lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added files

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2021-11-11 09:54:06 +01:00
parent 3fd80fede9
commit ea69981166
2 changed files with 733 additions and 628 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/week45/html/._week45-bs078.html
+502
View File
@@ -0,0 +1,502 @@
<!--
HTML file automatically generated from DocOnce source
(https://github.com/doconce/doconce/)
doconce format html week45.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week45-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 45: Decisions Trees, Random Forests, Bagging and Boosting">
<title>Week 45: Decisions Trees, Random Forests, Bagging and Boosting</title>
<!-- Bootstrap style: bootstrap -->
<!-- doconce format html week45.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week45-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 45', 2, None, 'overview-of-week-45'),
('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'),
('Gini Index (or Coefficient or Impurity)',
2,
None,
'gini-index-or-coefficient-or-impurity'),
('Why binary splits?', 2, None, 'why-binary-splits'),
('Computing a Tree using the Gini Index',
2,
None,
'computing-a-tree-using-the-gini-index'),
('The Table', 2, None, 'the-table'),
('Computing the various Gini Indices',
2,
None,
'computing-the-various-gini-indices'),
('Computing the various Gini Indices, Hours slept',
2,
None,
'computing-the-various-gini-indices-hours-slept'),
('Computing the various Gini Indices, Hours studied',
2,
None,
'computing-the-various-gini-indices-hours-studied'),
('A possible code using Scikit-Learn',
2,
None,
'a-possible-code-using-scikit-learn'),
('Visualizing Trees, More examples',
2,
None,
'visualizing-trees-more-examples'),
('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'),
('Making your own Bootstrap: Changing the Level of the Decision '
'Tree',
2,
None,
'making-your-own-bootstrap-changing-the-level-of-the-decision-tree'),
('Why Voting?', 2, None, 'why-voting'),
('Tossing coins', 2, None, 'tossing-coins'),
('Standard imports first', 2, None, 'standard-imports-first'),
('Simple Voting Example, head or tail',
2,
None,
'simple-voting-example-head-or-tail'),
('Using the Voting Classifier',
2,
None,
'using-the-voting-classifier'),
('Voting and Bagging', 2, None, 'voting-and-bagging'),
('Random forests', 2, None, 'random-forests'),
('Random Forest Algorithm', 2, None, 'random-forest-algorithm'),
('Random Forests Compared with other Methods on the Cancer Data',
2,
None,
'random-forests-compared-with-other-methods-on-the-cancer-data'),
('Compare Bagging on Trees with Random Forests',
2,
None,
'compare-bagging-on-trees-with-random-forests'),
("Boosting, a Bird's Eye View",
2,
None,
'boosting-a-bird-s-eye-view'),
('What is boosting? Additive Modelling/Iterative Fitting',
2,
None,
'what-is-boosting-additive-modelling-iterative-fitting'),
('Iterative Fitting, Regression and Squared-error Cost Function',
2,
None,
'iterative-fitting-regression-and-squared-error-cost-function'),
('Squared-Error Example and Iterative Fitting',
2,
None,
'squared-error-example-and-iterative-fitting'),
('Iterative Fitting, Classification and AdaBoost',
2,
None,
'iterative-fitting-classification-and-adaboost'),
('Adaptive Boosting, AdaBoost',
2,
None,
'adaptive-boosting-adaboost'),
('Building up AdaBoost', 2, None, 'building-up-adaboost'),
('Adaptive boosting: AdaBoost, Basic Algorithm',
2,
None,
'adaptive-boosting-adaboost-basic-algorithm'),
('Basic Steps of AdaBoost', 2, None, 'basic-steps-of-adaboost'),
('AdaBoost Examples', 2, None, 'adaboost-examples'),
('Gradient boosting: Basics with Steepest Descent/Functional '
'Gradient Descent',
2,
None,
'gradient-boosting-basics-with-steepest-descent-functional-gradient-descent'),
('The Squared-Error again! Steepest Descent',
2,
None,
'the-squared-error-again-steepest-descent'),
('Steepest Descent Example', 2, None, 'steepest-descent-example'),
('Gradient Boosting, algorithm',
2,
None,
'gradient-boosting-algorithm'),
('Gradient Boosting, Examples of Regression',
2,
None,
'gradient-boosting-examples-of-regression'),
('Gradient Boosting, Classification Example',
2,
None,
'gradient-boosting-classification-example'),
('XGBoost: Extreme Gradient Boosting',
2,
None,
'xgboost-extreme-gradient-boosting'),
('Regression Case', 2, None, 'regression-case'),
('Xgboost on the Cancer Data',
2,
None,
