-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_forest_iris.html
381 lines (322 loc) · 35.9 KB
/
plot_forest_iris.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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
<!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>Plot the decision surfaces of ensembles of trees on the iris dataset — 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="Single estimator versus bagging: bias-variance decomposition" href="plot_bias_variance.html" />
<link rel="prev" title="Gradient Boosting Out-of-Bag estimates" href="plot_gradient_boosting_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_forest_iris.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_gradient_boosting_oob.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Gradient Boos...
</span>
<span class="hiddenrellink">
Gradient Boosting Out-of-Bag estimates
</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="#">Plot the decision surfaces of ensembles of trees on the iris dataset</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="plot-the-decision-surfaces-of-ensembles-of-trees-on-the-iris-dataset">
<span id="example-ensemble-plot-forest-iris-py"></span><h1>Plot the decision surfaces of ensembles of trees on the iris dataset<a class="headerlink" href="#plot-the-decision-surfaces-of-ensembles-of-trees-on-the-iris-dataset" title="Permalink to this headline">¶</a></h1>
<p>Plot the decision surfaces of forests of randomized trees trained on pairs of
features of the iris dataset.</p>
<p>This plot compares the decision surfaces learned by a decision tree classifier
(first column), by a random forest classifier (second column), by an extra-
trees classifier (third column) and by an AdaBoost classifier (fourth column).</p>
<p>In the first row, the classifiers are built using the sepal width and the sepal
length features only, on the second row using the petal length and sepal length
only, and on the third row using the petal width and the petal length only.</p>
<p>In descending order of quality, when trained (outside of this example) on all
4 features using 30 estimators and scored using 10 fold cross validation, we see:</p>
<div class="highlight-python"><div class="highlight"><pre><a href="../../modules/generated/sklearn.ensemble.ExtraTreesClassifier.html#sklearn.ensemble.ExtraTreesClassifier"><span class="n">ExtraTreesClassifier</span></a><span class="p">()</span> <span class="c1"># 0.95 score</span>
<a href="../../modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier"><span class="n">RandomForestClassifier</span></a><span class="p">()</span> <span class="c1"># 0.94 score</span>
<span class="n">AdaBoost</span><span class="p">(</span><span class="n">DecisionTree</span><span class="p">(</span><span class="n">max_depth</span><span class="o">=</span><span class="mi">3</span><span class="p">))</span> <span class="c1"># 0.94 score</span>
<span class="n">DecisionTree</span><span class="p">(</span><span class="n">max_depth</span><span class="o">=</span><span class="bp">None</span><span class="p">)</span> <span class="c1"># 0.94 score</span>
</pre></div>
</div>
<p>Increasing <cite>max_depth</cite> for AdaBoost lowers the standard deviation of the scores (but
the average score does not improve).</p>
<p>See the console’s output for further details about each model.</p>
<p>In this example you might try to:</p>
<ol class="arabic simple">
<li>vary the <code class="docutils literal"><span class="pre">max_depth</span></code> for the <code class="docutils literal"><span class="pre">DecisionTreeClassifier</span></code> and
<code class="docutils literal"><span class="pre">AdaBoostClassifier</span></code>, perhaps try <code class="docutils literal"><span class="pre">max_depth=3</span></code> for the
<code class="docutils literal"><span class="pre">DecisionTreeClassifier</span></code> or <code class="docutils literal"><span class="pre">max_depth=None</span></code> for <code class="docutils literal"><span class="pre">AdaBoostClassifier</span></code></li>
<li>vary <code class="docutils literal"><span class="pre">n_estimators</span></code></li>
</ol>
<p>It is worth noting that RandomForests and ExtraTrees can be fitted in parallel
on many cores as each tree is built independently of the others. AdaBoost’s
samples are built sequentially and so do not use multiple cores.</p>
<img alt="../../_images/plot_forest_iris_001.png" class="align-center" src="../../_images/plot_forest_iris_001.png" />
<p><strong>Script output</strong>:</p>
<div class="highlight-python"><div class="highlight"><pre>DecisionTree with features [0, 1] has a score of 0.926666666667
RandomForest with 30 estimators with features [0, 1] has a score of 0.926666666667
ExtraTrees with 30 estimators with features [0, 1] has a score of 0.926666666667
AdaBoost with 30 estimators with features [0, 1] has a score of 0.84
DecisionTree with features [0, 2] has a score of 0.993333333333
RandomForest with 30 estimators with features [0, 2] has a score of 0.993333333333
ExtraTrees with 30 estimators with features [0, 2] has a score of 0.993333333333
AdaBoost with 30 estimators with features [0, 2] has a score of 0.993333333333
DecisionTree with features [2, 3] has a score of 0.993333333333
RandomForest with 30 estimators with features [2, 3] has a score of 0.993333333333
ExtraTrees with 30 estimators with features [2, 3] has a score of 0.993333333333
