs027.html">28</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs019.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,10 +232,15 @@ MathJax.Hub.Config({
|
||||
<a name="part0019"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec18" class="anchor">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
|
||||
<h2 id="___sec18" class="anchor">Simple regression model </h2>
|
||||
We are now ready to write our first program which aims at solving the above linear regression equations. We start with data we have produced ourselves, in this case normally distributed random numbers along the \( x \)-axis. These numbers define then the value of a function \( y(x)=4+3x+N(0,1) \). Thereafter we order the \( x \) values and employ our linear regression algorithm to set up the best fit. Here we find it useful to use the numpy function \( c\_ \) arrays where arrays are stacked along their last axis after being upgraded to at least two dimensions with ones post-pended to the shape. The following examples help in understanding what happens
|
||||
<p>
|
||||
We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>array([<span style="color: #666666">1</span>,<span style="color: #666666">2</span>,<span style="color: #666666">3</span>]), np<span style="color: #666666">.</span>array([<span style="color: #666666">4</span>,<span style="color: #666666">5</span>,<span style="color: #666666">6</span>])])
|
||||
<span style="color: #008000; font-weight: bold">print</span>(np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>array([[<span style="color: #666666">1</span>,<span style="color: #666666">2</span>,<span style="color: #666666">3</span>]]), <span style="color: #666666">0</span>, <span style="color: #666666">0</span>, np<span style="color: #666666">.</span>array([[<span style="color: #666666">4</span>,<span style="color: #666666">5</span>,<span style="color: #666666">6</span>]])])
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
@@ -214,23 +248,27 @@ We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
beta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(xnew)
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(beta)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Linear Regression'</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
We see that, as expected, a linear fit gives a seemingly (from the graph) good representation of the data.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -257,7 +295,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs027.html">28</a></li>
|
||||
<li><a href="._Regression-bs028.html">29</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs020.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,69 +232,32 @@ MathJax.Hub.Config({
|
||||
<a name="part0020"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec19" class="anchor">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec19" class="anchor">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We start with perhaps our simplest possible example, using <b>scikit-learn</b> to perform linear regression analysis on a data set produced by us.
|
||||
What follows is a simple Python code where we have defined function \( y \) in terms of the variable \( x \). Both are defined as vectors of dimension \( 1\times 100 \). The entries to the vector \( \hat{x} \) are given by random numbers generated with a uniform distribution with entries \( x_i \in [0,1] \) (more about probability distribution functions later). These values are then used to define a function \( y(x) \) (tabulated again as a vector) with a linear dependence on \( x \) plus a random noise added via the normal distribution.
|
||||
|
||||
<p>
|
||||
The Numpy functions are imported used the <b>import numpy as np</b>
|
||||
statement and the random number generator for the uniform distribution
|
||||
is called using the function <b>np.random.rand()</b>, where we specificy
|
||||
that we want \( 100 \) random variables. Using Numpy we define
|
||||
automatically an array with the specified number of elements, \( 100 \) in
|
||||
our case. With the Numpy function <b>randn()</b> we can compute random
|
||||
numbers with the normal distribution (mean value \( \mu \) equal to zero and
|
||||
variance \( \sigma^2 \) set to one) and produce the values of \( y \) assuming a linear
|
||||
dependence as function of \( x \)
|
||||
|
||||
$$
|
||||
y = 2x+N(0,1),
|
||||
$$
|
||||
|
||||
<p>
|
||||
where \( N(0,1) \) represents random numbers generated by the normal
|
||||
distribution. From <b>scikit-learn</b> we import then the
|
||||
<b>LinearRegression</b> functionality and make a prediction \( \tilde{y} =
|
||||
\alpha + \beta x \) using the function <b>fit(x,y)</b>. We call the set of
|
||||
data \( (\hat{x},\hat{y}) \) for our training data. The Python package
|
||||
<b>scikit-learn</b> has also a functionality which extracts the above
|
||||
fitting parameters \( \alpha \) and \( \beta \) (see below). Later we will
|
||||
distinguish between training data and test data.
|
||||
|
||||
<p>
|
||||
For plotting we use the Python package
|
||||
<a href="https://matplotlib.org/" target="_self">matplotlib</a> which produces publication
|
||||
quality figures. Feel free to explore the extensive
|
||||
<a href="https://matplotlib.org/gallery/index.html" target="_self">gallery</a> of examples. In
|
||||
this example we plot our original values of \( x \) and \( y \) as well as the
|
||||
prediction <b>ypredict</b> (\( \tilde{y} \)), which attempts at fitting our
|
||||
data with a straight line.
|
||||
|
||||
<p>
|
||||
The Python code follows here.
|
||||
We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">2*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">1</span>]])
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(xnew)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">5.0</span>])
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Simple Linear Regression'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
@@ -294,7 +286,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs028.html">29</a></li>
|
||||
<li><a href="._Regression-bs029.html">30</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs021.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,25 +232,71 @@ MathJax.Hub.Config({
|
||||
<a name="part0021"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec20" class="anchor">Simple linear regression model </h2>
|
||||
<h2 id="___sec20" class="anchor">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
This example serves several aims. It allows us to demonstrate several
|
||||
aspects of data analysis and later machine learning algorithms. The
|
||||
immediate visualization shows that our linear fit is not
|
||||
impressive. It goes through the data points, but there are many
|
||||
outliers which are not reproduced by our linear regression. We could
|
||||
now play around with this small program and change for example the
|
||||
factor in front of \( x \) and the normal distribution. Try to change the
|
||||
function \( y \) to
|
||||
We start with perhaps our simplest possible example, using <b>scikit-learn</b> to perform linear regression analysis on a data set produced by us.
|
||||
What follows is a simple Python code where we have defined function \( y \) in terms of the variable \( x \). Both are defined as vectors of dimension \( 1\times 100 \). The entries to the vector \( \hat{x} \) are given by random numbers generated with a uniform distribution with entries \( x_i \in [0,1] \) (more about probability distribution functions later). These values are then used to define a function \( y(x) \) (tabulated again as a vector) with a linear dependence on \( x \) plus a random noise added via the normal distribution.
|
||||
|
||||
<p>
|
||||
The Numpy functions are imported used the <b>import numpy as np</b>
|
||||
statement and the random number generator for the uniform distribution
|
||||
is called using the function <b>np.random.rand()</b>, where we specificy
|
||||
that we want \( 100 \) random variables. Using Numpy we define
|
||||
automatically an array with the specified number of elements, \( 100 \) in
|
||||
our case. With the Numpy function <b>randn()</b> we can compute random
|
||||
numbers with the normal distribution (mean value \( \mu \) equal to zero and
|
||||
variance \( \sigma^2 \) set to one) and produce the values of \( y \) assuming a linear
|
||||
dependence as function of \( x \)
|
||||
|
||||
$$
|
||||
y = 10x+0.01 \times N(0,1),
|
||||
y = 2x+N(0,1),
|
||||
$$
|
||||
|
||||
<p>
|
||||
where \( x \) is defined as before.
|
||||
where \( N(0,1) \) represents random numbers generated by the normal
|
||||
distribution. From <b>scikit-learn</b> we import then the
|
||||
<b>LinearRegression</b> functionality and make a prediction \( \tilde{y} =
|
||||
\alpha + \beta x \) using the function <b>fit(x,y)</b>. We call the set of
|
||||
data \( (\hat{x},\hat{y}) \) for our training data. The Python package
|
||||
<b>scikit-learn</b> has also a functionality which extracts the above
|
||||
fitting parameters \( \alpha \) and \( \beta \) (see below). Later we will
|
||||
distinguish between training data and test data.
|
||||
|
||||
<p>
|
||||
For plotting we use the Python package
|
||||
<a href="https://matplotlib.org/" target="_self">matplotlib</a> which produces publication
|
||||
quality figures. Feel free to explore the extensive
|
||||
<a href="https://matplotlib.org/gallery/index.html" target="_self">gallery</a> of examples. In
|
||||
this example we plot our original values of \( x \) and \( y \) as well as the
|
||||
prediction <b>ypredict</b> (\( \tilde{y} \)), which attempts at fitting our
|
||||
data with a straight line.
|
||||
|
||||
<p>
|
||||
The Python code follows here.
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">2*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">1</span>]])
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(xnew)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">5.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Simple Linear Regression'</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -248,7 +323,7 @@ where \( x \) is defined as before.
|
||||
<li><a href="._Regression-bs029.html">30</a></li>
|
||||
<li><a href="._Regression-bs030.html">31</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs022.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,15 +232,24 @@ MathJax.Hub.Config({
|
||||
<a name="part0022"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec21" class="anchor">Less noise </h2>
|
||||
<h2 id="___sec21" class="anchor">Simple linear regression model </h2>
|
||||
|
||||
<p>
|
||||
Does the fit look better? Indeed, by
|
||||
reducing the role of the normal distribution we see immediately that
|
||||
our linear prediction seemingly reproduces better the training
|
||||
set. However, this testing 'by the eye' is obviouly not satisfactory in the
|
||||
long run. Here we have only defined the training data and our model, and
|
||||
have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
This example serves several aims. It allows us to demonstrate several
|
||||
aspects of data analysis and later machine learning algorithms. The
|
||||
immediate visualization shows that our linear fit is not
|
||||
impressive. It goes through the data points, but there are many
|
||||
outliers which are not reproduced by our linear regression. We could
|
||||
now play around with this small program and change for example the
|
||||
factor in front of \( x \) and the normal distribution. Try to change the
|
||||
function \( y \) to
|
||||
|
||||
$$
|
||||
y = 10x+0.01 \times N(0,1),
|
||||
$$
|
||||
|
||||
<p>
|
||||
where \( x \) is defined as before.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -239,7 +277,7 @@ have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
<li><a href="._Regression-bs030.html">31</a></li>
|
||||
<li><a href="._Regression-bs031.html">32</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs023.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,24 +232,15 @@ MathJax.Hub.Config({
|
||||
<a name="part0023"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec22" class="anchor">How to study our fits </h2>
|
||||
<h2 id="___sec22" class="anchor">Less noise </h2>
|
||||
|
||||
<p>
|
||||
We need more rigorous criteria in defining whether we have succeeded or
|
||||
not in modeling our training data. You will be surprised to see that
|
||||
many scientists seldomly venture beyond this 'by the eye' approach. A
|
||||
standard approach for the <em>cost</em> function is the so-called \( \chi^2 \)
|
||||
function
|
||||
|
||||
$$ \chi^2 = \frac{1}{n}
|
||||
\sum_{i=0}^{n-1}\frac{(y_i-\tilde{y}_i)^2}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
<p>
|
||||
where \( \sigma_i^2 \) is the variance (to be defined later) of the entry
|
||||
\( y_i \). We may not know the explicit value of \( \sigma_i^2 \), it serves
|
||||
however the aim of scaling the equations and make the cost function
|
||||
dimensionless.
|
||||
Does the fit look better? Indeed, by
|
||||
reducing the role of the normal distribution we see immediately that
|
||||
our linear prediction seemingly reproduces better the training
|
||||
set. However, this testing 'by the eye' is obviouly not satisfactory in the
|
||||
long run. Here we have only defined the training data and our model, and
|
||||
have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -248,7 +268,7 @@ dimensionless.
|
||||
<li><a href="._Regression-bs031.html">32</a></li>
|
||||
<li><a href="._Regression-bs032.html">33</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs024.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,23 +232,24 @@ MathJax.Hub.Config({
|
||||
<a name="part0024"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec23" class="anchor">Minimizing the cost function </h2>
|
||||
<h2 id="___sec23" class="anchor">How to study our fits </h2>
|
||||
|
||||
<p>
|
||||
Minimizing the cost function is a central aspect of
|
||||
our discussions to come. Finding its minima as function of the model
|
||||
parameters (\( \alpha \) and \( \beta \) in our case) will be a recurring
|
||||
theme in these series of lectures. Essentially all machine learning
|
||||
algorithms we will discuss center around the minimization of the
|
||||
chosen cost function. This depends in turn on our specific
|
||||
model for describing the data, a typical situation in supervised
|
||||
learning. Automatizing the search for the minima of the cost function is a
|
||||
central ingredient in all algorithms. Typical methods which are
|
||||
employed are various variants of <b>gradient</b> methods. These will be
|
||||
discussed in more detail later. Again, you'll be surprised to hear that
|
||||
many practitioners minimize the above function ''by the eye', popularly dubbed as
|
||||
'chi by the eye'. That is, change a parameter and see (visually and numerically) that
|
||||
the \( \chi^2 \) function becomes smaller.
|
||||
We need more rigorous criteria in defining whether we have succeeded or
|
||||
not in modeling our training data. You will be surprised to see that
|
||||
many scientists seldomly venture beyond this 'by the eye' approach. A
|
||||
standard approach for the <em>cost</em> function is the so-called \( \chi^2 \)
|
||||
function
|
||||
|
||||
$$ \chi^2 = \frac{1}{n}
|
||||
\sum_{i=0}^{n-1}\frac{(y_i-\tilde{y}_i)^2}{\sigma_i^2},
|
||||
$$
|
||||
|
||||
<p>
|
||||
where \( \sigma_i^2 \) is the variance (to be defined later) of the entry
|
||||
\( y_i \). We may not know the explicit value of \( \sigma_i^2 \), it serves
|
||||
however the aim of scaling the equations and make the cost function
|
||||
dimensionless.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -247,7 +277,7 @@ the \( \chi^2 \) function becomes smaller.
|
||||
<li><a href="._Regression-bs032.html">33</a></li>
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs025.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,42 +232,23 @@ MathJax.Hub.Config({
|
||||
<a name="part0025"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec24" class="anchor">Relative error </h2>
|
||||
<h2 id="___sec24" class="anchor">Minimizing the cost function </h2>
|
||||
|
||||
<p>
|
||||
There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define
|
||||
the relative error as
|
||||
|
||||
$$
|
||||
\epsilon_{\mathrm{relative}}= \frac{\vert \hat{y} -\hat{\tilde{y}}\vert}{\vert \hat{y}\vert}.
|
||||
$$
|
||||
|
||||
We can modify easily the above Python code and plot the relative error instead
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">5*</span>x<span style="color: #666666">+0.01*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(x)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x, np<span style="color: #666666">.</span>abs(ypredict<span style="color: #666666">-</span>y)<span style="color: #666666">/</span><span style="color: #008000">abs</span>(y), <span style="color: #BA2121">"ro"</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">0.0</span>, <span style="color: #666666">0.5</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$\epsilon_{\mathrm{relative}}$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Relative error'</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
Depending on the parameter in front of the normal distribution, we may
|
||||
have a small or larger relative error. Try to play around with
|
||||
different training data sets and study (graphically) the value of the
|
||||
relative error.
|
||||
Minimizing the cost function is a central aspect of
|
||||
our discussions to come. Finding its minima as function of the model
|
||||
parameters (\( \alpha \) and \( \beta \) in our case) will be a recurring
|
||||
theme in these series of lectures. Essentially all machine learning
|
||||
algorithms we will discuss center around the minimization of the
|
||||
chosen cost function. This depends in turn on our specific
|
||||
model for describing the data, a typical situation in supervised
|
||||
learning. Automatizing the search for the minima of the cost function is a
|
||||
central ingredient in all algorithms. Typical methods which are
|
||||
employed are various variants of <b>gradient</b> methods. These will be
|
||||
discussed in more detail later. Again, you'll be surprised to hear that
|
||||
many practitioners minimize the above function ''by the eye', popularly dubbed as
|
||||
'chi by the eye'. That is, change a parameter and see (visually and numerically) that
|
||||
the \( \chi^2 \) function becomes smaller.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -266,7 +276,7 @@ relative error.
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs026.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,48 +232,43 @@ MathJax.Hub.Config({
|
||||
<a name="part0026"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec25" class="anchor">The richness of <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec25" class="anchor">Relative error </h2>
|
||||
|
||||
<p>
|
||||
As mentioned above, <b>scikit-learn</b> has an impressive functionality.
|
||||
We can for example extract the values of \( \alpha \) and \( \beta \) and
|
||||
their error estimates, or the variance and standard deviation and many
|
||||
other properties from the statistical data analysis.
|
||||
There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define
|
||||
the relative error as
|
||||
|
||||
<p>
|
||||
Here we show an
|
||||
example of the functionality of scikit-learn.
|
||||
$$
|
||||
\epsilon_{\mathrm{relative}}= \frac{\vert \hat{y} -\hat{\tilde{y}}\vert}{\vert \hat{y}\vert}.
|
||||
$$
|
||||
|
||||
We can modify easily the above Python code and plot the relative error instead
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> mean_squared_error, r2_score, mean_squared_log_error, mean_absolute_error
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">2.0+</span> <span style="color: #666666">5*</span>x<span style="color: #666666">+0.5*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">5*</span>x<span style="color: #666666">+0.01*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(x)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'The intercept alpha: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, linreg<span style="color: #666666">.</span>intercept_)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Coefficient beta : </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, linreg<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #408080; font-style: italic"># The mean squared error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Mean squared error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> mean_squared_error(y, ypredict))
|
||||
<span style="color: #408080; font-style: italic"># Explained variance score: 1 is perfect prediction </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Variance score: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> r2_score(y, ypredict))
|
||||
<span style="color: #408080; font-style: italic"># Mean squared log error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Mean squared log error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> mean_squared_log_error(y, ypredict) )
|
||||
<span style="color: #408080; font-style: italic"># Mean absolute error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Mean absolute error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> mean_absolute_error(y, ypredict))
|
||||
plt<span style="color: #666666">.</span>plot(x, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0.0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">1.5</span>, <span style="color: #666666">7.0</span>])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x, np<span style="color: #666666">.</span>abs(ypredict<span style="color: #666666">-</span>y)<span style="color: #666666">/</span><span style="color: #008000">abs</span>(y), <span style="color: #BA2121">"ro"</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">0.0</span>, <span style="color: #666666">0.5</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Linear Regression fit '</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$\epsilon_{\mathrm{relative}}$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Relative error'</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
Depending on the parameter in front of the normal distribution, we may
|
||||
have a small or larger relative error. Try to play around with
|
||||
different training data sets and study (graphically) the value of the
|
||||
relative error.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -271,7 +295,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs027.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,20 +232,48 @@ MathJax.Hub.Config({
|
||||
<a name="part0027"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec26" class="anchor">Functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec26" class="anchor">The richness of <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The function <b>coef</b> gives us the parameter \( \beta \) of our fit while <b>intercept</b> yields
|
||||
\( \alpha \). Depending on the constant in front of the normal distribution, we get values near or far from \( alpha =2 \) and \( \beta =5 \). Try to play around with different parameters in front of the normal distribution. The function <b>meansquarederror</b> gives us the mean square error, a risk metric corresponding to the expected value of the squared (quadratic) error or loss defined as
|
||||
$$ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n}
|
||||
\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2,
|
||||
$$
|
||||
As mentioned above, <b>scikit-learn</b> has an impressive functionality.
|
||||
We can for example extract the values of \( \alpha \) and \( \beta \) and
|
||||
their error estimates, or the variance and standard deviation and many
|
||||
other properties from the statistical data analysis.
|
||||
|
||||
<p>
|
||||
The smaller the value, the better the fit. Ideally we would like to
|
||||
have an MSE equal zero. The attentive reader has probably recognized
|
||||
this function as being similar to the \( \chi^2 \) function defined above.
|
||||
Here we show an
|
||||
example of the functionality of scikit-learn.
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> mean_squared_error, r2_score, mean_squared_log_error, mean_absolute_error
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">2.0+</span> <span style="color: #666666">5*</span>x<span style="color: #666666">+0.5*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
linreg <span style="color: #666666">=</span> LinearRegression()
|
||||
linreg<span style="color: #666666">.</span>fit(x,y)
|
||||
ypredict <span style="color: #666666">=</span> linreg<span style="color: #666666">.</span>predict(x)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'The intercept alpha: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, linreg<span style="color: #666666">.</span>intercept_)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Coefficient beta : </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, linreg<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #408080; font-style: italic"># The mean squared error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Mean squared error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> mean_squared_error(y, ypredict))
|
||||
<span style="color: #408080; font-style: italic"># Explained variance score: 1 is perfect prediction </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Variance score: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> r2_score(y, ypredict))
|
||||
<span style="color: #408080; font-style: italic"># Mean squared log error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Mean squared log error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> mean_squared_log_error(y, ypredict) )
|
||||
<span style="color: #408080; font-style: italic"># Mean absolute error </span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Mean absolute error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> mean_absolute_error(y, ypredict))
|
||||
plt<span style="color: #666666">.</span>plot(x, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0.0</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">1.5</span>, <span style="color: #666666">7.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Linear Regression fit '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -243,7 +300,7 @@ this function as being similar to the \( \chi^2 \) function defined above.
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs028.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,26 +232,19 @@ MathJax.Hub.Config({
|
||||
<a name="part0028"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec27" class="anchor">Other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec27" class="anchor">Functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The <b>r2score</b> function computes \( R^2 \), the coefficient of
|
||||
determination. It provides a measure of how well future samples are
|
||||
likely to be predicted by the model. Best possible score is 1.0 and it
|
||||
can be negative (because the model can be arbitrarily worse). A
|
||||
constant model that always predicts the expected value of \( \hat{y} \),
|
||||
disregarding the input features, would get a \( R^2 \) score of \( 0.0 \).
|
||||
The function <b>coef</b> gives us the parameter \( \beta \) of our fit while <b>intercept</b> yields
|
||||
\( \alpha \). Depending on the constant in front of the normal distribution, we get values near or far from \( alpha =2 \) and \( \beta =5 \). Try to play around with different parameters in front of the normal distribution. The function <b>meansquarederror</b> gives us the mean square error, a risk metric corresponding to the expected value of the squared (quadratic) error or loss defined as
|
||||
$$ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n}
|
||||
\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2,
|
||||
$$
|
||||
|
||||
<p>
|
||||
If \( \tilde{\hat{y}}_i \) is the predicted value of the \( i-th \) sample and \( y_i \) is the corresponding true value, then the score \( R^2 \) is defined as
|
||||
$$
|
||||
R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2},
|
||||
$$
|
||||
|
||||
where we have defined the mean value of \( \hat{y} \) as
|
||||
$$
|
||||
\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i.
|
||||
$$
|
||||
The smaller the value, the better the fit. Ideally we would like to
|
||||
have an MSE equal zero. The attentive reader has probably recognized
|
||||
this function as being similar to the \( \chi^2 \) function defined above.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -249,6 +271,8 @@ $$
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs029.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,27 +232,26 @@ MathJax.Hub.Config({
|
||||
<a name="part0029"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec28" class="anchor">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec28" class="anchor">Other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
Another quantity will meet again in our discussions of regression analysis is
|
||||
mean absolute error (MAE), a risk metric corresponding to the expected value of the absolute error loss or what we call the \( l1 \)-norm loss. In our discussion above we presented the relative error.
|
||||
The MAE is defined as follows
|
||||
$$
|
||||
\text{MAE}(\hat{y}, \hat{\tilde{y}}) = \frac{1}{n} \sum_{i=0}^{n-1} \left| y_i - \tilde{y}_i \right|.
|
||||
$$
|
||||
|
||||
Finally we present the
|
||||
squared logarithmic (quadratic) error
|
||||
$$
|
||||
\text{MSLE}(\hat{y}, \hat{\tilde{y}}) = \frac{1}{n} \sum_{i=0}^{n - 1} (\log_e (1 + y_i) - \log_e (1 + \tilde{y}_i) )^2,
|
||||
$$
|
||||
The <b>r2score</b> function computes \( R^2 \), the coefficient of
|
||||
determination. It provides a measure of how well future samples are
|
||||
likely to be predicted by the model. Best possible score is 1.0 and it
|
||||
can be negative (because the model can be arbitrarily worse). A
|
||||
constant model that always predicts the expected value of \( \hat{y} \),
|
||||
disregarding the input features, would get a \( R^2 \) score of \( 0.0 \).
|
||||
|
||||
<p>
|
||||
where \( \log_e (x) \) stands for the natural logarithm of \( x \). This error
|
||||
estimate is best to use when targets having exponential growth, such
|
||||
as population counts, average sales of a commodity over a span of
|
||||
years etc.
|
||||
If \( \tilde{\hat{y}}_i \) is the predicted value of the \( i-th \) sample and \( y_i \) is the corresponding true value, then the score \( R^2 \) is defined as
|
||||
$$
|
||||
R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2},
|
||||
$$
|
||||
|
||||
where we have defined the mean value of \( \hat{y} \) as
|
||||
$$
|
||||
\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i.
|
||||
$$
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -249,6 +277,9 @@ years etc.
