-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_document_clustering.html
595 lines (521 loc) · 51.6 KB
/
plot_document_clustering.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
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta name="Description" content="scikit-learn: machine learning in Python">
<title>Clustering text documents using k-means — scikit-learn 0.22.2 documentation</title>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/text/plot_document_clustering.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/gallery.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/jquery.js"></script>
</head>
<body>
<nav id="navbar" class="sk-docs-navbar navbar navbar-expand-md navbar-light bg-light py-0">
<div class="container-fluid sk-docs-container px-0">
<a class="navbar-brand py-0" href="../../index.html">
<img
class="sk-brand-img"
src="../../_static/scikit-learn-logo-small.png"
alt="logo"/>
</a>
<button
id="sk-navbar-toggler"
class="navbar-toggler"
type="button"
data-toggle="collapse"
data-target="#navbarSupportedContent"
aria-controls="navbarSupportedContent"
aria-expanded="false"
aria-label="Toggle navigation"
>
<span class="navbar-toggler-icon"></span>
</button>
<div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav mr-auto">
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../install.html">Install</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../user_guide.html">User Guide</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../modules/classes.html">API</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../index.html">Examples</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../getting_started.html">Getting Started</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../tutorial/index.html">Tutorial</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../glossary.html">Glossary</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../developers/index.html">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="../../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="../../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</a>
</li>
<li class="nav-item dropdown nav-more-item-dropdown">
<a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a>
<div class="dropdown-menu" aria-labelledby="navbarDropdown">
<a class="sk-nav-dropdown-item dropdown-item" href="../../getting_started.html">Getting Started</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../tutorial/index.html">Tutorial</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../glossary.html">Glossary</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../developers/index.html">Development</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../faq.html">FAQ</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="../../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</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="sk-sidebar-toc-logo">
<a href="../../index.html">
<img
class="sk-brand-img"
src="../../_static/scikit-learn-logo-small.png"
alt="logo"/>
</a>
</div>
<div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
<a href="plot_hashing_vs_dict_vectorizer.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="FeatureHasher and DictVectorizer Comparison">Prev</a><a href="../index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Examples">Up</a>
<a href="plot_document_classification_20newsgroups.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Classification of text documents using sparse features">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 0.22.2</strong><br/>
<a href="http://scikit-learn.org/dev/versions.html">Other versions</a>
</p>
</div>
<div class="alert alert-warning p-1 mb-2" role="alert">
<p class="text-center mb-0">
Please <a class="font-weight-bold" href="../../about.html#citing-scikit-learn"><string>cite us</string></a> if you use the software.
</p>
</div>
<div class="sk-sidebar-toc">
<ul>
<li><a class="reference internal" href="#">Clustering text documents using k-means</a></li>
</ul>
</div>
</div>
</div>
<div id="sk-page-content-wrapper">
<div class="sk-page-content container-fluid body px-md-3" role="main">
<div class="sphx-glr-download-link-note admonition note">
<p class="admonition-title">Note</p>
<p>Click <a class="reference internal" href="#sphx-glr-download-auto-examples-text-plot-document-clustering-py"><span class="std std-ref">here</span></a> to download the full example code or to run this example in your browser via Binder</p>
</div>
<div class="sphx-glr-example-title section" id="clustering-text-documents-using-k-means">
<span id="sphx-glr-auto-examples-text-plot-document-clustering-py"></span><h1>Clustering text documents using k-means<a class="headerlink" href="#clustering-text-documents-using-k-means" title="Permalink to this headline">¶</a></h1>
<p>This is an example showing how the scikit-learn can be used to cluster
documents by topics using a bag-of-words approach. This example uses
a scipy.sparse matrix to store the features instead of standard numpy arrays.</p>
<p>Two feature extraction methods can be used in this example:</p>
<blockquote>
<div><ul>
<li><p>TfidfVectorizer uses a in-memory vocabulary (a python dict) to map the most
