Files
FYS-STK4155/doc/pub/week36/html/._week36-bs002.html
T
2024-09-03 05:58:08 +02:00

852 lines
58 KiB
HTML

<!--
HTML file automatically generated from DocOnce source
(https://github.com/doconce/doconce/)
doconce format html week36.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week36-bs --no_mako
-->
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta name="description" content="Week 36: Linear Regression and Statistical interpretations">
<title>Week 36: Linear Regression and Statistical interpretations</title>
<!-- Bootstrap style: bootstrap -->
<!-- doconce format html week36.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week36-bs --no_mako -->
<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': [('Plans for week 36', 2, None, 'plans-for-week-36'),
('Material for lecture Monday September 2',
2,
None,
'material-for-lecture-monday-september-2'),
('Important technicalities: More on Rescaling data',
2,
None,
'important-technicalities-more-on-rescaling-data'),
('Test Function for what happens with OLS, Ridge and Lasso',
2,
None,
'test-function-for-what-happens-with-ols-ridge-and-lasso'),
('Linking the regression analysis with a statistical '
'interpretation',
2,
None,
'linking-the-regression-analysis-with-a-statistical-interpretation'),
('Assumptions made', 2, None, 'assumptions-made'),
('Expectation value and variance',
2,
None,
'expectation-value-and-variance'),
('Expectation value and variance for $\\boldsymbol{\\beta}$',
2,
None,
'expectation-value-and-variance-for-boldsymbol-beta'),
('Deriving OLS from a probability distribution',
2,
None,
'deriving-ols-from-a-probability-distribution'),
('Independent and Identically Distributed (iid)',
2,
None,
'independent-and-identically-distributed-iid'),
('Maximum Likelihood Estimation (MLE)',
2,
None,
'maximum-likelihood-estimation-mle'),
('A new Cost Function', 2, None, 'a-new-cost-function'),
("More basic Statistics and Bayes' theorem",
2,
None,
'more-basic-statistics-and-bayes-theorem'),
('Marginal Probability', 2, None, 'marginal-probability'),
('Conditional Probability', 2, None, 'conditional-probability'),
("Bayes' Theorem", 2, None, 'bayes-theorem'),
("Interpretations of Bayes' Theorem",
2,
None,
'interpretations-of-bayes-theorem'),
("Example of Usage of Bayes' theorem",
2,
None,
'example-of-usage-of-bayes-theorem'),
('Doing it correctly', 2, None, 'doing-it-correctly'),
("Bayes' Theorem and Ridge and Lasso Regression",
2,
None,
'bayes-theorem-and-ridge-and-lasso-regression'),
('Ridge and Bayes', 2, None, 'ridge-and-bayes'),
('Lasso and Bayes', 2, None, 'lasso-and-bayes'),
('Material for the active learning sessions Tuesday and '
'Wednesday',
2,
None,
'material-for-the-active-learning-sessions-tuesday-and-wednesday'),
('Linear Regression and the SVD',
2,
None,
'linear-regression-and-the-svd'),
('What does it mean?', 2, None, 'what-does-it-mean'),
('And finally $\\boldsymbol{X}\\boldsymbol{X}^T$',
2,
None,
'and-finally-boldsymbol-x-boldsymbol-x-t'),
('Code for SVD and Inversion of Matrices',
2,
None,
'code-for-svd-and-inversion-of-matrices'),
('Inverse of Rectangular Matrix',
2,
None,
'inverse-of-rectangular-matrix'),
('Ridge and LASSO Regression',
2,
None,
'ridge-and-lasso-regression'),
('From OLS to Ridge and Lasso',
2,
None,
'from-ols-to-ridge-and-lasso'),
('Deriving the Ridge Regression Equations',
2,
None,
'deriving-the-ridge-regression-equations'),
('Note on Scikit-Learn', 2, None, 'note-on-scikit-learn'),
('Comparison with OLS', 2, None, 'comparison-with-ols'),
('SVD analysis', 2, None, 'svd-analysis'),
('Interpreting the Ridge results',
2,
None,
'interpreting-the-ridge-results'),
('More interpretations', 2, None, 'more-interpretations'),
('Deriving the Lasso Regression Equations',
2,
None,
'deriving-the-lasso-regression-equations'),
('Simple example to illustrate Ordinary Least Squares, Ridge and '
'Lasso Regression',
2,
None,
'simple-example-to-illustrate-ordinary-least-squares-ridge-and-lasso-regression'),
('Ridge Regression', 2, None, 'ridge-regression'),
('Lasso Regression', 2, None, 'lasso-regression'),
('Yet another Example', 2, None, 'yet-another-example'),
('The OLS case', 2, None, 'the-ols-case'),
('The Ridge case', 2, None, 'the-ridge-case'),
('Writing the Cost Function',
2,
None,
'writing-the-cost-function'),
('Lasso case', 2, None, 'lasso-case'),
('The first Case', 2, None, 'the-first-case'),
('Simple code for solving the above problem',
2,
None,
'simple-code-for-solving-the-above-problem'),
('With Lasso Regression', 2, None, 'with-lasso-regression'),
('Another Example, now with a polynomial fit',
2,
None,
'another-example-now-with-a-polynomial-fit')]}
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="week36-bs.html">Week 36: Linear Regression and Statistical interpretations</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="._week36-bs001.html#plans-for-week-36" style="font-size: 80%;">Plans for week 36</a></li>
<!-- navigation toc: --> <li><a href="#material-for-lecture-monday-september-2" style="font-size: 80%;">Material for lecture Monday September 2</a></li>
