-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathputting_together.html
514 lines (430 loc) · 45.3 KB
/
putting_together.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
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
<!DOCTYPE html>
<!-- data-theme below is forced to be "light" but should be changed if we use pydata-theme-sphinx in the future -->
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" data-content_root="../../" data-theme="light"> <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" data-content_root="../../" data-theme="light"> <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta property="og:title" content="Putting it all together" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://scikit-learn/stable/tutorial/statistical_inference/putting_together.html" />
<meta property="og:site_name" content="scikit-learn" />
<meta property="og:description" content="Pipelining: We have seen that some estimators can transform data and that some estimators can predict variables. We can also create combined estimators: Face recognition with eigenfaces: The datase..." />
<meta property="og:image" content="https://scikit-learn/stable/_images/sphx_glr_plot_digits_pipe_001.png" />
<meta property="og:image:alt" content="scikit-learn" />
<meta name="description" content="Pipelining: We have seen that some estimators can transform data and that some estimators can predict variables. We can also create combined estimators: Face recognition with eigenfaces: The datase..." />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Putting it all together — scikit-learn 1.4.2 documentation</title>
<link rel="canonical" href="https://scikit-learn.org/stable/tutorial/statistical_inference/putting_together.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/copybutton.css" type="text/css" />
<link rel="stylesheet" href="../../_static/plot_directive.css" type="text/css" />
<link rel="stylesheet" href="../../https://fonts.googleapis.com/css?family=Vibur" type="text/css" />
<link rel="stylesheet" href="../../_static/jupyterlite_sphinx.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>
<script src="../../_static/js/details-permalink.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="../../auto_examples/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="../index.html" >Tutorial</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../whats_new/v1.4.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="../index.html" >Tutorial</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../whats_new/v1.4.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="unsupervised_learning.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Unsupervised learning: seeking representations of the data">Prev</a><a href="index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="A tutorial on statistical-learning for scientific data processing">Up</a>
<a href="../text_analytics/working_with_text_data.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Working With Text Data">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 1.4.2</strong><br/>
<a href="https://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="#">Putting it all together</a><ul>
<li><a class="reference internal" href="#pipelining">Pipelining</a></li>
<li><a class="reference internal" href="#face-recognition-with-eigenfaces">Face recognition with eigenfaces</a></li>
<li><a class="reference internal" href="#open-problem-stock-market-structure">Open problem: Stock Market Structure</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div>
<div id="sk-page-content-wrapper">
<div class="sk-page-content container-fluid body px-md-3" role="main">
<section id="putting-it-all-together">
<h1>Putting it all together<a class="headerlink" href="#putting-it-all-together" title="Link to this heading">¶</a></h1>
<section id="pipelining">
<h2>Pipelining<a class="headerlink" href="#pipelining" title="Link to this heading">¶</a></h2>
<p>We have seen that some estimators can transform data and that some estimators
can predict variables. We can also create combined estimators:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <span class="n">LogisticRegression</span>
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">GridSearchCV</span>
<span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <span class="n">Pipeline</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="c1"># Define a pipeline to search for the best combination of PCA truncation</span>
<span class="c1"># and classifier regularization.</span>
<span class="n">pca</span> <span class="o">=</span> <span class="n">PCA</span><span class="p">()</span>
<span class="c1"># Define a Standard Scaler to normalize inputs</span>
<span class="n">scaler</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">()</span>
<span class="c1"># set the tolerance to a large value to make the example faster</span>
<span class="n">logistic</span> <span class="o">=</span> <span class="n">LogisticRegression</span><span class="p">(</span><span class="n">max_iter</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">0.1</span><span class="p">)</span>
<span class="n">pipe</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">(</span><span class="n">steps</span><span class="o">=</span><span class="p">[(</span><span class="s2">"scaler"</span><span class="p">,</span> <span class="n">scaler</span><span class="p">),</span> <span class="p">(</span><span class="s2">"pca"</span><span class="p">,</span> <span class="n">pca</span><span class="p">),</span> <span class="p">(</span><span class="s2">"logistic"</span><span class="p">,</span> <span class="n">logistic</span><span class="p">)])</span>
