forked from scikit-learn/scikit-learn.github.io
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathplot_document_classification_20newsgroups.html
825 lines (705 loc) · 79.3 KB
/
plot_document_classification_20newsgroups.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
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
<!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>Classification of text documents using sparse features — scikit-learn 0.20.dev0 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: '0.20.dev0',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</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>
<script type="text/javascript" src="../../_static/js/extra.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS_SVG"></script>
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../../about.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Decision Tree Regression" href="../tree/plot_tree_regression.html" />
<link rel="prev" title="Clustering text documents using k-means" href="plot_document_clustering.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../../_static/js/bootstrap.min.js" type="text/javascript"></script>
<script>
VERSION_SUBDIR = (function(groups) {
return groups ? groups[1] : null;
})(location.href.match(/^https?:\/\/scikit-learn.org\/([^\/]+)/));
</script>
<link rel="canonical" href="http://scikit-learn.org/stable/auto_examples/text/plot_document_classification_20newsgroups.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
function showMenu() {
var topNav = document.getElementById("scikit-navbar");
if (topNav.className === "navbar") {
topNav.className += " responsive";
} else {
topNav.className = "navbar";
}
};
</script>
</head>
<body>
<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" id="scikit-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 <script>document.write(DOCUMENTATION_OPTIONS.VERSION + (VERSION_SUBDIR ? " (" + VERSION_SUBDIR + ")" : ""));</script></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="../../glossary.html">Glossary</a></li>
<li><a href="../../faq.html">FAQ</a></li>
<li><a href="../../developers/contributing.html">Contributing</a></li>
<li class="divider"></li>
<script>if (VERSION_SUBDIR != "stable") document.write('<li><a href="http://scikit-learn.org/stable/documentation.html">Stable version</a></li>')</script>
<script>if (VERSION_SUBDIR != "dev") document.write('<li><a href="http://scikit-learn.org/dev/documentation.html">Development version</a></li>')</script>
<li><a href="http://scikit-learn.org/dev/versions.html">All available versions</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>
<a href="javascript:void(0);" onclick="showMenu()">
<div class="nav-icon">
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
<div class="hamburger-line"></div>
</div>
</a>
<div class="search_form">
<div class="gcse-search" 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">
<div class="rellink">
<a href="plot_document_clustering.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Clustering te...
</span>
<span class="hiddenrellink">
Clustering text documents using k-means
</span>
</a>
</div>
<div class="spacer">
</div>
<div class="rellink">
<a href="../tree/plot_tree_regression.html"
accesskey="N">Next
<br/>
<span class="smallrellink">
Decision Tree...
</span>
<span class="hiddenrellink">
Decision Tree Regression
</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"><b>scikit-learn v0.20.dev0</b><br/>
<a href="http://scikit-learn.org/stable/support.html#documentation-resources">Other versions</a></p>
<p class="citing">Please <b><a href="../../about.html#citing-scikit-learn" style="font-size: 110%;">cite us </a></b>if you use the software.</p>
<ul>
<li><a class="reference internal" href="#">Classification of text documents using sparse features</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="sphx-glr-download-link-note admonition note">
<p class="first admonition-title">Note</p>
<p class="last">Click <a class="reference internal" href="#sphx-glr-download-auto-examples-text-plot-document-classification-20newsgroups-py"><span class="std std-ref">here</span></a> to download the full example code or run this example in your browser via Binder</p>
</div>
<div class="sphx-glr-example-title section" id="classification-of-text-documents-using-sparse-features">
<span id="sphx-glr-auto-examples-text-plot-document-classification-20newsgroups-py"></span><h1>Classification of text documents using sparse features<a class="headerlink" href="#classification-of-text-documents-using-sparse-features" title="Permalink to this headline">¶</a></h1>
<p>This is an example showing how scikit-learn can be used to classify documents
by topics using a bag-of-words approach. This example uses a scipy.sparse
matrix to store the features and demonstrates various classifiers that can
efficiently handle sparse matrices.</p>
<p>The dataset used in this example is the 20 newsgroups dataset. It will be
automatically downloaded, then cached.</p>
<p>The bar plot indicates the accuracy, training time (normalized) and test time
(normalized) of each classifier.</p>
<img alt="../../_images/sphx_glr_plot_document_classification_20newsgroups_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_plot_document_classification_20newsgroups_001.png" />
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none"><div class="highlight"><pre><span></span>Usage: plot_document_classification_20newsgroups.py [options]
Options:
-h, --help show this help message and exit
--report Print a detailed classification report.
--chi2_select=SELECT_CHI2
Select some number of features using a chi-squared
test
--confusion_matrix Print the confusion matrix.
--top10 Print ten most discriminative terms per class for
every classifier.
--all_categories Whether to use all categories or not.
--use_hashing Use a hashing vectorizer.
--n_features=N_FEATURES
n_features when using the hashing vectorizer.
--filtered Remove newsgroup information that is easily overfit:
headers, signatures, and quoting.
