-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_gmm_covariances.html
431 lines (371 loc) · 43.4 KB
/
plot_gmm_covariances.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
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
<meta property="og:title" content="GMM covariances" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://scikit-learn/stable/auto_examples/mixture/plot_gmm_covariances.html" />
<meta property="og:site_name" content="scikit-learn" />
<meta property="og:description" content="Demonstration of several covariances types for Gaussian mixture models. See Gaussian mixture models for more information on the estimator. Although GMM are often used for clustering, we can compare..." />
<meta property="og:image" content="https://scikit-learn.org/stable/_static/scikit-learn-logo-small.png" />
<meta property="og:image:alt" content="scikit-learn" />
<meta name="description" content="Demonstration of several covariances types for Gaussian mixture models. See Gaussian mixture models for more information on the estimator. Although GMM are often used for clustering, we can compare..." />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>GMM covariances — scikit-learn 1.2.2 documentation</title>
<link rel="canonical" href="http://scikit-learn.org/stable/auto_examples/mixture/plot_gmm_covariances.html" />
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="stylesheet" href="../../_static/css/vendor/bootstrap.min.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../_static/plot_directive.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-binder.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-dataframe.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-rendered-html.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
<script src="../../_static/js/vendor/jquery-3.6.3.slim.min.js"></script>
</head>
<body>
<nav id="navbar" class="sk-docs-navbar navbar navbar-expand-md navbar-light bg-light py-0">
<div class="container-fluid sk-docs-container px-0">
<a class="navbar-brand py-0" href="../../index.html">
<img
class="sk-brand-img"
src="../../_static/scikit-learn-logo-small.png"
alt="logo"/>
</a>
<button
id="sk-navbar-toggler"
class="navbar-toggler"
type="button"
data-toggle="collapse"
data-target="#navbarSupportedContent"
aria-controls="navbarSupportedContent"
aria-expanded="false"
aria-label="Toggle navigation"
>
<span class="navbar-toggler-icon"></span>
</button>
<div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav mr-auto">
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../install.html">Install</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../user_guide.html">User Guide</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../modules/classes.html">API</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../index.html">Examples</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://blog.scikit-learn.org/">Community</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../getting_started.html" >Getting Started</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../tutorial/index.html" >Tutorial</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../whats_new/v1.2.html" >What's new</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../glossary.html" >Glossary</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../faq.html" >FAQ</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../support.html" >Support</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../related_projects.html" >Related packages</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../roadmap.html" >Roadmap</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../governance.html" >Governance</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../about.html" >About us</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</li>
<li class="nav-item dropdown nav-more-item-dropdown">
<a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a>
<div class="dropdown-menu" aria-labelledby="navbarDropdown">
<a class="sk-nav-dropdown-item dropdown-item" href="../../getting_started.html" >Getting Started</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../tutorial/index.html" >Tutorial</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../whats_new/v1.2.html" >What's new</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../glossary.html" >Glossary</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../faq.html" >FAQ</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../support.html" >Support</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../related_projects.html" >Related packages</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../roadmap.html" >Roadmap</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../governance.html" >Governance</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../about.html" >About us</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</div>
</li>
</ul>
<div id="searchbox" role="search">
<div class="searchformwrapper">
<form class="search" action="../../search.html" method="get">
<input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
<input class="sk-search-text-btn" type="submit" value="Go" />
</form>
</div>
</div>
</div>
</div>
</nav>
<div class="d-flex" id="sk-doc-wrapper">
<input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
<label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
<div id="sk-sidebar-wrapper" class="border-right">
<div class="sk-sidebar-toc-wrapper">
<div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
<a href="plot_gmm_init.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="GMM Initialization Methods">Prev</a><a href="index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Gaussian Mixture Models">Up</a>
<a href="plot_gmm.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Gaussian Mixture Model Ellipsoids">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 1.2.2</strong><br/>
<a href="http://scikit-learn.org/dev/versions.html">Other versions</a>
</p>
</div>
<div class="alert alert-warning p-1 mb-2" role="alert">
<p class="text-center mb-0">
Please <a class="font-weight-bold" href="../../about.html#citing-scikit-learn"><string>cite us</string></a> if you use the software.