<span class="n">X_digits</span><span class="p">,</span> <span class="n">y_digits</span> <span class="o">=</span> <span class="n">datasets</span><span class="o">.</span><span class="n">load_digits</span><span class="p">(</span><span class="n">return_X_y</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="c1"># Parameters of pipelines can be set using '__' separated parameter names:</span>
<span class="n">param_grid</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">"pca__n_components"</span><span class="p">:</span> <span class="p">[</span><span class="mi">5</span><span class="p">,</span> <span class="mi">15</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span> <span class="mi">45</span><span class="p">,</span> <span class="mi">60</span><span class="p">],</span>
<span class="s2">"logistic__C"</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">logspace</span><span class="p">(</span><span class="o">-</span><span class="mi">4</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">4</span><span class="p">),</span>
<span class="p">}</span>
<span class="n">search</span> <span class="o">=</span> <span class="n">GridSearchCV</span><span class="p">(</span><span class="n">pipe</span><span class="p">,</span> <span class="n">param_grid</span><span class="p">,</span> <span class="n">n_jobs</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="n">search</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_digits</span><span class="p">,</span> <span class="n">y_digits</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Best parameter (CV score=</span><span class="si">%0.3f</span><span class="s2">):"</span> <span class="o">%</span> <span class="n">search</span><span class="o">.</span><span class="n">best_score_</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">search</span><span class="o">.</span><span class="n">best_params_</span><span class="p">)</span>
<span class="c1"># Plot the PCA spectrum</span>
<span class="n">pca</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_digits</span><span class="p">)</span>
<span class="n">fig</span><span class="p">,</span> <span class="p">(</span><span class="n">ax0</span><span class="p">,</span> <span class="n">ax1</span><span class="p">)</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">nrows</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">sharex</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">6</span><span class="p">,</span> <span class="mi">6</span><span class="p">))</span>
<span class="n">ax0</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span>
<span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">pca</span><span class="o">.</span><span class="n">n_components_</span> <span class="o">+</span> <span class="mi">1</span><span class="p">),</span> <span class="n">pca</span><span class="o">.</span><span class="n">explained_variance_ratio_</span><span class="p">,</span> <span class="s2">"+"</span><span class="p">,</span> <span class="n">linewidth</span><span class="o">=</span><span class="mi">2</span>
<span class="p">)</span>
<span class="n">ax0</span><span class="o">.</span><span class="n">set_ylabel</span><span class="p">(</span><span class="s2">"PCA explained variance ratio"</span><span class="p">)</span>
<span class="n">ax0</span><span class="o">.</span><span class="n">axvline</span><span class="p">(</span>
<span class="n">search</span><span class="o">.</span><span class="n">best_estimator_</span><span class="o">.</span><span class="n">named_steps</span><span class="p">[</span><span class="s2">"pca"</span><span class="p">]</span><span class="o">.</span><span class="n">n_components</span><span class="p">,</span>
<span class="n">linestyle</span><span class="o">=</span><span class="s2">":"</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="s2">"n_components chosen"</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">ax0</span><span class="o">.</span><span class="n">legend</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>
</pre></div>
</div>
<a class="reference external image-reference" href="../../auto_examples/compose/plot_digits_pipe.html"><img alt="../../_images/sphx_glr_plot_digits_pipe_001.png" class="align-center" src="../../_images/sphx_glr_plot_digits_pipe_001.png" style="width: 390.0px; height: 390.0px;" /></a>
</section>
<section id="face-recognition-with-eigenfaces">
<h2>Face recognition with eigenfaces<a class="headerlink" href="#face-recognition-with-eigenfaces" title="Link to this heading">¶</a></h2>
<p>The dataset used in this example is a preprocessed excerpt of the
“Labeled Faces in the Wild”, also known as <a class="reference external" href="http://vis-www.cs.umass.edu/lfw/">LFW</a>:</p>
<p><a class="reference external" href="http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz">http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz</a> (233MB)</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="sd">"""</span>
<span class="sd">===================================================</span>
<span class="sd">Faces recognition example using eigenfaces and SVMs</span>
<span class="sd">===================================================</span>
<span class="sd">The dataset used in this example is a preprocessed excerpt of the</span>
<span class="sd">"Labeled Faces in the Wild", aka LFW_:</span>
<span class="sd"> http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz (233MB)</span>
<span class="sd">.. _LFW: http://vis-www.cs.umass.edu/lfw/</span>
<span class="sd">"""</span>
<span class="c1"># %%</span>