frequent words to features indices and hence compute a word occurrence
frequency (sparse) matrix. The word frequencies are then reweighted using
the Inverse Document Frequency (IDF) vector collected feature-wise over
the corpus.</p></li>
<li><p>HashingVectorizer hashes word occurrences to a fixed dimensional space,
possibly with collisions. The word count vectors are then normalized to
each have l2-norm equal to one (projected to the euclidean unit-ball) which
seems to be important for k-means to work in high dimensional space.</p>
<p>HashingVectorizer does not provide IDF weighting as this is a stateless
model (the fit method does nothing). When IDF weighting is needed it can
be added by pipelining its output to a TfidfTransformer instance.</p>
</li>
</ul>
</div></blockquote>
<p>Two algorithms are demoed: ordinary k-means and its more scalable cousin
minibatch k-means.</p>
<p>Additionally, latent semantic analysis can also be used to reduce
dimensionality and discover latent patterns in the data.</p>
<p>It can be noted that k-means (and minibatch k-means) are very sensitive to
feature scaling and that in this case the IDF weighting helps improve the
quality of the clustering by quite a lot as measured against the “ground truth”
provided by the class label assignments of the 20 newsgroups dataset.</p>
<p>This improvement is not visible in the Silhouette Coefficient which is small
for both as this measure seem to suffer from the phenomenon called
“Concentration of Measure” or “Curse of Dimensionality” for high dimensional
datasets such as text data. Other measures such as V-measure and Adjusted Rand
Index are information theoretic based evaluation scores: as they are only based
on cluster assignments rather than distances, hence not affected by the curse
of dimensionality.</p>
<p>Note: as k-means is optimizing a non-convex objective function, it will likely
end up in a local optimum. Several runs with independent random init might be
necessary to get a good convergence.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Usage: plot_document_clustering.py [options]
Options:
-h, --help show this help message and exit
--lsa=N_COMPONENTS Preprocess documents with latent semantic analysis.
--no-minibatch Use ordinary k-means algorithm (in batch mode).
--no-idf Disable Inverse Document Frequency feature weighting.
--use-hashing Use a hashing feature vectorizer
--n-features=N_FEATURES
Maximum number of features (dimensions) to extract
from text.
--verbose Print progress reports inside k-means algorithm.
Loading 20 newsgroups dataset for categories:
['alt.atheism', 'talk.religion.misc', 'comp.graphics', 'sci.space']
3387 documents
4 categories
Extracting features from the training dataset using a sparse vectorizer
done in 0.869272s
n_samples: 3387, n_features: 10000
Clustering sparse data with MiniBatchKMeans(batch_size=1000, init_size=1000, n_clusters=4, n_init=1,
verbose=False)
done in 0.071s
Homogeneity: 0.219
Completeness: 0.338
V-measure: 0.266
Adjusted Rand-Index: 0.113
Silhouette Coefficient: 0.005
Top terms per cluster:
Cluster 0: cc ibm au buffalo monash com vnet software nicho university
Cluster 1: space nasa henry access digex toronto gov pat alaska shuttle
Cluster 2: com god university article don know graphics people posting like
Cluster 3: sgi keith livesey morality jon solntze wpd caltech objective moral
</pre></div>
</div>
<div class="line-block">
<div class="line"><br /></div>
</div>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Author: Peter Prettenhofer <[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">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.decomposition</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.decomposition.TruncatedSVD.html#sklearn.decomposition.TruncatedSVD" title="View documentation for sklearn.decomposition.TruncatedSVD"><span class="n">TruncatedSVD</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_extraction.text</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfTransformer.html#sklearn.feature_extraction.text.TfidfTransformer" title="View documentation for sklearn.feature_extraction.text.TfidfTransformer"><span class="n">TfidfTransformer</span></a>
<span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.pipeline.make_pipeline.html#sklearn.pipeline.make_pipeline" title="View documentation for sklearn.pipeline.make_pipeline"><span class="n">make_pipeline</span></a>
<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.preprocessing.Normalizer.html#sklearn.preprocessing.Normalizer" title="View documentation for sklearn.preprocessing.Normalizer"><span class="n">Normalizer</span></a>
<span class="kn">from</span> <span class="nn">sklearn</span> <span class="kn">import</span> <span class="n">metrics</span>
<span class="kn">from</span> <span class="nn">sklearn.cluster</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.cluster.KMeans.html#sklearn.cluster.KMeans" title="View documentation for sklearn.cluster.KMeans"><span class="n">KMeans</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.cluster.MiniBatchKMeans.html#sklearn.cluster.MiniBatchKMeans" title="View documentation for sklearn.cluster.MiniBatchKMeans"><span class="n">MiniBatchKMeans</span></a>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">from</span> <span class="nn">optparse</span> <span class="kn">import</span> <a href="https://docs.python.org/3/library/optparse.html#optparse.OptionParser" title="View documentation for optparse.OptionParser"><span class="n">OptionParser</span></a>