</p>
</div>
<div class="sk-sidebar-toc">
<ul>
<li><a class="reference internal" href="#">GMM covariances</a></li>
</ul>
</div>
</div>
</div>
<div id="sk-page-content-wrapper">
<div class="sk-page-content container-fluid body px-md-3" role="main">
<div class="sphx-glr-download-link-note admonition note">
<p class="admonition-title">Note</p>
<p>Click <a class="reference internal" href="#sphx-glr-download-auto-examples-mixture-plot-gmm-covariances-py"><span class="std std-ref">here</span></a>
to download the full example code or to run this example in your browser via Binder</p>
</div>
<section class="sphx-glr-example-title" id="gmm-covariances">
<span id="sphx-glr-auto-examples-mixture-plot-gmm-covariances-py"></span><h1>GMM covariances<a class="headerlink" href="#gmm-covariances" title="Permalink to this heading">¶</a></h1>
<p>Demonstration of several covariances types for Gaussian mixture models.</p>
<p>See <a class="reference internal" href="../../modules/mixture.html#gmm"><span class="std std-ref">Gaussian mixture models</span></a> for more information on the estimator.</p>
<p>Although GMM are often used for clustering, we can compare the obtained
clusters with the actual classes from the dataset. We initialize the means
of the Gaussians with the means of the classes from the training set to make
this comparison valid.</p>
<p>We plot predicted labels on both training and held out test data using a
variety of GMM covariance types on the iris dataset.
We compare GMMs with spherical, diagonal, full, and tied covariance
matrices in increasing order of performance. Although one would
expect full covariance to perform best in general, it is prone to
overfitting on small datasets and does not generalize well to held out
test data.</p>
<p>On the plots, train data is shown as dots, while test data is shown as
crosses. The iris dataset is four-dimensional. Only the first two
dimensions are shown here, and thus some points are separated in other
dimensions.</p>
<img src="../../_images/sphx_glr_plot_gmm_covariances_001.png" srcset="../../_images/sphx_glr_plot_gmm_covariances_001.png" alt="spherical, diag, tied, full" class = "sphx-glr-single-img"/><div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Author: Ron Weiss <[email protected]>, Gael Varoquaux</span>
<span class="c1"># Modified by Thierry Guillemot <[email protected]></span>
<span class="c1"># License: BSD 3 clause</span>
<span class="kn">import</span> <span class="nn">matplotlib</span> <span class="k">as</span> <span class="nn">mpl</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</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.mixture</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.mixture.GaussianMixture.html#sklearn.mixture.GaussianMixture" title="sklearn.mixture.GaussianMixture" class="sphx-glr-backref-module-sklearn-mixture sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">GaussianMixture</span></a>
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.model_selection.StratifiedKFold.html#sklearn.model_selection.StratifiedKFold" title="sklearn.model_selection.StratifiedKFold" class="sphx-glr-backref-module-sklearn-model_selection sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">StratifiedKFold</span></a>
<span class="n">colors</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"navy"</span><span class="p">,</span> <span class="s2">"turquoise"</span><span class="p">,</span> <span class="s2">"darkorange"</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">make_ellipses</span><span class="p">(</span><span class="n">gmm</span><span class="p">,</span> <span class="n">ax</span><span class="p">):</span>
<span class="k">for</span> <span class="n">n</span><span class="p">,</span> <span class="n">color</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">colors</span><span class="p">):</span>
<span class="k">if</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariance_type</span> <span class="o">==</span> <span class="s2">"full"</span><span class="p">:</span>
<span class="n">covariances</span> <span class="o">=</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariances_</span><span class="p">[</span><span class="n">n</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="k">elif</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariance_type</span> <span class="o">==</span> <span class="s2">"tied"</span><span class="p">:</span>
<span class="n">covariances</span> <span class="o">=</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariances_</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="k">elif</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariance_type</span> <span class="o">==</span> <span class="s2">"diag"</span><span class="p">:</span>
<span class="n">covariances</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.diag.html#numpy.diag" title="numpy.diag" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">diag</span></a><span class="p">(</span><span class="n">gmm</span><span class="o">.</span><span class="n">covariances_</span><span class="p">[</span><span class="n">n</span><span class="p">][:</span><span class="mi">2</span><span class="p">])</span>
