Morten Hjorth-Jensen
414 lines
27 KiB
HTML
414 lines
27 KiB
HTML
<!--
|
|
Automatically generated HTML file from DocOnce source
|
|
(https://github.com/doconce/doconce/)
|
|
-->
|
|
<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 37: Summary of Ridge and Lasso Regression and Resampling Methods">
|
|
|
|
<title>Week 37: Summary of Ridge and Lasso Regression and Resampling Methods</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': [('Plans for week 37', 2, None, 'plans-for-week-37'),
|
|
('Thursday September 16, Summary of Ridge and Lasso Regression '
|
|
'and start Resampling methods',
|
|
2,
|
|
None,
|
|
'thursday-september-16-summary-of-ridge-and-lasso-regression-and-start-resampling-methods'),
|
|
('Deriving OLS from a probability distribution',
|
|
2,
|
|
None,
|
|
'deriving-ols-from-a-probability-distribution'),
|
|
('Independent and Identically Distrubuted (iid)',
|
|
2,
|
|
None,
|
|
'independent-and-identically-distrubuted-iid'),
|
|
('Maximum Likelihood Estimation (MLE)',
|
|
2,
|
|
None,
|
|
'maximum-likelihood-estimation-mle'),
|
|
('A new Cost Function', 2, None, 'a-new-cost-function'),
|
|
("Bayes' Theorem", 2, None, 'bayes-theorem'),
|
|
("Interpretations of Bayes' Theorem",
|
|
2,
|
|
None,
|
|
'interpretations-of-bayes-theorem'),
|
|
('Test Function for what happens with OLS, Ridge and Lasso',
|
|
2,
|
|
None,
|
|
'test-function-for-what-happens-with-ols-ridge-and-lasso'),
|
|
('Rerunning the above code', 2, None, 'rerunning-the-above-code'),
|
|
("Invoking Bayes' theorem", 2, None, 'invoking-bayes-theorem'),
|
|
('Ridge and Bayes', 2, None, 'ridge-and-bayes'),
|
|
('Lasso and Bayes', 2, None, 'lasso-and-bayes'),
|
|
('Why resampling methods', 2, None, 'why-resampling-methods'),
|
|
('Resampling methods', 2, None, 'resampling-methods'),
|
|
('Resampling approaches can be computationally expensive',
|
|
2,
|
|
None,
|
|
'resampling-approaches-can-be-computationally-expensive'),
|
|
('Why resampling methods ?', 2, None, 'why-resampling-methods'),
|
|
('Statistical analysis', 2, None, 'statistical-analysis'),
|
|
('Resampling methods', 2, None, 'resampling-methods'),
|
|
('Resampling methods: Jackknife and Bootstrap',
|
|
2,
|
|
None,
|
|
'resampling-methods-jackknife-and-bootstrap'),
|
|
('Resampling methods: Jackknife',
|
|
2,
|
|
None,
|
|
'resampling-methods-jackknife'),
|
|
('Jackknife code example', 2, None, 'jackknife-code-example'),
|
|
('Resampling methods: Bootstrap',
|
|
2,
|
|
None,
|
|
'resampling-methods-bootstrap'),
|
|
('The Central Limit Theorem',
|
|
2,
|
|
None,
|
|
'the-central-limit-theorem'),
|
|
('Finding the Limit', 2, None, 'finding-the-limit'),
|
|
('Rewriting the $\\delta$-function',
|
|
2,
|
|
None,
|
|
'rewriting-the-delta-function'),
|
|
('Identifying Terms', 2, None, 'identifying-terms'),
|
|
('Wrapping it up', 2, None, 'wrapping-it-up'),
|
|
('Confidence Intervals', 2, None, 'confidence-intervals'),
|
|
('Standard Approach based on the Normal Distribution',
|
|
2,
|
|
None,
|
|
'standard-approach-based-on-the-normal-distribution'),
|
|
('Resampling methods: Bootstrap background',
|
|
2,
|
|
None,
|
|
'resampling-methods-bootstrap-background'),
|
|
('Resampling methods: More Bootstrap background',
|
|
2,
|
|
None,
|
|
'resampling-methods-more-bootstrap-background'),
|
|
('Resampling methods: Bootstrap approach',
|
|
2,
|
|
None,
|
|
'resampling-methods-bootstrap-approach'),
|
|
('Resampling methods: Bootstrap steps',
|
|
2,
|
|
None,
|
|
'resampling-methods-bootstrap-steps'),
|
|
('Code example for the Bootstrap method',
|
|
2,
|
|
None,
|
|
'code-example-for-the-bootstrap-method'),
|
|
('Plotting the Histogram', 2, None, 'plotting-the-histogram'),
|
|
('The bias-variance tradeoff',
|
|
2,
|
|
None,
|
|
'the-bias-variance-tradeoff'),
|
|
('A way to Read the Bias-Variance Tradeoff',
|
|
2,
|
|
None,
|
|
'a-way-to-read-the-bias-variance-tradeoff'),
|
|
('Example code for Bias-Variance tradeoff',
|
|
2,
|
|
None,
|
|
'example-code-for-bias-variance-tradeoff'),
|
|
('Understanding what happens',
|
|
2,
|
|
None,
|
|
'understanding-what-happens'),
|
|
('Summing up', 2, None, 'summing-up'),
|
|
("Another Example from Scikit-Learn's Repository",
|
|
2,
|
|
None,
|
|
'another-example-from-scikit-learn-s-repository'),
|
|
('Various steps in cross-validation',
|
|
2,
|
|
None,
|
|
'various-steps-in-cross-validation'),
|
|
('How to set up the cross-validation for Ridge and/or Lasso',
|
|
2,
|
|
None,
|
|