'xgboost-on-the-cancer-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="week45-bs.html">Week 45: Decisions Trees, Random Forests, Bagging and Boosting</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="._week45-bs001.html#overview-of-week-45" style="font-size: 80%;">Overview of week 45</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs002.html#decision-trees-overarching-aims" style="font-size: 80%;">Decision trees, overarching aims</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs003.html#basics-of-a-tree" style="font-size: 80%;">Basics of a tree</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs004.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="._week45-bs005.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="._week45-bs006.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="._week45-bs007.html#general-features" style="font-size: 80%;">General Features</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs008.html#how-do-we-set-it-up" style="font-size: 80%;">How do we set it up?</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs009.html#decision-trees-and-regression" style="font-size: 80%;">Decision trees and Regression</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs010.html#building-a-tree-regression" style="font-size: 80%;">Building a tree, regression</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs011.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="._week45-bs012.html#making-a-tree" style="font-size: 80%;">Making a tree</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs013.html#pruning-the-tree" style="font-size: 80%;">Pruning the tree</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs014.html#cost-complexity-pruning" style="font-size: 80%;">Cost complexity pruning</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs015.html#schematic-regression-procedure" style="font-size: 80%;">Schematic Regression Procedure</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs016.html#a-classification-tree" style="font-size: 80%;">A Classification Tree</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs017.html#growing-a-classification-tree" style="font-size: 80%;">Growing a classification tree</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs018.html#classification-tree-how-to-split-nodes" style="font-size: 80%;">Classification tree, how to split nodes</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs019.html#gini-index-or-coefficient-or-impurity" style="font-size: 80%;">Gini Index (or Coefficient or Impurity)</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs020.html#why-binary-splits" style="font-size: 80%;">Why binary splits?</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs021.html#computing-a-tree-using-the-gini-index" style="font-size: 80%;">Computing a Tree using the Gini Index</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs022.html#the-table" style="font-size: 80%;">The Table</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs023.html#computing-the-various-gini-indices" style="font-size: 80%;">Computing the various Gini Indices</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs024.html#computing-the-various-gini-indices-hours-slept" style="font-size: 80%;">Computing the various Gini Indices, Hours slept</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs025.html#computing-the-various-gini-indices-hours-studied" style="font-size: 80%;">Computing the various Gini Indices, Hours studied</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs026.html#a-possible-code-using-scikit-learn" style="font-size: 80%;">A possible code using Scikit-Learn</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs027.html#visualizing-trees-more-examples" style="font-size: 80%;">Visualizing Trees, More examples</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs028.html#visualizing-the-tree-the-moons" style="font-size: 80%;">Visualizing the Tree, The Moons</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs029.html#other-ways-of-visualizing-the-trees" style="font-size: 80%;">Other ways of visualizing the trees</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs030.html#printing-out-as-text" style="font-size: 80%;">Printing out as text</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs031.html#algorithms-for-setting-up-decision-trees" style="font-size: 80%;">Algorithms for Setting up Decision Trees</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs032.html#the-cart-algorithm-for-classification" style="font-size: 80%;">The CART algorithm for Classification</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs033.html#the-cart-algorithm-for-regression" style="font-size: 80%;">The CART algorithm for Regression</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs034.html#computing-the-gini-index" style="font-size: 80%;">Computing the Gini index</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs035.