<!-- navigation toc: --> <li><a href="#important-technicalities-more-on-rescaling-data" style="font-size: 80%;">Important technicalities: More on Rescaling data</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs003.html#test-function-for-what-happens-with-ols-ridge-and-lasso" style="font-size: 80%;">Test Function for what happens with OLS, Ridge and Lasso</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs004.html#linking-the-regression-analysis-with-a-statistical-interpretation" style="font-size: 80%;">Linking the regression analysis with a statistical interpretation</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs005.html#assumptions-made" style="font-size: 80%;">Assumptions made</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs006.html#expectation-value-and-variance" style="font-size: 80%;">Expectation value and variance</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs007.html#expectation-value-and-variance-for-boldsymbol-beta" style="font-size: 80%;">Expectation value and variance for \( \boldsymbol{\beta} \)</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs008.html#deriving-ols-from-a-probability-distribution" style="font-size: 80%;">Deriving OLS from a probability distribution</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs009.html#independent-and-identically-distributed-iid" style="font-size: 80%;">Independent and Identically Distributed (iid)</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs010.html#maximum-likelihood-estimation-mle" style="font-size: 80%;">Maximum Likelihood Estimation (MLE)</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs011.html#a-new-cost-function" style="font-size: 80%;">A new Cost Function</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs012.html#more-basic-statistics-and-bayes-theorem" style="font-size: 80%;">More basic Statistics and Bayes' theorem</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs013.html#marginal-probability" style="font-size: 80%;">Marginal Probability</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs014.html#conditional-probability" style="font-size: 80%;">Conditional Probability</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs015.html#bayes-theorem" style="font-size: 80%;">Bayes' Theorem</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs016.html#interpretations-of-bayes-theorem" style="font-size: 80%;">Interpretations of Bayes' Theorem</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs017.html#example-of-usage-of-bayes-theorem" style="font-size: 80%;">Example of Usage of Bayes' theorem</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs018.html#doing-it-correctly" style="font-size: 80%;">Doing it correctly</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs019.html#bayes-theorem-and-ridge-and-lasso-regression" style="font-size: 80%;">Bayes' Theorem and Ridge and Lasso Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs020.html#ridge-and-bayes" style="font-size: 80%;">Ridge and Bayes</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs021.html#lasso-and-bayes" style="font-size: 80%;">Lasso and Bayes</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs022.html#material-for-the-active-learning-sessions-tuesday-and-wednesday" style="font-size: 80%;">Material for the active learning sessions Tuesday and Wednesday</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs023.html#linear-regression-and-the-svd" style="font-size: 80%;">Linear Regression and the SVD</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs024.html#what-does-it-mean" style="font-size: 80%;">What does it mean?</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs025.html#and-finally-boldsymbol-x-boldsymbol-x-t" style="font-size: 80%;">And finally \( \boldsymbol{X}\boldsymbol{X}^T \)</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs026.html#code-for-svd-and-inversion-of-matrices" style="font-size: 80%;">Code for SVD and Inversion of Matrices</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs027.html#inverse-of-rectangular-matrix" style="font-size: 80%;">Inverse of Rectangular Matrix</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs028.html#ridge-and-lasso-regression" style="font-size: 80%;">Ridge and LASSO Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs029.html#from-ols-to-ridge-and-lasso" style="font-size: 80%;">From OLS to Ridge and Lasso</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs030.html#deriving-the-ridge-regression-equations" style="font-size: 80%;">Deriving the Ridge Regression Equations</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs031.html#note-on-scikit-learn" style="font-size: 80%;">Note on Scikit-Learn</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs032.html#comparison-with-ols" style="font-size: 80%;">Comparison with OLS</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs033.html#svd-analysis" style="font-size: 80%;">SVD analysis</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs034.html#interpreting-the-ridge-results" style="font-size: 80%;">Interpreting the Ridge results</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs035.html#more-interpretations" style="font-size: 80%;">More interpretations</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs036.html#deriving-the-lasso-regression-equations" style="font-size: 