<span class="k">elif</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariance_type</span> <span class="o">==</span> <span class="s2">"spherical"</span><span class="p">:</span>
<span class="n">covariances</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.eye.html#numpy.eye" title="numpy.eye" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">eye</span></a><span class="p">(</span><span class="n">gmm</span><span class="o">.</span><span class="n">means_</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="o">*</span> <span class="n">gmm</span><span class="o">.</span><span class="n">covariances_</span><span class="p">[</span><span class="n">n</span><span class="p">]</span>
<span class="n">v</span><span class="p">,</span> <span class="n">w</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.linalg.eigh.html#numpy.linalg.eigh" title="numpy.linalg.eigh" class="sphx-glr-backref-module-numpy-linalg sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">eigh</span></a><span class="p">(</span><span class="n">covariances</span><span class="p">)</span>
<span class="n">u</span> <span class="o">=</span> <span class="n">w</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">/</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.linalg.norm.html#numpy.linalg.norm" title="numpy.linalg.norm" class="sphx-glr-backref-module-numpy-linalg sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">norm</span></a><span class="p">(</span><span class="n">w</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="n">angle</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.arctan2.html#numpy.arctan2" title="numpy.arctan2" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">arctan2</span></a><span class="p">(</span><span class="n">u</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">u</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="n">angle</span> <span class="o">=</span> <span class="mi">180</span> <span class="o">*</span> <span class="n">angle</span> <span class="o">/</span> <a href="https://numpy.org/doc/stable/reference/constants.html#numpy.pi" title="numpy.pi" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">pi</span></a> <span class="c1"># convert to degrees</span>
<span class="n">v</span> <span class="o">=</span> <span class="mf">2.0</span> <span class="o">*</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.sqrt.html#numpy.sqrt" title="numpy.sqrt" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">sqrt</span></a><span class="p">(</span><span class="mf">2.0</span><span class="p">)</span> <span class="o">*</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.sqrt.html#numpy.sqrt" title="numpy.sqrt" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">sqrt</span></a><span class="p">(</span><span class="n">v</span><span class="p">)</span>
<span class="n">ell</span> <span class="o">=</span> <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.patches.Ellipse.html#matplotlib.patches.Ellipse" title="matplotlib.patches.Ellipse" class="sphx-glr-backref-module-matplotlib-patches sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">mpl</span><span class="o">.</span><span class="n">patches</span><span class="o">.</span><span class="n">Ellipse</span></a><span class="p">(</span>
<span class="n">gmm</span><span class="o">.</span><span class="n">means_</span><span class="p">[</span><span class="n">n</span><span class="p">,</span> <span class="p">:</span><span class="mi">2</span><span class="p">],</span> <span class="n">v</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">v</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">angle</span><span class="o">=</span><span class="mi">180</span> <span class="o">+</span> <span class="n">angle</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="n">color</span>
<span class="p">)</span>
<span class="n">ell</span><span class="o">.</span><span class="n">set_clip_box</span><span class="p">(</span><span class="n">ax</span><span class="o">.</span><span class="n">bbox</span><span class="p">)</span>
<span class="n">ell</span><span class="o">.</span><span class="n">set_alpha</span><span class="p">(</span><span class="mf">0.5</span><span class="p">)</span>
<span class="n">ax</span><span class="o">.</span><span class="n">add_artist</span><span class="p">(</span><span class="n">ell</span><span class="p">)</span>
<span class="n">ax</span><span class="o">.</span><span class="n">set_aspect</span><span class="p">(</span><span class="s2">"equal"</span><span class="p">,</span> <span class="s2">"datalim"</span><span class="p">)</span>
<span class="n">iris</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.load_iris.html#sklearn.datasets.load_iris" title="sklearn.datasets.load_iris" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">datasets</span><span class="o">.</span><span class="n">load_iris</span></a><span class="p">()</span>
<span class="c1"># Break up the dataset into non-overlapping training (75%) and testing</span>
