-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_gradient_boosting_regression.html
298 lines (247 loc) · 22.4 KB
/
plot_gradient_boosting_regression.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>Gradient Boosting regression — scikit-learn 0.17.1 documentation</title>
<!-- htmltitle is before nature.css - we use this hack to load bootstrap first -->
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="stylesheet" href="../../_static/css/bootstrap.min.css" media="screen" />
<link rel="stylesheet" href="../../_static/css/bootstrap-responsive.css"/>
<link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/gallery.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../',
VERSION: '0.17.1',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../_static/jquery.js"></script>
<script type="text/javascript" src="../../_static/underscore.js"></script>
<script type="text/javascript" src="../../_static/doctools.js"></script>
<script type="text/javascript" src="../../_static/js/copybutton.js"></script>
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../../about.html" />
<link rel="top" title="scikit-learn 0.17.1 documentation" href="../../index.html" />
<link rel="up" title="Examples" href="../index.html" />
<link rel="next" title="Prediction Intervals for Gradient Boosting Regression" href="plot_gradient_boosting_quantile.html" />
<link rel="prev" title="OOB Errors for Random Forests" href="plot_ensemble_oob.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../../_static/js/bootstrap.min.js" type="text/javascript"></script>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/ensemble/plot_gradient_boosting_regression.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
</script>
</head>
<body role="document">
<div class="header-wrapper">
<div class="header">
<p class="logo"><a href="../../index.html">
<img src="../../_static/scikit-learn-logo-small.png" alt="Logo"/>
</a>
</p><div class="navbar">
<ul>
<li><a href="../../index.html">Home</a></li>
<li><a href="../../install.html">Installation</a></li>
<li class="btn-li"><div class="btn-group">
<a href="../../documentation.html">Documentation</a>
<a class="btn dropdown-toggle" data-toggle="dropdown">
<span class="caret"></span>
</a>
<ul class="dropdown-menu">
<li class="link-title">Scikit-learn 0.17 (stable)</li>
<li><a href="../../tutorial/index.html">Tutorials</a></li>
<li><a href="../../user_guide.html">User guide</a></li>
<li><a href="../../modules/classes.html">API</a></li>
<li><a href="../../faq.html">FAQ</a></li>
<li><a href="../../developers/contributing.html">Contributing</a></li>
<li class="divider"></li>
<li><a href="http://scikit-learn.org/dev/documentation.html">Scikit-learn 0.18 (development)</a></li>
<li><a href="http://scikit-learn.org/0.16/documentation.html">Scikit-learn 0.16</a></li>
<li><a href="../../_downloads/scikit-learn-docs.pdf">PDF documentation</a></li>
</ul>
</div>
</li>
<li><a href="../index.html">Examples</a></li>
</ul>
<div class="search_form">
<div id="cse" style="width: 100%;"></div>
</div>
</div> <!-- end navbar --></div>
</div>
<!-- Github "fork me" ribbon -->
<a href="https://github.com/scikit-learn/scikit-learn">
<img class="fork-me"
style="position: absolute; top: 0; right: 0; border: 0;"
src="../../_static/img/forkme.png"
alt="Fork me on GitHub" />
</a>
<div class="content-wrapper">
<div class="sphinxsidebar">
<div class="sphinxsidebarwrapper">
<div class="rel">
<!-- rellinks[1:] is an ugly hack to avoid link to module
index -->
<div class="rellink">
<a href="plot_ensemble_oob.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
OOB Errors fo...