80%;">Deriving the Lasso Regression Equations</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs037.html#simple-example-to-illustrate-ordinary-least-squares-ridge-and-lasso-regression" style="font-size: 80%;">Simple example to illustrate Ordinary Least Squares, Ridge and Lasso Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs038.html#ridge-regression" style="font-size: 80%;">Ridge Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs039.html#lasso-regression" style="font-size: 80%;">Lasso Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs040.html#yet-another-example" style="font-size: 80%;">Yet another Example</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs041.html#the-ols-case" style="font-size: 80%;">The OLS case</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs042.html#the-ridge-case" style="font-size: 80%;">The Ridge case</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs043.html#writing-the-cost-function" style="font-size: 80%;">Writing the Cost Function</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs044.html#lasso-case" style="font-size: 80%;">Lasso case</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs045.html#the-first-case" style="font-size: 80%;">The first Case</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs046.html#simple-code-for-solving-the-above-problem" style="font-size: 80%;">Simple code for solving the above problem</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs047.html#with-lasso-regression" style="font-size: 80%;">With Lasso Regression</a></li>
<!-- navigation toc: --> <li><a href="._week36-bs048.html#another-example-now-with-a-polynomial-fit" style="font-size: 80%;">Another Example, now with a polynomial fit</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div> <!-- end of navigation bar -->
<div class="container">
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
<a name="part0002"></a>
<!-- !split -->
<h2 id="material-for-lecture-monday-september-2" class="anchor">Material for lecture Monday September 2 </h2>
<h2 id="important-technicalities-more-on-rescaling-data" class="anchor">Important technicalities: More on Rescaling data </h2>
<p>When you are comparing your own code with for example <b>Scikit-Learn</b>'s
library, there are some technicalities to keep in mind. The examples
here demonstrate some of these aspects with potential pitfalls.
</p>
<p>The discussion here focuses on the role of the intercept, how we can
set up the design matrix, what scaling we should use and other topics
which tend confuse us.
</p>
<p>The intercept can be interpreted as the expected value of our
target/output variables when all other predictors are set to zero.
Thus, if we cannot assume that the expected outputs/targets are zero
when all predictors are zero (the columns in the design matrix), it
may be a bad idea to implement a model which penalizes the intercept.
Furthermore, in for example Ridge and Lasso regression, the default solutions
from the library <b>Scikit-Learn</b> (when not shrinking \( \beta_0 \)) for the unknown parameters
\( \boldsymbol{\beta} \), are derived&#160;under the assumption that both \( \boldsymbol{y} \) and
\( \boldsymbol{X} \) are zero centered, that is we subtract the mean values.
</p>
<p>If our predictors&#160;represent different&#160;scales, then it is important to
standardize the design matrix \( \boldsymbol{X} \) by subtracting the mean of each
column from the corresponding column and dividing the column with its
standard deviation. Most machine learning libraries do this as a default. This means that if you compare your code with the results from a given library,
the results may differ.
</p>
<p>The
<a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html" target="_self">Standardscaler</a>
function in <b>Scikit-Learn</b> does this for us. For the data sets we
have been studying in our various examples, the data are in many cases
already scaled and there is no need to scale them. You as a user of different machine learning algorithms, should always perform a
survey of your data, with a critical assessment of them in case you need to scale the data.
</p>
<p>If you need to scale the data, not doing so will give an <em>unfair</em>
penalization of the parameters since their magnitude&#160;depends on the
scale of their corresponding&#160;predictor.
</p>
<p>The <b>Scikit-Learn</b> site <a href="https://scikit-learn.org/stable/auto_examples/preprocessing/plot_all_scaling.html#plot-all-scaling-standard-scaler-section" target="_self"><tt>https://scikit-learn.org/stable/auto_examples/preprocessing/plot_all_scaling.html#plot-all-scaling-standard-scaler-section</tt></a> has a good discussion of different ways of preprocessing data.</p>
<p>Suppose as an example that you
you have an input&#160;variable given by the heights of different persons.
Human height might be measured in inches or meters or
kilometers. If measured in kilometers, a&#160;standard linear regression
model with this predictor would probably give a much bigger
coefficient term, than if measured in millimeters.
This can clearly lead to problems in evaluating the cost/loss functions.