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
data loaded
2034 documents - 3.980MB (training set)
1353 documents - 2.867MB (test set)
4 categories
Extracting features from the training data using a sparse vectorizer
done in 0.476393s at 8.353MB/s
n_samples: 2034, n_features: 33809
Extracting features from the test data using the same vectorizer
done in 0.330373s at 8.680MB/s
n_samples: 1353, n_features: 33809
================================================================================
Ridge Classifier
________________________________________________________________________________
Training:
RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=None, solver='lsqr',
tol=0.01)
train time: 0.204s
test time: 0.002s
accuracy: 0.896
dimensionality: 33809
density: 1.000000
================================================================================
Perceptron
________________________________________________________________________________
Training:
Perceptron(alpha=0.0001, class_weight=None, eta0=1.0, fit_intercept=True,
max_iter=None, n_iter=50, n_jobs=1, penalty=None, random_state=0,
shuffle=True, tol=0.001, verbose=0, warm_start=False)
train time: 0.014s
test time: 0.002s
accuracy: 0.881
dimensionality: 33809
density: 0.232675
================================================================================
Passive-Aggressive
________________________________________________________________________________
Training:
PassiveAggressiveClassifier(C=1.0, average=False, class_weight=None,
fit_intercept=True, loss='hinge', max_iter=None, n_iter=50,
n_jobs=1, random_state=None, shuffle=True, tol=0.001,
verbose=0, warm_start=False)
train time: 0.026s
test time: 0.002s
accuracy: 0.901
dimensionality: 33809
density: 0.702069
================================================================================
kNN
________________________________________________________________________________
Training:
KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_jobs=1, n_neighbors=10, p=2,
weights='uniform')
train time: 0.001s
test time: 0.218s
accuracy: 0.858
================================================================================
Random forest
________________________________________________________________________________
Training:
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
max_depth=None, max_features='auto', max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=1,
oob_score=False, random_state=None, verbose=0,
warm_start=False)
train time: 1.579s
test time: 0.076s
accuracy: 0.845
================================================================================
L2 penalty
________________________________________________________________________________
Training:
LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, loss='squared_hinge', max_iter=1000,
multi_class='ovr', penalty='l2', random_state=None, tol=0.001,
verbose=0)
train time: 0.094s
test time: 0.001s
accuracy: 0.900
dimensionality: 33809
density: 1.000000
________________________________________________________________________________
Training:
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
eta0=0.0, fit_intercept=True, l1_ratio=0.15,
learning_rate='optimal', loss='hinge', max_iter=5, n_iter=50,
n_jobs=1, penalty='l2', power_t=0.5, random_state=None,
shuffle=True, tol=None, verbose=0, warm_start=False)
train time: 0.090s
test time: 0.002s
accuracy: 0.902
dimensionality: 33809
density: 0.666213
================================================================================
L1 penalty
________________________________________________________________________________
Training:
LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, loss='squared_hinge', max_iter=1000,
multi_class='ovr', penalty='l1', random_state=None, tol=0.001,
verbose=0)
train time: 0.169s
test time: 0.001s
accuracy: 0.873
dimensionality: 33809
density: 0.005575
________________________________________________________________________________
Training:
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
eta0=0.0, fit_intercept=True, l1_ratio=0.15,
learning_rate='optimal', loss='hinge', max_iter=5, n_iter=50,
n_jobs=1, penalty='l1', power_t=0.5, random_state=None,
shuffle=True, tol=None, verbose=0, warm_start=False)
train time: 0.312s
test time: 0.002s
accuracy: 0.888
dimensionality: 33809
density: 0.020128
================================================================================
Elastic-Net penalty
________________________________________________________________________________
Training:
SGDClassifier(alpha=0.0001, average=False, class_weight=None, epsilon=0.1,
eta0=0.0, fit_intercept=True, l1_ratio=0.15,
learning_rate='optimal', loss='hinge', max_iter=5, n_iter=50,
n_jobs=1, penalty='elasticnet', power_t=0.5, random_state=None,
shuffle=True, tol=None, verbose=0, warm_start=False)
train time: 0.529s
test time: 0.002s
accuracy: 0.901
dimensionality: 33809
density: 0.186615
================================================================================
NearestCentroid (aka Rocchio classifier)
________________________________________________________________________________
Training:
NearestCentroid(metric='euclidean', shrink_threshold=None)
train time: 0.005s
test time: 0.002s
accuracy: 0.855
================================================================================
Naive Bayes
________________________________________________________________________________
Training:
MultinomialNB(alpha=0.01, class_prior=None, fit_prior=True)
train time: 0.003s
test time: 0.001s
accuracy: 0.899
dimensionality: 33809
density: 1.000000
________________________________________________________________________________
Training:
BernoulliNB(alpha=0.01, binarize=0.0, class_prior=None, fit_prior=True)
train time: 0.004s
test time: 0.003s
accuracy: 0.884
dimensionality: 33809
density: 1.000000
________________________________________________________________________________
Training:
ComplementNB(alpha=0.1, class_prior=None, fit_prior=True, norm=False)
train time: 0.004s
test time: 0.001s
accuracy: 0.911
dimensionality: 33809
density: 1.000000
================================================================================
LinearSVC with L1-based feature selection
________________________________________________________________________________
Training:
Pipeline(memory=None,
steps=[('feature_selection', SelectFromModel(estimator=LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, loss='squared_hinge', max_iter=1000,
multi_class='ovr', penalty='l1', random_state=None, tol=0.001,
verbose=0),
norm_order=1, prefit=...ax_iter=1000,
multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
verbose=0))])
train time: 0.207s
test time: 0.003s
accuracy: 0.880
</pre></div>
</div>
<div class="line-block">
<div class="line"><br /></div>
</div>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># Author: Peter Prettenhofer <[email protected]></span>
<span class="c1"># Olivier Grisel <[email protected]></span>
