mhjensen
273 lines
17 KiB
HTML
273 lines
17 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="Week 45: Random Forests and Boosting">
|
|
|
|
<title>Week 45: Random Forests and Boosting</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': [('Random forests', 2, None, '___sec0'),
|
|
('Random Forest Algorithm', 2, None, '___sec1'),
|
|
('Random Forests Compared with other Methods on the Cancer Data',
|
|
2,
|
|
None,
|
|
'___sec2'),
|
|
('Compare Bagging on Trees with Random Forests',
|
|
2,
|
|
None,
|
|
'___sec3'),
|
|
("Boosting, a Bird's Eye View", 2, None, '___sec4'),
|
|
('What is boosting? Additive Modelling/Iterative Fitting',
|
|
2,
|
|
None,
|
|
'___sec5'),
|
|
('Iterative Fitting, Regression and Squared-error Cost Function',
|
|
2,
|
|
None,
|
|
'___sec6'),
|
|
('Squared-Error Example and Iterative Fitting',
|
|
2,
|
|
None,
|
|
'___sec7'),
|
|
('Iterative Fitting, Classification and AdaBoost',
|
|
2,
|
|
None,
|
|
'___sec8'),
|
|
('Adaptive Boosting, AdaBoost', 2, None, '___sec9'),
|
|
('Building up AdaBoost', 2, None, '___sec10'),
|
|
('Adaptive boosting: AdaBoost, Basic Algorithm',
|
|
2,
|
|
None,
|
|
'___sec11'),
|
|
('Basic Steps of AdaBoost', 2, None, '___sec12'),
|
|
('AdaBoost Examples', 2, None, '___sec13'),
|
|
('AdaBoost for Regression', 2, None, '___sec14'),
|
|
('Gradient boosting: Basics with Steepest Descent',
|
|
2,
|
|
None,
|
|
'___sec15'),
|
|
('The Squared-Error again! Steepest Descent',
|
|
2,
|
|
None,
|
|
'___sec16'),
|
|
('Steepest Descent Example', 2, None, '___sec17'),
|
|
('Gradient Boosting, algorithm', 2, None, '___sec18'),
|
|
('Gradient Boosting Example, Regression', 2, None, '___sec19'),
|
|
('Gradient Boosting, Examples of Regression',
|
|
2,
|
|
None,
|
|
'___sec20'),
|
|
('Gradient Boosting, Classification Example',
|
|
2,
|
|
None,
|
|
'___sec21'),
|
|
('XGBoost: Extreme Gradient Boosting', 2, None, '___sec22'),
|
|
('Regression Case', 2, None, '___sec23'),
|
|
('Xgboost on the Cancer Data', 2, None, '___sec24')]}
|
|
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: Random Forests 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#___sec0" style="font-size: 80%;">Random forests</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs002.html#___sec1" style="font-size: 80%;">Random Forest Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs003.html#___sec2" style="font-size: 80%;">Random Forests Compared with other Methods on the Cancer Data</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs004.html#___sec3" style="font-size: 80%;">Compare Bagging on Trees with Random Forests</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs005.html#___sec4" style="font-size: 80%;">Boosting, a Bird's Eye View</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs006.html#___sec5" style="font-size: 80%;">What is boosting? Additive Modelling/Iterative Fitting</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs007.html#___sec6" style="font-size: 80%;">Iterative Fitting, Regression and Squared-error Cost Function</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs008.html#___sec7" style="font-size: 80%;">Squared-Error Example and Iterative Fitting</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs009.html#___sec8" style="font-size: 80%;">Iterative Fitting, Classification and AdaBoost</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs010.html#___sec9" style="font-size: 80%;">Adaptive Boosting, AdaBoost</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs011.html#___sec10" style="font-size: 80%;">Building up AdaBoost</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs012.html#___sec11" style="font-size: 80%;">Adaptive boosting: AdaBoost, Basic Algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs013.html#___sec12" style="font-size: 80%;">Basic Steps of AdaBoost</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs014.html#___sec13" style="font-size: 80%;">AdaBoost Examples</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs015.html#___sec14" style="font-size: 80%;">AdaBoost for Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs016.html#___sec15" style="font-size: 80%;">Gradient boosting: Basics with Steepest Descent</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs017.html#___sec16" style="font-size: 80%;">The Squared-Error again! Steepest Descent</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs018.html#___sec17" style="font-size: 80%;">Steepest Descent Example</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs019.html#___sec18" style="font-size: 80%;">Gradient Boosting, algorithm</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#___sec19" style="font-size: 80%;">Gradient Boosting Example, Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs021.html#___sec20" style="font-size: 80%;">Gradient Boosting, Examples of Regression</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs022.html#___sec21" style="font-size: 80%;">Gradient Boosting, Classification Example</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs023.html#___sec22" style="font-size: 80%;">XGBoost: Extreme Gradient Boosting</a></li>
|
|
<!-- navigation toc: --> <li><a href="#___sec23" style="font-size: 80%;">Regression Case</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs025.html#___sec24" 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> </p><p> </p><p> </p> <!-- add vertical space -->
|
|
|
|
<a name="part0024"></a>
|
|
<!-- !split -->
|
|
|
|