AdaBoost with 30 estimators with features [2, 3] has a score of 0.993333333333
</pre></div>
</div>
<p><strong>Python source code:</strong> <a class="reference download internal" href="../../_downloads/plot_forest_iris.py"><code class="xref download docutils literal"><span class="pre">plot_forest_iris.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="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">clone</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.load_iris.html#sklearn.datasets.load_iris"><span class="n">load_iris</span></a>
<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <span class="p">(</span><a href="../../modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier"><span class="n">RandomForestClassifier</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.ensemble.ExtraTreesClassifier.html#sklearn.ensemble.ExtraTreesClassifier"><span class="n">ExtraTreesClassifier</span></a><span class="p">,</span>
<a href="../../modules/generated/sklearn.ensemble.AdaBoostClassifier.html#sklearn.ensemble.AdaBoostClassifier"><span class="n">AdaBoostClassifier</span></a><span class="p">)</span>
<span class="kn">from</span> <span class="nn">sklearn.externals.six.moves</span> <span class="kn">import</span> <span class="nb">xrange</span>
<span class="kn">from</span> <span class="nn">sklearn.tree</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.tree.DecisionTreeClassifier.html#sklearn.tree.DecisionTreeClassifier"><span class="n">DecisionTreeClassifier</span></a>
<span class="c1"># Parameters</span>
<span class="n">n_classes</span> <span class="o">=</span> <span class="mi">3</span>
<span class="n">n_estimators</span> <span class="o">=</span> <span class="mi">30</span>
<span class="n">plot_colors</span> <span class="o">=</span> <span class="s2">"ryb"</span>
<span class="n">cmap</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">cm</span><span class="o">.</span><span class="n">RdYlBu</span>
<span class="n">plot_step</span> <span class="o">=</span> <span class="mf">0.02</span> <span class="c1"># fine step width for decision surface contours</span>
<span class="n">plot_step_coarser</span> <span class="o">=</span> <span class="mf">0.5</span> <span class="c1"># step widths for coarse classifier guesses</span>
<span class="n">RANDOM_SEED</span> <span class="o">=</span> <span class="mi">13</span> <span class="c1"># fix the seed on each iteration</span>
<span class="c1"># Load data</span>
<span class="n">iris</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.load_iris.html#sklearn.datasets.load_iris"><span class="n">load_iris</span></a><span class="p">()</span>
<span class="n">plot_idx</span> <span class="o">=</span> <span class="mi">1</span>
<span class="n">models</span> <span class="o">=</span> <span class="p">[</span><a href="../../modules/generated/sklearn.tree.DecisionTreeClassifier.html#sklearn.tree.DecisionTreeClassifier"><span class="n">DecisionTreeClassifier</span></a><span class="p">(</span><span class="n">max_depth</span><span class="o">=</span><span class="bp">None</span><span class="p">),</span>
<a href="../../modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier"><span class="n">RandomForestClassifier</span></a><span class="p">(</span><span class="n">n_estimators</span><span class="o">=</span><span class="n">n_estimators</span><span class="p">),</span>
<a href="../../modules/generated/sklearn.ensemble.ExtraTreesClassifier.html#sklearn.ensemble.ExtraTreesClassifier"><span class="n">ExtraTreesClassifier</span></a><span class="p">(</span><span class="n">n_estimators</span><span class="o">=</span><span class="n">n_estimators</span><span class="p">),</span>
<a href="../../modules/generated/sklearn.ensemble.AdaBoostClassifier.html#sklearn.ensemble.AdaBoostClassifier"><span class="n">AdaBoostClassifier</span></a><span class="p">(</span><a href="../../modules/generated/sklearn.tree.DecisionTreeClassifier.html#sklearn.tree.DecisionTreeClassifier"><span class="n">DecisionTreeClassifier</span></a><span class="p">(</span><span class="n">max_depth</span><span class="o">=</span><span class="mi">3</span><span class="p">),</span>
<span class="n">n_estimators</span><span class="o">=</span><span class="n">n_estimators</span><span class="p">)]</span>
<span class="k">for</span> <span class="n">pair</span> <span class="ow">in</span> <span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">]):</span>
<span class="k">for</span> <span class="n">model</span> <span class="ow">in</span> <span class="n">models</span><span class="p">:</span>
<span class="c1"># We only take the two corresponding features</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">data</span><span class="p">[:,</span> <span class="n">pair</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">target</span>
<span class="c1"># Shuffle</span>
<span class="n">idx</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">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.random.seed.html#numpy.random.seed"><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span></a><span class="p">(</span><span class="n">RANDOM_SEED</span><span class="p">)</span>
<span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">idx</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="c1"># Standardize</span>
<span class="n">mean</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">std</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="p">(</span><span class="n">X</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o">/</span> <span class="n">std</span>
