Morten Hjorth-Jensen
441 lines
29 KiB
HTML
441 lines
29 KiB
HTML
<!--
|
|
HTML file automatically generated from DocOnce source
|
|
(https://github.com/doconce/doconce/)
|
|
doconce format html week44.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week44-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 44: Dimensionality Reduction, PCA and Clustering. Decision Trees">
|
|
<title>Week 44: Dimensionality Reduction, PCA and Clustering. Decision Trees</title>
|
|
<!-- Bootstrap style: bootstrap -->
|
|
<!-- doconce format html week44.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week44-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': [('Overview of week 44', 2, None, 'overview-of-week-44'),
|
|
('Digression First', 2, None, 'digression-first'),
|
|
('A short Discussion of Project 2',
|
|
2,
|
|
None,
|
|
'a-short-discussion-of-project-2'),
|
|
('Learning Rate and more', 2, None, 'learning-rate-and-more'),
|
|
('Thursday, Principal Component Analysis',
|
|
2,
|
|
None,
|
|
'thursday-principal-component-analysis'),
|
|
("A kind of Bird's view on PCA",
|
|
2,
|
|
None,
|
|
'a-kind-of-bird-s-view-on-pca'),
|
|
('Thursday: Clustering and Unsupervised Learning',
|
|
2,
|
|
None,
|
|
'thursday-clustering-and-unsupervised-learning'),
|
|
('Basic Idea of the $k$-means Clustering Algorithm',
|
|
2,
|
|
None,
|
|
'basic-idea-of-the-k-means-clustering-algorithm'),
|
|
('The $k$-means Algorithm', 2, None, 'the-k-means-algorithm'),
|
|
('Basic Math of the $k$-means Algorithm',
|
|
2,
|
|
None,
|
|
'basic-math-of-the-k-means-algorithm'),
|
|
('Within Cluster Point Scatter',
|
|
2,
|
|
None,
|
|
'within-cluster-point-scatter'),
|
|
('More Details', 2, None, 'more-details'),
|
|
('Total Cluster Variance', 2, None, 'total-cluster-variance'),
|
|
('The $k$-means Clustering Algorithm',
|
|
2,
|
|
None,
|
|
'the-k-means-clustering-algorithm'),
|
|
('Summarizing', 2, None, 'summarizing'),
|
|
('Writing our own Code, the Data Set',
|
|
2,
|
|
None,
|
|
'writing-our-own-code-the-data-set'),
|
|
('Implementing the $k$-means Algorithm',
|
|
2,
|
|
None,
|
|
'implementing-the-k-means-algorithm'),
|
|
('Plotting', 2, None, 'plotting'),
|
|
('Continuing', 2, None, 'continuing'),
|
|
('Wrapping it up', 2, None, 'wrapping-it-up'),
|
|
('Decision trees, overarching aims',
|
|
2,
|
|
None,
|
|
'decision-trees-overarching-aims'),
|
|
('Basics of a tree', 2, None, 'basics-of-a-tree'),
|
|
('A Sketch of a Tree, Regression problem',
|
|
2,
|
|
None,
|
|
'a-sketch-of-a-tree-regression-problem'),
|
|
('A Sketch of a Tree, Classification problem',
|
|
2,
|
|
None,
|
|
'a-sketch-of-a-tree-classification-problem'),
|
|
('A typical Decision Tree with its pertinent Jargon, '
|
|
'Classification Problem',
|
|
2,
|
|
None,
|
|
'a-typical-decision-tree-with-its-pertinent-jargon-classification-problem'),
|
|
('General Features', 2, None, 'general-features'),
|
|
('How do we set it up?', 2, None, 'how-do-we-set-it-up'),
|
|
('Decision trees and Regression',
|
|
2,
|
|
None,
|
|
'decision-trees-and-regression'),
|
|
('Building a tree, regression',
|
|
2,
|
|
None,
|
|
'building-a-tree-regression'),
|
|
('A top-down approach, recursive binary splitting',
|
|
2,
|
|
None,
|
|
'a-top-down-approach-recursive-binary-splitting'),
|
|
('Making a tree', 2, None, 'making-a-tree'),
|
|
('Pruning the tree', 2, None, 'pruning-the-tree'),
|
|
('Cost complexity pruning', 2, None, 'cost-complexity-pruning'),
|
|
('Schematic Regression Procedure',
|
|
2,
|
|
None,
|
|
'schematic-regression-procedure'),
|
|
('A Classification Tree', 2, None, 'a-classification-tree'),
|
|
('Growing a classification tree',
|
|
2,
|
|
None,
|
|
'growing-a-classification-tree'),
|
|
('Classification tree, how to split nodes',
|
|
2,
|
|
None,
|
|
'classification-tree-how-to-split-nodes'),
|
|
('Visualizing the Tree, Classification',
|
|
2,
|
|
None,
|
|
'visualizing-the-tree-classification'),
|
|
('Visualizing the Tree, The Moons',
|
|
2,
|
|
None,
|
|
'visualizing-the-tree-the-moons'),
|
|
('Other ways of visualizing the trees',
|
|
2,
|
|
None,
|
|
'other-ways-of-visualizing-the-trees'),
|
|
('Printing out as text', 2, None, 'printing-out-as-text'),
|
|
('Algorithms for Setting up Decision Trees',
|
|
2,
|
|
None,
|
|
'algorithms-for-setting-up-decision-trees'),
|
|
('The CART algorithm for Classification',
|
|
2,
|
|
None,
|
|