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs030.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,50 +232,27 @@ MathJax.Hub.Config({
|
||||
<a name="part0030"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec29" class="anchor">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec29" class="anchor">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We will discuss in more
|
||||
detail these and other functions in the various lectures. We conclude this part with another example. Instead of
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
Another quantity will meet again in our discussions of regression analysis is
|
||||
mean absolute error (MAE), a risk metric corresponding to the expected value of the absolute error loss or what we call the \( l1 \)-norm loss. In our discussion above we presented the relative error.
|
||||
The MAE is defined as follows
|
||||
$$
|
||||
\text{MAE}(\hat{y}, \hat{\tilde{y}}) = \frac{1}{n} \sum_{i=0}^{n-1} \left| y_i - \tilde{y}_i \right|.
|
||||
$$
|
||||
|
||||
Finally we present the
|
||||
squared logarithmic (quadratic) error
|
||||
$$
|
||||
\text{MSLE}(\hat{y}, \hat{\tilde{y}}) = \frac{1}{n} \sum_{i=0}^{n - 1} (\log_e (1 + y_i) - \log_e (1 + \tilde{y}_i) )^2,
|
||||
$$
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">random</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> PolynomialFeatures
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.pipeline</span> <span style="color: #008000; font-weight: bold">import</span> make_pipeline
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.02</span>,<span style="color: #666666">0.98</span>,<span style="color: #666666">200</span>)
|
||||
noise <span style="color: #666666">=</span> np<span style="color: #666666">.</span>asarray(random<span style="color: #666666">.</span>sample((<span style="color: #008000">range</span>(<span style="color: #666666">200</span>)),<span style="color: #666666">200</span>))
|
||||
y<span style="color: #666666">=</span>x<span style="color: #666666">**3*</span>noise
|
||||
yn<span style="color: #666666">=</span>x<span style="color: #666666">**3*100</span>
|
||||
poly3 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=3</span>)
|
||||
X <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf3 <span style="color: #666666">=</span> LinearRegression()
|
||||
clf3<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
Xplot<span style="color: #666666">=</span>poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly3_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x, clf3<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Cubic Fit'</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x,yn, color<span style="color: #666666">=</span><span style="color: #BA2121">'red'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"True Cubic"</span>)
|
||||
plt<span style="color: #666666">.</span>scatter(x, y, label<span style="color: #666666">=</span><span style="color: #BA2121">'Data'</span>, color<span style="color: #666666">=</span><span style="color: #BA2121">'orange'</span>, s<span style="color: #666666">=15</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">error</span>(a):
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> y:
|
||||
err<span style="color: #666666">=</span>(y<span style="color: #666666">-</span>yn)<span style="color: #666666">/</span>yn
|
||||
<span style="color: #008000; font-weight: bold">return</span> <span style="color: #008000">abs</span>(np<span style="color: #666666">.</span>sum(err))<span style="color: #666666">/</span><span style="color: #008000">len</span>(err)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (error(y))
|
||||
</pre></div>
|
||||
<p>
|
||||
Similarly, using <b>R</b>, we can perform similar studies.
|
||||
(more details on <b>R</b> will be inserted later).
|
||||
where \( \log_e (x) \) stands for the natural logarithm of \( x \). This error
|
||||
estimate is best to use when targets having exponential growth, such
|
||||
as population counts, average sales of a commodity over a span of
|
||||
years etc.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -271,6 +277,10 @@ Similarly, using <b>R</b>, we can perform similar studies.
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs031.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,47 +232,51 @@ MathJax.Hub.Config({
|
||||
<a name="part0031"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec30" class="anchor">Simple regression model with gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<h2 id="___sec30" class="anchor">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We will discuss in more
|
||||
detail these and other functions in the various lectures. We conclude this part with another example. Instead of
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
Add description of the various python commands.
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">math</span> <span style="color: #008000; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">random</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> PolynomialFeatures
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.pipeline</span> <span style="color: #008000; font-weight: bold">import</span> make_pipeline
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.02</span>,<span style="color: #666666">0.98</span>,<span style="color: #666666">200</span>)
|
||||
noise <span style="color: #666666">=</span> np<span style="color: #666666">.</span>asarray(random<span style="color: #666666">.</span>sample((<span style="color: #008000">range</span>(<span style="color: #666666">200</span>)),<span style="color: #666666">200</span>))
|
||||
y<span style="color: #666666">=</span>x<span style="color: #666666">**3*</span>noise
|
||||
yn<span style="color: #666666">=</span>x<span style="color: #666666">**3*100</span>
|
||||
poly3 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=3</span>)
|
||||
X <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf3 <span style="color: #666666">=</span> LinearRegression()
|
||||
clf3<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
theta_linreg <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta_linreg)
|
||||
theta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)
|
||||
|
||||
eta <span style="color: #666666">=</span> <span style="color: #666666">0.1</span>
|
||||
Niterations <span style="color: #666666">=</span> <span style="color: #666666">1000</span>
|
||||
m <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> <span style="color: #008000">iter</span> <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(Niterations):
|
||||
gradients <span style="color: #666666">=</span> <span style="color: #666666">2.0/</span>m<span style="color: #666666">*</span>xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>dot(theta)<span style="color: #666666">-</span>y)
|
||||
theta <span style="color: #666666">-=</span> eta<span style="color: #666666">*</span>gradients
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta)
|
||||
ypredict2 <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta_linreg)
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict2, <span style="color: #BA2121">"b-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
Xplot<span style="color: #666666">=</span>poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly3_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x, clf3<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Cubic Fit'</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x,yn, color<span style="color: #666666">=</span><span style="color: #BA2121">'red'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"True Cubic"</span>)
|
||||
plt<span style="color: #666666">.</span>scatter(x, y, label<span style="color: #666666">=</span><span style="color: #BA2121">'Data'</span>, color<span style="color: #666666">=</span><span style="color: #BA2121">'orange'</span>, s<span style="color: #666666">=15</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">error</span>(a):
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> y:
|
||||
err<span style="color: #666666">=</span>(y<span style="color: #666666">-</span>yn)<span style="color: #666666">/</span>yn
|
||||
<span style="color: #008000; font-weight: bold">return</span> <span style="color: #008000">abs</span>(np<span style="color: #666666">.</span>sum(err))<span style="color: #666666">/</span><span style="color: #008000">len</span>(err)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (error(y))
|
||||
</pre></div>
|
||||
<p>
|
||||
Using <b>R</b>, we can perform similar studies.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -266,6 +299,11 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs032.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,8 +232,7 @@ MathJax.Hub.Config({
|
||||
<a name="part0032"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec31" class="anchor">Simple regression model with stochastic gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<h2 id="___sec31" class="anchor">Polynomial Regression </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
@@ -213,17 +241,24 @@ Add info about the equations, play around with different learning rates
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> SGDRegressor
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
m <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(m,<span style="color: #666666">1</span>)<span style="color: #666666">+4.</span>
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">*</span>x<span style="color: #666666">+</span> <span style="color: #666666">+</span>x<span style="color: #666666">-</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(m,<span style="color: #666666">1</span>)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
theta_linreg <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta_linreg)
|
||||
sgdreg <span style="color: #666666">=</span> SGDRegressor(n_iter <span style="color: #666666">=</span> <span style="color: #666666">50</span>, penalty<span style="color: #666666">=</span><span style="color: #008000">None</span>, eta0<span style="color: #666666">=0.1</span>)
|
||||
sgdreg<span style="color: #666666">.</span>fit(x,y<span style="color: #666666">.</span>ravel())
|
||||
<span style="color: #008000; font-weight: bold">print</span>(sgdreg<span style="color: #666666">.</span>intercept_, sgdreg<span style="color: #666666">.</span>coef_)
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((m,<span style="color: #666666">1</span>)), x]
|
||||
theta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
@@ -246,6 +281,12 @@ sgdreg<span style="color: #666666">.</span>fit(x,y<span style="color: #666666">.
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs033.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -201,36 +230,32 @@ MathJax.Hub.Config({
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0033"></a>
|
||||
<!-- !split -->
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec32" class="anchor">Linking the regression analysis with a statistical interpretation </h2>
|
||||
|
||||
<h2 id="___sec32" class="anchor">Polynomial Regression </h2>
|
||||
<p>
|
||||
Before we proceed, and to link with our discussions of Bayesian statistics to come, it is useful the derive the standard regression analysis equations using a statistical interpretation. This allows us also to derive quantities like the variance and other expectation values in a rather straightforward way.
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">math</span> <span style="color: #008000; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<p>
|
||||
It is assumed that \( \varepsilon_i
|
||||
\sim \mathcal{N}(0, \sigma^2) \) and the \( \varepsilon_{i} \) are
|
||||
independent, i.e.:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mbox{Cov}(\varepsilon_{i_1},
|
||||
\varepsilon_{i_2}) & = \left\{ \begin{array}{lcc} \sigma^2 & \mbox{if}
|
||||
& i_1 = i_2, \\ 0 & \mbox{if} & i_1 \not= i_2. \end{array} \right.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
m <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(m,<span style="color: #666666">1</span>)<span style="color: #666666">+4.</span>
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">*</span>x<span style="color: #666666">+</span> <span style="color: #666666">+</span>x<span style="color: #666666">-</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(m,<span style="color: #666666">1</span>)
|
||||
The randomness of \( \varepsilon_i \) implies that
|
||||
\( \mathbf{Y}_i \) is also a random variable. In particular,
|
||||
\( \mathbf{Y}_i \) is normally distributed, because \( \varepsilon_i \sim
|
||||
\mathcal{N}(0, \sigma^2) \) and \( \mathbf{X}_{i,\ast} \, \beta \) is a
|
||||
non-random scalar. To specify the parameters of the distribution of
|
||||
\( \mathbf{Y}_i \) we need to calculate its first two moments.
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((m,<span style="color: #666666">1</span>)), x]
|
||||
theta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta)
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -251,6 +276,13 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs034.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,84 +232,37 @@ MathJax.Hub.Config({
|
||||
<a name="part0034"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec33" class="anchor">Ridge and Lasso Regression </h2>
|
||||
<h2 id="___sec33" class="anchor">Expectation value and variance </h2>
|
||||
|
||||
<p>
|
||||
Its expectation equals:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbb{E}(Y_i) & =
|
||||
\mathbb{E}(\mathbf{X}_{i, \ast} \, \beta) + \mathbb{E}(\varepsilon_i)
|
||||
\, \, \, = \, \, \, \mathbf{X}_{i, \ast} \, \beta,
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">import</span> linear_model
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> mean_squared_error, r2_score
|
||||
while
|
||||
its variance is
|
||||
$$
|
||||
\begin{align*} \mbox{Var}(Y_i) & = \mathbb{E} \{ [Y_i
|
||||
- \mathbb{E}(Y_i)]^2 \} \, \, \, = \, \, \, \mathbb{E} ( Y_i^2 ) -
|
||||
[\mathbb{E}(Y_i)]^2 \\ & = \mathbb{E} [ ( \mathbf{X}_{i, \ast} \,
|
||||
\beta + \varepsilon_i )^2] - ( \mathbf{X}_{i, \ast} \, \beta)^2 \\ &
|
||||
= \mathbb{E} [ ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2 \varepsilon_i
|
||||
\mathbf{X}_{i, \ast} \, \beta + \varepsilon_i^2 ] - ( \mathbf{X}_{i,
|
||||
\ast} \, \beta)^2 \\ & = ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2
|
||||
\mathbb{E}(\varepsilon_i) \mathbf{X}_{i, \ast} \, \beta +
|
||||
\mathbb{E}(\varepsilon_i^2 ) - ( \mathbf{X}_{i, \ast} \, \beta)^2
|
||||
\\ & = \mathbb{E}(\varepsilon_i^2 ) \, \, \, = \, \, \,
|
||||
\mbox{Var}(\varepsilon_i) \, \, \, = \, \, \, \sigma^2.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
<span style="color: #408080; font-style: italic">#creating data with random noise</span>
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>arange(<span style="color: #666666">50</span>)
|
||||
Hence, \( Y_i \sim \mathcal{N}( \mathbf{X}_{i, \ast} \, \beta, \sigma^2) \).
|
||||
|
||||
delta<span style="color: #666666">=</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>uniform(<span style="color: #666666">-2.5</span>,<span style="color: #666666">2.5</span>, size<span style="color: #666666">=</span>(<span style="color: #666666">50</span>))
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>shuffle(delta)
|
||||
y <span style="color: #666666">=0.5*</span>x<span style="color: #666666">+5+</span>delta
|
||||
|
||||
<span style="color: #408080; font-style: italic">#arranging data into 2x50 matrix</span>
|
||||
a<span style="color: #666666">=</span>np<span style="color: #666666">.</span>array(x) <span style="color: #408080; font-style: italic">#inputs</span>
|
||||
b<span style="color: #666666">=</span>np<span style="color: #666666">.</span>array(y) <span style="color: #408080; font-style: italic">#outputs</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Split into training and test</span>
|
||||
X_train<span style="color: #666666">=</span>a[:<span style="color: #666666">37</span>, np<span style="color: #666666">.</span>newaxis]
|
||||
X_test<span style="color: #666666">=</span>a[<span style="color: #666666">37</span>:, np<span style="color: #666666">.</span>newaxis]
|
||||
y_train<span style="color: #666666">=</span>b[:<span style="color: #666666">37</span>]
|
||||
y_test<span style="color: #666666">=</span>b[<span style="color: #666666">37</span>:]
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"X_train: "</span>, X_train<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"y_train: "</span>, y_train<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"X_test: "</span>, X_test<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"y_test: "</span>, y_test<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ordinary Least Squares"</span>)
|
||||
<span style="color: #408080; font-style: italic">#Add Ordinary Least Squares fit</span>
|
||||
reg<span style="color: #666666">=</span>LinearRegression()
|
||||
reg<span style="color: #666666">.</span>fit(X_train, y_train)
|
||||
pred<span style="color: #666666">=</span>reg<span style="color: #666666">.</span>predict(X_test)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Prediction Shape: "</span>, pred<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Coefficients: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, reg<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #408080; font-style: italic"># The mean squared error</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Mean squared error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">"</span>
|
||||
<span style="color: #666666">%</span> mean_squared_error(y_test, pred))
|
||||
<span style="color: #408080; font-style: italic"># Explained variance score: 1 is perfect prediction</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Variance score: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> r2_score(y_test, pred))
|
||||
|
||||
<span style="color: #408080; font-style: italic">#plot</span>
|
||||
plt<span style="color: #666666">.</span>scatter(X_test,y_test,color<span style="color: #666666">=</span><span style="color: #BA2121">'green'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Training Data"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(X_test, pred, color<span style="color: #666666">=</span><span style="color: #BA2121">'black'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Fit Line"</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Regression"</span>)
|
||||
|
||||
ridge<span style="color: #666666">=</span>linear_model<span style="color: #666666">.</span>RidgeCV(alphas<span style="color: #666666">=</span>[<span style="color: #666666">0.1</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">10.0</span>])
|
||||
ridge<span style="color: #666666">.</span>fit(X_train,y_train)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Coefficient: "</span>,ridge<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Intercept: "</span>, ridge<span style="color: #666666">.</span>intercept_)
|
||||
<span style="color: #408080; font-style: italic">#Look into graphing with Ridge fit</span>
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Lasso"</span>)
|
||||
lasso<span style="color: #666666">=</span>linear_model<span style="color: #666666">.</span>Lasso(alpha<span style="color: #666666">=0.1</span>)
|
||||
lasso<span style="color: #666666">.</span>fit(X_train,y_train)
|
||||
predl<span style="color: #666666">=</span>lasso<span style="color: #666666">.</span>predict(X_test)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Lasso Coefficient: "</span>, lasso<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Lasso Intercept: "</span>, lasso<span style="color: #666666">.</span>intercept_)
|
||||
plt<span style="color: #666666">.</span>scatter(X_test,y_test,color<span style="color: #666666">=</span><span style="color: #BA2121">'green'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Training Data"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(X_test, predl, color<span style="color: #666666">=</span><span style="color: #BA2121">'blue'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Lasso"</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -300,6 +282,14 @@ plt<span style="color: #666666">.</span>show()
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs035.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -207,16 +236,20 @@ MathJax.Hub.Config({
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
How can we use the singular value decomposition to find the parameters \( \beta_j \)? More details will come. We first note that a general \( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal matrix \( \hat{\Sigma} \) of dimensionality \( n\times n \) and two orthognal matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality \( m \times n \) and the last dimensionality \( n\times n \). We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{\Sigma}\hat{V}
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
Add codes and discuss this in connection with lasso and ridge, show example where the standard inversion of a matrix fails and where SVD comes to rescue
|
||||
A general
|
||||
\( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal
|
||||
matrix \( \hat{D} \) of dimensionality \( n\times n \) and two orthognal
|
||||
matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality
|
||||
\( m \times m \) and the last dimensionality \( n\times n \).
|
||||
We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{D}\hat{V}^T
|
||||
$$
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<p>
|
||||
@@ -236,6 +269,15 @@ Add codes and discuss this in connection with lasso and ridge, show example wher
|
||||
<li class="active"><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs036.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,11 +232,84 @@ MathJax.Hub.Config({
|
||||
<a name="part0036"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec35" class="anchor">Lasso and Ridge regression </h2>
|
||||
<h2 id="___sec35" class="anchor">Code examples for Ridge and Lasso Regression </h2>
|
||||
|
||||
<p>
|
||||
Discuss the mathematics here
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">import</span> linear_model
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LinearRegression
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> mean_squared_error, r2_score
|
||||
|
||||
<span style="color: #408080; font-style: italic">#creating data with random noise</span>
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>arange(<span style="color: #666666">50</span>)
|
||||
|
||||
delta<span style="color: #666666">=</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>uniform(<span style="color: #666666">-2.5</span>,<span style="color: #666666">2.5</span>, size<span style="color: #666666">=</span>(<span style="color: #666666">50</span>))
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>shuffle(delta)
|
||||
y <span style="color: #666666">=0.5*</span>x<span style="color: #666666">+5+</span>delta
|
||||
|
||||
<span style="color: #408080; font-style: italic">#arranging data into 2x50 matrix</span>
|
||||
a<span style="color: #666666">=</span>np<span style="color: #666666">.</span>array(x) <span style="color: #408080; font-style: italic">#inputs</span>
|
||||
b<span style="color: #666666">=</span>np<span style="color: #666666">.</span>array(y) <span style="color: #408080; font-style: italic">#outputs</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Split into training and test</span>
|
||||
X_train<span style="color: #666666">=</span>a[:<span style="color: #666666">37</span>, np<span style="color: #666666">.</span>newaxis]
|
||||
X_test<span style="color: #666666">=</span>a[<span style="color: #666666">37</span>:, np<span style="color: #666666">.</span>newaxis]
|
||||
y_train<span style="color: #666666">=</span>b[:<span style="color: #666666">37</span>]
|
||||
y_test<span style="color: #666666">=</span>b[<span style="color: #666666">37</span>:]
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"X_train: "</span>, X_train<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"y_train: "</span>, y_train<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"X_test: "</span>, X_test<span style="color: #666666">.</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"y_test: "</span>, y_test<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ordinary Least Squares"</span>)
|
||||
<span style="color: #408080; font-style: italic">#Add Ordinary Least Squares fit</span>
|
||||
reg<span style="color: #666666">=</span>LinearRegression()
|
||||
reg<span style="color: #666666">.</span>fit(X_train, y_train)
|
||||
pred<span style="color: #666666">=</span>reg<span style="color: #666666">.</span>predict(X_test)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Prediction Shape: "</span>, pred<span style="color: #666666">.</span>shape)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Coefficients: </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span>, reg<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #408080; font-style: italic"># The mean squared error</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Mean squared error: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">"</span>
|
||||
<span style="color: #666666">%</span> mean_squared_error(y_test, pred))
|
||||
<span style="color: #408080; font-style: italic"># Explained variance score: 1 is perfect prediction</span>
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Variance score: </span><span style="color: #BB6688; font-weight: bold">%.2f</span><span style="color: #BA2121">'</span> <span style="color: #666666">%</span> r2_score(y_test, pred))
|
||||
|
||||
<span style="color: #408080; font-style: italic">#plot</span>
|
||||
plt<span style="color: #666666">.</span>scatter(X_test,y_test,color<span style="color: #666666">=</span><span style="color: #BA2121">'green'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Training Data"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(X_test, pred, color<span style="color: #666666">=</span><span style="color: #BA2121">'black'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Fit Line"</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Regression"</span>)
|
||||
|
||||
ridge<span style="color: #666666">=</span>linear_model<span style="color: #666666">.</span>RidgeCV(alphas<span style="color: #666666">=</span>[<span style="color: #666666">0.1</span>,<span style="color: #666666">1.0</span>,<span style="color: #666666">10.0</span>])
|
||||
ridge<span style="color: #666666">.</span>fit(X_train,y_train)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Coefficient: "</span>,ridge<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Ridge Intercept: "</span>, ridge<span style="color: #666666">.</span>intercept_)
|
||||
<span style="color: #408080; font-style: italic">#Look into graphing with Ridge fit</span>
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"------------------------------------"</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span> (<span style="color: #BA2121">"Lasso"</span>)
|
||||
lasso<span style="color: #666666">=</span>linear_model<span style="color: #666666">.</span>Lasso(alpha<span style="color: #666666">=0.1</span>)
|
||||
lasso<span style="color: #666666">.</span>fit(X_train,y_train)
|
||||
predl<span style="color: #666666">=</span>lasso<span style="color: #666666">.</span>predict(X_test)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Lasso Coefficient: "</span>, lasso<span style="color: #666666">.</span>coef_)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Lasso Intercept: "</span>, lasso<span style="color: #666666">.</span>intercept_)
|
||||
plt<span style="color: #666666">.</span>scatter(X_test,y_test,color<span style="color: #666666">=</span><span style="color: #BA2121">'green'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Training Data"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(X_test, predl, color<span style="color: #666666">=</span><span style="color: #BA2121">'blue'</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">"Lasso"</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -225,6 +327,14 @@ Discuss the mathematics here
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li class="active"><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs037.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -203,14 +232,55 @@ MathJax.Hub.Config({
|
||||
<a name="part0037"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec36" class="anchor">Logistic regression </h2>
|
||||
Add discussion about classification versus regression, show examples of more than two cases and why regression is not the best approach. Motivate for k-nearest neighbors
|
||||
<h2 id="___sec36" class="anchor">From standard regression to Ridge regressions </h2>
|
||||
|
||||
<p>
|
||||
Add examples on classification problems
|
||||
One of the typical problems we encounter with linear regression, in particular
|
||||
when the matrix \( \hat{X} \) (our so-called design matrix) is high-dimensional,
|
||||
are problems with near singular or singular matrices. The column vectors of \( \hat{X} \)
|
||||
may be linearly dependent, normally referred to as super-collinearity.
|
||||
This means that the matrix may be rank deficient and it is basically impossible to
|
||||
to model the data using linear regression. As an example, consider the matrix
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbf{X} & = \left[
|
||||
\begin{array}{rrr}
|
||||
1 & -1 & 2
|
||||
\\
|
||||
1 & 0 & 1
|
||||
\\
|
||||
1 & 2 & -1
|
||||
\\
|
||||
1 & 1 & 0
|
||||
\end{array} \right]
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
<p>
|
||||
The columns of \( \hat{X} \) are linearly dependent. We se this easily since the
|
||||
the first column is the row-wise sum of the other two columns. The rank (more correct,
|
||||
the column rank) of a matrix is the dimension of the space spanned by the
|
||||
column vectors. Hence, the rank of \( \mathbf{X} \) is equal to the number
|
||||
of linearly independent columns. In this particular case the matrix has rank 2.
|
||||
|
||||
<p>
|
||||
Super-collinearity of an \( (n \times p) \)-dimensional design matrix \( \mathbf{X} \) implies
|
||||
that the inverse of the matrix \( \hat{X}^T\hat{x} \) (the matrix we needto invert to solve the linear regression equations) is non-invertible. If we have a square matrix that does not have an inverse, we say this matrix singular. The example here demonstrates this
|
||||
$$
|
||||
\begin{align*}
|
||||
\hat{X} & = \left[
|
||||
\begin{array}{rr}
|
||||
1 & -1
|
||||
\\
|
||||
1 & -1
|
||||
\end{array} \right].