<span class="c1"># Train</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">clone</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
<span class="n">scores</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">score</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
<span class="c1"># Create a title for each column and the console by using str() and</span>
<span class="c1"># slicing away useless parts of the string</span>
<span class="n">model_title</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">model</span><span class="p">))</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">][:</span><span class="o">-</span><span class="mi">2</span><span class="p">][:</span><span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="s2">"Classifier"</span><span class="p">)]</span>
<span class="n">model_details</span> <span class="o">=</span> <span class="n">model_title</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="s2">"estimators_"</span><span class="p">):</span>
<span class="n">model_details</span> <span class="o">+=</span> <span class="s2">" with {} estimators"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">estimators_</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span> <span class="n">model_details</span> <span class="o">+</span> <span class="s2">" with features"</span><span class="p">,</span> <span class="n">pair</span><span class="p">,</span> <span class="s2">"has a score of"</span><span class="p">,</span> <span class="n">scores</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">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="n">plot_idx</span><span class="p">)</span>
<span class="k">if</span> <span class="n">plot_idx</span> <span class="o"><=</span> <span class="nb">len</span><span class="p">(</span><span class="n">models</span><span class="p">):</span>
<span class="c1"># Add a title at the top of each column</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="n">model_title</span><span class="p">)</span>
<span class="c1"># Now plot the decision boundary using a fine mesh as input to a</span>
<span class="c1"># filled contour plot</span>
<span class="n">x_min</span><span class="p">,</span> <span class="n">x_max</span> <span class="o">=</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> <span class="o">+</span> <span class="mi">1</span>
<span class="n">y_min</span><span class="p">,</span> <span class="n">y_max</span> <span class="o">=</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="n">X</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> <span class="o">+</span> <span class="mi">1</span>
<span class="n">xx</span><span class="p">,</span> <span class="n">yy</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.meshgrid.html#numpy.meshgrid"><span class="n">np</span><span class="o">.</span><span class="n">meshgrid</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">x_min</span><span class="p">,</span> <span class="n">x_max</span><span class="p">,</span> <span class="n">plot_step</span><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">y_min</span><span class="p">,</span> <span class="n">y_max</span><span class="p">,</span> <span class="n">plot_step</span><span class="p">))</span>
<span class="c1"># Plot either a single DecisionTreeClassifier or alpha blend the</span>
<span class="c1"># decision surfaces of the ensemble of classifiers</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <a href="../../modules/generated/sklearn.tree.DecisionTreeClassifier.html#sklearn.tree.DecisionTreeClassifier"><span class="n">DecisionTreeClassifier</span></a><span class="p">):</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.c_.html#numpy.c_"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">xx</span><span class="o">.</span><span class="n">ravel</span><span class="p">(),</span> <span class="n">yy</span><span class="o">.</span><span class="n">ravel</span><span class="p">()])</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">Z</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">xx</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">cs</span> <span class="o">=</span> <a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.contourf"><span class="n">plt</span><span class="o">.</span><span class="n">contourf</span></a><span class="p">(</span><span class="n">xx</span><span class="p">,</span> <span class="n">yy</span><span class="p">,</span> <span class="n">Z</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">cmap</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Choose alpha blend level with respect to the number of estimators</span>
<span class="c1"># that are in use (noting that AdaBoost can use fewer estimators</span>
<span class="c1"># than its maximum if it achieves a good enough fit early on)</span>
<span class="n">estimator_alpha</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">estimators_</span><span class="p">)</span>
<span class="k">for</span> <span class="n">tree</span> <span class="ow">in</span> <span class="n">model</span><span class="o">.</span><span class="n">estimators_</span><span class="p">:</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">tree</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.c_.html#numpy.c_"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">xx</span><span class="o">.</span><span class="n">ravel</span><span class="p">(),</span> <span class="n">yy</span><span class="o">.</span><span class="n">ravel</span><span class="p">()])</span>