<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> <a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="c1"># Display progress logs on stdout</span>
<a href="https://docs.python.org/3/library/logging.html#logging.basicConfig" title="View documentation for logging.basicConfig"><span class="n">logging</span><span class="o">.</span><span class="n">basicConfig</span></a><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="nb">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> <a href="https://docs.python.org/3/library/optparse.html#optparse.OptionParser" title="View documentation for optparse.OptionParser"><span class="n">OptionParser</span></a><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">"--lsa"</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s2">"n_components"</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">help</span><span class="o">=</span><span class="s2">"Preprocess documents with latent semantic analysis."</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">"--no-minibatch"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_false"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"minibatch"</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Use ordinary k-means algorithm (in batch mode)."</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">"--no-idf"</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s2">"store_false"</span><span class="p">,</span> <span class="n">dest</span><span class="o">=</span><span class="s2">"use_idf"</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Disable Inverse Document Frequency feature weighting."</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">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Use a hashing feature 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="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">10000</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Maximum number of features (dimensions)"</span>
<span class="s2">" to extract from text."</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">"--verbose"</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">"verbose"</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s2">"Print progress reports inside k-means algorithm."</span><span class="p">)</span>
<span class="nb">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">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><a href="https://docs.python.org/3/library/sys.html#sys.modules" title="View documentation for sys.modules"><span class="n">sys</span><span class="o">.</span><span class="n">modules</span></a><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> <a href="https://docs.python.org/3/library/sys.html#sys.argv" title="View documentation for sys.argv"><span class="n">sys</span><span class="o">.</span><span class="n">argv</span></a><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>
<a href="https://docs.python.org/3/library/sys.html#sys.exit" title="View documentation for sys.exit"><span class="n">sys</span><span class="o">.</span><span class="n">exit</span></a><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="c1"># #############################################################################</span>
<span class="c1"># Load some categories from the training set</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="c1"># Uncomment the following to do the analysis on all the categories</span>
<span class="c1"># categories = None</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Loading 20 newsgroups dataset for categories:"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">categories</span><span class="p">)</span>
<span class="n">dataset</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">'all'</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="kc">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="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%d</span><span class="s2"> documents"</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">data</span><span class="p">))</span>
<span class="nb">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">dataset</span><span class="o">.</span><span class="n">target_names</span><span class="p">))</span>
<span class="nb">print</span><span class="p">()</span>
<span class="n">labels</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">target</span>
<span class="n">true_k</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/numpy/reference/generated/numpy.unique.html#numpy.unique" title="View documentation for numpy.unique"><span class="n">np</span><span class="o">.</span><span class="n">unique</span></a><span class="p">(</span><span class="n">labels</span><span class="p">)</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">"Extracting features from the training dataset "</span>
<span class="s2">"using a sparse vectorizer"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><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="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">use_idf</span><span class="p">:</span>
