Files
FYS-STK4155/doc/pub/week35/html/._week35-bs062.html
T
2025-08-26 07:02:47 +02:00

914 lines
62 KiB
HTML

<!--
HTML file automatically generated from DocOnce source
(https://github.com/doconce/doconce/)
doconce format html week35.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week35-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 35: From Ordinary Linear Regression to Ridge and Lasso Regression">
<title>Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression</title>
<!-- Bootstrap style: bootstrap -->
<!-- doconce format html week35.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week35-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 35', 2, None, 'plans-for-week-35'),
('Reading recommendations:', 3, None, 'reading-recommendations'),
('Reminder from last week', 2, None, 'reminder-from-last-week'),
('The equations for ordinary least squares',
2,
None,
'the-equations-for-ordinary-least-squares'),
('The cost/loss function', 2, None, 'the-cost-loss-function'),
('Interpretations and optimizing our parameters',
2,
None,
'interpretations-and-optimizing-our-parameters'),
('Interpretations and optimizing our parameters',
2,
None,
'interpretations-and-optimizing-our-parameters'),
('Some useful matrix and vector expressions',
2,
None,
'some-useful-matrix-and-vector-expressions'),
('The Jacobian', 2, None, 'the-jacobian'),
('Derivatives, example 1', 2, None, 'derivatives-example-1'),
('Example 2', 2, None, 'example-2'),
('Example 3', 2, None, 'example-3'),
('Example 4', 2, None, 'example-4'),
('The mean squared error and its derivative',
2,
None,
'the-mean-squared-error-and-its-derivative'),
('Meet the Hessian Matrix', 2, None, 'meet-the-hessian-matrix'),
('Interpretations and optimizing our parameters',
2,
None,
'interpretations-and-optimizing-our-parameters'),
('Example relevant for the exercises',
2,
None,
'example-relevant-for-the-exercises'),
('Own code for Ordinary Least Squares',
2,
None,
'own-code-for-ordinary-least-squares'),
('Adding error analysis and training set up',
2,
None,
'adding-error-analysis-and-training-set-up'),
('Splitting our Data in Training and Test data',
2,
None,
'splitting-our-data-in-training-and-test-data'),
('The complete code with a simple data set',
2,
None,
'the-complete-code-with-a-simple-data-set'),
('Making your own test-train splitting',
2,
None,
'making-your-own-test-train-splitting'),
('Reducing the number of degrees of freedom, overarching view',
2,
None,
'reducing-the-number-of-degrees-of-freedom-overarching-view'),
('Preprocessing our data', 2, None, 'preprocessing-our-data'),
('Functionality in Scikit-Learn',
2,
None,
'functionality-in-scikit-learn'),
('More preprocessing', 2, None, 'more-preprocessing'),
('Frequently used scaling functions',
2,
None,
'frequently-used-scaling-functions'),
('Example of own Standard scaling',
2,
None,
'example-of-own-standard-scaling'),
('Min-Max Scaling', 2, None, 'min-max-scaling'),
('Testing the Means Squared Error as function of Complexity',
2,
None,
'testing-the-means-squared-error-as-function-of-complexity'),
('Mathematical Interpretation of Ordinary Least Squares',
2,
None,
'mathematical-interpretation-of-ordinary-least-squares'),
('Residual Error', 2, None, 'residual-error'),
('Simple case', 2, None, 'simple-case'),
('The singular value decomposition',
2,
None,
'the-singular-value-decomposition'),
('Linear Regression Problems',
2,
None,
'linear-regression-problems'),
('Fixing the singularity', 2, None, 'fixing-the-singularity'),
('Ridge and LASSO Regression',
2,
None,
'ridge-and-lasso-regression'),
('Deriving the Ridge Regression Equations',
2,
None,
'deriving-the-ridge-regression-equations'),
('Basic math of the SVD', 2, None, 'basic-math-of-the-svd'),
('The SVD, a Fantastic Algorithm',
2,
None,
'the-svd-a-fantastic-algorithm'),
('Economy-size SVD', 2, None, 'economy-size-svd'),
('Codes for the SVD', 2, None, 'codes-for-the-svd'),
('Note about SVD Calculations',
2,
None,
'note-about-svd-calculations'),
('Mathematics of the SVD and implications',
2,
None,
'mathematics-of-the-svd-and-implications'),
('Example Matrix', 2, None, 'example-matrix'),
('Setting up the Matrix to be inverted',
2,
None,
'setting-up-the-matrix-to-be-inverted'),
('Further properties (important for our analyses later)',
2,
None,
'further-properties-important-for-our-analyses-later'),
('Meet the Covariance Matrix',
2,
None,
'meet-the-covariance-matrix'),
('Introducing the Covariance and Correlation functions',
2,
None,
'introducing-the-covariance-and-correlation-functions'),
('Covariance and Correlation Matrix',
2,
None,
'covariance-and-correlation-matrix'),
('Correlation Function and Design/Feature Matrix',
2,
None,
'correlation-function-and-design-feature-matrix'),
('Covariance Matrix Examples',
2,
None,
'covariance-matrix-examples'),
('Correlation Matrix', 2, None, 'correlation-matrix'),
('Correlation Matrix with Pandas',
2,
None,
'correlation-matrix-with-pandas'),
('Rewriting the Covariance and/or Correlation Matrix',
2,
None,
'rewriting-the-covariance-and-or-correlation-matrix'),
('Linking with the SVD', 2, None, 'linking-with-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'),
('Back to Ridge and LASSO Regression',
2,
None,
'back-to-ridge-and-lasso-regression'),
('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'),
('Material for exercises week 35',
2,
None,
'material-for-exercises-week-35'),
('Important technicalities: More on Rescaling data',
2,
None,