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
We see easily that \( \mbox{det}(\hat{X}) = x_{11} x_{22} - x_{12} x_{21} = 1 \times (-1) - 1 \times (-1) = 0 \). Hence, \( \mathbf{X} \) is singular and its inverse is undefined.
|
||||
This is equivalent to saying that the matrix \( \hat{X} \) has at least an eigenvalue which is zero.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
@@ -226,6 +296,15 @@ Add examples on classification problems
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li class="active"><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs038.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
|
||||
@@ -0,0 +1,307 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0038"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec37" class="anchor">Fixing the singularity </h2>
|
||||
|
||||
<p>
|
||||
If our design matrix \( \hat{X} \) which enters the linear regression problem
|
||||
$$
|
||||
\begin{align}
|
||||
\hat{\beta} & = (\hat{X}^{T} \hat{X})^{-1} \hat{X}^{T} \hat{y},
|
||||
\tag{1}
|
||||
\end{align}
|
||||
$$
|
||||
|
||||
has linearly dependent column vectors, we will not be able to compute the inverse
|
||||
of \( \hat{X}^T\hat{X} \) and we cannot find the parameters (estimators) \( \beta_i \).
|
||||
The estimators are only well-defined if \( (\hat{X}^{T}\hat{X})^{-1} \) exits.
|
||||
This is more likely to happen when the matrix \( \hat{X} \) is high-dimensional. In this case it is likely to encounter a situation where
|
||||
the regression parameters \( \beta_i \) cannot be estimated.
|
||||
|
||||
<p>
|
||||
The <em>ad hoc</em> approach which was introduced in the 70s was simply to add a diagonal component to the matrix to invert, that is we change
|
||||
$$
|
||||
\hat{X}^{T} \hat{X} \rightarrow \hat{X}^{T} \hat{X}+\lambda \hat{I},
|
||||
$$
|
||||
|
||||
where \( \hat{I} \) is the identity matrix.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs037.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs030.html">31</a></li>
|
||||
<li><a href="._Regression-bs031.html">32</a></li>
|
||||
<li><a href="._Regression-bs032.html">33</a></li>
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li class="active"><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs039.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,392 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0039"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec38" class="anchor">A second-order polynomial with Ridge and Lasso </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> r2_score
|
||||
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">4155</span>)
|
||||
|
||||
n_samples <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(n_samples,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">5*</span>x<span style="color: #666666">*</span>x <span style="color: #666666">+</span> <span style="color: #666666">0.1*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(n_samples,<span style="color: #666666">1</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Centering x and y.</span>
|
||||
x_ <span style="color: #666666">=</span> x <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(x)
|
||||
y_ <span style="color: #666666">=</span> y <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(y) <span style="color: #408080; font-style: italic"># beta_0 = mean(y)</span>
|
||||
|
||||
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((n_samples,<span style="color: #666666">1</span>)), x, x<span style="color: #666666">**2</span>]
|
||||
X_ <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[x_, x_<span style="color: #666666">**2</span>]
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic">### 1.</span>
|
||||
lmb_values <span style="color: #666666">=</span> [<span style="color: #666666">1e-4</span>, <span style="color: #666666">1e-3</span>, <span style="color: #666666">1e-2</span>, <span style="color: #666666">10</span>, <span style="color: #666666">1e2</span>, <span style="color: #666666">1e4</span>]
|
||||
num_values <span style="color: #666666">=</span> <span style="color: #008000">len</span>(lmb_values)
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Ridge-regression of centered and not centered data</span>
|
||||
beta_ridge <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #666666">3</span>,num_values))
|
||||
beta_ridge_centered <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #666666">3</span>,num_values))
|
||||
|
||||
I3 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(<span style="color: #666666">3</span>)
|
||||
I2 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(<span style="color: #666666">2</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i,lmb <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(lmb_values):
|
||||
beta_ridge[:,i] <span style="color: #666666">=</span> (np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X<span style="color: #666666">.</span>T @ X <span style="color: #666666">+</span> lmb<span style="color: #666666">*</span>I3) @ X<span style="color: #666666">.</span>T @ y)<span style="color: #666666">.</span>flatten()
|
||||
beta_ridge_centered[<span style="color: #666666">1</span>:,i] <span style="color: #666666">=</span> (np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X_<span style="color: #666666">.</span>T @ X_ <span style="color: #666666">+</span> lmb<span style="color: #666666">*</span>I2) @ X_<span style="color: #666666">.</span>T @ y_)<span style="color: #666666">.</span>flatten()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># sett beta_0 = np.mean(y)</span>
|
||||
beta_ridge_centered[<span style="color: #666666">0</span>,:] <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean(y)
|
||||
|
||||
<span style="color: #408080; font-style: italic">## OLS (ordinary least squares) solution </span>
|
||||
beta_ls <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X<span style="color: #666666">.</span>T @ X ) @ X<span style="color: #666666">.</span>T @ y
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Evaluate the models</span>
|
||||
pred_ls <span style="color: #666666">=</span> X @ beta_ls
|
||||
pred_ridge <span style="color: #666666">=</span> X @ beta_ridge
|
||||
pred_ridge_centered <span style="color: #666666">=</span> X_ @ beta_ridge_centered[<span style="color: #666666">1</span>:] <span style="color: #666666">+</span> beta_ridge_centered[<span style="color: #666666">0</span>,:]
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Plot the results</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Sorting</span>
|
||||
sort_ind <span style="color: #666666">=</span> np<span style="color: #666666">.</span>argsort(x[:,<span style="color: #666666">0</span>])
|
||||
|
||||
x_plot <span style="color: #666666">=</span> x[sort_ind,<span style="color: #666666">0</span>]
|
||||
x_centered_plot <span style="color: #666666">=</span> x_[sort_ind,<span style="color: #666666">0</span>]
|
||||
|
||||
pred_ls_plot <span style="color: #666666">=</span> pred_ls[sort_ind,<span style="color: #666666">0</span>]
|
||||
pred_ridge_plot <span style="color: #666666">=</span> pred_ridge[sort_ind,:]
|
||||
pred_ridge_centered_plot <span style="color: #666666">=</span> pred_ridge_centered[sort_ind,:]
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Plott not centered</span>
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ls_plot,label<span style="color: #666666">=</span><span style="color: #BA2121">'ls'</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ridge_plot[:,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x,y,<span style="color: #BA2121">'ro'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression on un-centered data'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Plott centered</span>
|
||||
plt<span style="color: #666666">.</span>figure()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_centered_plot,pred_ridge_centered_plot[:,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x_,y,<span style="color: #BA2121">'ro'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression on centered data'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic"># 2.</span>
|
||||
|
||||
pred_ridge_scikit <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((n_samples,num_values))
|
||||
<span style="color: #008000; font-weight: bold">for</span> i,lmb <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(lmb_values):
|
||||
pred_ridge_scikit[:,i] <span style="color: #666666">=</span> (Ridge(alpha<span style="color: #666666">=</span>lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000">False</span>)<span style="color: #666666">.</span>fit(X,y)<span style="color: #666666">.</span>predict(X))<span style="color: #666666">.</span>flatten() <span style="color: #408080; font-style: italic"># fit_intercept=False fordi bias er allerede i X</span>
|
||||
|
||||
plt<span style="color: #666666">.</span>figure()
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ls_plot,label<span style="color: #666666">=</span><span style="color: #BA2121">'ls'</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ridge_scikit[sort_ind,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'scikit-ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x,y,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression using scikit'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #408080; font-style: italic">### R2-score of the results</span>
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'lambda = </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for scikit: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge_scikit[:,i]))
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for own code, not centered: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge[:,i]))
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for own, centered: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge_centered[:,i]))
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs038.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs031.html">32</a></li>
|
||||
<li><a href="._Regression-bs032.html">33</a></li>
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li class="active"><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs040.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,304 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0040"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec39" class="anchor">Fitting vs. predicting when data is in the model class </h2>
|
||||
|
||||
<p>
|
||||
We start by considering the case
|
||||
\( f(x)=2x \).
|
||||
|
||||
<p>
|
||||
Then the data is clearly generated by a model that is contained within
|
||||
all three model classes we are using to make predictions (linear
|
||||
models, third order polynomials, and tenth order polynomials).
|
||||
|
||||
<p>
|
||||
Run the code for the following cases:
|
||||
|
||||
<ol>
|
||||
<li> For \( f(x)=2x \) , \( Ntrain=10 \) and \( \sigma =0 \) (noiseless case), train the three classes of models (linear, third-order polynomial, and tenth order polynomial) for a training set when \( x \in [0,1] \) . Make graphs comparing fits for different order of polynomials. Which model fits the data the best?</li>
|
||||
<li> Do you think that the data that has the least error on the training set will also make the best predictions? Why or why not? Can you try to discuss and formalize your intuition? What can go right and what can go wrong?</li>
|
||||
<li> Check your answer by seeing how well your fits predict newly generated test data (including on data outside the range you fit on, for example \( x \in [0,1.2] \) ) using the code below. How well do you do on points in the range of x where you trained the model? How about points outside the original training data set?</li>
|
||||
<li> Repeat the above for \( f(x)=2x \) , \( Ntrain=10 \) , and \( \sigma=1 \) . What changes?</li>
|
||||
</ol>
|
||||
|
||||
Repeat the exercises above for \( f(x)=2x \) , \( Ntrain=100 \) , and \( \sigma=1 \) . What changes?
|
||||
Summarize what you have learned about the relationship between model complexity (number of parameters), goodness of fit on training data, and the ability to predict well.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs039.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs032.html">33</a></li>
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li class="active"><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs041.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,291 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0041"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec40" class="anchor">Fitting versus predicting when data is not in the model class </h2>
|
||||
|
||||
<p>
|
||||
Thus far, we have considered the case where the data is generated using a model contained in the model class. Now consider \( f(x)=2x-10x^5+15x^{10} \) . Notice that the for linear and third-order polynomial the true model \( f(x) \) is not contained in model class.
|
||||
|
||||
<ol>
|
||||
<li> Do better fits lead to better predictions?</li>
|
||||
<li> What is the relationship between the true model for generating the data and the model class that has the most predictive power? How is this related to the model complexity? How does this depend on the number of data points \( Ntrain \) and \( \sigma \)?</li>
|
||||
</ol>
|
||||
|
||||
Summarize what you think you learned about the relationship of knowing the true model class and predictive power.
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs040.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs033.html">34</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li class="active"><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs042.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,365 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0042"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec41" class="anchor">The code </h2>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">sk</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">import</span> datasets, linear_model
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> PolynomialFeatures
|
||||
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">mpl</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">matplotlib</span> <span style="color: #008000; font-weight: bold">import</span> pyplot <span style="color: #008000; font-weight: bold">as</span> plt
|
||||
|
||||
<span style="color: #666666">%</span>matplotlib notebook
|
||||
|
||||
<span style="color: #408080; font-style: italic"># The Training Data</span>
|
||||
|
||||
N_train<span style="color: #666666">=100</span>
|
||||
|
||||
sigma_train<span style="color: #666666">=1</span>;
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train on integers</span>
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.05</span>,<span style="color: #666666">0.95</span>,N_train)
|
||||
<span style="color: #408080; font-style: italic"># Draw random noise</span>
|
||||
s <span style="color: #666666">=</span> sigma_train<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(N_train)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#linear</span>
|
||||
y<span style="color: #666666">=2*</span>x<span style="color: #666666">+</span>s
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Tenth Order</span>
|
||||
<span style="color: #408080; font-style: italic">#y=2*x-10*x**5+15*x**10+s</span>
|
||||
|
||||
p1<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x,y, <span style="color: #BA2121">"o"</span>,ms<span style="color: #666666">=15</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">'Training'</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear Regression</span>
|
||||
<span style="color: #408080; font-style: italic"># Create linear regression object</span>
|
||||
clf <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train the model using the training sets</span>
|
||||
clf<span style="color: #666666">.</span>fit(x[:, np<span style="color: #666666">.</span>newaxis], y)
|
||||
<span style="color: #408080; font-style: italic"># The coefficients</span>
|
||||
|
||||
xplot<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.02</span>,<span style="color: #666666">0.98</span>,<span style="color: #666666">200</span>)
|
||||
linear_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf<span style="color: #666666">.</span>predict(xplot[:, np<span style="color: #666666">.</span>newaxis]),label<span style="color: #666666">=</span><span style="color: #BA2121">'Linear'</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Polynomial Regression</span>
|
||||
|
||||
|
||||
poly3 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=3</span>)
|
||||
X <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf3 <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
clf3<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
|
||||
Xplot<span style="color: #666666">=</span>poly3<span style="color: #666666">.</span>fit_transform(xplot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly3_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf3<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Poly 3'</span>)
|
||||
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic">#poly5 = PolynomialFeatures(degree=5)</span>
|
||||
<span style="color: #408080; font-style: italic">#X = poly5.fit_transform(x[:,np.newaxis])</span>
|
||||
<span style="color: #408080; font-style: italic">#clf5 = linear_model.LinearRegression()</span>
|
||||
<span style="color: #408080; font-style: italic">#clf5.fit(X,y)</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Xplot=poly5.fit_transform(xplot[:,np.newaxis])</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.plot(xplot, clf5.predict(Xplot), 'r--',linewidth=1)</span>
|
||||
|
||||
poly10 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=10</span>)
|
||||
X <span style="color: #666666">=</span> poly10<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf10 <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
clf10<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
Xplot<span style="color: #666666">=</span>poly10<span style="color: #666666">.</span>fit_transform(xplot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly10_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf10<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Poly 10'</span>)
|
||||
|
||||
axes <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>gca()
|
||||
axes<span style="color: #666666">.</span>set_ylim([<span style="color: #666666">-7</span>,<span style="color: #666666">7</span>])
|
||||
|
||||
handles, labels<span style="color: #666666">=</span>axes<span style="color: #666666">.</span>get_legend_handles_labels()
|
||||
plt<span style="color: #666666">.</span>legend(handles,labels, loc<span style="color: #666666">=</span><span style="color: #BA2121">'lower center'</span>)
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">"$x$"</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">"$y$"</span>)
|
||||
Title<span style="color: #666666">=</span><span style="color: #BA2121">"$N=$"</span><span style="color: #666666">+</span><span style="color: #008000">str</span>(N_train)<span style="color: #666666">+</span><span style="color: #BA2121">", $\sigma=$"</span><span style="color: #666666">+</span><span style="color: #008000">str</span>(sigma_train)
|
||||
plt<span style="color: #666666">.</span>title(Title<span style="color: #666666">+</span><span style="color: #BA2121">" (train)"</span>)
|
||||
plt<span style="color: #666666">.</span>tight_layout()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs041.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs034.html">35</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li class="active"><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs043.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,327 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0043"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec42" class="anchor">Generating test data </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Generate Test Data</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Number of test data</span>
|
||||
N_test<span style="color: #666666">=20</span>
|
||||
|
||||
sigma_test<span style="color: #666666">=</span>sigma_train
|
||||
|
||||
max_x<span style="color: #666666">=1.2</span>
|
||||
x_test<span style="color: #666666">=</span>max_x<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>random(N_test)
|
||||
<span style="color: #408080; font-style: italic"># Draw random noise</span>
|
||||
s_test <span style="color: #666666">=</span> sigma_test<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(N_test)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear</span>
|
||||
y_test<span style="color: #666666">=2*</span>x_test<span style="color: #666666">+</span>s_test
|
||||
<span style="color: #408080; font-style: italic">#Tenth order</span>
|
||||
<span style="color: #408080; font-style: italic">#y_test=2*x_test-10*x_test**5+15*x_test**10+s_test</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Make design matrices for prediction</span>
|
||||
x_plot<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>,max_x, <span style="color: #666666">200</span>)
|
||||
X3 <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x_plot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
X10 <span style="color: #666666">=</span> poly10<span style="color: #666666">.</span>fit_transform(x_plot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
|
||||
<span style="color: #666666">%</span>matplotlib notebook
|
||||
|
||||
fig <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>figure()
|
||||
p1<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_test,y_test<span style="color: #666666">.</span>transpose(), <span style="color: #BA2121">'o'</span>, ms<span style="color: #666666">=12</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">'data'</span>)
|
||||
p2<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf<span style="color: #666666">.</span>predict(x_plot[:,np<span style="color: #666666">.</span>newaxis]), label<span style="color: #666666">=</span><span style="color: #BA2121">'linear'</span>)
|
||||
p3<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf3<span style="color: #666666">.</span>predict(X3), label<span style="color: #666666">=</span><span style="color: #BA2121">'3rd order'</span>)
|
||||
p10<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf10<span style="color: #666666">.</span>predict(X10), label<span style="color: #666666">=</span><span style="color: #BA2121">'10th order'</span>)
|
||||
|
||||
|
||||
plt<span style="color: #666666">.</span>legend(loc<span style="color: #666666">=2</span>)
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>legend(loc<span style="color: #666666">=</span><span style="color: #BA2121">'best'</span>)
|
||||
plt<span style="color: #666666">.</span>title(Title<span style="color: #666666">+</span><span style="color: #BA2121">" (pred.)"</span>)
|
||||
plt<span style="color: #666666">.</span>tight_layout()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear Filename</span>
|
||||
<span style="color: #408080; font-style: italic">#filename_test=Title+"pred-linear.pdf"</span>
|
||||
<span style="color: #408080; font-style: italic">#Tenth Order Filename</span>
|
||||
<span style="color: #408080; font-style: italic">#filename_test=Title+"pred-o10.pdf"</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.savefig(filename_test)</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.ylim((-6,12))</span>
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs042.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs035.html">36</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li class="active"><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs044.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,278 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0044"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec43" class="anchor">Lasso regression </h2>
|
||||
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs043.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs036.html">37</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li class="active"><a href="._Regression-bs044.html">45</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs045.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -0,0 +1,275 @@
|
||||
<!--
|
||||
Automatically generated HTML file from DocOnce source
|
||||
(https://github.com/hplgit/doconce/)
|
||||
-->
|
||||
<html>
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||||
<meta name="description" content="Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis">
|
||||
|
||||
<title>Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</title>
|
||||
|
||||
<!-- Bootstrap style: bootstrap -->
|
||||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||||
<!-- not necessary
|
||||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||||
-->
|
||||
|
||||
<style type="text/css">
|
||||
|
||||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||||
.dropdown-menu {
|
||||
height: auto;
|
||||
max-height: 400px;
|
||||
overflow-x: hidden;
|
||||
}
|
||||
|
||||
/* Adds an invisible element before each target to offset for the navigation
|
||||
bar */
|
||||
.anchor::before {
|
||||
content:"";
|
||||
display:block;
|
||||
height:50px; /* fixed header height for style bootstrap */
|
||||
margin:-50px 0 0; /* negative fixed header height */
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec9'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
|
||||
|
||||
|
||||
<script type="text/x-mathjax-config">
|
||||
MathJax.Hub.Config({
|
||||
TeX: {
|
||||
equationNumbers: { autoNumber: "none" },
|
||||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script type="text/javascript" async
|
||||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
<!-- Bootstrap navigation bar -->
|
||||
<div class="navbar navbar-default navbar-fixed-top">
|
||||
<div class="navbar-header">
|
||||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
<span class="icon-bar"></span>
|
||||
</button>
|
||||
<a class="navbar-brand" href="Regression-bs.html">Data Analysis and Machine Learning: Linear Regression and more Advanced Regression Analysis</a>
|
||||
</div>
|
||||
|
||||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||||
<ul class="nav navbar-nav navbar-right">
|
||||
<li class="dropdown">
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div> <!-- end of navigation bar -->
|
||||
|
||||
<div class="container">
|
||||
|
||||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||||
|
||||
<a name="part0045"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec44" class="anchor">Logistic regression </h2>
|
||||
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
<ul class="pagination">
|
||||
<li><a href="._Regression-bs044.html">«</a></li>
|
||||
<li><a href="._Regression-bs000.html">1</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs038.html">39</a></li>
|
||||
<li><a href="._Regression-bs039.html">40</a></li>
|
||||
<li><a href="._Regression-bs040.html">41</a></li>
|
||||
<li><a href="._Regression-bs041.html">42</a></li>
|
||||
<li><a href="._Regression-bs042.html">43</a></li>
|
||||
<li><a href="._Regression-bs043.html">44</a></li>
|
||||
<li><a href="._Regression-bs044.html">45</a></li>
|
||||
<li class="active"><a href="._Regression-bs045.html">46</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
</div> <!-- end container -->
|
||||
<!-- include javascript, jQuery *first* -->
|
||||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||||
|
||||
<!-- Bootstrap footer
|
||||
<footer>
|
||||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||||
</footer>
|
||||
-->
|
||||
|
||||
|
||||
<center style="font-size:80%">
|
||||
<!-- copyright only on the titlepage -->
|
||||
</center>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
@@ -41,17 +41,14 @@ Automatically generated HTML file from DocOnce source
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -59,12 +56,12 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -73,47 +70,71 @@ Automatically generated HTML file from DocOnce source
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -152,42 +173,50 @@ MathJax.Hub.Config({
|
||||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||||
<ul class="dropdown-menu">
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs001.html#___sec0" style="font-size: 80%;">Regression analysis, overarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs002.html#___sec1" style="font-size: 80%;">Regression analysis, overarching aims II</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs003.html#___sec2" style="font-size: 80%;">General linear models</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs004.html#___sec3" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs005.html#___sec4" style="font-size: 80%;">Rewriting the fitting procedure as a linear algebra problem, follows</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs006.html#___sec5" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs007.html#___sec6" style="font-size: 80%;">Generalizing the fitting procedure as a linear algebra problem</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs008.html#___sec7" style="font-size: 80%;">Optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs009.html#___sec8" style="font-size: 80%;">Optimizing our parameters, more details</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs010.html#___sec9" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs011.html#___sec10" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs012.html#___sec11" style="font-size: 80%;">Interpretations and optimizing our parameters</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs013.html#___sec12" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs014.html#___sec13" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs015.html#___sec14" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs016.html#___sec15" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs017.html#___sec16" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Simple regression model with gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Simple regression model with stochastic gradient descent</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs018.html#___sec17" style="font-size: 80%;">The \( \chi^2 \) function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs019.html#___sec18" style="font-size: 80%;">Simple regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs020.html#___sec19" style="font-size: 80%;">Simple regression model, now using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs021.html#___sec20" style="font-size: 80%;">Simple linear regression model using <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs022.html#___sec21" style="font-size: 80%;">Simple linear regression model</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs023.html#___sec22" style="font-size: 80%;">Less noise</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs024.html#___sec23" style="font-size: 80%;">How to study our fits</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs025.html#___sec24" style="font-size: 80%;">Minimizing the cost function</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs026.html#___sec25" style="font-size: 80%;">Relative error</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs027.html#___sec26" style="font-size: 80%;">The richness of <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs028.html#___sec27" style="font-size: 80%;">Functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs029.html#___sec28" style="font-size: 80%;">Other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs030.html#___sec29" style="font-size: 80%;">The mean absolute error and other functions in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs031.html#___sec30" style="font-size: 80%;">Cubic polynomial in <b>scikit-learn</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs032.html#___sec31" style="font-size: 80%;">Polynomial Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs033.html#___sec32" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs034.html#___sec33" style="font-size: 80%;">Expectation value and variance</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs035.html#___sec34" style="font-size: 80%;">The singular value decompostion</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Lasso and Ridge regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">Logistic regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs036.html#___sec35" style="font-size: 80%;">Code examples for Ridge and Lasso Regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs037.html#___sec36" style="font-size: 80%;">From standard regression to Ridge regressions</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs038.html#___sec37" style="font-size: 80%;">Fixing the singularity</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs039.html#___sec38" style="font-size: 80%;">A second-order polynomial with Ridge and Lasso</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs040.html#___sec39" style="font-size: 80%;">Fitting vs. predicting when data is in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs041.html#___sec40" style="font-size: 80%;">Fitting versus predicting when data is not in the model class</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs042.html#___sec41" style="font-size: 80%;">The code</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs043.html#___sec42" style="font-size: 80%;">Generating test data</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs044.html#___sec43" style="font-size: 80%;">Lasso regression</a></li>
|
||||
<!-- navigation toc: --> <li><a href="._Regression-bs045.html#___sec44" style="font-size: 80%;">Logistic regression</a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -222,7 +251,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Aug 24, 2018</h4></center> <!-- date -->
|
||||
<center><h4>Sep 6, 2018</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
|
||||
@@ -246,7 +275,7 @@ MathJax.Hub.Config({
|
||||
<li><a href="._Regression-bs008.html">9</a></li>
|
||||
<li><a href="._Regression-bs009.html">10</a></li>
|
||||
<li><a href="">...</a></li>
|
||||
<li><a href="._Regression-bs037.html">38</a></li>
|
||||
<li><a href="._Regression-bs045.html">46</a></li>
|
||||
<li><a href="._Regression-bs001.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
@@ -148,7 +148,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p> <br>
|
||||
<center><h4>Aug 24, 2018</h4></center> <!-- date -->
|
||||
<center><h4>Sep 6, 2018</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
|
||||
@@ -182,7 +182,35 @@ A regression model aims at finding a likelihood function \( p(y\vert \hat{x}) \)
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec1">General linear models </h2>
|
||||
<h2 id="___sec1">Regression analysis, overarching aims II </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
Consider an experiment in which \( p \) characteristics of \( n \) samples are
|
||||
measured. The data from this experiment are denoted \( \mathbf{X} \), with
|
||||
\( \mathbf{X} \) as above. The matrix \( \mathbf{X} \) is called the <em>design
|
||||
matrix</em>. Additional information of the samples is available in the
|
||||
form of \( \mathbf{Y} \) (also as above). The variable \( \mathbf{Y} \) is
|
||||
generally referred to as the <em>response variable</em>. The aim of
|
||||
regression analysis is to explain \( \mathbf{Y} \) in terms of
|
||||
\( \mathbf{X} \) through a functional relationship like \( Y_i =
|
||||
f(\mathbf{X}_{i,\ast}) \). When no prior knowledge on the form of
|
||||
\( f(\cdot) \) is available, it is common to assume a linear relationship
|
||||
between \( \mathbf{X} \) and \( \mathbf{Y} \). This assumption gives rise to
|
||||
the <em>linear regression model</em> where \( \beta = (\beta_1, \ldots,
|
||||
\beta_p)^{\top} \) is the <em>regression parameter</em>. The parameter
|
||||
\( \beta_j \), \( j=1, \ldots, p \), represents the effect size of covariate
|
||||
\( j \) on the response. That is, for each unit change in covariate \( j \)
|
||||
(while keeping the other covariates fixed) the observed change in the
|
||||
response is equal to \( \beta_j \).