'how-to-set-up-the-cross-validation-for-ridge-and-or-lasso'),
|
|
('Cross-validation in brief',
|
|
2,
|
|
None,
|
|
'cross-validation-in-brief'),
|
|
('Code Example for Cross-validation and $k$-fold '
|
|
'Cross-validation',
|
|
2,
|
|
None,
|
|
'code-example-for-cross-validation-and-k-fold-cross-validation'),
|
|
('More examples on bootstrap and cross-validation and errors',
|
|
2,
|
|
None,
|
|
'more-examples-on-bootstrap-and-cross-validation-and-errors'),
|
|
('The same example but now with cross-validation',
|
|
2,
|
|
None,
|
|
'the-same-example-but-now-with-cross-validation')]}
|
|
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="week37-bs.html">Week 37: Summary of Ridge and Lasso Regression and Resampling Methods</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="._week37-bs001.html#plans-for-week-37" style="font-size: 80%;">Plans for week 37</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs002.html#thursday-september-16-summary-of-ridge-and-lasso-regression-and-start-resampling-methods" style="font-size: 80%;">Thursday September 16, Summary of Ridge and Lasso Regression and start Resampling methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs003.html#deriving-ols-from-a-probability-distribution" style="font-size: 80%;">Deriving OLS from a probability distribution</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs004.html#independent-and-identically-distrubuted-iid" style="font-size: 80%;">Independent and Identically Distrubuted (iid)</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs005.html#maximum-likelihood-estimation-mle" style="font-size: 80%;">Maximum Likelihood Estimation (MLE)</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs006.html#a-new-cost-function" style="font-size: 80%;">A new Cost Function</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs007.html#bayes-theorem" style="font-size: 80%;">Bayes' Theorem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs008.html#interpretations-of-bayes-theorem" style="font-size: 80%;">Interpretations of Bayes' Theorem</a></li>
|
|
<!-- navigation toc: --> <li><a href="#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="._week37-bs010.html#rerunning-the-above-code" style="font-size: 80%;">Rerunning the above code</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs011.html#invoking-bayes-theorem" style="font-size: 80%;">Invoking Bayes' theorem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs012.html#ridge-and-bayes" style="font-size: 80%;">Ridge and Bayes</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs013.html#lasso-and-bayes" style="font-size: 80%;">Lasso and Bayes</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs017.html#why-resampling-methods" style="font-size: 80%;">Why resampling methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs019.html#resampling-methods" style="font-size: 80%;">Resampling methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs016.html#resampling-approaches-can-be-computationally-expensive" style="font-size: 80%;">Resampling approaches can be computationally expensive</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs017.html#why-resampling-methods" style="font-size: 80%;">Why resampling methods ?</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs018.html#statistical-analysis" style="font-size: 80%;">Statistical analysis</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs019.html#resampling-methods" style="font-size: 80%;">Resampling methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs020.html#resampling-methods-jackknife-and-bootstrap" style="font-size: 80%;">Resampling methods: Jackknife and Bootstrap</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs021.html#resampling-methods-jackknife" style="font-size: 80%;">Resampling methods: Jackknife</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs022.html#jackknife-code-example" style="font-size: 80%;">Jackknife code example</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs023.html#resampling-methods-bootstrap" style="font-size: 80%;">Resampling methods: Bootstrap</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs024.html#the-central-limit-theorem" style="font-size: 80%;">The Central Limit Theorem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs025.html#finding-the-limit" style="font-size: 80%;">Finding the Limit</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs026.html#rewriting-the-delta-function" style="font-size: 80%;">Rewriting the \( \delta \)-function</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs027.html#identifying-terms" style="font-size: 80%;">Identifying Terms</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs028.html#wrapping-it-up" style="font-size: 80%;">Wrapping it up</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs029.html#confidence-intervals" style="font-size: 80%;">Confidence Intervals</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs030.html#standard-approach-based-on-the-normal-distribution" style="font-size: 80%;">Standard Approach based on the Normal Distribution</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs031.html#resampling-methods-bootstrap-background" style="font-size: 80%;">Resampling methods: Bootstrap background</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs032.html#resampling-methods-more-bootstrap-background" style="font-size: 80%;">Resampling methods: More Bootstrap background</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs033.html#resampling-methods-bootstrap-approach" style="font-size: 80%;">Resampling methods: Bootstrap approach</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs034.html#resampling-methods-bootstrap-steps" style="font-size: 80%;">Resampling methods: Bootstrap steps</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs035.html#code-example-for-the-bootstrap-method" style="font-size: 80%;">Code example for the Bootstrap method</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs036.html#plotting-the-histogram" style="font-size: 80%;">Plotting the Histogram</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs037.html#the-bias-variance-tradeoff" style="font-size: 80%;">The bias-variance tradeoff</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs038.html#a-way-to-read-the-bias-variance-tradeoff" style="font-size: 80%;">A way to Read the Bias-Variance Tradeoff</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs039.html#example-code-for-bias-variance-tradeoff" style="font-size: 80%;">Example code for Bias-Variance tradeoff</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs040.html#understanding-what-happens" style="font-size: 80%;">Understanding what happens</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs041.html#summing-up" style="font-size: 80%;">Summing up</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs042.html#another-example-from-scikit-learn-s-repository" style="font-size: 80%;">Another Example from Scikit-Learn's Repository</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs043.html#various-steps-in-cross-validation" style="font-size: 80%;">Various steps in cross-validation</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs044.html#how-to-set-up-the-cross-validation-for-ridge-and-or-lasso" style="font-size: 80%;">How to set up the cross-validation for Ridge and/or Lasso</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs045.html#cross-validation-in-brief" style="font-size: 80%;">Cross-validation in brief</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs046.html#code-example-for-cross-validation-and-k-fold-cross-validation" style="font-size: 80%;">Code Example for Cross-validation and \( k \)-fold Cross-validation</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs047.html#more-examples-on-bootstrap-and-cross-validation-and-errors" style="font-size: 80%;">More examples on bootstrap and cross-validation and errors</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week37-bs048.html#the-same-example-but-now-with-cross-validation" style="font-size: 80%;">The same example but now with cross-validation</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="part0009"></a>
|
|
<!-- !split -->
|
|
|
|
<h2 id="test-function-for-what-happens-with-ols-ridge-and-lasso" class="anchor">Test Function for what happens with OLS, Ridge and Lasso </h2>
|
|
|
|
<p>
|
|
We will play around with a study of the values for the optimal
|
|
parameters \( \boldsymbol{\beta} \) using OLS, Ridge and Lasso regression. For
|
|
OLS, you will notice as function of the noise and polynomial degree,
|
|
that the parameters \( \beta \) will fluctuate from order to order in the
|
|
polynomial fit and that for larger and larger polynomial degrees of freedom, the parameters will tend to increase in value for OLS.
|
|
|
|
<p>
|
|
For Ridge and Lasso regression, the higher order parameters will typically be reduced, providing thereby less fluctuations from one order to another one.