'important-technicalities-more-on-rescaling-data')]}
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="week35-bs.html">Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression</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="._week35-bs001.html#plans-for-week-35" style="font-size: 80%;"><b>Plans for week 35</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs001.html#reading-recommendations" style="font-size: 80%;">&nbsp;&nbsp;&nbsp;Reading recommendations:</a></li>
<!-- navigation toc: --> <li><a href="._week35-bs002.html#reminder-from-last-week" style="font-size: 80%;"><b>Reminder from last week</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs003.html#the-equations-for-ordinary-least-squares" style="font-size: 80%;"><b>The equations for ordinary least squares</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs004.html#the-cost-loss-function" style="font-size: 80%;"><b>The cost/loss function</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs015.html#interpretations-and-optimizing-our-parameters" style="font-size: 80%;"><b>Interpretations and optimizing our parameters</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs015.html#interpretations-and-optimizing-our-parameters" style="font-size: 80%;"><b>Interpretations and optimizing our parameters</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs007.html#some-useful-matrix-and-vector-expressions" style="font-size: 80%;"><b>Some useful matrix and vector expressions</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs008.html#the-jacobian" style="font-size: 80%;"><b>The Jacobian</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs009.html#derivatives-example-1" style="font-size: 80%;"><b>Derivatives, example 1</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs010.html#example-2" style="font-size: 80%;"><b>Example 2</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs011.html#example-3" style="font-size: 80%;"><b>Example 3</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs012.html#example-4" style="font-size: 80%;"><b>Example 4</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs013.html#the-mean-squared-error-and-its-derivative" style="font-size: 80%;"><b>The mean squared error and its derivative</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs014.html#meet-the-hessian-matrix" style="font-size: 80%;"><b>Meet the Hessian Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs015.html#interpretations-and-optimizing-our-parameters" style="font-size: 80%;"><b>Interpretations and optimizing our parameters</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs016.html#example-relevant-for-the-exercises" style="font-size: 80%;"><b>Example relevant for the exercises</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs017.html#own-code-for-ordinary-least-squares" style="font-size: 80%;"><b>Own code for Ordinary Least Squares</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs018.html#adding-error-analysis-and-training-set-up" style="font-size: 80%;"><b>Adding error analysis and training set up</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs019.html#splitting-our-data-in-training-and-test-data" style="font-size: 80%;"><b>Splitting our Data in Training and Test data</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs020.html#the-complete-code-with-a-simple-data-set" style="font-size: 80%;"><b>The complete code with a simple data set</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs021.html#making-your-own-test-train-splitting" style="font-size: 80%;"><b>Making your own test-train splitting</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs022.html#reducing-the-number-of-degrees-of-freedom-overarching-view" style="font-size: 80%;"><b>Reducing the number of degrees of freedom, overarching view</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs023.html#preprocessing-our-data" style="font-size: 80%;"><b>Preprocessing our data</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs024.html#functionality-in-scikit-learn" style="font-size: 80%;"><b>Functionality in Scikit-Learn</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs025.html#more-preprocessing" style="font-size: 80%;"><b>More preprocessing</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs026.html#frequently-used-scaling-functions" style="font-size: 80%;"><b>Frequently used scaling functions</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs027.html#example-of-own-standard-scaling" style="font-size: 80%;"><b>Example of own Standard scaling</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs028.html#min-max-scaling" style="font-size: 80%;"><b>Min-Max Scaling</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs029.html#testing-the-means-squared-error-as-function-of-complexity" style="font-size: 80%;"><b>Testing the Means Squared Error as function of Complexity</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs030.html#mathematical-interpretation-of-ordinary-least-squares" style="font-size: 80%;"><b>Mathematical Interpretation of Ordinary Least Squares</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs031.html#residual-error" style="font-size: 80%;"><b>Residual Error</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs032.html#simple-case" style="font-size: 80%;"><b>Simple case</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs033.html#the-singular-value-decomposition" style="font-size: 80%;"><b>The singular value