<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">time</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">from</span> <span class="nn">scipy.stats</span> <span class="kn">import</span> <span class="n">loguniform</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">fetch_lfw_people</span>
<span class="kn">from</span> <span class="nn">sklearn.decomposition</span> <span class="kn">import</span> <span class="n">PCA</span>
<span class="kn">from</span> <span class="nn">sklearn.metrics</span> <span class="kn">import</span> <span class="n">ConfusionMatrixDisplay</span><span class="p">,</span> <span class="n">classification_report</span>
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">RandomizedSearchCV</span><span class="p">,</span> <span class="n">train_test_split</span>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">StandardScaler</span>
<span class="kn">from</span> <span class="nn">sklearn.svm</span> <span class="kn">import</span> <span class="n">SVC</span>
<span class="c1"># %%</span>
<span class="c1"># Download the data, if not already on disk and load it as numpy arrays</span>
<span class="n">lfw_people</span> <span class="o">=</span> <span class="n">fetch_lfw_people</span><span class="p">(</span><span class="n">min_faces_per_person</span><span class="o">=</span><span class="mi">70</span><span class="p">,</span> <span class="n">resize</span><span class="o">=</span><span class="mf">0.4</span><span class="p">)</span>
<span class="c1"># introspect the images arrays to find the shapes (for plotting)</span>
<span class="n">n_samples</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span> <span class="o">=</span> <span class="n">lfw_people</span><span class="o">.</span><span class="n">images</span><span class="o">.</span><span class="n">shape</span>
<span class="c1"># for machine learning we use the 2 data directly (as relative pixel</span>
<span class="c1"># positions info is ignored by this model)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">lfw_people</span><span class="o">.</span><span class="n">data</span>
<span class="n">n_features</span> <span class="o">=</span> <span class="n">X</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="c1"># the label to predict is the id of the person</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">lfw_people</span><span class="o">.</span><span class="n">target</span>
<span class="n">target_names</span> <span class="o">=</span> <span class="n">lfw_people</span><span class="o">.</span><span class="n">target_names</span>
<span class="n">n_classes</span> <span class="o">=</span> <span class="n">target_names</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="nb">print</span><span class="p">(</span><span class="s2">"Total dataset size:"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"n_samples: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">n_samples</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"n_features: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">n_features</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"n_classes: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">n_classes</span><span class="p">)</span>
<span class="c1"># %%</span>
<span class="c1"># Split into a training set and a test and keep 25% of the data for testing.</span>
<span class="n">X_train</span><span class="p">,</span> <span class="n">X_test</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">y_test</span> <span class="o">=</span> <span class="n">train_test_split</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">test_size</span><span class="o">=</span><span class="mf">0.25</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">42</span>
<span class="p">)</span>
<span class="n">scaler</span> <span class="o">=</span> <span class="n">StandardScaler</span><span class="p">()</span>
<span class="n">X_train</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">X_train</span><span class="p">)</span>
<span class="n">X_test</span> <span class="o">=</span> <span class="n">scaler</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
<span class="c1"># %%</span>
<span class="c1"># Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled</span>
<span class="c1"># dataset): unsupervised feature extraction / dimensionality reduction</span>
<span class="n">n_components</span> <span class="o">=</span> <span class="mi">150</span>
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Extracting the top </span><span class="si">%d</span><span class="s2"> eigenfaces from </span><span class="si">%d</span><span class="s2"> faces"</span> <span class="o">%</span> <span class="p">(</span><span class="n">n_components</span><span class="p">,</span> <span class="n">X_train</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="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">pca</span> <span class="o">=</span> <span class="n">PCA</span><span class="p">(</span><span class="n">n_components</span><span class="o">=</span><span class="n">n_components</span><span class="p">,</span> <span class="n">svd_solver</span><span class="o">=</span><span class="s2">"randomized"</span><span class="p">,</span> <span class="n">whiten</span><span class="o">=</span><span class="kc">True</span><span class="p">)</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="nb">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="n">eigenfaces</span> <span class="o">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">components_</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="n">n_components</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Projecting the input data on the eigenfaces orthonormal basis"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">X_train_pca</span> <span class="o">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">X_train</span><span class="p">)</span>