|
||||
|
||||
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec2">General linear models </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -204,7 +232,7 @@ where \( \epsilon_i \) is the error in our approximation.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec2">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -225,7 +253,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<h2 id="___sec4">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -275,7 +303,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec4">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -299,7 +327,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec6">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -330,7 +358,7 @@ The left-hand side of this equation forms know. Our error vector \( \hat{\epsilo
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec6">Optimizing our parameters </h2>
|
||||
<h2 id="___sec7">Optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -353,7 +381,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec7">Optimizing our parameters, more details </h2>
|
||||
<h2 id="___sec8">Optimizing our parameters, more details </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -382,7 +410,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec8">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -430,7 +458,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -461,7 +489,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec11">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -494,7 +522,7 @@ meaning that the solution for \( \hat{\beta} \) is the one which minimizes the r
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec11">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -517,7 +545,7 @@ where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -548,7 +576,7 @@ where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -577,7 +605,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -613,7 +641,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -642,7 +670,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec17">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -698,7 +726,7 @@ This approach (different linear and non-linear regression) suffers often from bo
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec17">Simple regression model </h2>
|
||||
<h2 id="___sec18">Simple regression model </h2>
|
||||
We are now ready to write our first program which aims at solving the above linear regression equations. We start with data we have produced ourselves, in this case normally distributed random numbers along the \( x \)-axis. These numbers define then the value of a function \( y(x)=4+3x+N(0,1) \). Thereafter we order the \( x \) values and employ our linear regression algorithm to set up the best fit. Here we find it useful to use the numpy function \( c\_ \) arrays where arrays are stacked along their last axis after being upgraded to at least two dimensions with ones post-pended to the shape. The following examples help in understanding what happens
|
||||
<p>
|
||||
|
||||
@@ -738,7 +766,7 @@ We see that, as expected, a linear fit gives a seemingly (from the graph) good r
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec18">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec19">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
@@ -770,7 +798,7 @@ plt.show()
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec19">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec20">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We start with perhaps our simplest possible example, using <b>scikit-learn</b> to perform linear regression analysis on a data set produced by us.
|
||||
@@ -841,7 +869,7 @@ plt.show()
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec20">Simple linear regression model </h2>
|
||||
<h2 id="___sec21">Simple linear regression model </h2>
|
||||
|
||||
<p>
|
||||
This example serves several aims. It allows us to demonstrate several
|
||||
@@ -865,7 +893,7 @@ where \( x \) is defined as before.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec21">Less noise </h2>
|
||||
<h2 id="___sec22">Less noise </h2>
|
||||
|
||||
<p>
|
||||
Does the fit look better? Indeed, by
|
||||
@@ -878,7 +906,7 @@ have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec22">How to study our fits </h2>
|
||||
<h2 id="___sec23">How to study our fits </h2>
|
||||
|
||||
<p>
|
||||
We need more rigorous criteria in defining whether we have succeeded or
|
||||
@@ -902,7 +930,7 @@ dimensionless.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec23">Minimizing the cost function </h2>
|
||||
<h2 id="___sec24">Minimizing the cost function </h2>
|
||||
|
||||
<p>
|
||||
Minimizing the cost function is a central aspect of
|
||||
@@ -923,7 +951,7 @@ the \( \chi^2 \) function becomes smaller.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec24">Relative error </h2>
|
||||
<h2 id="___sec25">Relative error </h2>
|
||||
|
||||
<p>
|
||||
There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define
|
||||
@@ -965,7 +993,7 @@ relative error.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec25">The richness of <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec26">The richness of <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
As mentioned above, <b>scikit-learn</b> has an impressive functionality.
|
||||
@@ -1011,7 +1039,7 @@ plt.show()
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec26">Functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec27">Functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The function <b>coef</b> gives us the parameter \( \beta \) of our fit while <b>intercept</b> yields
|
||||
@@ -1030,7 +1058,7 @@ this function as being similar to the \( \chi^2 \) function defined above.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec27">Other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec28">Other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The <b>r2score</b> function computes \( R^2 \), the coefficient of
|
||||
@@ -1058,7 +1086,7 @@ $$
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec28">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec29">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
Another quantity will meet again in our discussions of regression analysis is
|
||||
@@ -1087,12 +1115,13 @@ years etc.
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec29">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec30">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We will discuss in more
|
||||
detail these and other functions in the various lectures. We conclude this part with another example. Instead of
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
Add description of the various python commands.
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1129,84 +1158,12 @@ plt.show()
|
||||
<span style="color: #8B008B; font-weight: bold">print</span> (error(y))
|
||||
</pre></div>
|
||||
<p>
|
||||
Similarly, using <b>R</b>, we can perform similar studies.
|
||||
(more details on <b>R</b> will be inserted later).
|
||||
Using <b>R</b>, we can perform similar studies.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec30">Simple regression model with gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #228B22"># Importing various packages</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">math</span> <span style="color: #8B008B; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">random</span> <span style="color: #8B008B; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
|
||||
x = <span style="color: #B452CD">2</span>*np.random.rand(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">4</span>+<span style="color: #B452CD">3</span>*x+np.random.randn(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
xb = np.c_[np.ones((<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)), x]
|
||||
theta_linreg = np.linalg.inv(xb.T.dot(xb)).dot(xb.T).dot(y)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta_linreg)
|
||||
theta = np.random.randn(<span style="color: #B452CD">2</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
eta = <span style="color: #B452CD">0.1</span>
|
||||
Niterations = <span style="color: #B452CD">1000</span>
|
||||
m = <span style="color: #B452CD">100</span>
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> <span style="color: #658b00">iter</span> <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(Niterations):
|
||||
gradients = <span style="color: #B452CD">2.0</span>/m*xb.T.dot(xb.dot(theta)-y)
|
||||
theta -= eta*gradients
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta)
|
||||
xnew = np.array([[<span style="color: #B452CD">0</span>],[<span style="color: #B452CD">2</span>]])
|
||||
xbnew = np.c_[np.ones((<span style="color: #B452CD">2</span>,<span style="color: #B452CD">1</span>)), xnew]
|
||||
ypredict = xbnew.dot(theta)
|
||||
ypredict2 = xbnew.dot(theta_linreg)
|
||||
plt.plot(xnew, ypredict, <span style="color: #CD5555">"r-"</span>)
|
||||
plt.plot(xnew, ypredict2, <span style="color: #CD5555">"b-"</span>)
|
||||
plt.plot(x, y ,<span style="color: #CD5555">'ro'</span>)
|
||||
plt.axis([<span style="color: #B452CD">0</span>,<span style="color: #B452CD">2.0</span>,<span style="color: #B452CD">0</span>, <span style="color: #B452CD">15.0</span>])
|
||||
plt.xlabel(<span style="color: #CD5555">r'$x$'</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">r'$y$'</span>)
|
||||
plt.title(<span style="color: #CD5555">r'Random numbers '</span>)
|
||||
plt.show()
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec31">Simple regression model with stochastic gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #228B22"># Importing various packages</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">math</span> <span style="color: #8B008B; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">random</span> <span style="color: #8B008B; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> SGDRegressor
|
||||
|
||||
x = <span style="color: #B452CD">2</span>*np.random.rand(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">4</span>+<span style="color: #B452CD">3</span>*x+np.random.randn(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
xb = np.c_[np.ones((<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)), x]
|
||||
theta_linreg = np.linalg.inv(xb.T.dot(xb)).dot(xb.T).dot(y)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta_linreg)
|
||||
sgdreg = SGDRegressor(n_iter = <span style="color: #B452CD">50</span>, penalty=<span style="color: #658b00">None</span>, eta0=<span style="color: #B452CD">0.1</span>)
|
||||
sgdreg.fit(x,y.ravel())
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(sgdreg.intercept_, sgdreg.coef_)
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec32">Polynomial Regression </h2>
|
||||
<h2 id="___sec31">Polynomial Regression </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
@@ -1238,7 +1195,94 @@ plt.show()
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec33">Ridge and Lasso Regression </h2>
|
||||
<h2 id="___sec32">Linking the regression analysis with a statistical interpretation </h2>
|
||||
|
||||
<p>
|
||||
Before we proceed, and to link with our discussions of Bayesian statistics to come, it is useful the derive the standard regression analysis equations using a statistical interpretation. This allows us also to derive quantities like the variance and other expectation values in a rather straightforward way.
|
||||
|
||||
<p>
|
||||
It is assumed that \( \varepsilon_i
|
||||
\sim \mathcal{N}(0, \sigma^2) \) and the \( \varepsilon_{i} \) are
|
||||
independent, i.e.:
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align*}
|
||||
\mbox{Cov}(\varepsilon_{i_1},
|
||||
\varepsilon_{i_2}) & = \left\{ \begin{array}{lcc} \sigma^2 & \mbox{if}
|
||||
& i_1 = i_2, \\ 0 & \mbox{if} & i_1 \not= i_2. \end{array} \right.
|
||||
\end{align*}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
The randomness of \( \varepsilon_i \) implies that
|
||||
\( \mathbf{Y}_i \) is also a random variable. In particular,
|
||||
\( \mathbf{Y}_i \) is normally distributed, because \( \varepsilon_i \sim
|
||||
\mathcal{N}(0, \sigma^2) \) and \( \mathbf{X}_{i,\ast} \, \beta \) is a
|
||||
non-random scalar. To specify the parameters of the distribution of
|
||||
\( \mathbf{Y}_i \) we need to calculate its first two moments.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec33">Expectation value and variance </h2>
|
||||
|
||||
<p>
|
||||
Its expectation equals:
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbb{E}(Y_i) & =
|
||||
\mathbb{E}(\mathbf{X}_{i, \ast} \, \beta) + \mathbb{E}(\varepsilon_i)
|
||||
\, \, \, = \, \, \, \mathbf{X}_{i, \ast} \, \beta,
|
||||
\end{align*}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
while
|
||||
its variance is
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align*} \mbox{Var}(Y_i) & = \mathbb{E} \{ [Y_i
|
||||
- \mathbb{E}(Y_i)]^2 \} \, \, \, = \, \, \, \mathbb{E} ( Y_i^2 ) -
|
||||
[\mathbb{E}(Y_i)]^2 \\ & = \mathbb{E} [ ( \mathbf{X}_{i, \ast} \,
|
||||
\beta + \varepsilon_i )^2] - ( \mathbf{X}_{i, \ast} \, \beta)^2 \\ &
|
||||
= \mathbb{E} [ ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2 \varepsilon_i
|
||||
\mathbf{X}_{i, \ast} \, \beta + \varepsilon_i^2 ] - ( \mathbf{X}_{i,
|
||||
\ast} \, \beta)^2 \\ & = ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2
|
||||
\mathbb{E}(\varepsilon_i) \mathbf{X}_{i, \ast} \, \beta +
|
||||
\mathbb{E}(\varepsilon_i^2 ) - ( \mathbf{X}_{i, \ast} \, \beta)^2
|
||||
\\ & = \mathbb{E}(\varepsilon_i^2 ) \, \, \, = \, \, \,
|
||||
\mbox{Var}(\varepsilon_i) \, \, \, = \, \, \, \sigma^2.
|
||||
\end{align*}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
Hence, \( Y_i \sim \mathcal{N}( \mathbf{X}_{i, \ast} \, \beta, \sigma^2) \).
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
A general
|
||||
\( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal
|
||||
matrix \( \hat{D} \) of dimensionality \( n\times n \) and two orthognal
|
||||
matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality
|
||||
\( m \times m \) and the last dimensionality \( n\times n \).
|
||||
We have then
|
||||
<p> <br>
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{D}\hat{V}^T
|
||||
$$
|
||||
<p> <br>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec35">Code examples for Ridge and Lasso Regression </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1320,37 +1364,403 @@ plt.show()
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
How can we use the singular value decomposition to find the parameters \( \beta_j \)? More details will come. We first note that a general \( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal matrix \( \hat{\Sigma} \) of dimensionality \( n\times n \) and two orthognal matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality \( m \times n \) and the last dimensionality \( n\times n \). We have then
|
||||
<p> <br>
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{\Sigma}\hat{V}
|
||||
$$
|
||||
<p> <br>
|
||||
</div>
|
||||
<h2 id="___sec36">From standard regression to Ridge regressions </h2>
|
||||
|
||||
<p>
|
||||
Add codes and discuss this in connection with lasso and ridge, show example where the standard inversion of a matrix fails and where SVD comes to rescue
|
||||
One of the typical problems we encounter with linear regression, in particular
|
||||
when the matrix \( \hat{X} \) (our so-called design matrix) is high-dimensional,
|
||||
are problems with near singular or singular matrices. The column vectors of \( \hat{X} \)
|
||||
may be linearly dependent, normally referred to as super-collinearity.
|
||||
This means that the matrix may be rank deficient and it is basically impossible to
|
||||
to model the data using linear regression. As an example, consider the matrix
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbf{X} & = \left[
|
||||
\begin{array}{rrr}
|
||||
1 & -1 & 2
|
||||
\\
|
||||
1 & 0 & 1
|
||||
\\
|
||||
1 & 2 & -1
|
||||
\\
|
||||
1 & 1 & 0
|
||||
\end{array} \right]
|
||||
\end{align*}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
<p>
|
||||
The columns of \( \hat{X} \) are linearly dependent. We se this easily since the
|
||||
the first column is the row-wise sum of the other two columns. The rank (more correct,
|
||||
the column rank) of a matrix is the dimension of the space spanned by the
|
||||
column vectors. Hence, the rank of \( \mathbf{X} \) is equal to the number
|
||||
of linearly independent columns. In this particular case the matrix has rank 2.
|
||||
|
||||
<p>
|
||||
Super-collinearity of an \( (n \times p) \)-dimensional design matrix \( \mathbf{X} \) implies
|
||||
that the inverse of the matrix \( \hat{X}^T\hat{x} \) (the matrix we needto invert to solve the linear regression equations) is non-invertible. If we have a square matrix that does not have an inverse, we say this matrix singular. The example here demonstrates this
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align*}
|
||||
\hat{X} & = \left[
|
||||
\begin{array}{rr}
|
||||
1 & -1
|
||||
\\
|
||||
1 & -1
|
||||
\end{array} \right].
|
||||
\end{align*}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
We see easily that \( \mbox{det}(\hat{X}) = x_{11} x_{22} - x_{12} x_{21} = 1 \times (-1) - 1 \times (-1) = 0 \). Hence, \( \mathbf{X} \) is singular and its inverse is undefined.
|
||||
This is equivalent to saying that the matrix \( \hat{X} \) has at least an eigenvalue which is zero.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec35">Lasso and Ridge regression </h2>
|
||||
<h2 id="___sec37">Fixing the singularity </h2>
|
||||
|
||||
<p>
|
||||
Discuss the mathematics here
|
||||
If our design matrix \( \hat{X} \) which enters the linear regression problem
|
||||
<p> <br>
|
||||
$$
|
||||
\begin{align}
|
||||
\hat{\beta} & = (\hat{X}^{T} \hat{X})^{-1} \hat{X}^{T} \hat{y},
|
||||
\tag{1}
|
||||
\end{align}
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
has linearly dependent column vectors, we will not be able to compute the inverse
|
||||
of \( \hat{X}^T\hat{X} \) and we cannot find the parameters (estimators) \( \beta_i \).
|
||||
The estimators are only well-defined if \( (\hat{X}^{T}\hat{X})^{-1} \) exits.
|
||||
This is more likely to happen when the matrix \( \hat{X} \) is high-dimensional. In this case it is likely to encounter a situation where
|
||||
the regression parameters \( \beta_i \) cannot be estimated.