</span>
<span class="hiddenrellink">
OOB Errors for Random Forests
</span>
</a>
</div>
<!-- Ad a link to the 'up' page -->
<div class="spacer">
</div>
<div class="rellink">
<a href="../index.html">
Up
<br/>
<span class="smallrellink">
Examples
</span>
<span class="hiddenrellink">
Examples
</span>
</a>
</div>
</div>
<p class="doc-version">This documentation is for scikit-learn <strong>version 0.17.1</strong> — <a href="http://scikit-learn.org/stable/support.html#documentation-resources">Other versions</a></p>
<p class="citing">If you use the software, please consider <a href="../../about.html#citing-scikit-learn">citing scikit-learn</a>.</p>
<ul>
<li><a class="reference internal" href="#">Gradient Boosting regression</a></li>
</ul>
</div>
</div>
<input type="checkbox" id="nav-trigger" class="nav-trigger" checked />
<label for="nav-trigger"></label>
<div class="content">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<div class="section" id="gradient-boosting-regression">
<span id="example-ensemble-plot-gradient-boosting-regression-py"></span><h1>Gradient Boosting regression<a class="headerlink" href="#gradient-boosting-regression" title="Permalink to this headline">¶</a></h1>
<p>Demonstrate Gradient Boosting on the Boston housing dataset.</p>
<p>This example fits a Gradient Boosting model with least squares loss and
500 regression trees of depth 4.</p>
<img alt="../../_images/plot_gradient_boosting_regression_001.png" class="align-center" src="../../_images/plot_gradient_boosting_regression_001.png" />
<p><strong>Script output</strong>:</p>
<div class="highlight-python"><div class="highlight"><pre>MSE: 6.7027
</pre></div>
</div>
<p><strong>Python source code:</strong> <a class="reference download internal" href="../../_downloads/plot_gradient_boosting_regression.py"><code class="xref download docutils literal"><span class="pre">plot_gradient_boosting_regression.py</span></code></a></p>
<div class="highlight-python"><div class="highlight"><pre><span class="k">print</span><span class="p">(</span><span class="n">__doc__</span><span class="p">)</span>
<span class="c1"># Author: Peter Prettenhofer <[email protected]></span>
<span class="c1">#</span>
<span class="c1"># License: BSD 3 clause</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="kn">as</span> <span class="nn">plt</span>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">ensemble</span>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">datasets</span>
<span class="kn">from</span> <span class="nn">sklearn.utils</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.utils.shuffle.html#sklearn.utils.shuffle"><span class="n">shuffle</span></a>
<span class="kn">from</span> <span class="nn">sklearn.metrics</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.metrics.mean_squared_error.html#sklearn.metrics.mean_squared_error"><span class="n">mean_squared_error</span></a>
<span class="c1">###############################################################################</span>
<span class="c1"># Load data</span>
<span class="n">boston</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.load_boston.html#sklearn.datasets.load_boston"><span class="n">datasets</span><span class="o">.</span><span class="n">load_boston</span></a><span class="p">()</span>
<span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.utils.shuffle.html#sklearn.utils.shuffle"><span class="n">shuffle</span></a><span class="p">(</span><span class="n">boston</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">boston</span><span class="o">.</span><span class="n">target</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">13</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">offset</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mf">0.9</span><span class="p">)</span>
<span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span> <span class="o">=</span> <span class="n">X</span><span class="p">[:</span><span class="n">offset</span><span class="p">],</span> <span class="n">y</span><span class="p">[:</span><span class="n">offset</span><span class="p">]</span>
<span class="n">X_test</span><span class="p">,</span> <span class="n">y_test</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="n">offset</span><span class="p">:],</span> <span class="n">y</span><span class="p">[</span><span class="n">offset</span><span class="p">:]</span>
<span class="c1">###############################################################################</span>
<span class="c1"># Fit regression model</span>
<span class="n">params</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'n_estimators'</span><span class="p">:</span> <span class="mi">500</span><span class="p">,</span> <span class="s1">'max_depth'</span><span class="p">:</span> <span class="mi">4</span><span class="p">,</span> <span class="s1">'min_samples_split'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
<span class="s1">'learning_rate'</span><span class="p">:</span> <span class="mf">0.01</span><span class="p">,</span> <span class="s1">'loss'</span><span class="p">:</span> <span class="s1">'ls'</span><span class="p">}</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">ensemble</span><span class="o">.</span><span class="n">GradientBoostingRegressor</span><span class="p">(</span><span class="o">**</span><span class="n">params</span><span class="p">)</span>
<span class="n">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
<span class="n">mse</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.metrics.mean_squared_error.html#sklearn.metrics.mean_squared_error"><span class="n">mean_squared_error</span></a><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">clf</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"MSE: </span><span class="si">%.4f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">mse</span><span class="p">)</span>
<span class="c1">###############################################################################</span>
<span class="c1"># Plot training deviance</span>
<span class="c1"># compute test set deviance</span>