</p>
<p>Keep in mind that when you transform your data set before training a model, the same transformation needs to be done
on your eventual new data set before making a prediction. If we translate this into a Python code, it would could be implemented as
</p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class="highlight" style="background: #f8f8f8">
<pre style="line-height: 125%;"><span style="color: #BA2121; font-style: italic">&quot;&quot;&quot;</span>
<span style="color: #BA2121; font-style: italic">#Model training, we compute the mean value of y and X</span>
<span style="color: #BA2121; font-style: italic">y_train_mean = np.mean(y_train)</span>
<span style="color: #BA2121; font-style: italic">X_train_mean = np.mean(X_train,axis=0)</span>
<span style="color: #BA2121; font-style: italic">X_train = X_train - X_train_mean</span>
<span style="color: #BA2121; font-style: italic">y_train = y_train - y_train_mean</span>
<span style="color: #BA2121; font-style: italic"># The we fit our model with the training data</span>
<span style="color: #BA2121; font-style: italic">trained_model = some_model.fit(X_train,y_train)</span>
<span style="color: #BA2121; font-style: italic">#Model prediction, we need also to transform our data set used for the prediction.</span>
<span style="color: #BA2121; font-style: italic">X_test = X_test - X_train_mean #Use mean from training data</span>
<span style="color: #BA2121; font-style: italic">y_pred = trained_model(X_test)</span>
<span style="color: #BA2121; font-style: italic">y_pred = y_pred + y_train_mean</span>
<span style="color: #BA2121; font-style: italic">&quot;&quot;&quot;</span>
</pre>
</div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
</div>
</div>
</div>
</div>
</div>
<p>Let us try to understand what this may imply mathematically when we
subtract the mean values, also known as <em>zero centering</em>. For
simplicity, we will focus on ordinary regression, as done in the above example.
</p>
<p>The cost/loss function for regression is</p>
$$
C(\beta_0, \beta_1, ... , \beta_{p-1}) = \frac{1}{n}\sum_{i=0}^{n} \left(y_i - \beta_0 - \sum_{j=1}^{p-1} X_{ij}\beta_j\right)^2,.
$$
<p>Recall also that we use the squared value. This expression can lead to an
increased penalty for higher differences between predicted and
output/target values.
</p>
<p>What we have done is to single out the \( \beta_0 \) term in the
definition of the mean squared error (MSE). The design matrix \( X \)
does in this case not contain any intercept column. When we take the
derivative with respect to \( \beta_0 \), we want the derivative to obey
</p>
$$
\frac{\partial C}{\partial \beta_j} = 0,
$$
<p>for all \( j \). For \( \beta_0 \) we have</p>
$$
\frac{\partial C}{\partial \beta_0} = -\frac{2}{n}\sum_{i=0}^{n-1} \left(y_i - \beta_0 - \sum_{j=1}^{p-1} X_{ij} \beta_j\right).
$$
<p>Multiplying away the constant \( 2/n \), we obtain</p>
$$
\sum_{i=0}^{n-1} \beta_0 = \sum_{i=0}^{n-1}y_i - \sum_{i=0}^{n-1} \sum_{j=1}^{p-1} X_{ij} \beta_j.
$$
<p>Let us specialize first to the case where we have only two parameters \( \beta_0 \) and \( \beta_1 \).
Our result for \( \beta_0 \) simplifies then to
</p>
$$
n\beta_0 = \sum_{i=0}^{n-1}y_i - \sum_{i=0}^{n-1} X_{i1} \beta_1.
$$
<p>We obtain then</p>
$$
\beta_0 = \frac{1}{n}\sum_{i=0}^{n-1}y_i - \beta_1\frac{1}{n}\sum_{i=0}^{n-1} X_{i1}.
$$
<p>If we define</p>
$$
\mu_{\boldsymbol{x}_1}=\frac{1}{n}\sum_{i=0}^{n-1} X_{i1},
$$
<p>and the mean value of the outputs as</p>
$$
\mu_y=\frac{1}{n}\sum_{i=0}^{n-1}y_i,
$$
<p>we have</p>
$$
\beta_0 = \mu_y - \beta_1\mu_{\boldsymbol{x}_1}.
$$
<p>In the general case with more parameters than \( \beta_0 \) and \( \beta_1 \), we have</p>
$$
\beta_0 = \frac{1}{n}\sum_{i=0}^{n-1}y_i - \frac{1}{n}\sum_{i=0}^{n-1}\sum_{j=1}^{p-1} X_{ij}\beta_j.
$$
<p>We can rewrite the latter equation as</p>
$$
\beta_0 = \frac{1}{n}\sum_{i=0}^{n-1}y_i - \sum_{j=1}^{p-1} \mu_{\boldsymbol{x}_j}\beta_j,
$$
<p>where we have defined</p>
$$
\mu_{\boldsymbol{x}_j}=\frac{1}{n}\sum_{i=0}^{n-1} X_{ij},
$$
<p>the mean value for all elements of the column vector \( \boldsymbol{x}_j \).</p>
<p>Replacing \( y_i \) with \( y_i - y_i - \overline{\boldsymbol{y}} \) and centering also our design matrix results in a cost function (in vector-matrix disguise)</p>
$$
C(\boldsymbol{\beta}) = (\boldsymbol{\tilde{y}} - \tilde{X}\boldsymbol{\beta})^T(\boldsymbol{\tilde{y}} - \tilde{X}\boldsymbol{\beta}).
$$
<p>If we minimize with respect to \( \boldsymbol{\beta} \) we have then</p>
$$
\hat{\boldsymbol{\beta}} = (\tilde{X}^T\tilde{X})^{-1}\tilde{X}^T\boldsymbol{\tilde{y}},
$$
<p>where \( \boldsymbol{\tilde{y}} = \boldsymbol{y} - \overline{\boldsymbol{y}} \)
and \( \tilde{X}_{ij} = X_{ij} - \frac{1}{n}\sum_{k=0}^{n-1}X_{kj} \).