<span class="c1"># Mathieu Blondel <[email protected]></span>
<span class="c1"># Lars Buitinck</span>
<span class="c1"># License: BSD 3 clause</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">optparse</span> <span class="kn">import</span> <span class="n">OptionParser</span>
<span class="kn">import</span> <span class="nn">sys</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="kn">as</span> <span class="nn">plt</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.fetch_20newsgroups.html#sklearn.datasets.fetch_20newsgroups" title="View documentation for sklearn.datasets.fetch_20newsgroups"><span class="n">fetch_20newsgroups</span></a>
<span class="kn">from</span> <span class="nn">sklearn.feature_extraction.text</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer" title="View documentation for sklearn.feature_extraction.text.TfidfVectorizer"><span class="n">TfidfVectorizer</span></a>
<span class="kn">from</span> <span class="nn">sklearn.feature_extraction.text</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_extraction.text.HashingVectorizer.html#sklearn.feature_extraction.text.HashingVectorizer" title="View documentation for sklearn.feature_extraction.text.HashingVectorizer"><span class="n">HashingVectorizer</span></a>
<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_selection.SelectFromModel.html#sklearn.feature_selection.SelectFromModel" title="View documentation for sklearn.feature_selection.SelectFromModel"><span class="n">SelectFromModel</span></a>
<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_selection.SelectKBest.html#sklearn.feature_selection.SelectKBest" title="View documentation for sklearn.feature_selection.SelectKBest"><span class="n">SelectKBest</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.feature_selection.chi2.html#sklearn.feature_selection.chi2" title="View documentation for sklearn.feature_selection.chi2"><span class="n">chi2</span></a>
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.linear_model.RidgeClassifier.html#sklearn.linear_model.RidgeClassifier" title="View documentation for sklearn.linear_model.RidgeClassifier"><span class="n">RidgeClassifier</span></a>
<span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" title="View documentation for sklearn.pipeline.Pipeline"><span class="n">Pipeline</span></a>
<span class="kn">from</span> <span class="nn">sklearn.svm</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">LinearSVC</span></a>
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.linear_model.SGDClassifier.html#sklearn.linear_model.SGDClassifier" title="View documentation for sklearn.linear_model.SGDClassifier"><span class="n">SGDClassifier</span></a>
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.linear_model.Perceptron.html#sklearn.linear_model.Perceptron" title="View documentation for sklearn.linear_model.Perceptron"><span class="n">Perceptron</span></a>
<span class="kn">from</span> <span class="nn">sklearn.linear_model</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.linear_model.PassiveAggressiveClassifier.html#sklearn.linear_model.PassiveAggressiveClassifier" title="View documentation for sklearn.linear_model.PassiveAggressiveClassifier"><span class="n">PassiveAggressiveClassifier</span></a>
<span class="kn">from</span> <span class="nn">sklearn.naive_bayes</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.naive_bayes.BernoulliNB.html#sklearn.naive_bayes.BernoulliNB" title="View documentation for sklearn.naive_bayes.BernoulliNB"><span class="n">BernoulliNB</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.naive_bayes.ComplementNB.html#sklearn.naive_bayes.ComplementNB" title="View documentation for sklearn.naive_bayes.ComplementNB"><span class="n">ComplementNB</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.naive_bayes.MultinomialNB.html#sklearn.naive_bayes.MultinomialNB" title="View documentation for sklearn.naive_bayes.MultinomialNB"><span class="n">MultinomialNB</span></a>
<span class="kn">from</span> <span class="nn">sklearn.neighbors</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.neighbors.KNeighborsClassifier.html#sklearn.neighbors.KNeighborsClassifier" title="View documentation for sklearn.neighbors.KNeighborsClassifier"><span class="n">KNeighborsClassifier</span></a>
<span class="kn">from</span> <span class="nn">sklearn.neighbors</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.neighbors.NearestCentroid.html#sklearn.neighbors.NearestCentroid" title="View documentation for sklearn.neighbors.NearestCentroid"><span class="n">NearestCentroid</span></a>
<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier" title="View documentation for sklearn.ensemble.RandomForestClassifier"><span class="n">RandomForestClassifier</span></a>
<span class="kn">from</span> <span class="nn">sklearn.utils.extmath</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.utils.extmath.density.html#sklearn.utils.extmath.density" title="View documentation for sklearn.utils.extmath.density"><span class="n">density</span></a>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">metrics</span>
<span class="c1"># Display progress logs on stdout</span>
<span class="n">logging</span><span class="o">.</span><span class="n">basicConfig</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">,</span>
<span class="n">format</span><span class="o">=</span><span class="s1">'</span><span class="si">%(asctime)s</span><span class="s1"> </span><span class="si">%(levelname)s</span><span class="s1"> </span><span class="si">%(message)s</span><span class="s1">'</span><span class="p">)</span>
<span class="c1"># parse commandline arguments</span>
<span class="n">op</span> <span class="o">=</span> <span class="n">OptionParser</span><span class="p">()</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--report"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"print_report"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Print a detailed classification report."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--chi2_select"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="s2">"int"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"select_chi2"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Select some number of features using a chi-squared test"</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--confusion_matrix"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"print_cm"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Print the confusion matrix."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--top10"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"print_top10"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Print ten most discriminative terms per class"</span>