<span class="c1"># (25%) sets.</span>
<span class="n">skf</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.model_selection.StratifiedKFold.html#sklearn.model_selection.StratifiedKFold" title="sklearn.model_selection.StratifiedKFold" class="sphx-glr-backref-module-sklearn-model_selection sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">StratifiedKFold</span></a><span class="p">(</span><span class="n">n_splits</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>
<span class="c1"># Only take the first fold.</span>
<span class="n">train_index</span><span class="p">,</span> <span class="n">test_index</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="nb">iter</span><span class="p">(</span><span class="n">skf</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">iris</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">iris</span><span class="o">.</span><span class="n">target</span><span class="p">)))</span>
<span class="n">X_train</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">train_index</span><span class="p">]</span>
<span class="n">y_train</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">target</span><span class="p">[</span><span class="n">train_index</span><span class="p">]</span>
<span class="n">X_test</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">test_index</span><span class="p">]</span>
<span class="n">y_test</span> <span class="o">=</span> <span class="n">iris</span><span class="o">.</span><span class="n">target</span><span class="p">[</span><span class="n">test_index</span><span class="p">]</span>
<span class="n">n_classes</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.unique.html#numpy.unique" title="numpy.unique" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">unique</span></a><span class="p">(</span><span class="n">y_train</span><span class="p">))</span>
<span class="c1"># Try GMMs using different types of covariances.</span>
<span class="n">estimators</span> <span class="o">=</span> <span class="p">{</span>
<span class="n">cov_type</span><span class="p">:</span> <a href="../../modules/generated/sklearn.mixture.GaussianMixture.html#sklearn.mixture.GaussianMixture" title="sklearn.mixture.GaussianMixture" class="sphx-glr-backref-module-sklearn-mixture sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">GaussianMixture</span></a><span class="p">(</span>
<span class="n">n_components</span><span class="o">=</span><span class="n">n_classes</span><span class="p">,</span> <span class="n">covariance_type</span><span class="o">=</span><span class="n">cov_type</span><span class="p">,</span> <span class="n">max_iter</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span>
<span class="p">)</span>
<span class="k">for</span> <span class="n">cov_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"spherical"</span><span class="p">,</span> <span class="s2">"diag"</span><span class="p">,</span> <span class="s2">"tied"</span><span class="p">,</span> <span class="s2">"full"</span><span class="p">]</span>
<span class="p">}</span>
<span class="n">n_estimators</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">estimators</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.figure.html#matplotlib.pyplot.figure" title="matplotlib.pyplot.figure" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><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">3</span> <span class="o">*</span> <span class="n">n_estimators</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">6</span><span class="p">))</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.subplots_adjust.html#matplotlib.pyplot.subplots_adjust" title="matplotlib.pyplot.subplots_adjust" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">subplots_adjust</span></a><span class="p">(</span>
<span class="n">bottom</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">top</span><span class="o">=</span><span class="mf">0.95</span><span class="p">,</span> <span class="n">hspace</span><span class="o">=</span><span class="mf">0.15</span><span class="p">,</span> <span class="n">wspace</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">left</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">right</span><span class="o">=</span><span class="mf">0.99</span>
<span class="p">)</span>
<span class="k">for</span> <span class="n">index</span><span class="p">,</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">estimator</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">estimators</span><span class="o">.</span><span class="n">items</span><span class="p">()):</span>
<span class="c1"># Since we have class labels for the training data, we can</span>
<span class="c1"># initialize the GMM parameters in a supervised manner.</span>
<span class="n">estimator</span><span class="o">.</span><span class="n">means_init</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="numpy.array" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</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">i</span><span class="p">]</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="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_classes</span><span class="p">)]</span>