decomposition</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs034.html#linear-regression-problems" style="font-size: 80%;"><b>Linear Regression Problems</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs035.html#fixing-the-singularity" style="font-size: 80%;"><b>Fixing the singularity</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs036.html#ridge-and-lasso-regression" style="font-size: 80%;"><b>Ridge and LASSO Regression</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs037.html#deriving-the-ridge-regression-equations" style="font-size: 80%;"><b>Deriving the Ridge Regression Equations</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs038.html#basic-math-of-the-svd" style="font-size: 80%;"><b>Basic math of the SVD</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs039.html#the-svd-a-fantastic-algorithm" style="font-size: 80%;"><b>The SVD, a Fantastic Algorithm</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs040.html#economy-size-svd" style="font-size: 80%;"><b>Economy-size SVD</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs041.html#codes-for-the-svd" style="font-size: 80%;"><b>Codes for the SVD</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs042.html#note-about-svd-calculations" style="font-size: 80%;"><b>Note about SVD Calculations</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs043.html#mathematics-of-the-svd-and-implications" style="font-size: 80%;"><b>Mathematics of the SVD and implications</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs044.html#example-matrix" style="font-size: 80%;"><b>Example Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs045.html#setting-up-the-matrix-to-be-inverted" style="font-size: 80%;"><b>Setting up the Matrix to be inverted</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs046.html#further-properties-important-for-our-analyses-later" style="font-size: 80%;"><b>Further properties (important for our analyses later)</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs047.html#meet-the-covariance-matrix" style="font-size: 80%;"><b>Meet the Covariance Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs048.html#introducing-the-covariance-and-correlation-functions" style="font-size: 80%;"><b>Introducing the Covariance and Correlation functions</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs049.html#covariance-and-correlation-matrix" style="font-size: 80%;"><b>Covariance and Correlation Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs050.html#correlation-function-and-design-feature-matrix" style="font-size: 80%;"><b>Correlation Function and Design/Feature Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs051.html#covariance-matrix-examples" style="font-size: 80%;"><b>Covariance Matrix Examples</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs052.html#correlation-matrix" style="font-size: 80%;"><b>Correlation Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs053.html#correlation-matrix-with-pandas" style="font-size: 80%;"><b>Correlation Matrix with Pandas</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs054.html#rewriting-the-covariance-and-or-correlation-matrix" style="font-size: 80%;"><b>Rewriting the Covariance and/or Correlation Matrix</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs055.html#linking-with-the-svd" style="font-size: 80%;"><b>Linking with the SVD</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs056.html#what-does-it-mean" style="font-size: 80%;"><b>What does it mean?</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs057.html#and-finally-boldsymbol-x-boldsymbol-x-t" style="font-size: 80%;"><b>And finally \( \boldsymbol{X}\boldsymbol{X}^T \)</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs058.html#back-to-ridge-and-lasso-regression" style="font-size: 80%;"><b>Back to Ridge and LASSO Regression</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs059.html#interpreting-the-ridge-results" style="font-size: 80%;"><b>Interpreting the Ridge results</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs060.html#more-interpretations" style="font-size: 80%;"><b>More interpretations</b></a></li>
<!-- navigation toc: --> <li><a href="._week35-bs061.html#deriving-the-lasso-regression-equations" style="font-size: 80%;"><b>Deriving the Lasso Regression Equations</b></a></li>
<!-- navigation toc: --> <li><a href="#material-for-exercises-week-35" style="font-size: 80%;"><b>Material for exercises week 35</b></a></li>
<!-- navigation toc: --> <li><a href="#important-technicalities-more-on-rescaling-data" style="font-size: 80%;"><b>Important technicalities: More on Rescaling data</b></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="part0062"></a>
<!-- !split -->
<h2 id="material-for-exercises-week-35" class="anchor">Material for exercises week 35 </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="._week35-bs061.html">&laquo;</a></li>
<li><a href="._week35-bs000.html">1</a></li>
<li><a href="">...</a></li>
<li><a href="._week35-bs054.html">55</a></li>
<li><a href="._week35-bs055.html">56</a></li>
<li><a href="._week35-bs056.html">57</a></li>
<li><a href="._week35-bs057.html">58</a></li>
<li><a href="._week35-bs058.html">59</a></li>
<li><a href="._week35-bs059.html">60</a></li>
<li><a href="._week35-bs060.html">61</a></li>
<li><a href="._week35-bs061.html">62</a></li>
<li class="active"><a href="._week35-bs062.html">63</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>