'the-cart-algorithm-for-classification'),
|
|
('The CART algorithm for Regression',
|
|
2,
|
|
None,
|
|
'the-cart-algorithm-for-regression'),
|
|
('Computing the Gini index', 2, None, 'computing-the-gini-index'),
|
|
('Simple Python Code to read in Data and perform Classification',
|
|
2,
|
|
None,
|
|
'simple-python-code-to-read-in-data-and-perform-classification'),
|
|
('Computing the Gini Factor',
|
|
2,
|
|
None,
|
|
'computing-the-gini-factor'),
|
|
('Entropy and the ID3 algorithm',
|
|
2,
|
|
None,
|
|
'entropy-and-the-id3-algorithm'),
|
|
('Cancer Data again now with Decision Trees and other Methods',
|
|
2,
|
|
None,
|
|
'cancer-data-again-now-with-decision-trees-and-other-methods'),
|
|
('Another example, the moons again',
|
|
2,
|
|
None,
|
|
'another-example-the-moons-again'),
|
|
('Playing around with regions',
|
|
2,
|
|
None,
|
|
'playing-around-with-regions'),
|
|
('Regression trees', 2, None, 'regression-trees'),
|
|
('Final regressor code', 2, None, 'final-regressor-code'),
|
|
('Pros and cons of trees, pros',
|
|
2,
|
|
None,
|
|
'pros-and-cons-of-trees-pros'),
|
|
('Disadvantages', 2, None, 'disadvantages'),
|
|
('Ensemble Methods: From a Single Tree to Many Trees and Extreme '
|
|
'Boosting, Meet the Jungle of Methods',
|
|
2,
|
|
None,
|
|
'ensemble-methods-from-a-single-tree-to-many-trees-and-extreme-boosting-meet-the-jungle-of-methods'),
|
|
('An Overview of Ensemble Methods',
|
|
2,
|
|
None,
|
|
'an-overview-of-ensemble-methods'),
|
|
('Bagging', 2, None, 'bagging'),
|
|
('More bagging', 2, None, 'more-bagging'),
|
|
('Simple Voting Example, head or tail',
|
|
2,
|
|
None,
|
|
'simple-voting-example-head-or-tail'),
|
|
('Using the Voting Classifier',
|
|
2,
|
|
None,
|
|
'using-the-voting-classifier'),
|
|
('Please, not the moons again! Voting and Bagging',
|
|
2,
|
|
None,
|
|
'please-not-the-moons-again-voting-and-bagging'),
|
|
('Bagging Examples', 2, None, 'bagging-examples'),
|
|
('Making your own Bootstrap: Changing the Level of the Decision '
|
|
'Tree',
|
|
2,
|
|
None,
|
|
'making-your-own-bootstrap-changing-the-level-of-the-decision-tree')]}
|
|
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="week44-bs.html">Week 44: Dimensionality Reduction, PCA and Clustering. Decision Trees</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="._week44-bs001.html#overview-of-week-44" style="font-size: 80%;">Overview of week 44</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs002.html#digression-first" style="font-size: 80%;">Digression First</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs003.html#a-short-discussion-of-project-2" style="font-size: 80%;">A short Discussion of Project 2</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs004.html#learning-rate-and-more" style="font-size: 80%;">Learning Rate and more</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs005.html#thursday-principal-component-analysis" style="font-size: 80%;">Thursday, Principal Component Analysis</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs006.html#a-kind-of-bird-s-view-on-pca" style="font-size: 80%;">A kind of Bird's view on PCA</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs007.html#thursday-clustering-and-unsupervised-learning" style="font-size: 80%;">Thursday: Clustering and Unsupervised Learning</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs008.html#basic-idea-of-the-k-means-clustering-algorithm" style="font-size: 80%;">Basic Idea of the \( k \)-means Clustering Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs009.html#the-k-means-algorithm" style="font-size: 80%;">The \( k \)-means Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs010.html#basic-math-of-the-k-means-algorithm" style="font-size: 80%;">Basic Math of the \( k \)-means Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs011.html#within-cluster-point-scatter" style="font-size: 80%;">Within Cluster Point Scatter</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs012.html#more-details" style="font-size: 80%;">More Details</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs013.html#total-cluster-variance" style="font-size: 80%;">Total Cluster Variance</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs014.html#the-k-means-clustering-algorithm" style="font-size: 80%;">The \( k \)-means Clustering Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs015.html#summarizing" style="font-size: 