<span class="s2">" for every classifier."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--all_categories"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"all_categories"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Whether to use all categories or not."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--use_hashing"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Use a hashing vectorizer."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--n_features"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">2</span> <span class="o">**</span> <span class="mi">16</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"n_features when using the hashing vectorizer."</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">add_option</span><span class="p">(</span><span class="s2">"--filtered"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Remove newsgroup information that is easily overfit: "</span>
<span class="s2">"headers, signatures, and quoting."</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">is_interactive</span><span class="p">():</span>
<span class="k">return</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">modules</span><span class="p">[</span><span class="s1">'__main__'</span><span class="p">],</span> <span class="s1">'__file__'</span><span class="p">)</span>
<span class="c1"># work-around for Jupyter notebook and IPython console</span>
<span class="n">argv</span> <span class="o">=</span> <span class="p">[]</span> <span class="k">if</span> <span class="n">is_interactive</span><span class="p">()</span> <span class="k">else</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
<span class="p">(</span><span class="n">opts</span><span class="p">,</span> <span class="n">args</span><span class="p">)</span> <span class="o">=</span> <span class="n">op</span><span class="o">.</span><span class="n">parse_args</span><span class="p">(</span><span class="n">argv</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
<span class="n">op</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"this script takes no arguments."</span><span class="p">)</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="vm">__doc__</span><span class="p">)</span>
<span class="n">op</span><span class="o">.</span><span class="n">print_help</span><span class="p">()</span>
<span class="k">print</span><span class="p">()</span>
<span class="c1"># #############################################################################</span>
<span class="c1"># Load some categories from the training set</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">all_categories</span><span class="p">:</span>
<span class="n">categories</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">'alt.atheism'</span><span class="p">,</span>
<span class="s1">'talk.religion.misc'</span><span class="p">,</span>
<span class="s1">'comp.graphics'</span><span class="p">,</span>
<span class="s1">'sci.space'</span><span class="p">,</span>
<span class="p">]</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">filtered</span><span class="p">:</span>
<span class="n">remove</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'headers'</span><span class="p">,</span> <span class="s1">'footers'</span><span class="p">,</span> <span class="s1">'quotes'</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">remove</span> <span class="o">=</span> <span class="p">()</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Loading 20 newsgroups dataset for categories:"</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="n">categories</span> <span class="k">if</span> <span class="n">categories</span> <span class="k">else</span> <span class="s2">"all"</span><span class="p">)</span>
<span class="n">data_train</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_20newsgroups.html#sklearn.datasets.fetch_20newsgroups" title="View documentation for sklearn.datasets.fetch_20newsgroups"><span class="n">fetch_20newsgroups</span></a><span class="p">(</span><span class="n">subset</span><span class="o">=</span><span class="s1">'train'</span><span class="p">,</span> <span class="n">categories</span><span class="o">=</span><span class="n">categories</span><span class="p">,</span>
<span class="n">shuffle</span><span class="o">=</span><span class="bp">True</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">remove</span><span class="o">=</span><span class="n">remove</span><span class="p">)</span>
<span class="n">data_test</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_20newsgroups.html#sklearn.datasets.fetch_20newsgroups" title="View documentation for sklearn.datasets.fetch_20newsgroups"><span class="n">fetch_20newsgroups</span></a><span class="p">(</span><span class="n">subset</span><span class="o">=</span><span class="s1">'test'</span><span class="p">,</span> <span class="n">categories</span><span class="o">=</span><span class="n">categories</span><span class="p">,</span>
<span class="n">shuffle</span><span class="o">=</span><span class="bp">True</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">remove</span><span class="o">=</span><span class="n">remove</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'data loaded'</span><span class="p">)</span>
<span class="c1"># order of labels in `target_names` can be different from `categories`</span>
<span class="n">target_names</span> <span class="o">=</span> <span class="n">data_train</span><span class="o">.</span><span class="n">target_names</span>
<span class="k">def</span> <span class="nf">size_mb</span><span class="p">(</span><span class="n">docs</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">))</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">docs</span><span class="p">)</span> <span class="o">/</span> <span class="mf">1e6</span>
<span class="n">data_train_size_mb</span> <span class="o">=</span> <span class="n">size_mb</span><span class="p">(</span><span class="n">data_train</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="n">data_test_size_mb</span> <span class="o">=</span> <span class="n">size_mb</span><span class="p">(</span><span class="n">data_test</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> documents - </span><span class="si">%0.3f</span><span class="s2">MB (training set)"</span> <span class="o">%</span> <span class="p">(</span>
<span class="nb">len</span><span class="p">(</span><span class="n">data_train</span><span class="o">.</span><span class="n">data</span><span class="p">),</span> <span class="n">data_train_size_mb</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> documents - </span><span class="si">%0.3f</span><span class="s2">MB (test set)"</span> <span class="o">%</span> <span class="p">(</span>
<span class="nb">len</span><span class="p">(</span><span class="n">data_test</span><span class="o">.</span><span class="n">data</span><span class="p">),</span> <span class="n">data_test_size_mb</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> categories"</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">categories</span><span class="p">))</span>
<span class="k">print</span><span class="p">()</span>
<span class="c1"># split a training set and a test set</span>