</p>
<p>For Ridge regression we need to add \( \lambda \boldsymbol{\beta}^T\boldsymbol{\beta} \) to the cost function and get then</p>
$$
\hat{\boldsymbol{\beta}} = (\tilde{X}^T\tilde{X} + \lambda I)^{-1}\tilde{X}^T\boldsymbol{\tilde{y}}.
$$
<p>What does this mean? And why do we insist on all this? Let us look at some examples.</p>
<p>This code shows a simple first-order fit to a data set using the above transformed data, where we consider the role of the intercept first, by either excluding it or including it (<em>code example thanks to &#216;yvind Sigmundson Sch&#248;yen</em>). Here our scaling of the data is done by subtracting the mean values only.
Note also that we do not split the data into training and test.
</p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class="highlight" style="background: #f8f8f8">
<pre style="line-height: 125%;"><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
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">2021</span>)
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">MSE</span>(y_data,y_model):
n <span style="color: #666666">=</span> np<span style="color: #666666">.</span>size(y_model)
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>sum((y_data<span style="color: #666666">-</span>y_model)<span style="color: #666666">**2</span>)<span style="color: #666666">/</span>n
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">fit_beta</span>(X, y):
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>pinv(X<span style="color: #666666">.</span>T <span style="color: #666666">@</span> X) <span style="color: #666666">@</span> X<span style="color: #666666">.</span>T <span style="color: #666666">@</span> y
true_beta <span style="color: #666666">=</span> [<span style="color: #666666">2</span>, <span style="color: #666666">0.5</span>, <span style="color: #666666">3.7</span>]
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">0</span>, <span style="color: #666666">1</span>, <span style="color: #666666">11</span>)
y <span style="color: #666666">=</span> np<span style="color: #666666">.</span>sum(
np<span style="color: #666666">.</span>asarray([x <span style="color: #666666">**</span> p <span style="color: #666666">*</span> b <span style="color: #008000; font-weight: bold">for</span> p, b <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(true_beta)]), axis<span style="color: #666666">=0</span>
) <span style="color: #666666">+</span> <span style="color: #666666">0.1</span> <span style="color: #666666">*</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>normal(size<span style="color: #666666">=</span><span style="color: #008000">len</span>(x))
degree <span style="color: #666666">=</span> <span style="color: #666666">3</span>
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(x), degree))
<span style="color: #408080; font-style: italic"># Include the intercept in the design matrix</span>
<span style="color: #008000; font-weight: bold">for</span> p <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(degree):
X[:, p] <span style="color: #666666">=</span> x <span style="color: #666666">**</span> p
beta <span style="color: #666666">=</span> fit_beta(X, y)
<span style="color: #408080; font-style: italic"># Intercept is included in the design matrix</span>
skl <span style="color: #666666">=</span> LinearRegression(fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">False</span>)<span style="color: #666666">.</span>fit(X, y)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;True beta: </span><span style="color: #BB6688; font-weight: bold">{</span>true_beta<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Fitted beta: </span><span style="color: #BB6688; font-weight: bold">{</span>beta<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Sklearn fitted beta: </span><span style="color: #BB6688; font-weight: bold">{</span>skl<span style="color: #666666">.</span>coef_<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
ypredictOwn <span style="color: #666666">=</span> X <span style="color: #666666">@</span> beta
ypredictSKL <span style="color: #666666">=</span> skl<span style="color: #666666">.</span>predict(X)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;MSE with intercept column&quot;</span>)
<span style="color: #008000">print</span>(MSE(y,ypredictOwn))
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;MSE with intercept column from SKL&quot;</span>)
<span style="color: #008000">print</span>(MSE(y,ypredictSKL))
plt<span style="color: #666666">.</span>figure()
plt<span style="color: #666666">.</span>scatter(x, y, label<span style="color: #666666">=</span><span style="color: #BA2121">&quot;Data&quot;</span>)
plt<span style="color: #666666">.</span>plot(x, X <span style="color: #666666">@</span> beta, label<span style="color: #666666">=</span><span style="color: #BA2121">&quot;Fit&quot;</span>)
plt<span style="color: #666666">.</span>plot(x, skl<span style="color: #666666">.</span>predict(X), label<span style="color: #666666">=</span><span style="color: #BA2121">&quot;Sklearn (fit_intercept=False)&quot;</span>)