<h2 id="___sec23" class="anchor">Regression Case </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">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">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: #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">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">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> mean_squared_error
|
|
|
|
n <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
|
maxdegree <span style="color: #666666">=</span> <span style="color: #666666">6</span>
|
|
|
|
<span style="color: #408080; font-style: italic"># Make data set.</span>
|
|
x <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linspace(<span style="color: #666666">-3</span>, <span style="color: #666666">3</span>, n)<span style="color: #666666">.</span>reshape(<span style="color: #666666">-1</span>, <span style="color: #666666">1</span>)
|
|
y <span style="color: #666666">=</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>x<span style="color: #666666">**2</span>) <span style="color: #666666">+</span> <span style="color: #666666">1.5</span> <span style="color: #666666">*</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>(x<span style="color: #666666">-2</span>)<span style="color: #666666">**2</span>)<span style="color: #666666">+</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>normal(<span style="color: #666666">0</span>, <span style="color: #666666">0.1</span>, x<span style="color: #666666">.</span>shape)
|
|
|
|
error <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(maxdegree)
|
|
bias <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(maxdegree)
|
|
variance <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(maxdegree)
|
|
polydegree <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros(maxdegree)
|
|
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>)
|
|
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: #008000; font-weight: bold">for</span> degree <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(maxdegree):
|
|
model <span style="color: #666666">=</span> xgb<span style="color: #666666">.</span>XGBRegressor(objective <span style="color: #666666">=</span><span style="color: #BA2121">'reg:squarederror'</span>, colsaobjective <span style="color: #666666">=</span><span style="color: #BA2121">'reg:squarederror'</span>, colsample_bytree <span style="color: #666666">=</span> <span style="color: #666666">0.3</span>, learning_rate <span style="color: #666666">=</span> <span style="color: #666666">0.1</span>,max_depth <span style="color: #666666">=</span> degree, alpha <span style="color: #666666">=</span> <span style="color: #666666">10</span>, n_estimators <span style="color: #666666">=</span> <span style="color: #666666">200</span>)
|
|
|
|
model<span style="color: #666666">.</span>fit(X_train_scaled,y_train)
|
|
y_pred <span style="color: #666666">=</span> model<span style="color: #666666">.</span>predict(X_test_scaled)
|
|
polydegree[degree] <span style="color: #666666">=</span> degree
|
|
error[degree] <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean( np<span style="color: #666666">.</span>mean((y_test <span style="color: #666666">-</span> y_pred)<span style="color: #666666">**2</span>) )
|
|
bias[degree] <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean( (y_test <span style="color: #666666">-</span> np<span style="color: #666666">.</span>mean(y_pred))<span style="color: #666666">**2</span> )
|
|
variance[degree] <span style="color: #666666">=</span> np<span style="color: #666666">.</span>mean( np<span style="color: #666666">.</span>var(y_pred) )
|
|
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Max depth:'</span>, degree)
|
|
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Error:'</span>, error[degree])
|
|
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Bias^2:'</span>, bias[degree])
|
|
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'Var:'</span>, variance[degree])
|
|
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">'{} >= {} + {} = {}'</span><span style="color: #666666">.</span>format(error[degree], bias[degree], variance[degree], bias[degree]<span style="color: #666666">+</span>variance[degree]))
|
|
|
|
plt<span style="color: #666666">.</span>xlim(<span style="color: #666666">1</span>,maxdegree<span style="color: #666666">-1</span>)
|
|
plt<span style="color: #666666">.</span>plot(polydegree, error, label<span style="color: #666666">=</span><span style="color: #BA2121">'Error'</span>)
|
|
plt<span style="color: #666666">.</span>plot(polydegree, bias, label<span style="color: #666666">=</span><span style="color: #BA2121">'bias'</span>)
|
|
plt<span style="color: #666666">.</span>plot(polydegree, variance, label<span style="color: #666666">=</span><span style="color: #BA2121">'Variance'</span>)
|
|
plt<span style="color: #666666">.</span>legend()
|
|
plt<span style="color: #666666">.</span>show()
|
|
</pre></div>
|
|
<p>
|
|
<p>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._week45-bs023.html">«</a></li>
|
|
<li><a href="._week45-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week45-bs016.html">17</a></li>
|
|
<li><a href="._week45-bs017.html">18</a></li>
|
|
<li><a href="._week45-bs018.html">19</a></li>
|
|
<li><a href="._week45-bs019.html">20</a></li>
|
|
<li><a href="._week45-bs020.html">21</a></li>
|
|
<li><a href="._week45-bs021.html">22</a></li>
|
|
<li><a href="._week45-bs022.html">23</a></li>
|
|
<li><a href="._week45-bs023.html">24</a></li>
|
|
<li class="active"><a href="._week45-bs024.html">25</a></li>
|
|
<li><a href="._week45-bs025.html">26</a></li>
|
|
<li><a href="._week45-bs025.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>
|
|
|
|
|