<span class="n">y_train</span><span class="p">,</span> <span class="n">y_test</span> <span class="o">=</span> <span class="n">data_train</span><span class="o">.</span><span class="n">target</span><span class="p">,</span> <span class="n">data_test</span><span class="o">.</span><span class="n">target</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Extracting features from the training data using a sparse vectorizer"</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="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">use_hashing</span><span class="p">:</span>
<span class="n">vectorizer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.feature_extraction.text.HashingVectorizer.html#sklearn.feature_extraction.text.HashingVectorizer" title="View documentation for sklearn.feature_extraction.text.HashingVectorizer"><span class="n">HashingVectorizer</span></a><span class="p">(</span><span class="n">stop_words</span><span class="o">=</span><span class="s1">'english'</span><span class="p">,</span> <span class="n">alternate_sign</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
<span class="n">n_features</span><span class="o">=</span><span class="n">opts</span><span class="o">.</span><span class="n">n_features</span><span class="p">)</span>
<span class="n">X_train</span> <span class="o">=</span> <span class="n">vectorizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">data_train</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">vectorizer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer" title="View documentation for sklearn.feature_extraction.text.TfidfVectorizer"><span class="n">TfidfVectorizer</span></a><span class="p">(</span><span class="n">sublinear_tf</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">max_df</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
<span class="n">stop_words</span><span class="o">=</span><span class="s1">'english'</span><span class="p">)</span>
<span class="n">X_train</span> <span class="o">=</span> <span class="n">vectorizer</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">data_train</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="n">duration</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%f</span><span class="s2">s at </span><span class="si">%0.3f</span><span class="s2">MB/s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">duration</span><span class="p">,</span> <span class="n">data_train_size_mb</span> <span class="o">/</span> <span class="n">duration</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"n_samples: </span><span class="si">%d</span><span class="s2">, n_features: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">X_train</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="k">print</span><span class="p">()</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Extracting features from the test data using the same vectorizer"</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_test</span> <span class="o">=</span> <span class="n">vectorizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">data_test</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="n">duration</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%f</span><span class="s2">s at </span><span class="si">%0.3f</span><span class="s2">MB/s"</span> <span class="o">%</span> <span class="p">(</span><span class="n">duration</span><span class="p">,</span> <span class="n">data_test_size_mb</span> <span class="o">/</span> <span class="n">duration</span><span class="p">))</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"n_samples: </span><span class="si">%d</span><span class="s2">, n_features: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">X_test</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="k">print</span><span class="p">()</span>
<span class="c1"># mapping from integer feature name to original token string</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">use_hashing</span><span class="p">:</span>
<span class="n">feature_names</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">feature_names</span> <span class="o">=</span> <span class="n">vectorizer</span><span class="o">.</span><span class="n">get_feature_names</span><span class="p">()</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">select_chi2</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Extracting </span><span class="si">%d</span><span class="s2"> best features by a chi-squared test"</span> <span class="o">%</span>
<span class="n">opts</span><span class="o">.</span><span class="n">select_chi2</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">ch2</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.feature_selection.SelectKBest.html#sklearn.feature_selection.SelectKBest" title="View documentation for sklearn.feature_selection.SelectKBest"><span class="n">SelectKBest</span></a><span class="p">(</span><a href="../../modules/generated/sklearn.feature_selection.chi2.html#sklearn.feature_selection.chi2" title="View documentation for sklearn.feature_selection.chi2"><span class="n">chi2</span></a><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="n">opts</span><span class="o">.</span><span class="n">select_chi2</span><span class="p">)</span>
<span class="n">X_train</span> <span class="o">=</span> <span class="n">ch2</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">y_train</span><span class="p">)</span>
<span class="n">X_test</span> <span class="o">=</span> <span class="n">ch2</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="k">if</span> <span class="n">feature_names</span><span class="p">:</span>
<span class="c1"># keep selected feature names</span>
<span class="n">feature_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">feature_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="n">ch2</span><span class="o">.</span><span class="n">get_support</span><span class="p">(</span><span class="n">indices</span><span class="o">=</span><span class="bp">True</span><span class="p">)]</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"done in </span><span class="si">%f</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="k">print</span><span class="p">()</span>
<span class="k">if</span> <span class="n">feature_names</span><span class="p">:</span>
<span class="n">feature_names</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.asarray.html#numpy.asarray" title="View documentation for numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">feature_names</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">trim</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="sd">"""Trim string to fit on terminal (assuming 80-column display)"""</span>
<span class="k">return</span> <span class="n">s</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">80</span> <span class="k">else</span> <span class="n">s</span><span class="p">[:</span><span class="mi">77</span><span class="p">]</span> <span class="o">+</span> <span class="s2">"..."</span>