|
||||
|
||||
<p>
|
||||
The <em>ad hoc</em> approach which was introduced in the 70s was simply to add a diagonal component to the matrix to invert, that is we change
|
||||
<p> <br>
|
||||
$$
|
||||
\hat{X}^{T} \hat{X} \rightarrow \hat{X}^{T} \hat{X}+\lambda \hat{I},
|
||||
$$
|
||||
<p> <br>
|
||||
|
||||
where \( \hat{I} \) is the identity matrix.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec36">Logistic regression </h2>
|
||||
Add discussion about classification versus regression, show examples of more than two cases and why regression is not the best approach. Motivate for k-nearest neighbors
|
||||
<h2 id="___sec38">A second-order polynomial with Ridge and Lasso </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.metrics</span> <span style="color: #8B008B; font-weight: bold">import</span> r2_score
|
||||
|
||||
np.random.seed(<span style="color: #B452CD">4155</span>)
|
||||
|
||||
n_samples = <span style="color: #B452CD">100</span>
|
||||
|
||||
x = np.random.rand(n_samples,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">5</span>*x*x + <span style="color: #B452CD">0.1</span>*np.random.rand(n_samples,<span style="color: #B452CD">1</span>)
|
||||
|
||||
<span style="color: #228B22"># Centering x and y.</span>
|
||||
x_ = x - np.mean(x)
|
||||
y_ = y - np.mean(y) <span style="color: #228B22"># beta_0 = mean(y)</span>
|
||||
|
||||
X = np.c_[np.ones((n_samples,<span style="color: #B452CD">1</span>)), x, x**<span style="color: #B452CD">2</span>]
|
||||
X_ = np.c_[x_, x_**<span style="color: #B452CD">2</span>]
|
||||
|
||||
|
||||
<span style="color: #228B22">### 1.</span>
|
||||
lmb_values = [<span style="color: #B452CD">1e-4</span>, <span style="color: #B452CD">1e-3</span>, <span style="color: #B452CD">1e-2</span>, <span style="color: #B452CD">10</span>, <span style="color: #B452CD">1e2</span>, <span style="color: #B452CD">1e4</span>]
|
||||
num_values = <span style="color: #658b00">len</span>(lmb_values)
|
||||
|
||||
<span style="color: #228B22">## Ridge-regression of centered and not centered data</span>
|
||||
beta_ridge = np.zeros((<span style="color: #B452CD">3</span>,num_values))
|
||||
beta_ridge_centered = np.zeros((<span style="color: #B452CD">3</span>,num_values))
|
||||
|
||||
I3 = np.eye(<span style="color: #B452CD">3</span>)
|
||||
I2 = np.eye(<span style="color: #B452CD">2</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i,lmb <span style="color: #8B008B">in</span> <span style="color: #658b00">enumerate</span>(lmb_values):
|
||||
beta_ridge[:,i] = (np.linalg.inv( X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X + lmb*I3) <span style="color: #a61717; background-color: #e3d2d2">@</span> X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y).flatten()
|
||||
beta_ridge_centered[<span style="color: #B452CD">1</span>:,i] = (np.linalg.inv( X_.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X_ + lmb*I2) <span style="color: #a61717; background-color: #e3d2d2">@</span> X_.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y_).flatten()
|
||||
|
||||
<span style="color: #228B22"># sett beta_0 = np.mean(y)</span>
|
||||
beta_ridge_centered[<span style="color: #B452CD">0</span>,:] = np.mean(y)
|
||||
|
||||
<span style="color: #228B22">## OLS (ordinary least squares) solution </span>
|
||||
beta_ls = np.linalg.inv( X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X ) <span style="color: #a61717; background-color: #e3d2d2">@</span> X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y
|
||||
|
||||
<span style="color: #228B22">## Evaluate the models</span>
|
||||
pred_ls = X <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ls
|
||||
pred_ridge = X <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ridge
|
||||
pred_ridge_centered = X_ <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ridge_centered[<span style="color: #B452CD">1</span>:] + beta_ridge_centered[<span style="color: #B452CD">0</span>,:]
|
||||
|
||||
<span style="color: #228B22">## Plot the results</span>
|
||||
|
||||
<span style="color: #228B22"># Sorting</span>
|
||||
sort_ind = np.argsort(x[:,<span style="color: #B452CD">0</span>])
|
||||
|
||||
x_plot = x[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
x_centered_plot = x_[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
|
||||
pred_ls_plot = pred_ls[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
pred_ridge_plot = pred_ridge[sort_ind,:]
|
||||
pred_ridge_centered_plot = pred_ridge_centered[sort_ind,:]
|
||||
|
||||
<span style="color: #228B22"># Plott not centered</span>
|
||||
plt.plot(x_plot,pred_ls_plot,label=<span style="color: #CD5555">'ls'</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_plot,pred_ridge_plot[:,i],label=<span style="color: #CD5555">'ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x,y,<span style="color: #CD5555">'ro'</span>)
|
||||
|
||||
plt.title(<span style="color: #CD5555">'linear regression on un-centered data'</span>)
|
||||
plt.legend()
|
||||
|
||||
<span style="color: #228B22"># Plott centered</span>
|
||||
plt.figure()
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_centered_plot,pred_ridge_centered_plot[:,i],label=<span style="color: #CD5555">'ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x_,y,<span style="color: #CD5555">'ro'</span>)
|
||||
|
||||
plt.title(<span style="color: #CD5555">'linear regression on centered data'</span>)
|
||||
plt.legend()
|
||||
|
||||
|
||||
<span style="color: #228B22"># 2.</span>
|
||||
|
||||
pred_ridge_scikit = np.zeros((n_samples,num_values))
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i,lmb <span style="color: #8B008B">in</span> <span style="color: #658b00">enumerate</span>(lmb_values):
|
||||
pred_ridge_scikit[:,i] = (Ridge(alpha=lmb,fit_intercept=<span style="color: #658b00">False</span>).fit(X,y).predict(X)).flatten() <span style="color: #228B22"># fit_intercept=False fordi bias er allerede i X</span>
|
||||
|
||||
plt.figure()
|
||||
|
||||
plt.plot(x_plot,pred_ls_plot,label=<span style="color: #CD5555">'ls'</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_plot,pred_ridge_scikit[sort_ind,i],label=<span style="color: #CD5555">'scikit-ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x,y,<span style="color: #CD5555">'ro'</span>)
|
||||
plt.legend()
|
||||
plt.title(<span style="color: #CD5555">'linear regression using scikit'</span>)
|
||||
|
||||
plt.show()
|
||||
|
||||
<span style="color: #228B22">### R2-score of the results</span>
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'lambda = %g'</span>%lmb_values[i])
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for scikit: %g'</span>%r2_score(y,pred_ridge_scikit[:,i]))
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for own code, not centered: %g'</span>%r2_score(y,pred_ridge[:,i]))
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for own, centered: %g\n'</span>%r2_score(y,pred_ridge_centered[:,i]))
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec39">Fitting vs. predicting when data is in the model class </h2>
|
||||
|
||||
<p>
|
||||
Add examples on classification problems
|
||||
We start by considering the case
|
||||
\( f(x)=2x \).
|
||||
|
||||
<p>
|
||||
Then the data is clearly generated by a model that is contained within
|
||||
all three model classes we are using to make predictions (linear
|
||||
models, third order polynomials, and tenth order polynomials).
|
||||
|
||||
<p>
|
||||
Run the code for the following cases:
|
||||
|
||||
<ol>
|
||||
<p><li> For \( f(x)=2x \) , \( Ntrain=10 \) and \( \sigma =0 \) (noiseless case), train the three classes of models (linear, third-order polynomial, and tenth order polynomial) for a training set when \( x \in [0,1] \) . Make graphs comparing fits for different order of polynomials. Which model fits the data the best?</li>
|
||||
<p><li> Do you think that the data that has the least error on the training set will also make the best predictions? Why or why not? Can you try to discuss and formalize your intuition? What can go right and what can go wrong?</li>
|
||||
<p><li> Check your answer by seeing how well your fits predict newly generated test data (including on data outside the range you fit on, for example \( x \in [0,1.2] \) ) using the code below. How well do you do on points in the range of x where you trained the model? How about points outside the original training data set?</li>
|
||||
<p><li> Repeat the above for \( f(x)=2x \) , \( Ntrain=10 \) , and \( \sigma=1 \) . What changes?</li>
|
||||
</ol>
|
||||
<p>
|
||||
|
||||
Repeat the exercises above for \( f(x)=2x \) , \( Ntrain=100 \) , and \( \sigma=1 \) . What changes?
|
||||
Summarize what you have learned about the relationship between model complexity (number of parameters), goodness of fit on training data, and the ability to predict well.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec40">Fitting versus predicting when data is not in the model class </h2>
|
||||
|
||||
<p>
|
||||
Thus far, we have considered the case where the data is generated using a model contained in the model class. Now consider \( f(x)=2x-10x^5+15x^{10} \) . Notice that the for linear and third-order polynomial the true model \( f(x) \) is not contained in model class.
|
||||
|
||||
<ol>
|
||||
<p><li> Do better fits lead to better predictions?</li>
|
||||
<p><li> What is the relationship between the true model for generating the data and the model class that has the most predictive power? How is this related to the model complexity? How does this depend on the number of data points \( Ntrain \) and \( \sigma \)?</li>
|
||||
</ol>
|
||||
<p>
|
||||
|
||||
Summarize what you think you learned about the relationship of knowing the true model class and predictive power.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec41">The code </h2>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">sklearn</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">sk</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn</span> <span style="color: #8B008B; font-weight: bold">import</span> datasets, linear_model
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> PolynomialFeatures
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">mpl</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">matplotlib</span> <span style="color: #8B008B; font-weight: bold">import</span> pyplot <span style="color: #8B008B; font-weight: bold">as</span> plt
|
||||
|
||||
%matplotlib notebook
|
||||
|
||||
<span style="color: #228B22"># The Training Data</span>
|
||||
|
||||
N_train=<span style="color: #B452CD">100</span>
|
||||
|
||||
sigma_train=<span style="color: #B452CD">1</span>;
|
||||
|
||||
<span style="color: #228B22"># Train on integers</span>
|
||||
x=np.linspace(<span style="color: #B452CD">0.05</span>,<span style="color: #B452CD">0.95</span>,N_train)
|
||||
<span style="color: #228B22"># Draw random noise</span>
|
||||
s = sigma_train*np.random.randn(N_train)
|
||||
|
||||
<span style="color: #228B22">#linear</span>
|
||||
y=<span style="color: #B452CD">2</span>*x+s
|
||||
|
||||
<span style="color: #228B22">#Tenth Order</span>
|
||||
<span style="color: #228B22">#y=2*x-10*x**5+15*x**10+s</span>
|
||||
|
||||
p1=plt.plot(x,y, <span style="color: #CD5555">"o"</span>,ms=<span style="color: #B452CD">15</span>, label=<span style="color: #CD5555">'Training'</span>)
|
||||
|
||||
<span style="color: #228B22">#Linear Regression</span>
|
||||
<span style="color: #228B22"># Create linear regression object</span>
|
||||
clf = linear_model.LinearRegression()
|
||||
|
||||
<span style="color: #228B22"># Train the model using the training sets</span>
|
||||
clf.fit(x[:, np.newaxis], y)
|
||||
<span style="color: #228B22"># The coefficients</span>
|
||||
|
||||
xplot=np.linspace(<span style="color: #B452CD">0.02</span>,<span style="color: #B452CD">0.98</span>,<span style="color: #B452CD">200</span>)
|
||||
linear_plot=plt.plot(xplot, clf.predict(xplot[:, np.newaxis]),label=<span style="color: #CD5555">'Linear'</span>)
|
||||
|
||||
<span style="color: #228B22">#Polynomial Regression</span>
|
||||
|
||||
|
||||
poly3 = PolynomialFeatures(degree=<span style="color: #B452CD">3</span>)
|
||||
X = poly3.fit_transform(x[:,np.newaxis])
|
||||
clf3 = linear_model.LinearRegression()
|
||||
clf3.fit(X,y)
|
||||
|
||||
|
||||
Xplot=poly3.fit_transform(xplot[:,np.newaxis])
|
||||
poly3_plot=plt.plot(xplot, clf3.predict(Xplot), label=<span style="color: #CD5555">'Poly 3'</span>)
|
||||
|
||||
|
||||
|
||||
<span style="color: #228B22">#poly5 = PolynomialFeatures(degree=5)</span>
|
||||
<span style="color: #228B22">#X = poly5.fit_transform(x[:,np.newaxis])</span>
|
||||
<span style="color: #228B22">#clf5 = linear_model.LinearRegression()</span>
|
||||
<span style="color: #228B22">#clf5.fit(X,y)</span>
|
||||
|
||||
<span style="color: #228B22">#Xplot=poly5.fit_transform(xplot[:,np.newaxis])</span>
|
||||
<span style="color: #228B22">#plt.plot(xplot, clf5.predict(Xplot), 'r--',linewidth=1)</span>
|
||||
|
||||
poly10 = PolynomialFeatures(degree=<span style="color: #B452CD">10</span>)
|
||||
X = poly10.fit_transform(x[:,np.newaxis])
|
||||
clf10 = linear_model.LinearRegression()
|
||||
clf10.fit(X,y)
|
||||
|
||||
Xplot=poly10.fit_transform(xplot[:,np.newaxis])
|
||||
poly10_plot=plt.plot(xplot, clf10.predict(Xplot), label=<span style="color: #CD5555">'Poly 10'</span>)
|
||||
|
||||
axes = plt.gca()
|
||||
axes.set_ylim([-<span style="color: #B452CD">7</span>,<span style="color: #B452CD">7</span>])
|
||||
|
||||
handles, labels=axes.get_legend_handles_labels()
|
||||
plt.legend(handles,labels, loc=<span style="color: #CD5555">'lower center'</span>)
|
||||
plt.xlabel(<span style="color: #CD5555">"$x$"</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">"$y$"</span>)
|
||||
Title=<span style="color: #CD5555">"$N=$"</span>+<span style="color: #658b00">str</span>(N_train)+<span style="color: #CD5555">", $\sigma=$"</span>+<span style="color: #658b00">str</span>(sigma_train)
|
||||
plt.title(Title+<span style="color: #CD5555">" (train)"</span>)
|
||||
plt.tight_layout()
|
||||
plt.show()
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec42">Generating test data </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #228B22"># Generate Test Data</span>
|
||||
|
||||
<span style="color: #228B22">#Number of test data</span>
|
||||
N_test=<span style="color: #B452CD">20</span>
|
||||
|
||||
sigma_test=sigma_train
|
||||
|
||||
max_x=<span style="color: #B452CD">1.2</span>
|
||||
x_test=max_x*np.random.random(N_test)
|
||||
<span style="color: #228B22"># Draw random noise</span>
|
||||
s_test = sigma_test*np.random.randn(N_test)
|
||||
|
||||
<span style="color: #228B22">#Linear</span>
|
||||
y_test=<span style="color: #B452CD">2</span>*x_test+s_test
|
||||
<span style="color: #228B22">#Tenth order</span>
|
||||
<span style="color: #228B22">#y_test=2*x_test-10*x_test**5+15*x_test**10+s_test</span>
|
||||
|
||||
<span style="color: #228B22">#Make design matrices for prediction</span>
|
||||
x_plot=np.linspace(<span style="color: #B452CD">0</span>,max_x, <span style="color: #B452CD">200</span>)
|
||||
X3 = poly3.fit_transform(x_plot[:,np.newaxis])
|
||||
X10 = poly10.fit_transform(x_plot[:,np.newaxis])
|
||||
|
||||
%matplotlib notebook
|
||||
|
||||
fig = plt.figure()
|
||||
p1=plt.plot(x_test,y_test.transpose(), <span style="color: #CD5555">'o'</span>, ms=<span style="color: #B452CD">12</span>, label=<span style="color: #CD5555">'data'</span>)
|
||||
p2=plt.plot(x_plot,clf.predict(x_plot[:,np.newaxis]), label=<span style="color: #CD5555">'linear'</span>)
|
||||
p3=plt.plot(x_plot,clf3.predict(X3), label=<span style="color: #CD5555">'3rd order'</span>)
|
||||
p10=plt.plot(x_plot,clf10.predict(X10), label=<span style="color: #CD5555">'10th order'</span>)
|
||||
|
||||
|
||||
plt.legend(loc=<span style="color: #B452CD">2</span>)
|
||||
plt.xlabel(<span style="color: #CD5555">'$x$'</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">'$y$'</span>)
|
||||
plt.legend(loc=<span style="color: #CD5555">'best'</span>)
|
||||
plt.title(Title+<span style="color: #CD5555">" (pred.)"</span>)
|
||||
plt.tight_layout()
|
||||
plt.show()
|
||||
|
||||
<span style="color: #228B22">#Linear Filename</span>
|
||||
<span style="color: #228B22">#filename_test=Title+"pred-linear.pdf"</span>
|
||||
<span style="color: #228B22">#Tenth Order Filename</span>
|
||||
<span style="color: #228B22">#filename_test=Title+"pred-o10.pdf"</span>
|
||||
<span style="color: #228B22">#plt.savefig(filename_test)</span>
|
||||
<span style="color: #228B22">#plt.ylim((-6,12))</span>
|
||||
</pre></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec43">Lasso regression </h2>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec44">Logistic regression </h2>
|
||||
</section>
|
||||
|
||||
|
||||
|
||||
@@ -61,17 +61,14 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -79,12 +76,12 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -93,47 +90,71 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -175,7 +196,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Aug 24, 2018</h4></center> <!-- date -->
|
||||
<center><h4>Sep 6, 2018</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
@@ -205,7 +226,38 @@ A regression model aims at finding a likelihood function \( p(y\vert \hat{x}) \)
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">General linear models </h2>
|
||||
<h2 id="___sec1">Regression analysis, overarching aims II </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
<p>
|
||||
Consider an experiment in which \( p \) characteristics of \( n \) samples are
|
||||
measured. The data from this experiment are denoted \( \mathbf{X} \), with
|
||||
\( \mathbf{X} \) as above. The matrix \( \mathbf{X} \) is called the <em>design
|
||||
matrix</em>. Additional information of the samples is available in the
|
||||
form of \( \mathbf{Y} \) (also as above). The variable \( \mathbf{Y} \) is
|
||||
generally referred to as the <em>response variable</em>. The aim of
|
||||
regression analysis is to explain \( \mathbf{Y} \) in terms of
|
||||
\( \mathbf{X} \) through a functional relationship like \( Y_i =
|
||||
f(\mathbf{X}_{i,\ast}) \). When no prior knowledge on the form of
|
||||
\( f(\cdot) \) is available, it is common to assume a linear relationship
|
||||
between \( \mathbf{X} \) and \( \mathbf{Y} \). This assumption gives rise to
|
||||
the <em>linear regression model</em> where \( \beta = (\beta_1, \ldots,
|
||||
\beta_p)^{\top} \) is the <em>regression parameter</em>. The parameter
|
||||
\( \beta_j \), \( j=1, \ldots, p \), represents the effect size of covariate
|
||||
\( j \) on the response. That is, for each unit change in covariate \( j \)
|
||||
(while keeping the other covariates fixed) the observed change in the
|
||||
response is equal to \( \beta_j \).
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec2">General linear models </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -226,7 +278,7 @@ where \( \epsilon_i \) is the error in our approximation.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec2">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -246,7 +298,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<h2 id="___sec4">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -287,7 +339,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec4">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -310,7 +362,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec6">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -338,7 +390,7 @@ The left-hand side of this equation forms know. Our error vector \( \hat{\epsilo
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec6">Optimizing our parameters </h2>
|
||||
<h2 id="___sec7">Optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -360,7 +412,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec7">Optimizing our parameters, more details </h2>
|
||||
<h2 id="___sec8">Optimizing our parameters, more details </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -384,7 +436,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec8">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -423,7 +475,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -449,7 +501,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec11">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -477,7 +529,7 @@ meaning that the solution for \( \hat{\beta} \) is the one which minimizes the r
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec11">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -500,7 +552,7 @@ where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -528,7 +580,7 @@ where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -554,7 +606,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -585,7 +637,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -609,7 +661,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec17">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -655,7 +707,7 @@ This approach (different linear and non-linear regression) suffers often from bo
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">Simple regression model </h2>
|
||||
<h2 id="___sec18">Simple regression model </h2>
|
||||
We are now ready to write our first program which aims at solving the above linear regression equations. We start with data we have produced ourselves, in this case normally distributed random numbers along the \( x \)-axis. These numbers define then the value of a function \( y(x)=4+3x+N(0,1) \). Thereafter we order the \( x \) values and employ our linear regression algorithm to set up the best fit. Here we find it useful to use the numpy function \( c\_ \) arrays where arrays are stacked along their last axis after being upgraded to at least two dimensions with ones post-pended to the shape. The following examples help in understanding what happens
|
||||
<p>
|
||||
|
||||
@@ -695,7 +747,7 @@ We see that, as expected, a linear fit gives a seemingly (from the graph) good r
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec18">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec19">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
@@ -726,7 +778,7 @@ plt.show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec19">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec20">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We start with perhaps our simplest possible example, using <b>scikit-learn</b> to perform linear regression analysis on a data set produced by us.
|
||||
@@ -794,7 +846,7 @@ plt.show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec20">Simple linear regression model </h2>
|
||||
<h2 id="___sec21">Simple linear regression model </h2>
|
||||
|
||||
<p>
|
||||
This example serves several aims. It allows us to demonstrate several
|
||||
@@ -816,7 +868,7 @@ where \( x \) is defined as before.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec21">Less noise </h2>
|
||||
<h2 id="___sec22">Less noise </h2>
|
||||
|
||||
<p>
|
||||
Does the fit look better? Indeed, by
|
||||
@@ -829,7 +881,7 @@ have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec22">How to study our fits </h2>
|
||||
<h2 id="___sec23">How to study our fits </h2>
|
||||
|
||||
<p>
|
||||
We need more rigorous criteria in defining whether we have succeeded or
|
||||
@@ -851,7 +903,7 @@ dimensionless.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec23">Minimizing the cost function </h2>
|
||||
<h2 id="___sec24">Minimizing the cost function </h2>
|
||||
|
||||
<p>
|
||||
Minimizing the cost function is a central aspect of
|
||||
@@ -872,7 +924,7 @@ the \( \chi^2 \) function becomes smaller.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec24">Relative error </h2>
|
||||
<h2 id="___sec25">Relative error </h2>
|
||||
|
||||
<p>
|
||||
There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define
|
||||
@@ -912,7 +964,7 @@ relative error.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec25">The richness of <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec26">The richness of <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
As mentioned above, <b>scikit-learn</b> has an impressive functionality.
|
||||
@@ -957,7 +1009,7 @@ plt.show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec26">Functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec27">Functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The function <b>coef</b> gives us the parameter \( \beta \) of our fit while <b>intercept</b> yields
|
||||
@@ -974,7 +1026,7 @@ this function as being similar to the \( \chi^2 \) function defined above.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec27">Other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec28">Other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The <b>r2score</b> function computes \( R^2 \), the coefficient of
|
||||
@@ -998,7 +1050,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec28">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec29">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
Another quantity will meet again in our discussions of regression analysis is
|
||||
@@ -1023,12 +1075,13 @@ years etc.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec29">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec30">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We will discuss in more
|
||||
detail these and other functions in the various lectures. We conclude this part with another example. Instead of
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
Add description of the various python commands.