<span class="n">X_test_pca</span> <span class="o">=</span> <span class="n">pca</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="c1"># %%</span>
<span class="c1"># Train a SVM classification model</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Fitting the classifier to the training set"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">param_grid</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">"C"</span><span class="p">:</span> <span class="n">loguniform</span><span class="p">(</span><span class="mf">1e3</span><span class="p">,</span> <span class="mf">1e5</span><span class="p">),</span>
<span class="s2">"gamma"</span><span class="p">:</span> <span class="n">loguniform</span><span class="p">(</span><span class="mf">1e-4</span><span class="p">,</span> <span class="mf">1e-1</span><span class="p">),</span>
<span class="p">}</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">RandomizedSearchCV</span><span class="p">(</span>
<span class="n">SVC</span><span class="p">(</span><span class="n">kernel</span><span class="o">=</span><span class="s2">"rbf"</span><span class="p">,</span> <span class="n">class_weight</span><span class="o">=</span><span class="s2">"balanced"</span><span class="p">),</span> <span class="n">param_grid</span><span class="p">,</span> <span class="n">n_iter</span><span class="o">=</span><span class="mi">10</span>
<span class="p">)</span>
<span class="n">clf</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_train_pca</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Best estimator found by grid search:"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">clf</span><span class="o">.</span><span class="n">best_estimator_</span><span class="p">)</span>
<span class="c1"># %%</span>
<span class="c1"># Quantitative evaluation of the model quality on the test set</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Predicting people's names on the test set"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span>
<span class="n">y_pred</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test_pca</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="n">classification_report</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> <span class="n">target_names</span><span class="o">=</span><span class="n">target_names</span><span class="p">))</span>
<span class="n">ConfusionMatrixDisplay</span><span class="o">.</span><span class="n">from_estimator</span><span class="p">(</span>
<span class="n">clf</span><span class="p">,</span> <span class="n">X_test_pca</span><span class="p">,</span> <span class="n">y_test</span><span class="p">,</span> <span class="n">display_labels</span><span class="o">=</span><span class="n">target_names</span><span class="p">,</span> <span class="n">xticks_rotation</span><span class="o">=</span><span class="s2">"vertical"</span>
<span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span><span class="p">()</span>
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="c1"># %%</span>
<span class="c1"># Qualitative evaluation of the predictions using matplotlib</span>
<span class="k">def</span> <span class="nf">plot_gallery</span><span class="p">(</span><span class="n">images</span><span class="p">,</span> <span class="n">titles</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">n_row</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">n_col</span><span class="o">=</span><span class="mi">4</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Helper function to plot a gallery of portraits"""</span>
<span class="n">plt</span><span class="o">.</span><span class="n">figure</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mf">1.8</span> <span class="o">*</span> <span class="n">n_col</span><span class="p">,</span> <span class="mf">2.4</span> <span class="o">*</span> <span class="n">n_row</span><span class="p">))</span>
<span class="n">plt</span><span class="o">.</span><span class="n">subplots_adjust</span><span class="p">(</span><span class="n">bottom</span><span class="o">=</span><span class="mi">0</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="n">top</span><span class="o">=</span><span class="mf">0.90</span><span class="p">,</span> <span class="n">hspace</span><span class="o">=</span><span class="mf">0.35</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_row</span> <span class="o">*</span> <span class="n">n_col</span><span class="p">):</span>
<span class="n">plt</span><span class="o">.</span><span class="n">subplot</span><span class="p">(</span><span class="n">n_row</span><span class="p">,</span> <span class="n">n_col</span><span class="p">,</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">images</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">)),</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">gray</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="n">titles</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">size</span><span class="o">=</span><span class="mi">12</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">xticks</span><span class="p">(())</span>
<span class="n">plt</span><span class="o">.</span><span class="n">yticks</span><span class="p">(())</span>
<span class="c1"># %%</span>
<span class="c1"># plot the result of the prediction on a portion of the test set</span>
<span class="k">def</span> <span class="nf">title</span><span class="p">(</span><span class="n">y_pred</span><span class="p">,</span> <span class="n">y_test</span><span class="p">,</span> <span class="n">target_names</span><span class="p">,</span> <span class="n">i</span><span class="p">):</span>