<span class="c1"># #############################################################################</span>
<span class="c1"># Benchmark classifiers</span>
<span class="k">def</span> <span class="nf">benchmark</span><span class="p">(</span><span class="n">clf</span><span class="p">):</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'_'</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Training: "</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="n">clf</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">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
<span class="n">train_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"train time: </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="n">train_time</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">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</span><span class="p">)</span>
<span class="n">test_time</span> <span class="o">=</span> <span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"test time: </span><span class="si">%0.3f</span><span class="s2">s"</span> <span class="o">%</span> <span class="n">test_time</span><span class="p">)</span>
<span class="n">score</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.metrics.accuracy_score.html#sklearn.metrics.accuracy_score" title="View documentation for sklearn.metrics.accuracy_score"><span class="n">metrics</span><span class="o">.</span><span class="n">accuracy_score</span></a><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"accuracy: </span><span class="si">%0.3f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">score</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">clf</span><span class="p">,</span> <span class="s1">'coef_'</span><span class="p">):</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"dimensionality: </span><span class="si">%d</span><span class="s2">"</span> <span class="o">%</span> <span class="n">clf</span><span class="o">.</span><span class="n">coef_</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="k">print</span><span class="p">(</span><span class="s2">"density: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <a href="../../modules/generated/sklearn.utils.extmath.density.html#sklearn.utils.extmath.density" title="View documentation for sklearn.utils.extmath.density"><span class="n">density</span></a><span class="p">(</span><span class="n">clf</span><span class="o">.</span><span class="n">coef_</span><span class="p">))</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">print_top10</span> <span class="ow">and</span> <span class="n">feature_names</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"top 10 keywords per class:"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">target_names</span><span class="p">):</span>
<span class="n">top10</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.argsort.html#numpy.argsort" title="View documentation for numpy.argsort"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">clf</span><span class="o">.</span><span class="n">coef_</span><span class="p">[</span><span class="n">i</span><span class="p">])[</span><span class="o">-</span><span class="mi">10</span><span class="p">:]</span>
<span class="k">print</span><span class="p">(</span><span class="n">trim</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">feature_names</span><span class="p">[</span><span class="n">top10</span><span class="p">]))))</span>
<span class="k">print</span><span class="p">()</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">print_report</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"classification report:"</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><a href="../../modules/generated/sklearn.metrics.classification_report.html#sklearn.metrics.classification_report" title="View documentation for sklearn.metrics.classification_report"><span class="n">metrics</span><span class="o">.</span><span class="n">classification_report</span></a><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">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="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">print_cm</span><span class="p">:</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"confusion matrix:"</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><a href="../../modules/generated/sklearn.metrics.confusion_matrix.html#sklearn.metrics.confusion_matrix" title="View documentation for sklearn.metrics.confusion_matrix"><span class="n">metrics</span><span class="o">.</span><span class="n">confusion_matrix</span></a><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">pred</span><span class="p">))</span>
<span class="k">print</span><span class="p">()</span>
<span class="n">clf_descr</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">clf</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'('</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">return</span> <span class="n">clf_descr</span><span class="p">,</span> <span class="n">score</span><span class="p">,</span> <span class="n">train_time</span><span class="p">,</span> <span class="n">test_time</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">clf</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="p">(</span>
<span class="p">(</span><a href="../../modules/generated/sklearn.linear_model.RidgeClassifier.html#sklearn.linear_model.RidgeClassifier" title="View documentation for sklearn.linear_model.RidgeClassifier"><span class="n">RidgeClassifier</span></a><span class="p">(</span><span class="n">tol</span><span class="o">=</span><span class="mf">1e-2</span><span class="p">,</span> <span class="n">solver</span><span class="o">=</span><span class="s2">"lsqr"</span><span class="p">),</span> <span class="s2">"Ridge Classifier"</span><span class="p">),</span>
<span class="p">(</span><a href="../../modules/generated/sklearn.linear_model.Perceptron.html#sklearn.linear_model.Perceptron" title="View documentation for sklearn.linear_model.Perceptron"><span class="n">Perceptron</span></a><span class="p">(</span><span class="n">n_iter</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">),</span> <span class="s2">"Perceptron"</span><span class="p">),</span>
<span class="p">(</span><a href="../../modules/generated/sklearn.linear_model.PassiveAggressiveClassifier.html#sklearn.linear_model.PassiveAggressiveClassifier" title="View documentation for sklearn.linear_model.PassiveAggressiveClassifier"><span class="n">PassiveAggressiveClassifier</span></a><span class="p">(</span><span class="n">n_iter</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">),</span>
<span class="s2">"Passive-Aggressive"</span><span class="p">),</span>
<span class="p">(</span><a href="../../modules/generated/sklearn.neighbors.KNeighborsClassifier.html#sklearn.neighbors.KNeighborsClassifier" title="View documentation for sklearn.neighbors.KNeighborsClassifier"><span class="n">KNeighborsClassifier</span></a><span class="p">(</span><span class="n">n_neighbors</span><span class="o">=</span><span class="mi">10</span><span class="p">),</span> <span class="s2">"kNN"</span><span class="p">),</span>