<span style="color: #408080; font-style: italic"># Do not include the intercept in the design matrix</span>
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(x), degree <span style="color: #666666">-</span> <span style="color: #666666">1</span>))
<span style="color: #008000; font-weight: bold">for</span> p <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(degree <span style="color: #666666">-</span> <span style="color: #666666">1</span>):
X[:, p] <span style="color: #666666">=</span> x <span style="color: #666666">**</span> (p <span style="color: #666666">+</span> <span style="color: #666666">1</span>)
<span style="color: #408080; font-style: italic"># Intercept is not included in the design matrix</span>
skl <span style="color: #666666">=</span> LinearRegression(fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">True</span>)<span style="color: #666666">.</span>fit(X, y)
<span style="color: #408080; font-style: italic"># Use centered values for X and y when computing coefficients</span>
y_offset <span style="color: #666666">=</span> np<span style="color: #666666">.</span>average(y, axis<span style="color: #666666">=0</span>)
X_offset <span style="color: #666666">=</span> np<span style="color: #666666">.</span>average(X, axis<span style="color: #666666">=0</span>)
beta <span style="color: #666666">=</span> fit_beta(X <span style="color: #666666">-</span> X_offset, y <span style="color: #666666">-</span> y_offset)
intercept <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean(y_offset <span style="color: #666666">-</span> X_offset <span style="color: #666666">@</span> beta)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Manual intercept: </span><span style="color: #BB6688; font-weight: bold">{</span>intercept<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Fitted beta (without intercept): </span><span style="color: #BB6688; font-weight: bold">{</span>beta<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Sklearn intercept: </span><span style="color: #BB6688; font-weight: bold">{</span>skl<span style="color: #666666">.</span>intercept_<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;Sklearn fitted beta (without intercept): </span><span style="color: #BB6688; font-weight: bold">{</span>skl<span style="color: #666666">.</span>coef_<span style="color: #BB6688; font-weight: bold">}</span><span style="color: #BA2121">&quot;</span>)
ypredictOwn <span style="color: #666666">=</span> X <span style="color: #666666">@</span> beta
ypredictSKL <span style="color: #666666">=</span> skl<span style="color: #666666">.</span>predict(X)
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;MSE with Manual intercept&quot;</span>)
<span style="color: #008000">print</span>(MSE(y,ypredictOwn<span style="color: #666666">+</span>intercept))
<span style="color: #008000">print</span>(<span style="color: #BA2121">f&quot;MSE with Sklearn intercept&quot;</span>)
<span style="color: #008000">print</span>(MSE(y,ypredictSKL))
plt<span style="color: #666666">.</span>plot(x, X <span style="color: #666666">@</span> beta <span style="color: #666666">+</span> intercept, <span style="color: #BA2121">&quot;--&quot;</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">&quot;Fit (manual intercept)&quot;</span>)
plt<span style="color: #666666">.</span>plot(x, skl<span style="color: #666666">.</span>predict(X), <span style="color: #BA2121">&quot;--&quot;</span>, label<span style="color: #666666">=</span><span style="color: #BA2121">&quot;Sklearn (fit_intercept=True)&quot;</span>)
plt<span style="color: #666666">.</span>grid()
plt<span style="color: #666666">.</span>legend()
plt<span style="color: #666666">.</span>show()
</pre>
</div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
</div>
</div>
</div>
</div>
</div>
<p>The intercept is the value of our output/target variable
when all our features are zero and our function crosses the \( y \)-axis (for a one-dimensional case).
</p>
<p>Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include \( \beta_0 \). For different values
of \( \lambda \), this may lead to different MSE values.
</p>
<p>To remind the reader, the regularization term, with the intercept in Ridge regression, is given by</p>
$$
\lambda \vert\vert \boldsymbol{\beta} \vert\vert_2^2 = \lambda \sum_{j=0}^{p-1}\beta_j^2,
$$
<p>but when we take out the intercept, this equation becomes</p>
$$
\lambda \vert\vert \boldsymbol{\beta} \vert\vert_2^2 = \lambda \sum_{j=1}^{p-1}\beta_j^2.
$$
<p>For Lasso regression we have</p>
$$
\lambda \vert\vert \boldsymbol{\beta} \vert\vert_1 = \lambda \sum_{j=1}^{p-1}\vert\beta_j\vert.
$$
<p>It means that, when scaling the design matrix and the outputs/targets,
by subtracting the mean values, we have an optimization problem which
is not penalized by the intercept. The MSE value can then be smaller
since it focuses only on the remaining quantities. If we however bring
back the intercept, we will get a MSE which then contains the
intercept.