<span class="n">test_score</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.zeros.html#numpy.zeros"><span class="n">np</span><span class="o">.</span><span class="n">zeros</span></a><span class="p">((</span><span class="n">params</span><span class="p">[</span><span class="s1">'n_estimators'</span><span class="p">],),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">y_pred</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">clf</span><span class="o">.</span><span class="n">staged_predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">)):</span>
<span class="n">test_score</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">loss_</span><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">y_pred</span><span class="p">)</span>
<a href="http://matplotlib.org/api/figure_api.html#matplotlib.figure"><span class="n">plt</span><span class="o">.</span><span class="n">figure</span></a><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">6</span><span class="p">))</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.title"><span class="n">plt</span><span class="o">.</span><span class="n">title</span></a><span class="p">(</span><span class="s1">'Deviance'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot"><span class="n">plt</span><span class="o">.</span><span class="n">plot</span></a><span class="p">(</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.arange.html#numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'n_estimators'</span><span class="p">])</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">clf</span><span class="o">.</span><span class="n">train_score_</span><span class="p">,</span> <span class="s1">'b-'</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="s1">'Training Set Deviance'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot"><span class="n">plt</span><span class="o">.</span><span class="n">plot</span></a><span class="p">(</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.arange.html#numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'n_estimators'</span><span class="p">])</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">test_score</span><span class="p">,</span> <span class="s1">'r-'</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="s1">'Test Set Deviance'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/legend_api.html#matplotlib.legend"><span class="n">plt</span><span class="o">.</span><span class="n">legend</span></a><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s1">'upper right'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.xlabel"><span class="n">plt</span><span class="o">.</span><span class="n">xlabel</span></a><span class="p">(</span><span class="s1">'Boosting Iterations'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.ylabel"><span class="n">plt</span><span class="o">.</span><span class="n">ylabel</span></a><span class="p">(</span><span class="s1">'Deviance'</span><span class="p">)</span>
<span class="c1">###############################################################################</span>
<span class="c1"># Plot feature importance</span>
<span class="n">feature_importance</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">feature_importances_</span>
<span class="c1"># make importances relative to max importance</span>
<span class="n">feature_importance</span> <span class="o">=</span> <span class="mf">100.0</span> <span class="o">*</span> <span class="p">(</span><span class="n">feature_importance</span> <span class="o">/</span> <span class="n">feature_importance</span><span class="o">.</span><span class="n">max</span><span class="p">())</span>
<span class="n">sorted_idx</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.argsort.html#numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">feature_importance</span><span class="p">)</span>
<span class="n">pos</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.arange.html#numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="n">sorted_idx</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">+</span> <span class="o">.</span><span class="mi">5</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.subplot"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.barh"><span class="n">plt</span><span class="o">.</span><span class="n">barh</span></a><span class="p">(</span><span class="n">pos</span><span class="p">,</span> <span class="n">feature_importance</span><span class="p">[</span><span class="n">sorted_idx</span><span class="p">],</span> <span class="n">align</span><span class="o">=</span><span class="s1">'center'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.yticks"><span class="n">plt</span><span class="o">.</span><span class="n">yticks</span></a><span class="p">(</span><span class="n">pos</span><span class="p">,</span> <span class="n">boston</span><span class="o">.</span><span class="n">feature_names</span><span class="p">[</span><span class="n">sorted_idx</span><span class="p">])</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.xlabel"><span class="n">plt</span><span class="o">.</span><span class="n">xlabel</span></a><span class="p">(</span><span class="s1">'Relative Importance'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.title"><span class="n">plt</span><span class="o">.</span><span class="n">title</span></a><span class="p">(</span><span class="s1">'Variable Importance'</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.show"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
<p><strong>Total running time of the example:</strong> 0.72 seconds
( 0 minutes 0.72 seconds)</p>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2010 - 2014, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/ensemble/plot_gradient_boosting_regression.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_ensemble_oob.html">Previous
</a>
</div>
</div>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-22606712-2']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
<script src="http://www.google.com/jsapi" type="text/javascript"></script>
<script type="text/javascript"> google.load('search', '1',
{language : 'en'}); google.setOnLoadCallback(function() {
var customSearchControl = new
google.search.CustomSearchControl('016639176250731907682:tjtqbvtvij0');
customSearchControl.setResultSetSize(google.search.Search.FILTERED_CSE_RESULTSET);
var options = new google.search.DrawOptions();
options.setAutoComplete(true);
customSearchControl.draw('cse', options); }, true);
</script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>