<span class="c1"># Perform an IDF normalization on the output of HashingVectorizer</span>
<span class="n">hasher</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">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">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="kc">False</span><span class="p">,</span>
<span class="n">norm</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
<span class="n">vectorizer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.pipeline.make_pipeline.html#sklearn.pipeline.make_pipeline" title="View documentation for sklearn.pipeline.make_pipeline"><span class="n">make_pipeline</span></a><span class="p">(</span><span class="n">hasher</span><span class="p">,</span> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfTransformer.html#sklearn.feature_extraction.text.TfidfTransformer" title="View documentation for sklearn.feature_extraction.text.TfidfTransformer"><span class="n">TfidfTransformer</span></a><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.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">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">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="kc">False</span><span class="p">,</span> <span class="n">norm</span><span class="o">=</span><span class="s1">'l2'</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">max_df</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">max_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">min_df</span><span class="o">=</span><span class="mi">2</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">use_idf</span><span class="o">=</span><span class="n">opts</span><span class="o">.</span><span class="n">use_idf</span><span class="p">)</span>
<span class="n">X</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">dataset</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
<span class="nb">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><a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><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">"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</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="nb">print</span><span class="p">()</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">n_components</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Performing dimensionality reduction using LSA"</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><span class="p">()</span>
<span class="c1"># Vectorizer results are normalized, which makes KMeans behave as</span>
<span class="c1"># spherical k-means for better results. Since LSA/SVD results are</span>
<span class="c1"># not normalized, we have to redo the normalization.</span>
<span class="n">svd</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.decomposition.TruncatedSVD.html#sklearn.decomposition.TruncatedSVD" title="View documentation for sklearn.decomposition.TruncatedSVD"><span class="n">TruncatedSVD</span></a><span class="p">(</span><span class="n">opts</span><span class="o">.</span><span class="n">n_components</span><span class="p">)</span>
<span class="n">normalizer</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.preprocessing.Normalizer.html#sklearn.preprocessing.Normalizer" title="View documentation for sklearn.preprocessing.Normalizer"><span class="n">Normalizer</span></a><span class="p">(</span><span class="n">copy</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="n">lsa</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.pipeline.make_pipeline.html#sklearn.pipeline.make_pipeline" title="View documentation for sklearn.pipeline.make_pipeline"><span class="n">make_pipeline</span></a><span class="p">(</span><span class="n">svd</span><span class="p">,</span> <span class="n">normalizer</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">lsa</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="nb">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><a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="n">explained_variance</span> <span class="o">=</span> <span class="n">svd</span><span class="o">.</span><span class="n">explained_variance_ratio_</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Explained variance of the SVD step: </span><span class="si">{}</span><span class="s2">%"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="nb">int</span><span class="p">(</span><span class="n">explained_variance</span> <span class="o">*</span> <span class="mi">100</span><span class="p">)))</span>
<span class="nb">print</span><span class="p">()</span>
<span class="c1"># #############################################################################</span>
<span class="c1"># Do the actual clustering</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">minibatch</span><span class="p">:</span>