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="._week45-bs036.html#computing-the-gini-factor" style="font-size: 80%;">Computing the Gini Factor</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs037.html#entropy-and-the-id3-algorithm" style="font-size: 80%;">Entropy and the ID3 algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs038.html#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="._week45-bs039.html#another-example-the-moons-again" style="font-size: 80%;">Another example, the moons again</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs040.html#playing-around-with-regions" style="font-size: 80%;">Playing around with regions</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs041.html#regression-trees" style="font-size: 80%;">Regression trees</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs042.html#final-regressor-code" style="font-size: 80%;">Final regressor code</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs043.html#pros-and-cons-of-trees-pros" style="font-size: 80%;">Pros and cons of trees, pros</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs044.html#disadvantages" style="font-size: 80%;">Disadvantages</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs045.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="._week45-bs046.html#an-overview-of-ensemble-methods" style="font-size: 80%;">An Overview of Ensemble Methods</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs047.html#bagging" style="font-size: 80%;">Bagging</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs048.html#more-bagging" style="font-size: 80%;">More bagging</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs049.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>
<!-- navigation toc: --> <li><a href="._week45-bs050.html#why-voting" style="font-size: 80%;">Why Voting?</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs051.html#tossing-coins" style="font-size: 80%;">Tossing coins</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs052.html#standard-imports-first" style="font-size: 80%;">Standard imports first</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs053.html#simple-voting-example-head-or-tail" style="font-size: 80%;">Simple Voting Example, head or tail</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs054.html#using-the-voting-classifier" style="font-size: 80%;">Using the Voting Classifier</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs055.html#voting-and-bagging" style="font-size: 80%;">Voting and Bagging</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs056.html#random-forests" style="font-size: 80%;">Random forests</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs057.html#random-forest-algorithm" style="font-size: 80%;">Random Forest Algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs058.html#random-forests-compared-with-other-methods-on-the-cancer-data" style="font-size: 80%;">Random Forests Compared with other Methods on the Cancer Data</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs059.html#compare-bagging-on-trees-with-random-forests" style="font-size: 80%;">Compare Bagging on Trees with Random Forests</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs060.html#boosting-a-bird-s-eye-view" style="font-size: 80%;">Boosting, a Bird's Eye View</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs061.html#what-is-boosting-additive-modelling-iterative-fitting" style="font-size: 80%;">What is boosting? Additive Modelling/Iterative Fitting</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs062.html#iterative-fitting-regression-and-squared-error-cost-function" style="font-size: 80%;">Iterative Fitting, Regression and Squared-error Cost Function</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs063.html#squared-error-example-and-iterative-fitting" style="font-size: 80%;">Squared-Error Example and Iterative Fitting</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs064.html#iterative-fitting-classification-and-adaboost" style="font-size: 80%;">Iterative Fitting, Classification and AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs065.html#adaptive-boosting-adaboost" style="font-size: 80%;">Adaptive Boosting, AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs066.html#building-up-adaboost" style="font-size: 80%;">Building up AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs067.html#adaptive-boosting-adaboost-basic-algorithm" style="font-size: 80%;">Adaptive boosting: AdaBoost, Basic Algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs068.html#basic-steps-of-adaboost" style="font-size: 80%;">Basic Steps of AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs069.html#adaboost-examples" style="font-size: 80%;">AdaBoost Examples</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs070.html#gradient-boosting-basics-with-steepest-descent-functional-gradient-descent" style="font-size: 80%;">Gradient boosting: Basics with Steepest Descent/Functional Gradient Descent</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs071.html#the-squared-error-again-steepest-descent" style="font-size: 80%;">The Squared-Error again! Steepest Descent</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs072.html#steepest-descent-example" style="font-size: 80%;">Steepest Descent Example</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs073.html#gradient-boosting-algorithm" style="font-size: 80%;">Gradient Boosting, algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs074.html#gradient-boosting-examples-of-regression" style="font-size: 80%;">Gradient Boosting, Examples of Regression</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs075.html#gradient-boosting-classification-example" style="font-size: 80%;">Gradient Boosting, Classification Example</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs076.html#xgboost-extreme-gradient-boosting" style="font-size: 80%;">XGBoost: Extreme Gradient Boosting</a></li>