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1065,82 +1118,12 @@ plt.show()
|
||||
<span style="color: #8B008B; font-weight: bold">print</span> (error(y))
|
||||
</pre></div>
|
||||
<p>
|
||||
Similarly, using <b>R</b>, we can perform similar studies.
|
||||
(more details on <b>R</b> will be inserted later).
|
||||
Using <b>R</b>, we can perform similar studies.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec30">Simple regression model with gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #228B22"># Importing various packages</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">math</span> <span style="color: #8B008B; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">random</span> <span style="color: #8B008B; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
|
||||
x = <span style="color: #B452CD">2</span>*np.random.rand(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">4</span>+<span style="color: #B452CD">3</span>*x+np.random.randn(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
xb = np.c_[np.ones((<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)), x]
|
||||
theta_linreg = np.linalg.inv(xb.T.dot(xb)).dot(xb.T).dot(y)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta_linreg)
|
||||
theta = np.random.randn(<span style="color: #B452CD">2</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
eta = <span style="color: #B452CD">0.1</span>
|
||||
Niterations = <span style="color: #B452CD">1000</span>
|
||||
m = <span style="color: #B452CD">100</span>
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> <span style="color: #658b00">iter</span> <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(Niterations):
|
||||
gradients = <span style="color: #B452CD">2.0</span>/m*xb.T.dot(xb.dot(theta)-y)
|
||||
theta -= eta*gradients
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta)
|
||||
xnew = np.array([[<span style="color: #B452CD">0</span>],[<span style="color: #B452CD">2</span>]])
|
||||
xbnew = np.c_[np.ones((<span style="color: #B452CD">2</span>,<span style="color: #B452CD">1</span>)), xnew]
|
||||
ypredict = xbnew.dot(theta)
|
||||
ypredict2 = xbnew.dot(theta_linreg)
|
||||
plt.plot(xnew, ypredict, <span style="color: #CD5555">"r-"</span>)
|
||||
plt.plot(xnew, ypredict2, <span style="color: #CD5555">"b-"</span>)
|
||||
plt.plot(x, y ,<span style="color: #CD5555">'ro'</span>)
|
||||
plt.axis([<span style="color: #B452CD">0</span>,<span style="color: #B452CD">2.0</span>,<span style="color: #B452CD">0</span>, <span style="color: #B452CD">15.0</span>])
|
||||
plt.xlabel(<span style="color: #CD5555">r'$x$'</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">r'$y$'</span>)
|
||||
plt.title(<span style="color: #CD5555">r'Random numbers '</span>)
|
||||
plt.show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec31">Simple regression model with stochastic gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #228B22"># Importing various packages</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">math</span> <span style="color: #8B008B; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">random</span> <span style="color: #8B008B; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> SGDRegressor
|
||||
|
||||
x = <span style="color: #B452CD">2</span>*np.random.rand(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">4</span>+<span style="color: #B452CD">3</span>*x+np.random.randn(<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)
|
||||
|
||||
xb = np.c_[np.ones((<span style="color: #B452CD">100</span>,<span style="color: #B452CD">1</span>)), x]
|
||||
theta_linreg = np.linalg.inv(xb.T.dot(xb)).dot(xb.T).dot(y)
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(theta_linreg)
|
||||
sgdreg = SGDRegressor(n_iter = <span style="color: #B452CD">50</span>, penalty=<span style="color: #658b00">None</span>, eta0=<span style="color: #B452CD">0.1</span>)
|
||||
sgdreg.fit(x,y.ravel())
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(sgdreg.intercept_, sgdreg.coef_)
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec32">Polynomial Regression </h2>
|
||||
<h2 id="___sec31">Polynomial Regression </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
@@ -1168,10 +1151,92 @@ plt.ylabel(<span style="color: #CD5555">r'$y$'</span>)
|
||||
plt.title(<span style="color: #CD5555">r'Random numbers '</span>)
|
||||
plt.show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec32">Linking the regression analysis with a statistical interpretation </h2>
|
||||
|
||||
<p>
|
||||
Before we proceed, and to link with our discussions of Bayesian statistics to come, it is useful the derive the standard regression analysis equations using a statistical interpretation. This allows us also to derive quantities like the variance and other expectation values in a rather straightforward way.
|
||||
|
||||
<p>
|
||||
It is assumed that \( \varepsilon_i
|
||||
\sim \mathcal{N}(0, \sigma^2) \) and the \( \varepsilon_{i} \) are
|
||||
independent, i.e.:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mbox{Cov}(\varepsilon_{i_1},
|
||||
\varepsilon_{i_2}) & = \left\{ \begin{array}{lcc} \sigma^2 & \mbox{if}
|
||||
& i_1 = i_2, \\ 0 & \mbox{if} & i_1 \not= i_2. \end{array} \right.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
The randomness of \( \varepsilon_i \) implies that
|
||||
\( \mathbf{Y}_i \) is also a random variable. In particular,
|
||||
\( \mathbf{Y}_i \) is normally distributed, because \( \varepsilon_i \sim
|
||||
\mathcal{N}(0, \sigma^2) \) and \( \mathbf{X}_{i,\ast} \, \beta \) is a
|
||||
non-random scalar. To specify the parameters of the distribution of
|
||||
\( \mathbf{Y}_i \) we need to calculate its first two moments.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec33">Ridge and Lasso Regression </h2>
|
||||
<h2 id="___sec33">Expectation value and variance </h2>
|
||||
|
||||
<p>
|
||||
Its expectation equals:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbb{E}(Y_i) & =
|
||||
\mathbb{E}(\mathbf{X}_{i, \ast} \, \beta) + \mathbb{E}(\varepsilon_i)
|
||||
\, \, \, = \, \, \, \mathbf{X}_{i, \ast} \, \beta,
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
while
|
||||
its variance is
|
||||
$$
|
||||
\begin{align*} \mbox{Var}(Y_i) & = \mathbb{E} \{ [Y_i
|
||||
- \mathbb{E}(Y_i)]^2 \} \, \, \, = \, \, \, \mathbb{E} ( Y_i^2 ) -
|
||||
[\mathbb{E}(Y_i)]^2 \\ & = \mathbb{E} [ ( \mathbf{X}_{i, \ast} \,
|
||||
\beta + \varepsilon_i )^2] - ( \mathbf{X}_{i, \ast} \, \beta)^2 \\ &
|
||||
= \mathbb{E} [ ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2 \varepsilon_i
|
||||
\mathbf{X}_{i, \ast} \, \beta + \varepsilon_i^2 ] - ( \mathbf{X}_{i,
|
||||
\ast} \, \beta)^2 \\ & = ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2
|
||||
\mathbb{E}(\varepsilon_i) \mathbf{X}_{i, \ast} \, \beta +
|
||||
\mathbb{E}(\varepsilon_i^2 ) - ( \mathbf{X}_{i, \ast} \, \beta)^2
|
||||
\\ & = \mathbb{E}(\varepsilon_i^2 ) \, \, \, = \, \, \,
|
||||
\mbox{Var}(\varepsilon_i) \, \, \, = \, \, \, \sigma^2.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
Hence, \( Y_i \sim \mathcal{N}( \mathbf{X}_{i, \ast} \, \beta, \sigma^2) \).
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
<p>
|
||||
A general
|
||||
\( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal
|
||||
matrix \( \hat{D} \) of dimensionality \( n\times n \) and two orthognal
|
||||
matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality
|
||||
\( m \times m \) and the last dimensionality \( n\times n \).
|
||||
We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{D}\hat{V}^T
|
||||
$$
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec35">Code examples for Ridge and Lasso Regression </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1252,38 +1317,390 @@ plt.show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
How can we use the singular value decomposition to find the parameters \( \beta_j \)? More details will come. We first note that a general \( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal matrix \( \hat{\Sigma} \) of dimensionality \( n\times n \) and two orthognal matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality \( m \times n \) and the last dimensionality \( n\times n \). We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{\Sigma}\hat{V}
|
||||
$$
|
||||
</div>
|
||||
|
||||
<h2 id="___sec36">From standard regression to Ridge regressions </h2>
|
||||
|
||||
<p>
|
||||
Add codes and discuss this in connection with lasso and ridge, show example where the standard inversion of a matrix fails and where SVD comes to rescue
|
||||
One of the typical problems we encounter with linear regression, in particular
|
||||
when the matrix \( \hat{X} \) (our so-called design matrix) is high-dimensional,
|
||||
are problems with near singular or singular matrices. The column vectors of \( \hat{X} \)
|
||||
may be linearly dependent, normally referred to as super-collinearity.
|
||||
This means that the matrix may be rank deficient and it is basically impossible to
|
||||
to model the data using linear regression. As an example, consider the matrix
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbf{X} & = \left[
|
||||
\begin{array}{rrr}
|
||||
1 & -1 & 2
|
||||
\\
|
||||
1 & 0 & 1
|
||||
\\
|
||||
1 & 2 & -1
|
||||
\\
|
||||
1 & 1 & 0
|
||||
\end{array} \right]
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
<p>
|
||||
The columns of \( \hat{X} \) are linearly dependent. We se this easily since the
|
||||
the first column is the row-wise sum of the other two columns. The rank (more correct,
|
||||
the column rank) of a matrix is the dimension of the space spanned by the
|
||||
column vectors. Hence, the rank of \( \mathbf{X} \) is equal to the number
|
||||
of linearly independent columns. In this particular case the matrix has rank 2.
|
||||
|
||||
<p>
|
||||
Super-collinearity of an \( (n \times p) \)-dimensional design matrix \( \mathbf{X} \) implies
|
||||
that the inverse of the matrix \( \hat{X}^T\hat{x} \) (the matrix we needto invert to solve the linear regression equations) is non-invertible. If we have a square matrix that does not have an inverse, we say this matrix singular. The example here demonstrates this
|
||||
$$
|
||||
\begin{align*}
|
||||
\hat{X} & = \left[
|
||||
\begin{array}{rr}
|
||||
1 & -1
|
||||
\\
|
||||
1 & -1
|
||||
\end{array} \right].
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
We see easily that \( \mbox{det}(\hat{X}) = x_{11} x_{22} - x_{12} x_{21} = 1 \times (-1) - 1 \times (-1) = 0 \). Hence, \( \mathbf{X} \) is singular and its inverse is undefined.
|
||||
This is equivalent to saying that the matrix \( \hat{X} \) has at least an eigenvalue which is zero.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec35">Lasso and Ridge regression </h2>
|
||||
<h2 id="___sec37">Fixing the singularity </h2>
|
||||
|
||||
<p>
|
||||
Discuss the mathematics here
|
||||
If our design matrix \( \hat{X} \) which enters the linear regression problem
|
||||
$$
|
||||
\begin{align}
|
||||
\hat{\beta} & = (\hat{X}^{T} \hat{X})^{-1} \hat{X}^{T} \hat{y},
|
||||
\label{_auto1}
|
||||
\end{align}
|
||||
$$
|
||||
|
||||
has linearly dependent column vectors, we will not be able to compute the inverse
|
||||
of \( \hat{X}^T\hat{X} \) and we cannot find the parameters (estimators) \( \beta_i \).
|
||||
The estimators are only well-defined if \( (\hat{X}^{T}\hat{X})^{-1} \) exits.
|
||||
This is more likely to happen when the matrix \( \hat{X} \) is high-dimensional. In this case it is likely to encounter a situation where
|
||||
the regression parameters \( \beta_i \) cannot be estimated.
|
||||
|
||||
<p>
|
||||
The <em>ad hoc</em> approach which was introduced in the 70s was simply to add a diagonal component to the matrix to invert, that is we change
|
||||
$$
|
||||
\hat{X}^{T} \hat{X} \rightarrow \hat{X}^{T} \hat{X}+\lambda \hat{I},
|
||||
$$
|
||||
|
||||
where \( \hat{I} \) is the identity matrix.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec36">Logistic regression </h2>
|
||||
Add discussion about classification versus regression, show examples of more than two cases and why regression is not the best approach. Motivate for k-nearest neighbors
|
||||
<h2 id="___sec38">A second-order polynomial with Ridge and Lasso </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib.pyplot</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">plt</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.metrics</span> <span style="color: #8B008B; font-weight: bold">import</span> r2_score
|
||||
|
||||
np.random.seed(<span style="color: #B452CD">4155</span>)
|
||||
|
||||
n_samples = <span style="color: #B452CD">100</span>
|
||||
|
||||
x = np.random.rand(n_samples,<span style="color: #B452CD">1</span>)
|
||||
y = <span style="color: #B452CD">5</span>*x*x + <span style="color: #B452CD">0.1</span>*np.random.rand(n_samples,<span style="color: #B452CD">1</span>)
|
||||
|
||||
<span style="color: #228B22"># Centering x and y.</span>
|
||||
x_ = x - np.mean(x)
|
||||
y_ = y - np.mean(y) <span style="color: #228B22"># beta_0 = mean(y)</span>
|
||||
|
||||
X = np.c_[np.ones((n_samples,<span style="color: #B452CD">1</span>)), x, x**<span style="color: #B452CD">2</span>]
|
||||
X_ = np.c_[x_, x_**<span style="color: #B452CD">2</span>]
|
||||
|
||||
|
||||
<span style="color: #228B22">### 1.</span>
|
||||
lmb_values = [<span style="color: #B452CD">1e-4</span>, <span style="color: #B452CD">1e-3</span>, <span style="color: #B452CD">1e-2</span>, <span style="color: #B452CD">10</span>, <span style="color: #B452CD">1e2</span>, <span style="color: #B452CD">1e4</span>]
|
||||
num_values = <span style="color: #658b00">len</span>(lmb_values)
|
||||
|
||||
<span style="color: #228B22">## Ridge-regression of centered and not centered data</span>
|
||||
beta_ridge = np.zeros((<span style="color: #B452CD">3</span>,num_values))
|
||||
beta_ridge_centered = np.zeros((<span style="color: #B452CD">3</span>,num_values))
|
||||
|
||||
I3 = np.eye(<span style="color: #B452CD">3</span>)
|
||||
I2 = np.eye(<span style="color: #B452CD">2</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i,lmb <span style="color: #8B008B">in</span> <span style="color: #658b00">enumerate</span>(lmb_values):
|
||||
beta_ridge[:,i] = (np.linalg.inv( X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X + lmb*I3) <span style="color: #a61717; background-color: #e3d2d2">@</span> X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y).flatten()
|
||||
beta_ridge_centered[<span style="color: #B452CD">1</span>:,i] = (np.linalg.inv( X_.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X_ + lmb*I2) <span style="color: #a61717; background-color: #e3d2d2">@</span> X_.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y_).flatten()
|
||||
|
||||
<span style="color: #228B22"># sett beta_0 = np.mean(y)</span>
|
||||
beta_ridge_centered[<span style="color: #B452CD">0</span>,:] = np.mean(y)
|
||||
|
||||
<span style="color: #228B22">## OLS (ordinary least squares) solution </span>
|
||||
beta_ls = np.linalg.inv( X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> X ) <span style="color: #a61717; background-color: #e3d2d2">@</span> X.T <span style="color: #a61717; background-color: #e3d2d2">@</span> y
|
||||
|
||||
<span style="color: #228B22">## Evaluate the models</span>
|
||||
pred_ls = X <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ls
|
||||
pred_ridge = X <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ridge
|
||||
pred_ridge_centered = X_ <span style="color: #a61717; background-color: #e3d2d2">@</span> beta_ridge_centered[<span style="color: #B452CD">1</span>:] + beta_ridge_centered[<span style="color: #B452CD">0</span>,:]
|
||||
|
||||
<span style="color: #228B22">## Plot the results</span>
|
||||
|
||||
<span style="color: #228B22"># Sorting</span>
|
||||
sort_ind = np.argsort(x[:,<span style="color: #B452CD">0</span>])
|
||||
|
||||
x_plot = x[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
x_centered_plot = x_[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
|
||||
pred_ls_plot = pred_ls[sort_ind,<span style="color: #B452CD">0</span>]
|
||||
pred_ridge_plot = pred_ridge[sort_ind,:]
|
||||
pred_ridge_centered_plot = pred_ridge_centered[sort_ind,:]
|
||||
|
||||
<span style="color: #228B22"># Plott not centered</span>
|
||||
plt.plot(x_plot,pred_ls_plot,label=<span style="color: #CD5555">'ls'</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_plot,pred_ridge_plot[:,i],label=<span style="color: #CD5555">'ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x,y,<span style="color: #CD5555">'ro'</span>)
|
||||
|
||||
plt.title(<span style="color: #CD5555">'linear regression on un-centered data'</span>)
|
||||
plt.legend()
|
||||
|
||||
<span style="color: #228B22"># Plott centered</span>
|
||||
plt.figure()
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_centered_plot,pred_ridge_centered_plot[:,i],label=<span style="color: #CD5555">'ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x_,y,<span style="color: #CD5555">'ro'</span>)
|
||||
|
||||
plt.title(<span style="color: #CD5555">'linear regression on centered data'</span>)
|
||||
plt.legend()
|
||||
|
||||
|
||||
<span style="color: #228B22"># 2.</span>
|
||||
|
||||
pred_ridge_scikit = np.zeros((n_samples,num_values))
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i,lmb <span style="color: #8B008B">in</span> <span style="color: #658b00">enumerate</span>(lmb_values):
|
||||
pred_ridge_scikit[:,i] = (Ridge(alpha=lmb,fit_intercept=<span style="color: #658b00">False</span>).fit(X,y).predict(X)).flatten() <span style="color: #228B22"># fit_intercept=False fordi bias er allerede i X</span>
|
||||
|
||||
plt.figure()
|
||||
|
||||
plt.plot(x_plot,pred_ls_plot,label=<span style="color: #CD5555">'ls'</span>)
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
plt.plot(x_plot,pred_ridge_scikit[sort_ind,i],label=<span style="color: #CD5555">'scikit-ridge, lmb=%g'</span>%lmb_values[i])
|
||||
|
||||
plt.plot(x,y,<span style="color: #CD5555">'ro'</span>)
|
||||
plt.legend()
|
||||
plt.title(<span style="color: #CD5555">'linear regression using scikit'</span>)
|
||||
|
||||
plt.show()
|
||||
|
||||
<span style="color: #228B22">### R2-score of the results</span>
|
||||
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(num_values):
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'lambda = %g'</span>%lmb_values[i])
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for scikit: %g'</span>%r2_score(y,pred_ridge_scikit[:,i]))
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for own code, not centered: %g'</span>%r2_score(y,pred_ridge[:,i]))
|
||||
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'r2 for own, centered: %g\n'</span>%r2_score(y,pred_ridge_centered[:,i]))
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec39">Fitting vs. predicting when data is in the model class </h2>
|
||||
|
||||
<p>
|
||||
Add examples on classification problems
|
||||
We start by considering the case
|
||||
\( f(x)=2x \).
|
||||
|
||||
<p>
|
||||
Then the data is clearly generated by a model that is contained within
|
||||
all three model classes we are using to make predictions (linear
|
||||
models, third order polynomials, and tenth order polynomials).
|
||||
|
||||
<p>
|
||||
Run the code for the following cases:
|
||||
|
||||
<ol>
|
||||
<li> For \( f(x)=2x \) , \( Ntrain=10 \) and \( \sigma =0 \) (noiseless case), train the three classes of models (linear, third-order polynomial, and tenth order polynomial) for a training set when \( x \in [0,1] \) . Make graphs comparing fits for different order of polynomials. Which model fits the data the best?</li>
|
||||
<li> Do you think that the data that has the least error on the training set will also make the best predictions? Why or why not? Can you try to discuss and formalize your intuition? What can go right and what can go wrong?</li>
|
||||
<li> Check your answer by seeing how well your fits predict newly generated test data (including on data outside the range you fit on, for example \( x \in [0,1.2] \) ) using the code below. How well do you do on points in the range of x where you trained the model? How about points outside the original training data set?</li>
|
||||
<li> Repeat the above for \( f(x)=2x \) , \( Ntrain=10 \) , and \( \sigma=1 \) . What changes?</li>
|
||||
</ol>
|
||||
|
||||
Repeat the exercises above for \( f(x)=2x \) , \( Ntrain=100 \) , and \( \sigma=1 \) . What changes?
|
||||
Summarize what you have learned about the relationship between model complexity (number of parameters), goodness of fit on training data, and the ability to predict well.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec40">Fitting versus predicting when data is not in the model class </h2>
|
||||
|
||||
<p>
|
||||
Thus far, we have considered the case where the data is generated using a model contained in the model class. Now consider \( f(x)=2x-10x^5+15x^{10} \) . Notice that the for linear and third-order polynomial the true model \( f(x) \) is not contained in model class.
