222 lines
12 KiB
HTML
222 lines
12 KiB
HTML
<!--
|
|
Automatically generated HTML file from DocOnce source
|
|
(https://github.com/hplgit/doconce/)
|
|
-->
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="description" content="Data Analysis and Machine Learning: Trees, forests and all that">
|
|
|
|
<title>Data Analysis and Machine Learning: Trees, forests and all that</title>
|
|
|
|
<!-- Bootstrap style: bootstrap -->
|
|
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
|
<!-- not necessary
|
|
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
|
-->
|
|
|
|
<style type="text/css">
|
|
|
|
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
|
.dropdown-menu {
|
|
height: auto;
|
|
max-height: 400px;
|
|
overflow-x: hidden;
|
|
}
|
|
|
|
/* Adds an invisible element before each target to offset for the navigation
|
|
bar */
|
|
.anchor::before {
|
|
content:"";
|
|
display:block;
|
|
height:50px; /* fixed header height for style bootstrap */
|
|
margin:-50px 0 0; /* negative fixed header height */
|
|
}
|
|
</style>
|
|
|
|
|
|
</head>
|
|
|
|
<!-- tocinfo
|
|
{'highest level': 2,
|
|
'sections': [('Decision trees, overarching aims', 2, None, '___sec0'),
|
|
('How do we set it up?', 2, None, '___sec1'),
|
|
('Decision trees and Regression', 2, None, '___sec2'),
|
|
('Maxwell-Boltzmann velocity distribution', 2, None, '___sec3'),
|
|
('Building a tree, regression', 2, None, '___sec4'),
|
|
('A top-down approach, recursive binary splitting',
|
|
2,
|
|
None,
|
|
'___sec5'),
|
|
('Making a tree', 2, None, '___sec6'),
|
|
('Pruning the tree', 2, None, '___sec7'),
|
|
('Cost complexity pruning', 2, None, '___sec8'),
|
|
('A schematic procedure', 2, None, '___sec9'),
|
|
('A classification tree', 2, None, '___sec10'),
|
|
('Growing a classification tree', 2, None, '___sec11'),
|
|
('Classification tree, how to split nodes', 2, None, '___sec12'),
|
|
('Entropy and the ID3 algorithm', 2, None, '___sec13'),
|
|
('Writing your own code for a classification tree',
|
|
2,
|
|
None,
|
|
'___sec14'),
|
|
('Back to moons again', 2, None, '___sec15'),
|
|
('Playing around with regions', 2, None, '___sec16'),
|
|
('Regression trees', 2, None, '___sec17'),
|
|
('Final regressor code', 2, None, '___sec18'),
|
|
('Classification again: The zoo data', 2, None, '___sec19'),
|
|
('Pros and cons of trees, pros', 2, None, '___sec20'),
|
|
('Disadvantages', 2, None, '___sec21'),
|
|
('Bagging', 2, None, '___sec22'),
|
|
('Simple example, head or tail', 2, None, '___sec23'),
|
|
('Random forests', 2, None, '___sec24'),
|
|
('A simple scikit-learn example', 2, None, '___sec25'),
|
|
('Please, not the moons again!', 2, None, '___sec26'),
|
|
('Bagging examples', 2, None, '___sec27'),
|
|
('Then random forests', 2, None, '___sec28'),
|
|
('Boosting and more', 2, None, '___sec29')]}
|
|
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="DecisionTrees-bs.html">Data Analysis and Machine Learning: Trees, forests and all that</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="._DecisionTrees-bs001.html#___sec0" style="font-size: 80%;">Decision trees, overarching aims</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs002.html#___sec1" style="font-size: 80%;">How do we set it up?</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs003.html#___sec2" style="font-size: 80%;">Decision trees and Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs004.html#___sec3" style="font-size: 80%;">Maxwell-Boltzmann velocity distribution</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs005.html#___sec4" style="font-size: 80%;">Building a tree, regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs006.html#___sec5" style="font-size: 80%;">A top-down approach, recursive binary splitting</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs007.html#___sec6" style="font-size: 80%;">Making a tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs008.html#___sec7" style="font-size: 80%;">Pruning the tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs009.html#___sec8" style="font-size: 80%;">Cost complexity pruning</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs010.html#___sec9" style="font-size: 80%;">A schematic procedure</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs011.html#___sec10" style="font-size: 80%;">A classification tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs012.html#___sec11" style="font-size: 80%;">Growing a classification tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs013.html#___sec12" style="font-size: 80%;">Classification tree, how to split