80%;">Summarizing</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs016.html#writing-our-own-code-the-data-set" style="font-size: 80%;">Writing our own Code, the Data Set</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs017.html#implementing-the-k-means-algorithm" style="font-size: 80%;">Implementing the \( k \)-means Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs018.html#plotting" style="font-size: 80%;">Plotting</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs019.html#continuing" style="font-size: 80%;">Continuing</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs020.html#wrapping-it-up" style="font-size: 80%;">Wrapping it up</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs021.html#decision-trees-overarching-aims" style="font-size: 80%;">Decision trees, overarching aims</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs022.html#basics-of-a-tree" style="font-size: 80%;">Basics of a tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs023.html#a-sketch-of-a-tree-regression-problem" style="font-size: 80%;">A Sketch of a Tree, Regression problem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs024.html#a-sketch-of-a-tree-classification-problem" style="font-size: 80%;">A Sketch of a Tree, Classification problem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs025.html#a-typical-decision-tree-with-its-pertinent-jargon-classification-problem" style="font-size: 80%;">A typical Decision Tree with its pertinent Jargon, Classification Problem</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs026.html#general-features" style="font-size: 80%;">General Features</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs027.html#how-do-we-set-it-up" style="font-size: 80%;">How do we set it up?</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs028.html#decision-trees-and-regression" style="font-size: 80%;">Decision trees and Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs029.html#building-a-tree-regression" style="font-size: 80%;">Building a tree, regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs030.html#a-top-down-approach-recursive-binary-splitting" style="font-size: 80%;">A top-down approach, recursive binary splitting</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs031.html#making-a-tree" style="font-size: 80%;">Making a tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs032.html#pruning-the-tree" style="font-size: 80%;">Pruning the tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs033.html#cost-complexity-pruning" style="font-size: 80%;">Cost complexity pruning</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs034.html#schematic-regression-procedure" style="font-size: 80%;">Schematic Regression Procedure</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs035.html#a-classification-tree" style="font-size: 80%;">A Classification Tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs036.html#growing-a-classification-tree" style="font-size: 80%;">Growing a classification tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs037.html#classification-tree-how-to-split-nodes" style="font-size: 80%;">Classification tree, how to split nodes</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs038.html#visualizing-the-tree-classification" style="font-size: 80%;">Visualizing the Tree, Classification</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs039.html#visualizing-the-tree-the-moons" style="font-size: 80%;">Visualizing the Tree, The Moons</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs040.html#other-ways-of-visualizing-the-trees" style="font-size: 80%;">Other ways of visualizing the trees</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs041.html#printing-out-as-text" style="font-size: 80%;">Printing out as text</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs042.html#algorithms-for-setting-up-decision-trees" style="font-size: 80%;">Algorithms for Setting up Decision Trees</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs043.html#the-cart-algorithm-for-classification" style="font-size: 80%;">The CART algorithm for Classification</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs044.html#the-cart-algorithm-for-regression" style="font-size: 80%;">The CART algorithm for Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs045.html#computing-the-gini-index" style="font-size: 80%;">Computing the Gini index</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs046.html#simple-python-code-to-read-in-data-and-perform-classification" style="font-size: 80%;">Simple Python Code to read in Data and perform Classification</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs047.html#computing-the-gini-factor" style="font-size: 80%;">Computing the Gini Factor</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs048.html#entropy-and-the-id3-algorithm" style="font-size: 80%;">Entropy and the ID3 algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="#cancer-data-again-now-with-decision-trees-and-other-methods" style="font-size: 80%;">Cancer Data again now with Decision Trees and other Methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs050.html#another-example-the-moons-again" style="font-size: 80%;">Another example, the moons again</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs051.html#playing-around-with-regions" style="font-size: 80%;">Playing around with regions</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs052.html#regression-trees" style="font-size: 80%;">Regression trees</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs053.html#final-regressor-code" style="font-size: 80%;">Final regressor code</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs054.html#pros-and-cons-of-trees-pros" style="font-size: 80%;">Pros and cons of trees, pros</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs055.html#disadvantages" style="font-size: 80%;">Disadvantages</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs056.html#ensemble-methods-from-a-single-tree-to-many-trees-and-extreme-boosting-meet-the-jungle-of-methods" style="font-size: 80%;">Ensemble Methods: From a Single Tree to Many Trees and Extreme Boosting, Meet the Jungle of Methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs057.html#an-overview-of-ensemble-methods" style="font-size: 80%;">An Overview of Ensemble Methods</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs058.html#bagging" style="font-size: 80%;">Bagging</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs059.html#more-bagging" style="font-size: 80%;">More bagging</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs060.html#simple-voting-example-head-or-tail" style="font-size: 80%;">Simple Voting Example, head or tail</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs061.html#using-the-voting-classifier" style="font-size: 80%;">Using the Voting Classifier</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs062.html#please-not-the-moons-again-voting-and-bagging" style="font-size: 80%;">Please, not the moons again! Voting and Bagging</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs063.html#bagging-examples" style="font-size: 80%;">Bagging Examples</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week44-bs064.html#making-your-own-bootstrap-changing-the-level-of-the-decision-tree" style="font-size: 80%;">Making your own Bootstrap: Changing the Level of the Decision Tree</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="part0049"></a>
|
|
<!-- !split -->
|
|
<h2 id="cancer-data-again-now-with-decision-trees-and-other-methods" class="anchor">Cancer Data again now with Decision Trees and other Methods </h2>
|
|
|
|
<!-- 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">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
|
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
|
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.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.datasets</span> <span style="color: #008000; font-weight: bold">import</span> load_breast_cancer
|
|
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.svm</span> <span style="color: #008000; font-weight: bold">import</span> SVC
|
|
<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> LogisticRegression
|
|
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.tree</span> <span style="color: #008000; font-weight: bold">import</span> DecisionTreeClassifier
|
|
|
|
<span style="color: #408080; font-style: italic"># Load the data</span>
|
|
cancer <span style="color: #666666">=</span> load_breast_cancer()
|
|
|
|
X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(cancer<span style="color: #666666">.</span>data,cancer<span style="color: #666666">.</span>target,random_state<span style="color: #666666">=0</span>)