|
|
|
|
<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.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">R2</span>(y_data, y_model):
|
|
<span style="color: #008000; font-weight: bold">return</span> <span style="color: #666666">1</span> <span style="color: #666666">-</span> np<span style="color: #666666">.</span>sum((y_data <span style="color: #666666">-</span> y_model) <span style="color: #666666">**</span> <span style="color: #666666">2</span>) <span style="color: #666666">/</span> np<span style="color: #666666">.</span>sum((y_data <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(y_data)) <span style="color: #666666">**</span> <span style="color: #666666">2</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: #408080; font-style: italic"># Make data set.</span>
|
|
n <span style="color: #666666">=</span> <span style="color: #666666">10000</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>)<span style="color: #666666">+</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>randn(n)
|
|
|
|
Maxpolydegree <span style="color: #666666">=</span> <span style="color: #666666">5</span>
|
|
X <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(x),Maxpolydegree))
|
|
X[:,<span style="color: #666666">0</span>] <span style="color: #666666">=</span> <span style="color: #666666">1.0</span>
|
|
|
|
<span style="color: #008000; font-weight: bold">for</span> polydegree <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: #008000; font-weight: bold">for</span> degree <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(polydegree):
|
|
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>)
|
|
|
|
<span style="color: #408080; font-style: italic"># matrix inversion to find beta</span>
|
|
OLSbeta <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> X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> y_train
|
|
<span style="color: #008000">print</span>(OLSbeta)
|
|
ypredictOLS <span style="color: #666666">=</span> X_test <span style="color: #666666">@</span> OLSbeta
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test MSE OLS"</span>)
|
|
<span style="color: #008000">print</span>(MSE(y_test,ypredictOLS))
|
|
<span style="color: #408080; font-style: italic"># Repeat now for Lasso and Ridge regression and various values of the regularization parameter using Scikit-Learn</span>
|
|
<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">4</span>
|
|
MSERidgePredict <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(nlambdas)
|
|
MSELassoPredict <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">-3</span>, <span style="color: #666666">1</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]
|
|
<span style="color: #408080; font-style: italic"># Make the fit using Ridge and Lasso</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)
|
|
RegLasso <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Lasso(lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">False</span>)
|
|
RegLasso<span style="color: #666666">.</span>fit(X_train,y_train)
|
|
<span style="color: #408080; font-style: italic"># and then make the prediction</span>
|
|
ypredictRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_test)
|
|
ypredictLasso <span style="color: #666666">=</span> RegLasso<span style="color: #666666">.</span>predict(X_test)
|
|
<span style="color: #408080; font-style: italic"># Compute the MSE and print it</span>
|
|
MSERidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictRidge)
|
|
MSELassoPredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictLasso)
|
|
<span style="color: #008000">print</span>(lmb,RegRidge<span style="color: #666666">.</span>coef_)
|
|
<span style="color: #008000">print</span>(lmb,RegLasso<span style="color: #666666">.</span>coef_)
|
|
<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), MSERidgePredict, <span style="color: #BA2121">'b'</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">'MSE Ridge Test'</span>)
|
|
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSELassoPredict, <span style="color: #BA2121">'r'</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">'MSE Lasso Test'</span>)
|
|
plt<span style="color: #666666">.</span>xlabel(<span style="color: #BA2121">'log10(lambda)'</span>)
|
|
plt<span style="color: #666666">.</span>ylabel(<span style="color: #BA2121">'MSE'</span>)
|
|
plt<span style="color: #666666">.</span>legend()
|
|
plt<span style="color: #666666">.</span>show()
|
|
</pre></div>
|
|
<p>
|
|
How can we understand this?
|
|
|
|
<p>
|
|
<p>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._week37-bs008.html">«</a></li>
|
|
<li><a href="._week37-bs000.html">1</a></li>
|
|
<li><a href="._week37-bs001.html">2</a></li>
|
|
<li><a href="._week37-bs002.html">3</a></li>
|
|
<li><a href="._week37-bs003.html">4</a></li>
|
|
<li><a href="._week37-bs004.html">5</a></li>
|
|
<li><a href="._week37-bs005.html">6</a></li>
|
|
<li><a href="._week37-bs006.html">7</a></li>
|
|
<li><a href="._week37-bs007.html">8</a></li>
|
|
<li><a href="._week37-bs008.html">9</a></li>
|
|
<li class="active"><a href="._week37-bs009.html">10</a></li>
|
|
<li><a href="._week37-bs010.html">11</a></li>
|
|
<li><a href="._week37-bs011.html">12</a></li>
|
|
<li><a href="._week37-bs012.html">13</a></li>
|
|
<li><a href="._week37-bs013.html">14</a></li>
|
|
<li><a href="._week37-bs014.html">15</a></li>
|
|
<li><a href="._week37-bs015.html">16</a></li>
|
|
<li><a href="._week37-bs016.html">17</a></li>
|
|
<li><a href="._week37-bs017.html">18</a></li>
|
|
<li><a href="._week37-bs018.html">19</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week37-bs048.html">49</a></li>
|
|
<li><a href="._week37-bs010.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="https://..."><img width="250" align=right src="https://..."></a>
|
|
</footer>
|
|
-->
|
|
|
|
|
|
<center style="font-size:80%">
|
|
<!-- copyright only on the titlepage -->
|
|
</center>
|
|
|
|
|
|
</body>
|
|
</html>
|
|
|
|
|