<span class="n">km</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.cluster.MiniBatchKMeans.html#sklearn.cluster.MiniBatchKMeans" title="View documentation for sklearn.cluster.MiniBatchKMeans"><span class="n">MiniBatchKMeans</span></a><span class="p">(</span><span class="n">n_clusters</span><span class="o">=</span><span class="n">true_k</span><span class="p">,</span> <span class="n">init</span><span class="o">=</span><span class="s1">'k-means++'</span><span class="p">,</span> <span class="n">n_init</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">init_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="n">opts</span><span class="o">.</span><span class="n">verbose</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">km</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.cluster.KMeans.html#sklearn.cluster.KMeans" title="View documentation for sklearn.cluster.KMeans"><span class="n">KMeans</span></a><span class="p">(</span><span class="n">n_clusters</span><span class="o">=</span><span class="n">true_k</span><span class="p">,</span> <span class="n">init</span><span class="o">=</span><span class="s1">'k-means++'</span><span class="p">,</span> <span class="n">max_iter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">n_init</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">verbose</span><span class="o">=</span><span class="n">opts</span><span class="o">.</span><span class="n">verbose</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Clustering sparse data with </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">km</span><span class="p">)</span>
<span class="n">t0</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><span class="p">()</span>
<span class="n">km</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="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><a href="https://docs.python.org/3/library/time.html#time.time" title="View documentation for time.time"><span class="n">time</span></a><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="nb">print</span><span class="p">(</span><span class="s2">"Homogeneity: </span><span class="si">%0.3f</span><span class="s2">"</span> <span class="o">%</span> <a href="../../modules/generated/sklearn.metrics.homogeneity_score.html#sklearn.metrics.homogeneity_score" title="View documentation for sklearn.metrics.homogeneity_score"><span class="n">metrics</span><span class="o">.</span><span class="n">homogeneity_score</span></a><span class="p">(</span><span class="n">labels</span><span class="p">,</span> <span class="n">km</span><span class="o">.</span><span class="n">labels_</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Completeness: </span><span class="si">%0.3f</span><span class="s2">"</span> <span class="o">%</span> <a href="../../modules/generated/sklearn.metrics.completeness_score.html#sklearn.metrics.completeness_score" title="View documentation for sklearn.metrics.completeness_score"><span class="n">metrics</span><span class="o">.</span><span class="n">completeness_score</span></a><span class="p">(</span><span class="n">labels</span><span class="p">,</span> <span class="n">km</span><span class="o">.</span><span class="n">labels_</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"V-measure: </span><span class="si">%0.3f</span><span class="s2">"</span> <span class="o">%</span> <a href="../../modules/generated/sklearn.metrics.v_measure_score.html#sklearn.metrics.v_measure_score" title="View documentation for sklearn.metrics.v_measure_score"><span class="n">metrics</span><span class="o">.</span><span class="n">v_measure_score</span></a><span class="p">(</span><span class="n">labels</span><span class="p">,</span> <span class="n">km</span><span class="o">.</span><span class="n">labels_</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Adjusted Rand-Index: </span><span class="si">%.3f</span><span class="s2">"</span>
<span class="o">%</span> <a href="../../modules/generated/sklearn.metrics.adjusted_rand_score.html#sklearn.metrics.adjusted_rand_score" title="View documentation for sklearn.metrics.adjusted_rand_score"><span class="n">metrics</span><span class="o">.</span><span class="n">adjusted_rand_score</span></a><span class="p">(</span><span class="n">labels</span><span class="p">,</span> <span class="n">km</span><span class="o">.</span><span class="n">labels_</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Silhouette Coefficient: </span><span class="si">%0.3f</span><span class="s2">"</span>
<span class="o">%</span> <a href="../../modules/generated/sklearn.metrics.silhouette_score.html#sklearn.metrics.silhouette_score" title="View documentation for sklearn.metrics.silhouette_score"><span class="n">metrics</span><span class="o">.</span><span class="n">silhouette_score</span></a><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">km</span><span class="o">.</span><span class="n">labels_</span><span class="p">,</span> <span class="n">sample_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">))</span>
<span class="nb">print</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">opts</span><span class="o">.</span><span class="n">use_hashing</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Top terms per cluster:"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">opts</span><span class="o">.</span><span class="n">n_components</span><span class="p">:</span>
<span class="n">original_space_centroids</span> <span class="o">=</span> <span class="n">svd</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span><span class="n">km</span><span class="o">.</span><span class="n">cluster_centers_</span><span class="p">)</span>