|
||||
|
||||
<ol>
|
||||
<li> Do better fits lead to better predictions?</li>
|
||||
<li> What is the relationship between the true model for generating the data and the model class that has the most predictive power? How is this related to the model complexity? How does this depend on the number of data points \( Ntrain \) and \( \sigma \)?</li>
|
||||
</ol>
|
||||
|
||||
Summarize what you think you learned about the relationship of knowing the true model class and predictive power.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec41">The code </h2>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">sklearn</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">sk</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn</span> <span style="color: #8B008B; font-weight: bold">import</span> datasets, linear_model
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> PolynomialFeatures
|
||||
|
||||
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">matplotlib</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">mpl</span>
|
||||
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">matplotlib</span> <span style="color: #8B008B; font-weight: bold">import</span> pyplot <span style="color: #8B008B; font-weight: bold">as</span> plt
|
||||
|
||||
%matplotlib notebook
|
||||
|
||||
<span style="color: #228B22"># The Training Data</span>
|
||||
|
||||
N_train=<span style="color: #B452CD">100</span>
|
||||
|
||||
sigma_train=<span style="color: #B452CD">1</span>;
|
||||
|
||||
<span style="color: #228B22"># Train on integers</span>
|
||||
x=np.linspace(<span style="color: #B452CD">0.05</span>,<span style="color: #B452CD">0.95</span>,N_train)
|
||||
<span style="color: #228B22"># Draw random noise</span>
|
||||
s = sigma_train*np.random.randn(N_train)
|
||||
|
||||
<span style="color: #228B22">#linear</span>
|
||||
y=<span style="color: #B452CD">2</span>*x+s
|
||||
|
||||
<span style="color: #228B22">#Tenth Order</span>
|
||||
<span style="color: #228B22">#y=2*x-10*x**5+15*x**10+s</span>
|
||||
|
||||
p1=plt.plot(x,y, <span style="color: #CD5555">"o"</span>,ms=<span style="color: #B452CD">15</span>, label=<span style="color: #CD5555">'Training'</span>)
|
||||
|
||||
<span style="color: #228B22">#Linear Regression</span>
|
||||
<span style="color: #228B22"># Create linear regression object</span>
|
||||
clf = linear_model.LinearRegression()
|
||||
|
||||
<span style="color: #228B22"># Train the model using the training sets</span>
|
||||
clf.fit(x[:, np.newaxis], y)
|
||||
<span style="color: #228B22"># The coefficients</span>
|
||||
|
||||
xplot=np.linspace(<span style="color: #B452CD">0.02</span>,<span style="color: #B452CD">0.98</span>,<span style="color: #B452CD">200</span>)
|
||||
linear_plot=plt.plot(xplot, clf.predict(xplot[:, np.newaxis]),label=<span style="color: #CD5555">'Linear'</span>)
|
||||
|
||||
<span style="color: #228B22">#Polynomial Regression</span>
|
||||
|
||||
|
||||
poly3 = PolynomialFeatures(degree=<span style="color: #B452CD">3</span>)
|
||||
X = poly3.fit_transform(x[:,np.newaxis])
|
||||
clf3 = linear_model.LinearRegression()
|
||||
clf3.fit(X,y)
|
||||
|
||||
|
||||
Xplot=poly3.fit_transform(xplot[:,np.newaxis])
|
||||
poly3_plot=plt.plot(xplot, clf3.predict(Xplot), label=<span style="color: #CD5555">'Poly 3'</span>)
|
||||
|
||||
|
||||
|
||||
<span style="color: #228B22">#poly5 = PolynomialFeatures(degree=5)</span>
|
||||
<span style="color: #228B22">#X = poly5.fit_transform(x[:,np.newaxis])</span>
|
||||
<span style="color: #228B22">#clf5 = linear_model.LinearRegression()</span>
|
||||
<span style="color: #228B22">#clf5.fit(X,y)</span>
|
||||
|
||||
<span style="color: #228B22">#Xplot=poly5.fit_transform(xplot[:,np.newaxis])</span>
|
||||
<span style="color: #228B22">#plt.plot(xplot, clf5.predict(Xplot), 'r--',linewidth=1)</span>
|
||||
|
||||
poly10 = PolynomialFeatures(degree=<span style="color: #B452CD">10</span>)
|
||||
X = poly10.fit_transform(x[:,np.newaxis])
|
||||
clf10 = linear_model.LinearRegression()
|
||||
clf10.fit(X,y)
|
||||
|
||||
Xplot=poly10.fit_transform(xplot[:,np.newaxis])
|
||||
poly10_plot=plt.plot(xplot, clf10.predict(Xplot), label=<span style="color: #CD5555">'Poly 10'</span>)
|
||||
|
||||
axes = plt.gca()
|
||||
axes.set_ylim([-<span style="color: #B452CD">7</span>,<span style="color: #B452CD">7</span>])
|
||||
|
||||
handles, labels=axes.get_legend_handles_labels()
|
||||
plt.legend(handles,labels, loc=<span style="color: #CD5555">'lower center'</span>)
|
||||
plt.xlabel(<span style="color: #CD5555">"$x$"</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">"$y$"</span>)
|
||||
Title=<span style="color: #CD5555">"$N=$"</span>+<span style="color: #658b00">str</span>(N_train)+<span style="color: #CD5555">", $\sigma=$"</span>+<span style="color: #658b00">str</span>(sigma_train)
|
||||
plt.title(Title+<span style="color: #CD5555">" (train)"</span>)
|
||||
plt.tight_layout()
|
||||
plt.show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec42">Generating test data </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
||||
<div class="highlight" style="background: #eeeedd"><pre style="line-height: 125%"><span></span><span style="color: #228B22"># Generate Test Data</span>
|
||||
|
||||
<span style="color: #228B22">#Number of test data</span>
|
||||
N_test=<span style="color: #B452CD">20</span>
|
||||
|
||||
sigma_test=sigma_train
|
||||
|
||||
max_x=<span style="color: #B452CD">1.2</span>
|
||||
x_test=max_x*np.random.random(N_test)
|
||||
<span style="color: #228B22"># Draw random noise</span>
|
||||
s_test = sigma_test*np.random.randn(N_test)
|
||||
|
||||
<span style="color: #228B22">#Linear</span>
|
||||
y_test=<span style="color: #B452CD">2</span>*x_test+s_test
|
||||
<span style="color: #228B22">#Tenth order</span>
|
||||
<span style="color: #228B22">#y_test=2*x_test-10*x_test**5+15*x_test**10+s_test</span>
|
||||
|
||||
<span style="color: #228B22">#Make design matrices for prediction</span>
|
||||
x_plot=np.linspace(<span style="color: #B452CD">0</span>,max_x, <span style="color: #B452CD">200</span>)
|
||||
X3 = poly3.fit_transform(x_plot[:,np.newaxis])
|
||||
X10 = poly10.fit_transform(x_plot[:,np.newaxis])
|
||||
|
||||
%matplotlib notebook
|
||||
|
||||
fig = plt.figure()
|
||||
p1=plt.plot(x_test,y_test.transpose(), <span style="color: #CD5555">'o'</span>, ms=<span style="color: #B452CD">12</span>, label=<span style="color: #CD5555">'data'</span>)
|
||||
p2=plt.plot(x_plot,clf.predict(x_plot[:,np.newaxis]), label=<span style="color: #CD5555">'linear'</span>)
|
||||
p3=plt.plot(x_plot,clf3.predict(X3), label=<span style="color: #CD5555">'3rd order'</span>)
|
||||
p10=plt.plot(x_plot,clf10.predict(X10), label=<span style="color: #CD5555">'10th order'</span>)
|
||||
|
||||
|
||||
plt.legend(loc=<span style="color: #B452CD">2</span>)
|
||||
plt.xlabel(<span style="color: #CD5555">'$x$'</span>)
|
||||
plt.ylabel(<span style="color: #CD5555">'$y$'</span>)
|
||||
plt.legend(loc=<span style="color: #CD5555">'best'</span>)
|
||||
plt.title(Title+<span style="color: #CD5555">" (pred.)"</span>)
|
||||
plt.tight_layout()
|
||||
plt.show()
|
||||
|
||||
<span style="color: #228B22">#Linear Filename</span>
|
||||
<span style="color: #228B22">#filename_test=Title+"pred-linear.pdf"</span>
|
||||
<span style="color: #228B22">#Tenth Order Filename</span>
|
||||
<span style="color: #228B22">#filename_test=Title+"pred-o10.pdf"</span>
|
||||
<span style="color: #228B22">#plt.savefig(filename_test)</span>
|
||||
<span style="color: #228B22">#plt.ylim((-6,12))</span>
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec43">Lasso regression </h2>
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec44">Logistic regression </h2>
|
||||
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
|
||||
@@ -66,17 +66,14 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Regression analysis, overarching aims', 2, None, '___sec0'),
|
||||
('General linear models', 2, None, '___sec1'),
|
||||
('Regression analysis, overarching aims II', 2, None, '___sec1'),
|
||||
('General linear models', 2, None, '___sec2'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec2'),
|
||||
'___sec3'),
|
||||
('Rewriting the fitting procedure as a linear algebra problem, '
|
||||
'follows',
|
||||
2,
|
||||
None,
|
||||
'___sec3'),
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec4'),
|
||||
@@ -84,12 +81,12 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
2,
|
||||
None,
|
||||
'___sec5'),
|
||||
('Optimizing our parameters', 2, None, '___sec6'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec7'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
('Generalizing the fitting procedure as a linear algebra problem',
|
||||
2,
|
||||
None,
|
||||
'___sec8'),
|
||||
'___sec6'),
|
||||
('Optimizing our parameters', 2, None, '___sec7'),
|
||||
('Optimizing our parameters, more details', 2, None, '___sec8'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
@@ -98,47 +95,71 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
2,
|
||||
None,
|
||||
'___sec10'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec11'),
|
||||
('Interpretations and optimizing our parameters',
|
||||
2,
|
||||
None,
|
||||
'___sec11'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec12'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec13'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec14'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec15'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec16'),
|
||||
('Simple regression model', 2, None, '___sec17'),
|
||||
('The $\\chi^2$ function', 2, None, '___sec17'),
|
||||
('Simple regression model', 2, None, '___sec18'),
|
||||
('Simple regression model, now using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec18'),
|
||||
'___sec19'),
|
||||
('Simple linear regression model using _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec19'),
|
||||
('Simple linear regression model', 2, None, '___sec20'),
|
||||
('Less noise', 2, None, '___sec21'),
|
||||
('How to study our fits', 2, None, '___sec22'),
|
||||
('Minimizing the cost function', 2, None, '___sec23'),
|
||||
('Relative error', 2, None, '___sec24'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec25'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec26'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
'___sec20'),
|
||||
('Simple linear regression model', 2, None, '___sec21'),
|
||||
('Less noise', 2, None, '___sec22'),
|
||||
('How to study our fits', 2, None, '___sec23'),
|
||||
('Minimizing the cost function', 2, None, '___sec24'),
|
||||
('Relative error', 2, None, '___sec25'),
|
||||
('The richness of _scikit-learn_', 2, None, '___sec26'),
|
||||
('Functions in _scikit-learn_', 2, None, '___sec27'),
|
||||
('Other functions in _scikit-learn_', 2, None, '___sec28'),
|
||||
('The mean absolute error and other functions in _scikit-learn_',
|
||||
2,
|
||||
None,
|
||||
'___sec28'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec29'),
|
||||
('Simple regression model with gradient descent',
|
||||
'___sec29'),
|
||||
('Cubic polynomial in _scikit-learn_', 2, None, '___sec30'),
|
||||
('Polynomial Regression', 2, None, '___sec31'),
|
||||
('Linking the regression analysis with a statistical '
|
||||
'interpretation',
|
||||
2,
|
||||
None,
|
||||
'___sec30'),
|
||||
('Simple regression model with stochastic gradient descent',
|
||||
2,
|
||||
None,
|
||||
'___sec31'),
|
||||
('Polynomial Regression', 2, None, '___sec32'),
|
||||
('Ridge and Lasso Regression', 2, None, '___sec33'),
|
||||
'___sec32'),
|
||||
('Expectation value and variance', 2, None, '___sec33'),
|
||||
('The singular value decompostion', 2, None, '___sec34'),
|
||||
('Lasso and Ridge regression', 2, None, '___sec35'),
|
||||
('Logistic regression', 2, None, '___sec36')]}
|
||||
('Code examples for Ridge and Lasso Regression',
|
||||
2,
|
||||
None,
|
||||
'___sec35'),
|
||||
('From standard regression to Ridge regressions',
|
||||
2,
|
||||
None,
|
||||
'___sec36'),
|
||||
('Fixing the singularity', 2, None, '___sec37'),
|
||||
('A second-order polynomial with Ridge and Lasso',
|
||||
2,
|
||||
None,
|
||||
'___sec38'),
|
||||
('Fitting vs. predicting when data is in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec39'),
|
||||
('Fitting versus predicting when data is not in the model class',
|
||||
2,
|
||||
None,
|
||||
'___sec40'),
|
||||
('The code', 2, None, '___sec41'),
|
||||
('Generating test data', 2, None, '___sec42'),
|
||||
('Lasso regression', 2, None, '___sec43'),
|
||||
('Logistic regression', 2, None, '___sec44')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -180,7 +201,7 @@ MathJax.Hub.Config({
|
||||
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Aug 24, 2018</h4></center> <!-- date -->
|
||||
<center><h4>Sep 6, 2018</h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
@@ -210,7 +231,38 @@ A regression model aims at finding a likelihood function \( p(y\vert \hat{x}) \)
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">General linear models </h2>
|
||||
<h2 id="___sec1">Regression analysis, overarching aims II </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
<p>
|
||||
Consider an experiment in which \( p \) characteristics of \( n \) samples are
|
||||
measured. The data from this experiment are denoted \( \mathbf{X} \), with
|
||||
\( \mathbf{X} \) as above. The matrix \( \mathbf{X} \) is called the <em>design
|
||||
matrix</em>. Additional information of the samples is available in the
|
||||
form of \( \mathbf{Y} \) (also as above). The variable \( \mathbf{Y} \) is
|
||||
generally referred to as the <em>response variable</em>. The aim of
|
||||
regression analysis is to explain \( \mathbf{Y} \) in terms of
|
||||
\( \mathbf{X} \) through a functional relationship like \( Y_i =
|
||||
f(\mathbf{X}_{i,\ast}) \). When no prior knowledge on the form of
|
||||
\( f(\cdot) \) is available, it is common to assume a linear relationship
|
||||
between \( \mathbf{X} \) and \( \mathbf{Y} \). This assumption gives rise to
|
||||
the <em>linear regression model</em> where \( \beta = (\beta_1, \ldots,
|
||||
\beta_p)^{\top} \) is the <em>regression parameter</em>. The parameter
|
||||
\( \beta_j \), \( j=1, \ldots, p \), represents the effect size of covariate
|
||||
\( j \) on the response. That is, for each unit change in covariate \( j \)
|
||||
(while keeping the other covariates fixed) the observed change in the
|
||||
response is equal to \( \beta_j \).
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec2">General linear models </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -231,7 +283,7 @@ where \( \epsilon_i \) is the error in our approximation.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec2">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -251,7 +303,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec3">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<h2 id="___sec4">Rewriting the fitting procedure as a linear algebra problem, follows </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -292,7 +344,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec4">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -315,7 +367,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec5">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<h2 id="___sec6">Generalizing the fitting procedure as a linear algebra problem </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -343,7 +395,7 @@ The left-hand side of this equation forms know. Our error vector \( \hat{\epsilo
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec6">Optimizing our parameters </h2>
|
||||
<h2 id="___sec7">Optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -365,7 +417,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec7">Optimizing our parameters, more details </h2>
|
||||
<h2 id="___sec8">Optimizing our parameters, more details </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -389,7 +441,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec8">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -428,7 +480,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec9">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -454,7 +506,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec10">Interpretations and optimizing our parameters </h2>
|
||||
<h2 id="___sec11">Interpretations and optimizing our parameters </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -482,7 +534,7 @@ meaning that the solution for \( \hat{\beta} \) is the one which minimizes the r
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec11">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -505,7 +557,7 @@ where the matrix \( \hat{\Sigma} \) is a diagonal matrix with \( \sigma_i \) as
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec12">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -533,7 +585,7 @@ where we have defined the matrix \( \hat{A} =\hat{X}/\hat{\Sigma} \) with matrix
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec13">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -559,7 +611,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec14">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -590,7 +642,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec15">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -614,7 +666,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec16">The \( \chi^2 \) function </h2>
|
||||
<h2 id="___sec17">The \( \chi^2 \) function </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
@@ -660,7 +712,7 @@ This approach (different linear and non-linear regression) suffers often from bo
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec17">Simple regression model </h2>
|
||||
<h2 id="___sec18">Simple regression model </h2>
|
||||
We are now ready to write our first program which aims at solving the above linear regression equations. We start with data we have produced ourselves, in this case normally distributed random numbers along the \( x \)-axis. These numbers define then the value of a function \( y(x)=4+3x+N(0,1) \). Thereafter we order the \( x \) values and employ our linear regression algorithm to set up the best fit. Here we find it useful to use the numpy function \( c\_ \) arrays where arrays are stacked along their last axis after being upgraded to at least two dimensions with ones post-pended to the shape. The following examples help in understanding what happens
|
||||
<p>
|
||||
|
||||
@@ -700,7 +752,7 @@ We see that, as expected, a linear fit gives a seemingly (from the graph) good r
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec18">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec19">Simple regression model, now using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We can repeat the above algorithm using <b>scikit-learn</b> as follows
|
||||
@@ -731,7 +783,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec19">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec20">Simple linear regression model using <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We start with perhaps our simplest possible example, using <b>scikit-learn</b> to perform linear regression analysis on a data set produced by us.
|
||||
@@ -799,7 +851,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec20">Simple linear regression model </h2>
|
||||
<h2 id="___sec21">Simple linear regression model </h2>
|
||||
|
||||
<p>
|
||||
This example serves several aims. It allows us to demonstrate several
|
||||
@@ -821,7 +873,7 @@ where \( x \) is defined as before.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec21">Less noise </h2>
|
||||
<h2 id="___sec22">Less noise </h2>
|
||||
|
||||
<p>
|
||||
Does the fit look better? Indeed, by
|
||||
@@ -834,7 +886,7 @@ have not discussed a more rigorous approach to the <b>cost</b> function.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec22">How to study our fits </h2>
|
||||
<h2 id="___sec23">How to study our fits </h2>
|
||||
|
||||
<p>
|
||||
We need more rigorous criteria in defining whether we have succeeded or
|
||||
@@ -856,7 +908,7 @@ dimensionless.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec23">Minimizing the cost function </h2>
|
||||
<h2 id="___sec24">Minimizing the cost function </h2>
|
||||
|
||||
<p>
|
||||
Minimizing the cost function is a central aspect of
|
||||
@@ -877,7 +929,7 @@ the \( \chi^2 \) function becomes smaller.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec24">Relative error </h2>
|
||||
<h2 id="___sec25">Relative error </h2>
|
||||
|
||||
<p>
|
||||
There are many ways to define the cost function. A simpler approach is to look at the relative difference between the training data and the predicted data, that is we define
|
||||
@@ -917,7 +969,7 @@ relative error.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec25">The richness of <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec26">The richness of <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
As mentioned above, <b>scikit-learn</b> has an impressive functionality.
|
||||
@@ -962,7 +1014,7 @@ plt<span style="color: #666666">.</span>show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec26">Functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec27">Functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The function <b>coef</b> gives us the parameter \( \beta \) of our fit while <b>intercept</b> yields
|
||||
@@ -979,7 +1031,7 @@ this function as being similar to the \( \chi^2 \) function defined above.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec27">Other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec28">Other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
The <b>r2score</b> function computes \( R^2 \), the coefficient of
|
||||
@@ -1003,7 +1055,7 @@ $$
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec28">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec29">The mean absolute error and other functions in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
Another quantity will meet again in our discussions of regression analysis is
|
||||
@@ -1028,12 +1080,13 @@ years etc.
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec29">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
<h2 id="___sec30">Cubic polynomial in <b>scikit-learn</b> </h2>
|
||||
|
||||
<p>
|
||||
We will discuss in more
|
||||
detail these and other functions in the various lectures. We conclude this part with another example. Instead of
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
a linear \( x \)-dependence we study now a cubic polynomial and use the polynomial regression analysis tools of scikit-learn.
|
||||
Add description of the various python commands.
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1070,82 +1123,12 @@ plt<span style="color: #666666">.</span>show()
|
||||
<span style="color: #008000; font-weight: bold">print</span> (error(y))
|
||||
</pre></div>
|
||||
<p>
|
||||
Similarly, using <b>R</b>, we can perform similar studies.
|
||||
(more details on <b>R</b> will be inserted later).
|
||||
Using <b>R</b>, we can perform similar studies.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec30">Simple regression model with gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">math</span> <span style="color: #008000; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
theta_linreg <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta_linreg)
|
||||
theta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)
|
||||
|
||||
eta <span style="color: #666666">=</span> <span style="color: #666666">0.1</span>
|
||||
Niterations <span style="color: #666666">=</span> <span style="color: #666666">1000</span>
|
||||
m <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> <span style="color: #008000">iter</span> <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(Niterations):
|
||||
gradients <span style="color: #666666">=</span> <span style="color: #666666">2.0/</span>m<span style="color: #666666">*</span>xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>dot(theta)<span style="color: #666666">-</span>y)
|
||||
theta <span style="color: #666666">-=</span> eta<span style="color: #666666">*</span>gradients
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta)
|
||||
xnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>array([[<span style="color: #666666">0</span>],[<span style="color: #666666">2</span>]])
|
||||
xbnew <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">2</span>,<span style="color: #666666">1</span>)), xnew]
|
||||
ypredict <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta)
|
||||
ypredict2 <span style="color: #666666">=</span> xbnew<span style="color: #666666">.</span>dot(theta_linreg)
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict, <span style="color: #BA2121">"r-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(xnew, ypredict2, <span style="color: #BA2121">"b-"</span>)
|
||||
plt<span style="color: #666666">.</span>plot(x, y ,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>axis([<span style="color: #666666">0</span>,<span style="color: #666666">2.0</span>,<span style="color: #666666">0</span>, <span style="color: #666666">15.0</span>])
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">r'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec31">Simple regression model with stochastic gradient descent </h2>
|
||||
Add info about the equations, play around with different learning rates
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Importing various packages</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">math</span> <span style="color: #008000; font-weight: bold">import</span> exp, sqrt
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">random</span> <span style="color: #008000; font-weight: bold">import</span> random, seed
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> SGDRegressor
|
||||
|
||||
x <span style="color: #666666">=</span> <span style="color: #666666">2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">4+3*</span>x<span style="color: #666666">+</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)
|
||||
|
||||
xb <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((<span style="color: #666666">100</span>,<span style="color: #666666">1</span>)), x]
|
||||
theta_linreg <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv(xb<span style="color: #666666">.</span>T<span style="color: #666666">.</span>dot(xb))<span style="color: #666666">.</span>dot(xb<span style="color: #666666">.</span>T)<span style="color: #666666">.</span>dot(y)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(theta_linreg)
|
||||
sgdreg <span style="color: #666666">=</span> SGDRegressor(n_iter <span style="color: #666666">=</span> <span style="color: #666666">50</span>, penalty<span style="color: #666666">=</span><span style="color: #008000">None</span>, eta0<span style="color: #666666">=0.1</span>)
|
||||
sgdreg<span style="color: #666666">.</span>fit(x,y<span style="color: #666666">.</span>ravel())
|
||||
<span style="color: #008000; font-weight: bold">print</span>(sgdreg<span style="color: #666666">.</span>intercept_, sgdreg<span style="color: #666666">.</span>coef_)
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec32">Polynomial Regression </h2>
|
||||
<h2 id="___sec31">Polynomial Regression </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
@@ -1173,10 +1156,92 @@ plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">r
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">r'Random numbers '</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec32">Linking the regression analysis with a statistical interpretation </h2>
|
||||
|
||||
<p>
|
||||
Before we proceed, and to link with our discussions of Bayesian statistics to come, it is useful the derive the standard regression analysis equations using a statistical interpretation. This allows us also to derive quantities like the variance and other expectation values in a rather straightforward way.
|
||||
|
||||
<p>
|
||||
It is assumed that \( \varepsilon_i
|
||||
\sim \mathcal{N}(0, \sigma^2) \) and the \( \varepsilon_{i} \) are
|
||||
independent, i.e.:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mbox{Cov}(\varepsilon_{i_1},
|
||||
\varepsilon_{i_2}) & = \left\{ \begin{array}{lcc} \sigma^2 & \mbox{if}
|
||||
& i_1 = i_2, \\ 0 & \mbox{if} & i_1 \not= i_2. \end{array} \right.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
The randomness of \( \varepsilon_i \) implies that
|
||||
\( \mathbf{Y}_i \) is also a random variable. In particular,
|
||||
\( \mathbf{Y}_i \) is normally distributed, because \( \varepsilon_i \sim
|
||||
\mathcal{N}(0, \sigma^2) \) and \( \mathbf{X}_{i,\ast} \, \beta \) is a
|
||||
non-random scalar. To specify the parameters of the distribution of
|
||||
\( \mathbf{Y}_i \) we need to calculate its first two moments.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec33">Ridge and Lasso Regression </h2>
|
||||
<h2 id="___sec33">Expectation value and variance </h2>
|
||||
|
||||
<p>
|
||||
Its expectation equals:
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbb{E}(Y_i) & =
|
||||
\mathbb{E}(\mathbf{X}_{i, \ast} \, \beta) + \mathbb{E}(\varepsilon_i)
|
||||
\, \, \, = \, \, \, \mathbf{X}_{i, \ast} \, \beta,
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
while
|
||||
its variance is
|
||||
$$
|
||||
\begin{align*} \mbox{Var}(Y_i) & = \mathbb{E} \{ [Y_i
|
||||
- \mathbb{E}(Y_i)]^2 \} \, \, \, = \, \, \, \mathbb{E} ( Y_i^2 ) -
|
||||
[\mathbb{E}(Y_i)]^2 \\ & = \mathbb{E} [ ( \mathbf{X}_{i, \ast} \,
|
||||
\beta + \varepsilon_i )^2] - ( \mathbf{X}_{i, \ast} \, \beta)^2 \\ &
|
||||
= \mathbb{E} [ ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2 \varepsilon_i
|
||||
\mathbf{X}_{i, \ast} \, \beta + \varepsilon_i^2 ] - ( \mathbf{X}_{i,
|
||||
\ast} \, \beta)^2 \\ & = ( \mathbf{X}_{i, \ast} \, \beta)^2 + 2
|
||||
\mathbb{E}(\varepsilon_i) \mathbf{X}_{i, \ast} \, \beta +
|
||||
\mathbb{E}(\varepsilon_i^2 ) - ( \mathbf{X}_{i, \ast} \, \beta)^2
|
||||
\\ & = \mathbb{E}(\varepsilon_i^2 ) \, \, \, = \, \, \,
|
||||
\mbox{Var}(\varepsilon_i) \, \, \, = \, \, \, \sigma^2.