|
|
<span style="color: #008000">print</span>(X_train<span style="color: #666666">.</span>shape)
|
|
<span style="color: #008000">print</span>(X_test<span style="color: #666666">.</span>shape)
|
|
<span style="color: #408080; font-style: italic"># Logistic Regression</span>
|
|
logreg <span style="color: #666666">=</span> LogisticRegression(solver<span style="color: #666666">=</span><span style="color: #BA2121">'lbfgs'</span>)
|
|
logreg<span style="color: #666666">.</span>fit(X_train, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy with Logistic Regression: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test,y_test)))
|
|
<span style="color: #408080; font-style: italic"># Support vector machine</span>
|
|
svm <span style="color: #666666">=</span> SVC(gamma<span style="color: #666666">=</span><span style="color: #BA2121">'auto'</span>, C<span style="color: #666666">=100</span>)
|
|
svm<span style="color: #666666">.</span>fit(X_train, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy with SVM: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(svm<span style="color: #666666">.</span>score(X_test,y_test)))
|
|
<span style="color: #408080; font-style: italic"># Decision Trees</span>
|
|
deep_tree_clf <span style="color: #666666">=</span> DecisionTreeClassifier(max_depth<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">None</span>)
|
|
deep_tree_clf<span style="color: #666666">.</span>fit(X_train, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy with Decision Trees: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(deep_tree_clf<span style="color: #666666">.</span>score(X_test,y_test)))
|
|
<span style="color: #408080; font-style: italic">#now scale the data</span>
|
|
<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
|
|
scaler <span style="color: #666666">=</span> StandardScaler()
|
|
scaler<span style="color: #666666">.</span>fit(X_train)
|
|
X_train_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_train)
|
|
X_test_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_test)
|
|
<span style="color: #408080; font-style: italic"># Logistic Regression</span>
|
|
logreg<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy Logistic Regression with scaled data: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
|
|
<span style="color: #408080; font-style: italic"># Support Vector Machine</span>
|
|
svm<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy SVM with scaled data: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
|
|
<span style="color: #408080; font-style: italic"># Decision Trees</span>
|
|
deep_tree_clf<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
|
|
<span style="color: #008000">print</span>(<span style="color: #BA2121">"Test set accuracy with Decision Trees and scaled data: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">"</span><span style="color: #666666">.</span>format(deep_tree_clf<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
|
|
</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>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._week44-bs048.html">«</a></li>
|
|
<li><a href="._week44-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week44-bs041.html">42</a></li>
|
|
<li><a href="._week44-bs042.html">43</a></li>
|
|
<li><a href="._week44-bs043.html">44</a></li>
|
|
<li><a href="._week44-bs044.html">45</a></li>
|
|
<li><a href="._week44-bs045.html">46</a></li>
|
|
<li><a href="._week44-bs046.html">47</a></li>
|
|
<li><a href="._week44-bs047.html">48</a></li>
|
|
<li><a href="._week44-bs048.html">49</a></li>
|
|
<li class="active"><a href="._week44-bs049.html">50</a></li>
|
|
<li><a href="._week44-bs050.html">51</a></li>
|
|
<li><a href="._week44-bs051.html">52</a></li>
|
|
<li><a href="._week44-bs052.html">53</a></li>
|
|
<li><a href="._week44-bs053.html">54</a></li>
|
|
<li><a href="._week44-bs054.html">55</a></li>
|
|
<li><a href="._week44-bs055.html">56</a></li>
|
|
<li><a href="._week44-bs056.html">57</a></li>
|
|
<li><a href="._week44-bs057.html">58</a></li>
|
|
<li><a href="._week44-bs058.html">59</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week44-bs064.html">65</a></li>
|
|
<li><a href="._week44-bs050.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>
|
|
|