<span class="p">(</span><a href="../../modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier" title="View documentation for 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="mi">100</span><span class="p">),</span> <span class="s2">"Random forest"</span><span class="p">)):</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><span class="n">clf</span><span class="p">))</span>
<span class="k">for</span> <span class="n">penalty</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"l2"</span><span class="p">,</span> <span class="s2">"l1"</span><span class="p">]:</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2"> penalty"</span> <span class="o">%</span> <span class="n">penalty</span><span class="o">.</span><span class="n">upper</span><span class="p">())</span>
<span class="c1"># Train Liblinear model</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">LinearSVC</span></a><span class="p">(</span><span class="n">penalty</span><span class="o">=</span><span class="n">penalty</span><span class="p">,</span> <span class="n">dual</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">)))</span>
<span class="c1"># Train SGD model</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.linear_model.SGDClassifier.html#sklearn.linear_model.SGDClassifier" title="View documentation for sklearn.linear_model.SGDClassifier"><span class="n">SGDClassifier</span></a><span class="p">(</span><span class="n">alpha</span><span class="o">=.</span><span class="mo">0001</span><span class="p">,</span> <span class="n">n_iter</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span>
<span class="n">penalty</span><span class="o">=</span><span class="n">penalty</span><span class="p">,</span>
<span class="n">max_iter</span><span class="o">=</span><span class="mi">5</span><span class="p">)))</span>
<span class="c1"># Train SGD with Elastic Net penalty</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Elastic-Net penalty"</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.linear_model.SGDClassifier.html#sklearn.linear_model.SGDClassifier" title="View documentation for sklearn.linear_model.SGDClassifier"><span class="n">SGDClassifier</span></a><span class="p">(</span><span class="n">alpha</span><span class="o">=.</span><span class="mo">0001</span><span class="p">,</span> <span class="n">n_iter</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span>
<span class="n">penalty</span><span class="o">=</span><span class="s2">"elasticnet"</span><span class="p">,</span>
<span class="n">max_iter</span><span class="o">=</span><span class="mi">5</span><span class="p">)))</span>
<span class="c1"># Train NearestCentroid without threshold</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"NearestCentroid (aka Rocchio classifier)"</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.neighbors.NearestCentroid.html#sklearn.neighbors.NearestCentroid" title="View documentation for sklearn.neighbors.NearestCentroid"><span class="n">NearestCentroid</span></a><span class="p">()))</span>
<span class="c1"># Train sparse Naive Bayes classifiers</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Naive Bayes"</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.naive_bayes.MultinomialNB.html#sklearn.naive_bayes.MultinomialNB" title="View documentation for sklearn.naive_bayes.MultinomialNB"><span class="n">MultinomialNB</span></a><span class="p">(</span><span class="n">alpha</span><span class="o">=.</span><span class="mo">01</span><span class="p">)))</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.naive_bayes.BernoulliNB.html#sklearn.naive_bayes.BernoulliNB" title="View documentation for sklearn.naive_bayes.BernoulliNB"><span class="n">BernoulliNB</span></a><span class="p">(</span><span class="n">alpha</span><span class="o">=.</span><span class="mo">01</span><span class="p">)))</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.naive_bayes.ComplementNB.html#sklearn.naive_bayes.ComplementNB" title="View documentation for sklearn.naive_bayes.ComplementNB"><span class="n">ComplementNB</span></a><span class="p">(</span><span class="n">alpha</span><span class="o">=.</span><span class="mi">1</span><span class="p">)))</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'='</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"LinearSVC with L1-based feature selection"</span><span class="p">)</span>
<span class="c1"># The smaller C, the stronger the regularization.</span>
<span class="c1"># The more regularization, the more sparsity.</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">benchmark</span><span class="p">(</span><a href="../../modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" title="View documentation for sklearn.pipeline.Pipeline"><span class="n">Pipeline</span></a><span class="p">([</span>
<span class="p">(</span><span class="s1">'feature_selection'</span><span class="p">,</span> <a href="../../modules/generated/sklearn.feature_selection.SelectFromModel.html#sklearn.feature_selection.SelectFromModel" title="View documentation for sklearn.feature_selection.SelectFromModel"><span class="n">SelectFromModel</span></a><span class="p">(</span><a href="../../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">LinearSVC</span></a><span class="p">(</span><span class="n">penalty</span><span class="o">=</span><span class="s2">"l1"</span><span class="p">,</span> <span class="n">dual</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
<span class="n">tol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">))),</span>
<span class="p">(</span><span class="s1">'classification'</span><span class="p">,</span> <a href="../../modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC" title="View documentation for sklearn.svm.LinearSVC"><span class="n">LinearSVC</span></a><span class="p">(</span><span class="n">penalty</span><span class="o">=</span><span class="s2">"l2"</span><span class="p">))])))</span>
<span class="c1"># make some plots</span>
<span class="n">indices</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.arange.html#numpy.arange" title="View documentation for numpy.arange"><span class="n">np</span><span class="o">.</span><span class="n">arange</span></a><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">results</span><span class="p">))</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[[</span><span class="n">x</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">results</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="mi">4</span><span class="p">)]</span>
<span class="n">clf_names</span><span class="p">,</span> <span class="n">score</span><span class="p">,</span> <span class="n">training_time</span><span class="p">,</span> <span class="n">test_time</span> <span class="o">=</span> <span class="n">results</span>