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
Hence, \( Y_i \sim \mathcal{N}( \mathbf{X}_{i, \ast} \, \beta, \sigma^2) \).
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
<p>
|
||||
A general
|
||||
\( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal
|
||||
matrix \( \hat{D} \) of dimensionality \( n\times n \) and two orthognal
|
||||
matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality
|
||||
\( m \times m \) and the last dimensionality \( n\times n \).
|
||||
We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{D}\hat{V}^T
|
||||
$$
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec35">Code examples for Ridge and Lasso Regression </h2>
|
||||
|
||||
<p>
|
||||
|
||||
@@ -1257,38 +1322,390 @@ plt<span style="color: #666666">.</span>show()
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec34">The singular value decompostion </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
How can we use the singular value decomposition to find the parameters \( \beta_j \)? More details will come. We first note that a general \( m\times n \) matrix \( \hat{A} \) can be written in terms of a diagonal matrix \( \hat{\Sigma} \) of dimensionality \( n\times n \) and two orthognal matrices \( \hat{U} \) and \( \hat{V} \), where the first has dimensionality \( m \times n \) and the last dimensionality \( n\times n \). We have then
|
||||
$$
|
||||
\hat{A} = \hat{U}\hat{\Sigma}\hat{V}
|
||||
$$
|
||||
</div>
|
||||
|
||||
<h2 id="___sec36">From standard regression to Ridge regressions </h2>
|
||||
|
||||
<p>
|
||||
Add codes and discuss this in connection with lasso and ridge, show example where the standard inversion of a matrix fails and where SVD comes to rescue
|
||||
One of the typical problems we encounter with linear regression, in particular
|
||||
when the matrix \( \hat{X} \) (our so-called design matrix) is high-dimensional,
|
||||
are problems with near singular or singular matrices. The column vectors of \( \hat{X} \)
|
||||
may be linearly dependent, normally referred to as super-collinearity.
|
||||
This means that the matrix may be rank deficient and it is basically impossible to
|
||||
to model the data using linear regression. As an example, consider the matrix
|
||||
$$
|
||||
\begin{align*}
|
||||
\mathbf{X} & = \left[
|
||||
\begin{array}{rrr}
|
||||
1 & -1 & 2
|
||||
\\
|
||||
1 & 0 & 1
|
||||
\\
|
||||
1 & 2 & -1
|
||||
\\
|
||||
1 & 1 & 0
|
||||
\end{array} \right]
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
<p>
|
||||
The columns of \( \hat{X} \) are linearly dependent. We se this easily since the
|
||||
the first column is the row-wise sum of the other two columns. The rank (more correct,
|
||||
the column rank) of a matrix is the dimension of the space spanned by the
|
||||
column vectors. Hence, the rank of \( \mathbf{X} \) is equal to the number
|
||||
of linearly independent columns. In this particular case the matrix has rank 2.
|
||||
|
||||
<p>
|
||||
Super-collinearity of an \( (n \times p) \)-dimensional design matrix \( \mathbf{X} \) implies
|
||||
that the inverse of the matrix \( \hat{X}^T\hat{x} \) (the matrix we needto invert to solve the linear regression equations) is non-invertible. If we have a square matrix that does not have an inverse, we say this matrix singular. The example here demonstrates this
|
||||
$$
|
||||
\begin{align*}
|
||||
\hat{X} & = \left[
|
||||
\begin{array}{rr}
|
||||
1 & -1
|
||||
\\
|
||||
1 & -1
|
||||
\end{array} \right].
|
||||
\end{align*}
|
||||
$$
|
||||
|
||||
We see easily that \( \mbox{det}(\hat{X}) = x_{11} x_{22} - x_{12} x_{21} = 1 \times (-1) - 1 \times (-1) = 0 \). Hence, \( \mathbf{X} \) is singular and its inverse is undefined.
|
||||
This is equivalent to saying that the matrix \( \hat{X} \) has at least an eigenvalue which is zero.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec35">Lasso and Ridge regression </h2>
|
||||
<h2 id="___sec37">Fixing the singularity </h2>
|
||||
|
||||
<p>
|
||||
Discuss the mathematics here
|
||||
If our design matrix \( \hat{X} \) which enters the linear regression problem
|
||||
$$
|
||||
\begin{align}
|
||||
\hat{\beta} & = (\hat{X}^{T} \hat{X})^{-1} \hat{X}^{T} \hat{y},
|
||||
\label{_auto1}
|
||||
\end{align}
|
||||
$$
|
||||
|
||||
has linearly dependent column vectors, we will not be able to compute the inverse
|
||||
of \( \hat{X}^T\hat{X} \) and we cannot find the parameters (estimators) \( \beta_i \).
|
||||
The estimators are only well-defined if \( (\hat{X}^{T}\hat{X})^{-1} \) exits.
|
||||
This is more likely to happen when the matrix \( \hat{X} \) is high-dimensional. In this case it is likely to encounter a situation where
|
||||
the regression parameters \( \beta_i \) cannot be estimated.
|
||||
|
||||
<p>
|
||||
The <em>ad hoc</em> approach which was introduced in the 70s was simply to add a diagonal component to the matrix to invert, that is we change
|
||||
$$
|
||||
\hat{X}^{T} \hat{X} \rightarrow \hat{X}^{T} \hat{X}+\lambda \hat{I},
|
||||
$$
|
||||
|
||||
where \( \hat{I} \) is the identity matrix.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec36">Logistic regression </h2>
|
||||
Add discussion about classification versus regression, show examples of more than two cases and why regression is not the best approach. Motivate for k-nearest neighbors
|
||||
<h2 id="___sec38">A second-order polynomial with Ridge and Lasso </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> Ridge
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> r2_score
|
||||
|
||||
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">4155</span>)
|
||||
|
||||
n_samples <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
|
||||
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(n_samples,<span style="color: #666666">1</span>)
|
||||
y <span style="color: #666666">=</span> <span style="color: #666666">5*</span>x<span style="color: #666666">*</span>x <span style="color: #666666">+</span> <span style="color: #666666">0.1*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(n_samples,<span style="color: #666666">1</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Centering x and y.</span>
|
||||
x_ <span style="color: #666666">=</span> x <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(x)
|
||||
y_ <span style="color: #666666">=</span> y <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(y) <span style="color: #408080; font-style: italic"># beta_0 = mean(y)</span>
|
||||
|
||||
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[np<span style="color: #666666">.</span>ones((n_samples,<span style="color: #666666">1</span>)), x, x<span style="color: #666666">**2</span>]
|
||||
X_ <span style="color: #666666">=</span> np<span style="color: #666666">.</span>c_[x_, x_<span style="color: #666666">**2</span>]
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic">### 1.</span>
|
||||
lmb_values <span style="color: #666666">=</span> [<span style="color: #666666">1e-4</span>, <span style="color: #666666">1e-3</span>, <span style="color: #666666">1e-2</span>, <span style="color: #666666">10</span>, <span style="color: #666666">1e2</span>, <span style="color: #666666">1e4</span>]
|
||||
num_values <span style="color: #666666">=</span> <span style="color: #008000">len</span>(lmb_values)
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Ridge-regression of centered and not centered data</span>
|
||||
beta_ridge <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #666666">3</span>,num_values))
|
||||
beta_ridge_centered <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #666666">3</span>,num_values))
|
||||
|
||||
I3 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(<span style="color: #666666">3</span>)
|
||||
I2 <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(<span style="color: #666666">2</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i,lmb <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(lmb_values):
|
||||
beta_ridge[:,i] <span style="color: #666666">=</span> (np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X<span style="color: #666666">.</span>T @ X <span style="color: #666666">+</span> lmb<span style="color: #666666">*</span>I3) @ X<span style="color: #666666">.</span>T @ y)<span style="color: #666666">.</span>flatten()
|
||||
beta_ridge_centered[<span style="color: #666666">1</span>:,i] <span style="color: #666666">=</span> (np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X_<span style="color: #666666">.</span>T @ X_ <span style="color: #666666">+</span> lmb<span style="color: #666666">*</span>I2) @ X_<span style="color: #666666">.</span>T @ y_)<span style="color: #666666">.</span>flatten()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># sett beta_0 = np.mean(y)</span>
|
||||
beta_ridge_centered[<span style="color: #666666">0</span>,:] <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean(y)
|
||||
|
||||
<span style="color: #408080; font-style: italic">## OLS (ordinary least squares) solution </span>
|
||||
beta_ls <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>inv( X<span style="color: #666666">.</span>T @ X ) @ X<span style="color: #666666">.</span>T @ y
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Evaluate the models</span>
|
||||
pred_ls <span style="color: #666666">=</span> X @ beta_ls
|
||||
pred_ridge <span style="color: #666666">=</span> X @ beta_ridge
|
||||
pred_ridge_centered <span style="color: #666666">=</span> X_ @ beta_ridge_centered[<span style="color: #666666">1</span>:] <span style="color: #666666">+</span> beta_ridge_centered[<span style="color: #666666">0</span>,:]
|
||||
|
||||
<span style="color: #408080; font-style: italic">## Plot the results</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Sorting</span>
|
||||
sort_ind <span style="color: #666666">=</span> np<span style="color: #666666">.</span>argsort(x[:,<span style="color: #666666">0</span>])
|
||||
|
||||
x_plot <span style="color: #666666">=</span> x[sort_ind,<span style="color: #666666">0</span>]
|
||||
x_centered_plot <span style="color: #666666">=</span> x_[sort_ind,<span style="color: #666666">0</span>]
|
||||
|
||||
pred_ls_plot <span style="color: #666666">=</span> pred_ls[sort_ind,<span style="color: #666666">0</span>]
|
||||
pred_ridge_plot <span style="color: #666666">=</span> pred_ridge[sort_ind,:]
|
||||
pred_ridge_centered_plot <span style="color: #666666">=</span> pred_ridge_centered[sort_ind,:]
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Plott not centered</span>
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ls_plot,label<span style="color: #666666">=</span><span style="color: #BA2121">'ls'</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ridge_plot[:,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x,y,<span style="color: #BA2121">'ro'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression on un-centered data'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Plott centered</span>
|
||||
plt<span style="color: #666666">.</span>figure()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_centered_plot,pred_ridge_centered_plot[:,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x_,y,<span style="color: #BA2121">'ro'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression on centered data'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic"># 2.</span>
|
||||
|
||||
pred_ridge_scikit <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((n_samples,num_values))
|
||||
<span style="color: #008000; font-weight: bold">for</span> i,lmb <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(lmb_values):
|
||||
pred_ridge_scikit[:,i] <span style="color: #666666">=</span> (Ridge(alpha<span style="color: #666666">=</span>lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000">False</span>)<span style="color: #666666">.</span>fit(X,y)<span style="color: #666666">.</span>predict(X))<span style="color: #666666">.</span>flatten() <span style="color: #408080; font-style: italic"># fit_intercept=False fordi bias er allerede i X</span>
|
||||
|
||||
plt<span style="color: #666666">.</span>figure()
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ls_plot,label<span style="color: #666666">=</span><span style="color: #BA2121">'ls'</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
plt<span style="color: #666666">.</span>plot(x_plot,pred_ridge_scikit[sort_ind,i],label<span style="color: #666666">=</span><span style="color: #BA2121">'scikit-ridge, lmb=</span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
|
||||
plt<span style="color: #666666">.</span>plot(x,y,<span style="color: #BA2121">'ro'</span>)
|
||||
plt<span style="color: #666666">.</span>legend()
|
||||
plt<span style="color: #666666">.</span>title(<span style="color: #BA2121">'linear regression using scikit'</span>)
|
||||
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #408080; font-style: italic">### R2-score of the results</span>
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(num_values):
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'lambda = </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>lmb_values[i])
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for scikit: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge_scikit[:,i]))
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for own code, not centered: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge[:,i]))
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'r2 for own, centered: </span><span style="color: #BB6688; font-weight: bold">%g</span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">'</span><span style="color: #666666">%</span>r2_score(y,pred_ridge_centered[:,i]))
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec39">Fitting vs. predicting when data is in the model class </h2>
|
||||
|
||||
<p>
|
||||
Add examples on classification problems
|
||||
We start by considering the case
|
||||
\( f(x)=2x \).
|
||||
|
||||
<p>
|
||||
Then the data is clearly generated by a model that is contained within
|
||||
all three model classes we are using to make predictions (linear
|
||||
models, third order polynomials, and tenth order polynomials).
|
||||
|
||||
<p>
|
||||
Run the code for the following cases:
|
||||
|
||||
<ol>
|
||||
<li> For \( f(x)=2x \) , \( Ntrain=10 \) and \( \sigma =0 \) (noiseless case), train the three classes of models (linear, third-order polynomial, and tenth order polynomial) for a training set when \( x \in [0,1] \) . Make graphs comparing fits for different order of polynomials. Which model fits the data the best?</li>
|
||||
<li> Do you think that the data that has the least error on the training set will also make the best predictions? Why or why not? Can you try to discuss and formalize your intuition? What can go right and what can go wrong?</li>
|
||||
<li> Check your answer by seeing how well your fits predict newly generated test data (including on data outside the range you fit on, for example \( x \in [0,1.2] \) ) using the code below. How well do you do on points in the range of x where you trained the model? How about points outside the original training data set?</li>
|
||||
<li> Repeat the above for \( f(x)=2x \) , \( Ntrain=10 \) , and \( \sigma=1 \) . What changes?</li>
|
||||
</ol>
|
||||
|
||||
Repeat the exercises above for \( f(x)=2x \) , \( Ntrain=100 \) , and \( \sigma=1 \) . What changes?
|
||||
Summarize what you have learned about the relationship between model complexity (number of parameters), goodness of fit on training data, and the ability to predict well.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec40">Fitting versus predicting when data is not in the model class </h2>
|
||||
|
||||
<p>
|
||||
Thus far, we have considered the case where the data is generated using a model contained in the model class. Now consider \( f(x)=2x-10x^5+15x^{10} \) . Notice that the for linear and third-order polynomial the true model \( f(x) \) is not contained in model class.
|
||||
|
||||
<ol>
|
||||
<li> Do better fits lead to better predictions?</li>
|
||||
<li> What is the relationship between the true model for generating the data and the model class that has the most predictive power? How is this related to the model complexity? How does this depend on the number of data points \( Ntrain \) and \( \sigma \)?</li>
|
||||
</ol>
|
||||
|
||||
Summarize what you think you learned about the relationship of knowing the true model class and predictive power.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec41">The code </h2>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">sk</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn</span> <span style="color: #008000; font-weight: bold">import</span> datasets, linear_model
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> PolynomialFeatures
|
||||
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">mpl</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">matplotlib</span> <span style="color: #008000; font-weight: bold">import</span> pyplot <span style="color: #008000; font-weight: bold">as</span> plt
|
||||
|
||||
<span style="color: #666666">%</span>matplotlib notebook
|
||||
|
||||
<span style="color: #408080; font-style: italic"># The Training Data</span>
|
||||
|
||||
N_train<span style="color: #666666">=100</span>
|
||||
|
||||
sigma_train<span style="color: #666666">=1</span>;
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train on integers</span>
|
||||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.05</span>,<span style="color: #666666">0.95</span>,N_train)
|
||||
<span style="color: #408080; font-style: italic"># Draw random noise</span>
|
||||
s <span style="color: #666666">=</span> sigma_train<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(N_train)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#linear</span>
|
||||
y<span style="color: #666666">=2*</span>x<span style="color: #666666">+</span>s
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Tenth Order</span>
|
||||
<span style="color: #408080; font-style: italic">#y=2*x-10*x**5+15*x**10+s</span>
|
||||
|
||||
p1<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x,y, <span style="color: #BA2121">"o"</span>,ms<span style="color: #666666">=15</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">'Training'</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear Regression</span>
|
||||
<span style="color: #408080; font-style: italic"># Create linear regression object</span>
|
||||
clf <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Train the model using the training sets</span>
|
||||
clf<span style="color: #666666">.</span>fit(x[:, np<span style="color: #666666">.</span>newaxis], y)
|
||||
<span style="color: #408080; font-style: italic"># The coefficients</span>
|
||||
|
||||
xplot<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0.02</span>,<span style="color: #666666">0.98</span>,<span style="color: #666666">200</span>)
|
||||
linear_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf<span style="color: #666666">.</span>predict(xplot[:, np<span style="color: #666666">.</span>newaxis]),label<span style="color: #666666">=</span><span style="color: #BA2121">'Linear'</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Polynomial Regression</span>
|
||||
|
||||
|
||||
poly3 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=3</span>)
|
||||
X <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf3 <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
clf3<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
|
||||
Xplot<span style="color: #666666">=</span>poly3<span style="color: #666666">.</span>fit_transform(xplot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly3_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf3<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Poly 3'</span>)
|
||||
|
||||
|
||||
|
||||
<span style="color: #408080; font-style: italic">#poly5 = PolynomialFeatures(degree=5)</span>
|
||||
<span style="color: #408080; font-style: italic">#X = poly5.fit_transform(x[:,np.newaxis])</span>
|
||||
<span style="color: #408080; font-style: italic">#clf5 = linear_model.LinearRegression()</span>
|
||||
<span style="color: #408080; font-style: italic">#clf5.fit(X,y)</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Xplot=poly5.fit_transform(xplot[:,np.newaxis])</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.plot(xplot, clf5.predict(Xplot), 'r--',linewidth=1)</span>
|
||||
|
||||
poly10 <span style="color: #666666">=</span> PolynomialFeatures(degree<span style="color: #666666">=10</span>)
|
||||
X <span style="color: #666666">=</span> poly10<span style="color: #666666">.</span>fit_transform(x[:,np<span style="color: #666666">.</span>newaxis])
|
||||
clf10 <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>LinearRegression()
|
||||
clf10<span style="color: #666666">.</span>fit(X,y)
|
||||
|
||||
Xplot<span style="color: #666666">=</span>poly10<span style="color: #666666">.</span>fit_transform(xplot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
poly10_plot<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(xplot, clf10<span style="color: #666666">.</span>predict(Xplot), label<span style="color: #666666">=</span><span style="color: #BA2121">'Poly 10'</span>)
|
||||
|
||||
axes <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>gca()
|
||||
axes<span style="color: #666666">.</span>set_ylim([<span style="color: #666666">-7</span>,<span style="color: #666666">7</span>])
|
||||
|
||||
handles, labels<span style="color: #666666">=</span>axes<span style="color: #666666">.</span>get_legend_handles_labels()
|
||||
plt<span style="color: #666666">.</span>legend(handles,labels, loc<span style="color: #666666">=</span><span style="color: #BA2121">'lower center'</span>)
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">"$x$"</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">"$y$"</span>)
|
||||
Title<span style="color: #666666">=</span><span style="color: #BA2121">"$N=$"</span><span style="color: #666666">+</span><span style="color: #008000">str</span>(N_train)<span style="color: #666666">+</span><span style="color: #BA2121">", $\sigma=$"</span><span style="color: #666666">+</span><span style="color: #008000">str</span>(sigma_train)
|
||||
plt<span style="color: #666666">.</span>title(Title<span style="color: #666666">+</span><span style="color: #BA2121">" (train)"</span>)
|
||||
plt<span style="color: #666666">.</span>tight_layout()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec42">Generating test data </h2>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Generate Test Data</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Number of test data</span>
|
||||
N_test<span style="color: #666666">=20</span>
|
||||
|
||||
sigma_test<span style="color: #666666">=</span>sigma_train
|
||||
|
||||
max_x<span style="color: #666666">=1.2</span>
|
||||
x_test<span style="color: #666666">=</span>max_x<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>random(N_test)
|
||||
<span style="color: #408080; font-style: italic"># Draw random noise</span>
|
||||
s_test <span style="color: #666666">=</span> sigma_test<span style="color: #666666">*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(N_test)
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear</span>
|
||||
y_test<span style="color: #666666">=2*</span>x_test<span style="color: #666666">+</span>s_test
|
||||
<span style="color: #408080; font-style: italic">#Tenth order</span>
|
||||
<span style="color: #408080; font-style: italic">#y_test=2*x_test-10*x_test**5+15*x_test**10+s_test</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Make design matrices for prediction</span>
|
||||
x_plot<span style="color: #666666">=</span>np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>,max_x, <span style="color: #666666">200</span>)
|
||||
X3 <span style="color: #666666">=</span> poly3<span style="color: #666666">.</span>fit_transform(x_plot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
X10 <span style="color: #666666">=</span> poly10<span style="color: #666666">.</span>fit_transform(x_plot[:,np<span style="color: #666666">.</span>newaxis])
|
||||
|
||||
<span style="color: #666666">%</span>matplotlib notebook
|
||||
|
||||
fig <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>figure()
|
||||
p1<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_test,y_test<span style="color: #666666">.</span>transpose(), <span style="color: #BA2121">'o'</span>, ms<span style="color: #666666">=12</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">'data'</span>)
|
||||
p2<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf<span style="color: #666666">.</span>predict(x_plot[:,np<span style="color: #666666">.</span>newaxis]), label<span style="color: #666666">=</span><span style="color: #BA2121">'linear'</span>)
|
||||
p3<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf3<span style="color: #666666">.</span>predict(X3), label<span style="color: #666666">=</span><span style="color: #BA2121">'3rd order'</span>)
|
||||
p10<span style="color: #666666">=</span>plt<span style="color: #666666">.</span>plot(x_plot,clf10<span style="color: #666666">.</span>predict(X10), label<span style="color: #666666">=</span><span style="color: #BA2121">'10th order'</span>)
|
||||
|
||||
|
||||
plt<span style="color: #666666">.</span>legend(loc<span style="color: #666666">=2</span>)
|
||||
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">'$x$'</span>)
|
||||
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">'$y$'</span>)
|
||||
plt<span style="color: #666666">.</span>legend(loc<span style="color: #666666">=</span><span style="color: #BA2121">'best'</span>)
|
||||
plt<span style="color: #666666">.</span>title(Title<span style="color: #666666">+</span><span style="color: #BA2121">" (pred.)"</span>)
|
||||
plt<span style="color: #666666">.</span>tight_layout()
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Linear Filename</span>
|
||||
<span style="color: #408080; font-style: italic">#filename_test=Title+"pred-linear.pdf"</span>
|
||||
<span style="color: #408080; font-style: italic">#Tenth Order Filename</span>
|
||||
<span style="color: #408080; font-style: italic">#filename_test=Title+"pred-o10.pdf"</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.savefig(filename_test)</span>
|
||||
<span style="color: #408080; font-style: italic">#plt.ylim((-6,12))</span>
|
||||
</pre></div>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec43">Lasso regression </h2>
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec44">Logistic regression </h2>
|
||||
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
+248
-1887
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user