<span class="p">)</span>
<span class="c1"># Train the other parameters using the EM algorithm.</span>
<span class="n">estimator</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">h</span> <span class="o">=</span> <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.subplot.html#matplotlib.pyplot.subplot" title="matplotlib.pyplot.subplot" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">subplot</span></a><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="n">n_estimators</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span> <span class="n">index</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">make_ellipses</span><span class="p">(</span><span class="n">estimator</span><span class="p">,</span> <span class="n">h</span><span class="p">)</span>
<span class="k">for</span> <span class="n">n</span><span class="p">,</span> <span class="n">color</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">colors</span><span class="p">):</span>
<span class="n">data</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">iris</span><span class="o">.</span><span class="n">target</span> <span class="o">==</span> <span class="n">n</span><span class="p">]</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.scatter.html#matplotlib.pyplot.scatter" title="matplotlib.pyplot.scatter" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">scatter</span></a><span class="p">(</span>
<span class="n">data</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">data</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">s</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="n">color</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">n</span><span class="p">]</span>
<span class="p">)</span>
<span class="c1"># Plot the test data with crosses</span>
<span class="k">for</span> <span class="n">n</span><span class="p">,</span> <span class="n">color</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">colors</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">X_test</span><span class="p">[</span><span class="n">y_test</span> <span class="o">==</span> <span class="n">n</span><span class="p">]</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.scatter.html#matplotlib.pyplot.scatter" title="matplotlib.pyplot.scatter" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">scatter</span></a><span class="p">(</span><span class="n">data</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">data</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">marker</span><span class="o">=</span><span class="s2">"x"</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="n">color</span><span class="p">)</span>
<span class="n">y_train_pred</span> <span class="o">=</span> <span class="n">estimator</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_train</span><span class="p">)</span>
<span class="n">train_accuracy</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.mean.html#numpy.mean" title="numpy.mean" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">mean</span></a><span class="p">(</span><span class="n">y_train_pred</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span> <span class="o">==</span> <span class="n">y_train</span><span class="o">.</span><span class="n">ravel</span><span class="p">())</span> <span class="o">*</span> <span class="mi">100</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.text.html#matplotlib.pyplot.text" title="matplotlib.pyplot.text" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">text</span></a><span class="p">(</span><span class="mf">0.05</span><span class="p">,</span> <span class="mf">0.9</span><span class="p">,</span> <span class="s2">"Train accuracy: </span><span class="si">%.1f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">train_accuracy</span><span class="p">,</span> <span class="n">transform</span><span class="o">=</span><span class="n">h</span><span class="o">.</span><span class="n">transAxes</span><span class="p">)</span>
<span class="n">y_test_pred</span> <span class="o">=</span> <span class="n">estimator</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="n">test_accuracy</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.mean.html#numpy.mean" title="numpy.mean" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">mean</span></a><span class="p">(</span><span class="n">y_test_pred</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span> <span class="o">==</span> <span class="n">y_test</span><span class="o">.</span><span class="n">ravel</span><span class="p">())</span> <span class="o">*</span> <span class="mi">100</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.text.html#matplotlib.pyplot.text" title="matplotlib.pyplot.text" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">text</span></a><span class="p">(</span><span class="mf">0.05</span><span class="p">,</span> <span class="mf">0.8</span><span class="p">,</span> <span class="s2">"Test accuracy: </span><span class="si">%.1f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">test_accuracy</span><span class="p">,</span> <span class="n">transform</span><span class="o">=</span><span class="n">h</span><span class="o">.