<span class="n">training_time</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">training_time</span><span class="p">)</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">training_time</span><span class="p">)</span>
<span class="n">test_time</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.array.html#numpy.array" title="View documentation for numpy.array"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span><span class="n">test_time</span><span class="p">)</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">test_time</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.figure.html#matplotlib.pyplot.figure" title="View documentation for matplotlib.pyplot.figure"><span class="n">plt</span><span class="o">.</span><span class="n">figure</span></a><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">8</span><span class="p">))</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.title.html#matplotlib.pyplot.title" title="View documentation for matplotlib.pyplot.title"><span class="n">plt</span><span class="o">.</span><span class="n">title</span></a><span class="p">(</span><span class="s2">"Score"</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.barh.html#matplotlib.pyplot.barh" title="View documentation for matplotlib.pyplot.barh"><span class="n">plt</span><span class="o">.</span><span class="n">barh</span></a><span class="p">(</span><span class="n">indices</span><span class="p">,</span> <span class="n">score</span><span class="p">,</span> <span class="o">.</span><span class="mi">2</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"score"</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s1">'navy'</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.barh.html#matplotlib.pyplot.barh" title="View documentation for matplotlib.pyplot.barh"><span class="n">plt</span><span class="o">.</span><span class="n">barh</span></a><span class="p">(</span><span class="n">indices</span> <span class="o">+</span> <span class="o">.</span><span class="mi">3</span><span class="p">,</span> <span class="n">training_time</span><span class="p">,</span> <span class="o">.</span><span class="mi">2</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"training time"</span><span class="p">,</span>
<span class="n">color</span><span class="o">=</span><span class="s1">'c'</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.barh.html#matplotlib.pyplot.barh" title="View documentation for matplotlib.pyplot.barh"><span class="n">plt</span><span class="o">.</span><span class="n">barh</span></a><span class="p">(</span><span class="n">indices</span> <span class="o">+</span> <span class="o">.</span><span class="mi">6</span><span class="p">,</span> <span class="n">test_time</span><span class="p">,</span> <span class="o">.</span><span class="mi">2</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"test time"</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="s1">'darkorange'</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.yticks.html#matplotlib.pyplot.yticks" title="View documentation for matplotlib.pyplot.yticks"><span class="n">plt</span><span class="o">.</span><span class="n">yticks</span></a><span class="p">(())</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.legend.html#matplotlib.pyplot.legend" title="View documentation for matplotlib.pyplot.legend"><span class="n">plt</span><span class="o">.</span><span class="n">legend</span></a><span class="p">(</span><span class="n">loc</span><span class="o">=</span><span class="s1">'best'</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplots_adjust.html#matplotlib.pyplot.subplots_adjust" title="View documentation for matplotlib.pyplot.subplots_adjust"><span class="n">plt</span><span class="o">.</span><span class="n">subplots_adjust</span></a><span class="p">(</span><span class="n">left</span><span class="o">=.</span><span class="mi">25</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplots_adjust.html#matplotlib.pyplot.subplots_adjust" title="View documentation for matplotlib.pyplot.subplots_adjust"><span class="n">plt</span><span class="o">.</span><span class="n">subplots_adjust</span></a><span class="p">(</span><span class="n">top</span><span class="o">=.</span><span class="mi">95</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.subplots_adjust.html#matplotlib.pyplot.subplots_adjust" title="View documentation for matplotlib.pyplot.subplots_adjust"><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="mo">05</span><span class="p">)</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="n">indices</span><span class="p">,</span> <span class="n">clf_names</span><span class="p">):</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.text.html#matplotlib.pyplot.text" title="View documentation for matplotlib.pyplot.text"><span class="n">plt</span><span class="o">.</span><span class="n">text</span></a><span class="p">(</span><span class="o">-.</span><span class="mi">3</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span>
<a href="https://matplotlib.org/api/_as_gen/matplotlib.pyplot.show.html#matplotlib.pyplot.show" title="View documentation for 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 script:</strong> ( 0 minutes 4.951 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-text-plot-document-classification-20newsgroups-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn.github.io/master?urlpath=lab/tree/notebooks/auto_examples/text/plot_document_classification_20newsgroups.ipynb"><img alt="https://static.mybinder.org/badge.svg" src="https://static.mybinder.org/badge.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../../_downloads/plot_document_classification_20newsgroups.py" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_document_classification_20newsgroups.py</span></code></a></div>
<div class="sphx-glr-download docutils container">
<a class="reference download internal" href="../../_downloads/plot_document_classification_20newsgroups.ipynb" download=""><code class="xref download docutils literal"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_document_classification_20newsgroups.ipynb</span></code></a></div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.readthedocs.io">Gallery generated by Sphinx-Gallery</a></p>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2007 - 2018, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/text/plot_document_classification_20newsgroups.rst.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_document_clustering.html">Previous
</a>
</div>
<div class="buttonNext">
<a href="../tree/plot_tree_regression.html">Next
</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>
(function() {
var cx = '016639176250731907682:tjtqbvtvij0';
var gcse = document.createElement('script'); gcse.type = 'text/javascript'; gcse.async = true;
gcse.src = 'https://cse.google.com/cse.js?cx=' + cx;
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(gcse, s);
})();
</script>
</body>
</html>