<span class="n">pred_name</span> <span class="o">=</span> <span class="n">target_names</span><span class="p">[</span><span class="n">y_pred</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">" "</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="n">true_name</span> <span class="o">=</span> <span class="n">target_names</span><span class="p">[</span><span class="n">y_test</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">" "</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">return</span> <span class="s2">"predicted: </span><span class="si">%s</span><span class="se">\n</span><span class="s2">true: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">pred_name</span><span class="p">,</span> <span class="n">true_name</span><span class="p">)</span>
<span class="n">prediction_titles</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">title</span><span class="p">(</span><span class="n">y_pred</span><span class="p">,</span> <span class="n">y_test</span><span class="p">,</span> <span class="n">target_names</span><span class="p">,</span> <span class="n">i</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">y_pred</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="p">]</span>
<span class="n">plot_gallery</span><span class="p">(</span><span class="n">X_test</span><span class="p">,</span> <span class="n">prediction_titles</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">)</span>
<span class="c1"># %%</span>
<span class="c1"># plot the gallery of the most significative eigenfaces</span>
<span class="n">eigenface_titles</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"eigenface </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">i</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">eigenfaces</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="n">plot_gallery</span><span class="p">(</span><span class="n">eigenfaces</span><span class="p">,</span> <span class="n">eigenface_titles</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="c1"># %%</span>
<span class="c1"># Face recognition problem would be much more effectively solved by training</span>
<span class="c1"># convolutional neural networks but this family of models is outside of the scope of</span>
<span class="c1"># the scikit-learn library. Interested readers should instead try to use pytorch or</span>
<span class="c1"># tensorflow to implement such models.</span>
</pre></div>
</div>
<figure class="align-default" id="id1">
<a class="reference internal image-reference" href="../../_images/plot_face_recognition_1.png"><img alt="../../_images/plot_face_recognition_1.png" src="../../_images/plot_face_recognition_1.png" style="width: 360.0px; height: 359.5px;" /></a>
<figcaption>
<p><span class="caption-text"><strong>Prediction</strong></span><a class="headerlink" href="#id1" title="Link to this image">¶</a></p>
</figcaption>
</figure>
<figure class="align-default" id="id2">
<a class="reference internal image-reference" href="../../_images/plot_face_recognition_2.png"><img alt="../../_images/plot_face_recognition_2.png" src="../../_images/plot_face_recognition_2.png" style="width: 360.0px; height: 359.5px;" /></a>
<figcaption>
<p><span class="caption-text"><strong>Eigenfaces</strong></span><a class="headerlink" href="#id2" title="Link to this image">¶</a></p>
</figcaption>
</figure>
<p>Expected results for the top 5 most represented people in the dataset:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span> <span class="n">precision</span> <span class="n">recall</span> <span class="n">f1</span><span class="o">-</span><span class="n">score</span> <span class="n">support</span>
<span class="n">Gerhard_Schroeder</span> <span class="mf">0.91</span> <span class="mf">0.75</span> <span class="mf">0.82</span> <span class="mi">28</span>
<span class="n">Donald_Rumsfeld</span> <span class="mf">0.84</span> <span class="mf">0.82</span> <span class="mf">0.83</span> <span class="mi">33</span>
<span class="n">Tony_Blair</span> <span class="mf">0.65</span> <span class="mf">0.82</span> <span class="mf">0.73</span> <span class="mi">34</span>
<span class="n">Colin_Powell</span> <span class="mf">0.78</span> <span class="mf">0.88</span> <span class="mf">0.83</span> <span class="mi">58</span>
<span class="n">George_W_Bush</span> <span class="mf">0.93</span> <span class="mf">0.86</span> <span class="mf">0.90</span> <span class="mi">129</span>
<span class="n">avg</span> <span class="o">/</span> <span class="n">total</span> <span class="mf">0.86</span> <span class="mf">0.84</span> <span class="mf">0.85</span> <span class="mi">282</span>
</pre></div>
</div>
</section>
<section id="open-problem-stock-market-structure">
<h2>Open problem: Stock Market Structure<a class="headerlink" href="#open-problem-stock-market-structure" title="Link to this heading">¶</a></h2>
<p>Can we predict the variation in stock prices for Google over a given time frame?</p>
<p><a class="reference internal" href="../../auto_examples/applications/plot_stock_market.html#stock-market"><span class="std std-ref">Learning a graph structure</span></a></p>
</section>
</section>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2024, scikit-learn developers (BSD License).
<a href="../../_sources/tutorial/statistical_inference/putting_together.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 src="../../_static/clipboard.min.js"></script>
<script src="../../_static/copybutton.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');
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
// 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>');
});
/*** 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>