</span><span class="n">transAxes</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.xticks.html#matplotlib.pyplot.xticks" title="matplotlib.pyplot.xticks" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">xticks</span></a><span class="p">(())</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.yticks.html#matplotlib.pyplot.yticks" title="matplotlib.pyplot.yticks" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">yticks</span></a><span class="p">(())</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.title.html#matplotlib.pyplot.title" title="matplotlib.pyplot.title" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">title</span></a><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.legend.html#matplotlib.pyplot.legend" title="matplotlib.pyplot.legend" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">legend</span></a><span class="p">(</span><span class="n">scatterpoints</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">loc</span><span class="o">=</span><span class="s2">"lower right"</span><span class="p">,</span> <span class="n">prop</span><span class="o">=</span><span class="nb">dict</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">12</span><span class="p">))</span>
<a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="matplotlib.pyplot.show" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">show</span></a><span class="p">()</span>
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 0.226 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-mixture-plot-gmm-covariances-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.2.X?urlpath=lab/tree/notebooks/auto_examples/mixture/plot_gmm_covariances.ipynb"><img alt="Launch binder" src="../../_images/binder_badge_logo24.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/22c1b876aa7bf8b912208cbfed5299c7/plot_gmm_covariances.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_gmm_covariances.py</span></code></a></p>
</div>
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/471829dadf19abf3dd2b87b08c9ffc92/plot_gmm_covariances.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_gmm_covariances.ipynb</span></code></a></p>
</div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.github.io">Gallery generated by Sphinx-Gallery</a></p>
</section>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2023, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/mixture/plot_gmm_covariances.rst.txt" rel="nofollow">Show this page source</a>
</footer>
</div>
</div>
</div>
<script src="../../_static/js/vendor/bootstrap.min.js"></script>
<script>
window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date;
ga('create', 'UA-22606712-2', 'auto');
ga('set', 'anonymizeIp', true);
ga('send', 'pageview');
</script>
<script async src='https://www.google-analytics.com/analytics.js'></script>
<script defer data-domain="scikit-learn.org" src="https://views.scientific-python.org/js/script.js">
</script>
<script>
$(document).ready(function() {
/* Add a [>>>] button on the top-right corner of code samples to hide
* the >>> and ... prompts and the output and thus make the code
* copyable. */
var div = $('.highlight-python .highlight,' +
'.highlight-python3 .highlight,' +
'.highlight-pycon .highlight,' +
'.highlight-default .highlight')
var pre = div.find('pre');
// get the styles from the current theme
pre.parent().parent().css('position', 'relative');
var hide_text = 'Hide prompts and outputs';
var show_text = 'Show prompts and outputs';
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
if (jthis.find('.gp').length > 0) {
var button = $('<span class="copybutton">>>></span>');
button.attr('title', hide_text);
button.data('hidden', 'false');
jthis.prepend(button);
}
// tracebacks (.gt) contain bare text elements that need to be
// wrapped in a span to work with .nextUntil() (see later)
jthis.find('pre:has(.gt)').contents().filter(function() {
return ((this.nodeType == 3) && (this.data.trim().length > 0));
}).wrap('<span>');
});
// define the behavior of the button when it's clicked
$('.copybutton').click(function(e){
e.preventDefault();
var button = $(this);
if (button.data('hidden') === 'false') {
// hide the code output
button.parent().find('.go, .gp, .gt').hide();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
button.css('text-decoration', 'line-through');
button.attr('title', show_text);
button.data('hidden', 'true');
} else {
// show the code output
button.parent().find('.go, .gp, .gt').show();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
button.css('text-decoration', 'none');
button.attr('title', hide_text);
button.data('hidden', 'false');
}
});
/*** Add permalink buttons next to glossary terms ***/
$('dl.glossary > dt[id]').append(function() {
return ('<a class="headerlink" href="#' +
this.getAttribute('id') +
'" title="Permalink to this term">¶</a>');
});
});
</script>
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>