<span class="n">Z</span> <span class="o">=</span> <span class="n">Z</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">xx</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">cs</span> <span class="o">=</span> <a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.contourf"><span class="n">plt</span><span class="o">.</span><span class="n">contourf</span></a><span class="p">(</span><span class="n">xx</span><span class="p">,</span> <span class="n">yy</span><span class="p">,</span> <span class="n">Z</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="n">estimator_alpha</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">cmap</span><span class="p">)</span>
<span class="c1"># Build a coarser grid to plot a set of ensemble classifications</span>
<span class="c1"># to show how these are different to what we see in the decision</span>
<span class="c1"># surfaces. These points are regularly space and do not have a black outline</span>
<span class="n">xx_coarser</span><span class="p">,</span> <span class="n">yy_coarser</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.meshgrid.html#numpy.meshgrid"><span class="n">np</span><span class="o">.</span><span class="n">meshgrid</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">x_min</span><span class="p">,</span> <span class="n">x_max</span><span class="p">,</span> <span class="n">plot_step_coarser</span><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">y_min</span><span class="p">,</span> <span class="n">y_max</span><span class="p">,</span> <span class="n">plot_step_coarser</span><span class="p">))</span>
<span class="n">Z_points_coarser</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.c_.html#numpy.c_"><span class="n">np</span><span class="o">.</span><span class="n">c_</span></a><span class="p">[</span><span class="n">xx_coarser</span><span class="o">.</span><span class="n">ravel</span><span class="p">(),</span> <span class="n">yy_coarser</span><span class="o">.</span><span class="n">ravel</span><span class="p">()])</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">xx_coarser</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">cs_points</span> <span class="o">=</span> <a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.scatter"><span class="n">plt</span><span class="o">.</span><span class="n">scatter</span></a><span class="p">(</span><span class="n">xx_coarser</span><span class="p">,</span> <span class="n">yy_coarser</span><span class="p">,</span> <span class="n">s</span><span class="o">=</span><span class="mi">15</span><span class="p">,</span> <span class="n">c</span><span class="o">=</span><span class="n">Z_points_coarser</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">cmap</span><span class="p">,</span> <span class="n">edgecolors</span><span class="o">=</span><span class="s2">"none"</span><span class="p">)</span>
<span class="c1"># Plot the training points, these are clustered together and have a</span>
<span class="c1"># black outline</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="nb">xrange</span><span class="p">(</span><span class="n">n_classes</span><span class="p">),</span> <span class="n">plot_colors</span><span class="p">):</span>
<span class="n">idx</span> <span class="o">=</span> <a href="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.where.html#numpy.where"><span class="n">np</span><span class="o">.</span><span class="n">where</span></a><span class="p">(</span><span class="n">y</span> <span class="o">==</span> <span class="n">i</span><span class="p">)</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.scatter"><span class="n">plt</span><span class="o">.</span><span class="n">scatter</span></a><span class="p">(</span><span class="n">X</span><span class="p">[</span><span class="n">idx</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">X</span><span class="p">[</span><span class="n">idx</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">c</span><span class="o">=</span><span class="n">c</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">iris</span><span class="o">.</span><span class="n">target_names</span><span class="p">[</span><span class="n">i</span><span class="p">],</span>
<span class="n">cmap</span><span class="o">=</span><span class="n">cmap</span><span class="p">)</span>
<span class="n">plot_idx</span> <span class="o">+=</span> <span class="mi">1</span> <span class="c1"># move on to the next plot in sequence</span>
<a href="http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.suptitle"><span class="n">plt</span><span class="o">.</span><span class="n">suptitle</span></a><span class="p">(</span><span class="s2">"Classifiers on feature subsets of the Iris dataset"</span><span class="p">)</span>
<a href="http://matplotlib.org/api/axis_api.html#matplotlib.axis"><span class="n">plt</span><span class="o">.</span><span class="n">axis</span></a><span class="p">(</span><span class="s2">"tight"</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> 9.44 seconds
( 0 minutes 9.44 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_forest_iris.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_gradient_boosting_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>