</p>
<p>Armed with this wisdom, we attempt first to simply set the intercept equal to <b>False</b> in our implementation of Ridge regression for our well-known vanilla data set.</p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class="highlight" style="background: #f8f8f8">
<pre style="line-height: 125%;"><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">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</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.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> train_test_split
<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">def</span> <span style="color: #0000FF">MSE</span>(y_data,y_model):
n <span style="color: #666666">=</span> np<span style="color: #666666">.</span>size(y_model)
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>sum((y_data<span style="color: #666666">-</span>y_model)<span style="color: #666666">**2</span>)<span style="color: #666666">/</span>n
<span style="color: #408080; font-style: italic"># A seed just to ensure that the random numbers are the same for every run.</span>
<span style="color: #408080; font-style: italic"># Useful for eventual debugging.</span>
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">3155</span>)
n <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)
y <span style="color: #666666">=</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>x<span style="color: #666666">**2</span>) <span style="color: #666666">+</span> <span style="color: #666666">1.5</span> <span style="color: #666666">*</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>(x<span style="color: #666666">-2</span>)<span style="color: #666666">**2</span>)
Maxpolydegree <span style="color: #666666">=</span> <span style="color: #666666">20</span>
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((n,Maxpolydegree))
<span style="color: #408080; font-style: italic">#We include explicitely the intercept column</span>
<span style="color: #008000; font-weight: bold">for</span> degree <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(Maxpolydegree):
X[:,degree] <span style="color: #666666">=</span> x<span style="color: #666666">**</span>degree
<span style="color: #408080; font-style: italic"># We split the data in test and training data</span>
X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(X, y, test_size<span style="color: #666666">=0.2</span>)
p <span style="color: #666666">=</span> Maxpolydegree
I <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(p,p)
<span style="color: #408080; font-style: italic"># Decide which values of lambda to use</span>
nlambdas <span style="color: #666666">=</span> <span style="color: #666666">6</span>
MSEOwnRidgePredict <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(nlambdas)
MSERidgePredict <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(nlambdas)
lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-4</span>, <span style="color: #666666">2</span>, nlambdas)
<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>(nlambdas):
lmb <span style="color: #666666">=</span> lambdas[i]
OwnRidgeBeta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>pinv(X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> X_train<span style="color: #666666">+</span>lmb<span style="color: #666666">*</span>I) <span style="color: #666666">@</span> X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> y_train
<span style="color: #408080; font-style: italic"># Note: we include the intercept column and no scaling</span>
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">False</span>)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
<span style="color: #408080; font-style: italic"># and then make the prediction</span>
ytildeOwnRidge <span style="color: #666666">=</span> X_train <span style="color: #666666">@</span> OwnRidgeBeta
ypredictOwnRidge <span style="color: #666666">=</span> X_test <span style="color: #666666">@</span> OwnRidgeBeta
ytildeRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_train)
ypredictRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_test)
MSEOwnRidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictRidge)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(OwnRidgeBeta)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>coef_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSEOwnRidgePredict, <span style="color: #BA2121">&#39;r&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE own Ridge Test&#39;</span>)
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSERidgePredict, <span style="color: #BA2121">&#39;g&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE Ridge Test&#39;</span>)
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">&#39;log10(lambda)&#39;</span>)
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">&#39;MSE&#39;</span>)
plt<span style="color: #666666">.</span>legend()
plt<span style="color: #666666">.</span>show()
</pre>
</div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
</div>
</div>
</div>
</div>
</div>
<p>The results here agree when we force <b>Scikit-Learn</b>'s Ridge function to include the first column in our design matrix.
We see that the results agree very well. Here we have thus explicitely included the intercept column in the design matrix.
What happens if we do not include the intercept in our fit?
Let us see how we can change this code by zero centering.
</p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class="highlight" style="background: #f8f8f8">
<pre style="line-height: 125%;"><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">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</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.model_selection</span> <span style="color: #008000; font-weight: bold">import</span> train_test_split
<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.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> StandardScaler
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">MSE</span>(y_data,y_model):
n <span style="color: #666666">=</span> np<span style="color: #666666">.</span>size(y_model)
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>sum((y_data<span style="color: #666666">-</span>y_model)<span style="color: #666666">**2</span>)<span style="color: #666666">/</span>n
<span style="color: #408080; font-style: italic"># A seed just to ensure that the random numbers are the same for every run.</span>
<span style="color: #408080; font-style: italic"># Useful for eventual debugging.</span>
np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>seed(<span style="color: #666666">315</span>)
n <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)