nodes</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs014.html#___sec13" style="font-size: 80%;">Entropy and the ID3 algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs015.html#___sec14" style="font-size: 80%;">Writing your own code for a classification tree</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs016.html#___sec15" style="font-size: 80%;">Back to moons again</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs017.html#___sec16" style="font-size: 80%;">Playing around with regions</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs018.html#___sec17" style="font-size: 80%;">Regression trees</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs019.html#___sec18" style="font-size: 80%;">Final regressor code</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs020.html#___sec19" style="font-size: 80%;">Classification again: The zoo data</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs021.html#___sec20" style="font-size: 80%;">Pros and cons of trees, pros</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs022.html#___sec21" style="font-size: 80%;">Disadvantages</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs023.html#___sec22" style="font-size: 80%;">Bagging</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs024.html#___sec23" style="font-size: 80%;">Simple example, head or tail</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs025.html#___sec24" style="font-size: 80%;">Random forests</a></li>
|
|
<!-- navigation toc: --> <li><a href="#___sec25" style="font-size: 80%;">A simple scikit-learn example</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs027.html#___sec26" style="font-size: 80%;">Please, not the moons again!</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs028.html#___sec27" style="font-size: 80%;">Bagging examples</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs029.html#___sec28" style="font-size: 80%;">Then random forests</a></li>
|
|
<!-- navigation toc: --> <li><a href="._DecisionTrees-bs030.html#___sec29" style="font-size: 80%;">Boosting and more</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="part0026"></a>
|
|
<!-- !split -->
|
|
|
|
<h2 id="___sec25" class="anchor">A simple scikit-learn example </h2>
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
|
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.ensemble</span> <span style="color: #008000; font-weight: bold">import</span> RandomForestClassifier
|
|
<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: #408080; font-style: italic"># Data set not specificied</span>
|
|
X <span style="color: #666666">=</span> dataset<span style="color: #666666">.</span>XXX
|
|
Y <span style="color: #666666">=</span> dataset<span style="color: #666666">.</span>YYY
|
|
<span style="color: #408080; font-style: italic">#Instantiate the model with 100 trees and entropy as splitting criteria</span>
|
|
Random_Forest_model <span style="color: #666666">=</span> RandomForestClassifier(n_estimators<span style="color: #666666">=100</span>,criterion<span style="color: #666666">=</span><span style="color: #BA2121">"entropy"</span>)
|
|
<span style="color: #408080; font-style: italic">#Cross validation</span>
|
|
accuracy <span style="color: #666666">=</span> cross_validate(Random_Forest_model,X,Y,cv<span style="color: #666666">=10</span>)[<span style="color: #BA2121">'test_score'</span>]
|
|
</pre></div>
|
|
<p>
|
|
<p>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._DecisionTrees-bs025.html">«</a></li>
|
|
<li><a href="._DecisionTrees-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._DecisionTrees-bs018.html">19</a></li>
|
|
<li><a href="._DecisionTrees-bs019.html">20</a></li>
|
|
<li><a href="._DecisionTrees-bs020.html">21</a></li>
|
|
<li><a href="._DecisionTrees-bs021.html">22</a></li>
|
|
<li><a href="._DecisionTrees-bs022.html">23</a></li>
|
|
<li><a href="._DecisionTrees-bs023.html">24</a></li>
|
|
<li><a href="._DecisionTrees-bs024.html">25</a></li>
|
|
<li><a href="._DecisionTrees-bs025.html">26</a></li>
|
|
<li class="active"><a href="._DecisionTrees-bs026.html">27</a></li>
|
|
<li><a href="._DecisionTrees-bs027.html">28</a></li>
|
|
<li><a href="._DecisionTrees-bs028.html">29</a></li>
|
|
<li><a href="._DecisionTrees-bs029.html">30</a></li>
|
|
<li><a href="._DecisionTrees-bs030.html">31</a></li>
|
|
<li><a href="._DecisionTrees-bs027.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="http://..."><img width="250" align=right src="http://..."></a>
|
|
</footer>
|
|
-->
|
|
|
|
|
|
<center style="font-size:80%">
|
|
<!-- copyright only on the titlepage -->
|
|
</center>
|
|
|
|
|
|
</body>
|
|
</html>
|
|
|
|
|