<!-- navigation toc: --> <li><a href="._week45-bs077.html#regression-case" style="font-size: 80%;">Regression Case</a></li>
<!-- navigation toc: --> <li><a href="#xgboost-on-the-cancer-data" style="font-size: 80%;">Xgboost on the Cancer Data</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="part0078"></a>
<!-- !split -->
<h2 id="xgboost-on-the-cancer-data" class="anchor">Xgboost on the Cancer Data </h2>
<p>As you will see from the confusion matrix below, XGBoots does an excellent job on the Wisconsin cancer data and outperforms essentially all agorithms we have discussed till now. </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">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.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> LabelEncoder
<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> cross_validate
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">scikitplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">skplt</span>
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">xgboost</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">xgb</span>
<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">#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)
xg_clf <span style="color: #666666">=</span> xgb<span style="color: #666666">.</span>XGBClassifier()
xg_clf<span style="color: #666666">.</span>fit(X_train_scaled,y_train)
y_test <span style="color: #666666">=</span> xg_clf<span style="color: #666666">.</span>predict(X_test_scaled)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Test set accuracy with Random Forests and scaled data: </span><span style="color: #BB6688; font-weight: bold">{:.2f}</span><span style="color: #BA2121">&quot;</span><span style="color: #666666">.</span>format(xg_clf<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">scikitplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">skplt</span>
y_pred <span style="color: #666666">=</span> xg_clf<span style="color: #666666">.</span>predict(X_test_scaled)
skplt<span style="color: #666666">.</span>metrics<span style="color: #666666">.</span>plot_confusion_matrix(y_test, y_pred, normalize<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">True</span>)
save_fig(<span style="color: #BA2121">&quot;xdclassiffierconfusion&quot;</span>)
plt<span style="color: #666666">.</span>show()
y_probas <span style="color: #666666">=</span> xg_clf<span style="color: #666666">.</span>predict_proba(X_test_scaled)
skplt<span style="color: #666666">.</span>metrics<span style="color: #666666">.</span>plot_roc(y_test, y_probas)
save_fig(<span style="color: #BA2121">&quot;xdclassiffierroc&quot;</span>)
plt<span style="color: #666666">.</span>show()
skplt<span style="color: #666666">.</span>metrics<span style="color: #666666">.</span>plot_cumulative_gain(y_test, y_probas)
save_fig(<span style="color: #BA2121">&quot;gdclassiffiercgain&quot;</span>)
plt<span style="color: #666666">.</span>show()
xgb<span style="color: #666666">.</span>plot_tree(xg_clf,num_trees<span style="color: #666666">=0</span>)
plt<span style="color: #666666">.</span>rcParams[<span style="color: #BA2121">&#39;figure.figsize&#39;</span>] <span style="color: #666666">=</span> [<span style="color: #666666">50</span>, <span style="color: #666666">10</span>]
save_fig(<span style="color: #BA2121">&quot;xgtree&quot;</span>)
plt<span style="color: #666666">.</span>show()
xgb<span style="color: #666666">.</span>plot_importance(xg_clf)
plt<span style="color: #666666">.</span>rcParams[<span style="color: #BA2121">&#39;figure.figsize&#39;</span>] <span style="color: #666666">=</span> [<span style="color: #666666">5</span>, <span style="color: #666666">5</span>]
save_fig(<span style="color: #BA2121">&quot;xgparams&quot;</span>)
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>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
<li><a href="._week45-bs077.html">&laquo;</a></li>
<li><a href="._week45-bs000.html">1</a></li>
<li><a href="">...</a></li>
<li><a href="._week45-bs070.html">71</a></li>
<li><a href="._week45-bs071.html">72</a></li>
<li><a href="._week45-bs072.html">73</a></li>
<li><a href="._week45-bs073.html">74</a></li>
<li><a href="._week45-bs074.html">75</a></li>
<li><a href="._week45-bs075.html">76</a></li>
<li><a href="._week45-bs076.html">77</a></li>
<li><a href="._week45-bs077.html">78</a></li>
<li class="active"><a href="._week45-bs078.html">79</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>
doc/pub/week45/ipynb/week45.ipynb
+231 -628
View File
File diff suppressed because it is too large Load Diff