y <span style="color: #666666">=</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>x<span style="color: #666666">**2</span>) <span style="color: #666666">+</span> <span style="color: #666666">1.5</span> <span style="color: #666666">*</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>(x<span style="color: #666666">-2</span>)<span style="color: #666666">**2</span>)
Maxpolydegree <span style="color: #666666">=</span> <span style="color: #666666">20</span>
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((n,Maxpolydegree<span style="color: #666666">-1</span>))
<span style="color: #008000; font-weight: bold">for</span> degree <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #666666">1</span>,Maxpolydegree): <span style="color: #408080; font-style: italic">#No intercept column</span>
X[:,degree<span style="color: #666666">-1</span>] <span style="color: #666666">=</span> x<span style="color: #666666">**</span>(degree)
<span style="color: #408080; font-style: italic"># We split the data in test and training data</span>
X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(X, y, test_size<span style="color: #666666">=0.2</span>)
<span style="color: #408080; font-style: italic">#For our own implementation, we will need to deal with the intercept by centering the design matrix and the target variable</span>
X_train_mean <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean(X_train,axis<span style="color: #666666">=0</span>)
<span style="color: #408080; font-style: italic">#Center by removing mean from each feature</span>
X_train_scaled <span style="color: #666666">=</span> X_train <span style="color: #666666">-</span> X_train_mean
X_test_scaled <span style="color: #666666">=</span> X_test <span style="color: #666666">-</span> X_train_mean
<span style="color: #408080; font-style: italic">#The model intercept (called y_scaler) is given by the mean of the target variable (IF X is centered)</span>
<span style="color: #408080; font-style: italic">#Remove the intercept from the training data.</span>
y_scaler <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean(y_train)
y_train_scaled <span style="color: #666666">=</span> y_train <span style="color: #666666">-</span> y_scaler
p <span style="color: #666666">=</span> Maxpolydegree<span style="color: #666666">-1</span>
I <span style="color: #666666">=</span> np<span style="color: #666666">.</span>eye(p,p)
<span style="color: #408080; font-style: italic"># Decide which values of lambda to use</span>
nlambdas <span style="color: #666666">=</span> <span style="color: #666666">6</span>
MSEOwnRidgePredict <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(nlambdas)
MSERidgePredict <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(nlambdas)
lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-4</span>, <span style="color: #666666">2</span>, nlambdas)
<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>(nlambdas):
lmb <span style="color: #666666">=</span> lambdas[i]
OwnRidgeBeta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>pinv(X_train_scaled<span style="color: #666666">.</span>T <span style="color: #666666">@</span> X_train_scaled<span style="color: #666666">+</span>lmb<span style="color: #666666">*</span>I) <span style="color: #666666">@</span> X_train_scaled<span style="color: #666666">.</span>T <span style="color: #666666">@</span> (y_train_scaled)
intercept_ <span style="color: #666666">=</span> y_scaler <span style="color: #666666">-</span> X_train_mean<span style="color: #AA22FF">@OwnRidgeBeta</span> <span style="color: #408080; font-style: italic">#The intercept can be shifted so the model can predict on uncentered data</span>
<span style="color: #408080; font-style: italic">#Add intercept to prediction</span>
ypredictOwnRidge <span style="color: #666666">=</span> X_test_scaled <span style="color: #666666">@</span> OwnRidgeBeta <span style="color: #666666">+</span> y_scaler
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
ypredictRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_test)
MSEOwnRidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictRidge)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(OwnRidgeBeta) <span style="color: #408080; font-style: italic">#Intercept is given by mean of target variable</span>
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>coef_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&#39;Intercept from own implementation:&#39;</span>)
<span style="color: #008000">print</span>(intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&#39;Intercept from Scikit-Learn Ridge implementation&#39;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSEOwnRidgePredict, <span style="color: #BA2121">&#39;b--&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE own Ridge Test&#39;</span>)
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSERidgePredict, <span style="color: #BA2121">&#39;g--&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE SL Ridge Test&#39;</span>)
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">&#39;log10(lambda)&#39;</span>)
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">&#39;MSE&#39;</span>)
plt<span style="color: #666666">.</span>legend()
plt<span style="color: #666666">.</span>show()
</pre>
</div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stdout output_text">
</div>
</div>
</div>
</div>
</div>
<p>We see here, when compared to the code which includes explicitely the
intercept column, that our MSE value is actually smaller. This is
because the regularization term does not include the intercept value
\( \beta_0 \) in the fitting. This applies to Lasso regularization as
well. It means that our optimization is now done only with the
centered matrix and/or vector that enter the fitting procedure.
</p>
<p>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
<li><a href="._week36-bs001.html">&laquo;</a></li>
<li><a href="._week36-bs000.html">1</a></li>
<li><a href="._week36-bs001.html">2</a></li>
<li class="active"><a href="._week36-bs002.html">3</a></li>
<li><a href="._week36-bs003.html">4</a></li>
<li><a href="._week36-bs004.html">5</a></li>
<li><a href="._week36-bs005.html">6</a></li>
<li><a href="._week36-bs006.html">7</a></li>
<li><a href="._week36-bs007.html">8</a></li>
<li><a href="._week36-bs008.html">9</a></li>
<li><a href="._week36-bs009.html">10</a></li>
<li><a href="._week36-bs010.html">11</a></li>
<li><a href="._week36-bs011.html">12</a></li>
<li><a href="">...</a></li>
<li><a href="._week36-bs048.html">49</a></li>
<li><a href="._week36-bs003.html">&raquo;</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="https://..."><img width="250" align=right src="https://..."></a>
</footer>
-->
<center style="font-size:80%">
<!-- copyright only on the titlepage -->
</center>
</body>
</html>