<span class="n">order_centroids</span> <span class="o">=</span> <span class="n">original_space_centroids</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">order_centroids</span> <span class="o">=</span> <span class="n">km</span><span class="o">.</span><span class="n">cluster_centers_</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[:,</span> <span class="p">::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="n">terms</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">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">true_k</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Cluster </span><span class="si">%d</span><span class="s2">:"</span> <span class="o">%</span> <span class="n">i</span><span class="p">,</span> <span class="n">end</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span>
<span class="k">for</span> <span class="n">ind</span> <span class="ow">in</span> <span class="n">order_centroids</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="p">:</span><span class="mi">10</span><span class="p">]:</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">' </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">terms</span><span class="p">[</span><span class="n">ind</span><span class="p">],</span> <span class="n">end</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span>
<span class="nb">print</span><span class="p">()</span>
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 1.400 seconds)</p>
<p><strong>Estimated memory usage:</strong> 50 MB</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-text-plot-document-clustering-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn/0.22.X?urlpath=lab/tree/notebooks/auto_examples/text/plot_document_clustering.ipynb"><img alt="https://mybinder.org/badge_logo.svg" src="https://mybinder.org/badge_logo.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/a9e0daa78401c4560c040c0b1265020c/plot_document_clustering.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_document_clustering.py</span></code></a></p>
</div>
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/596995361fb1ef43bd4a8082b612aaee/plot_document_clustering.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_document_clustering.ipynb</span></code></a></p>
</div>
</div>
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.github.io">Gallery generated by Sphinx-Gallery</a></p>
</div>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2019, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/text/plot_document_clustering.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>
$(document).ready(function() {
/* Add a [>>>] button on the top-right corner of code samples to hide
* the >>> and ... prompts and the output and thus make the code
* copyable. */
var div = $('.highlight-python .highlight,' +
'.highlight-python3 .highlight,' +
'.highlight-pycon .highlight,' +
'.highlight-default .highlight')
var pre = div.find('pre');
// get the styles from the current theme
pre.parent().parent().css('position', 'relative');
var hide_text = 'Hide prompts and outputs';
var show_text = 'Show prompts and outputs';
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
if (jthis.find('.gp').length > 0) {
var button = $('<span class="copybutton">>>></span>');
button.attr('title', hide_text);
button.data('hidden', 'false');
jthis.prepend(button);
}
// tracebacks (.gt) contain bare text elements that need to be
// wrapped in a span to work with .nextUntil() (see later)
jthis.find('pre:has(.gt)').contents().filter(function() {
return ((this.nodeType == 3) && (this.data.trim().length > 0));
}).wrap('<span>');
});
// define the behavior of the button when it's clicked
$('.copybutton').click(function(e){
e.preventDefault();
var button = $(this);
if (button.data('hidden') === 'false') {
// hide the code output
button.parent().find('.go, .gp, .gt').hide();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
button.css('text-decoration', 'line-through');
button.attr('title', show_text);
button.data('hidden', 'true');
} else {
// show the code output
button.parent().find('.go, .gp, .gt').show();
button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
button.css('text-decoration', 'none');
button.attr('title', hide_text);
button.data('hidden', 'false');
}
});
/*** Add permalink buttons next to glossary terms ***/
$('dl.glossary > dt[id]').append(function() {
return ('<a class="headerlink" href="#' +
this.getAttribute('id') +
'" title="Permalink to this term">¶</a>');
});
/*** Hide navbar when scrolling down ***/
// Returns true when headerlink target matches hash in url
(function() {
hashTargetOnTop = function() {
var hash = window.location.hash;
if ( hash.length < 2 ) { return false; }
var target = document.getElementById( hash.slice(1) );
if ( target === null ) { return false; }
var top = target.getBoundingClientRect().top;
return (top < 2) && (top > -2);
};
// Hide navbar on load if hash target is on top
var navBar = document.getElementById("navbar");
var navBarToggler = document.getElementById("sk-navbar-toggler");
var navBarHeightHidden = "-" + navBar.getBoundingClientRect().height + "px";
var $window = $(window);
hideNavBar = function() {
navBar.style.top = navBarHeightHidden;
};
showNavBar = function() {
navBar.style.top = "0";
}
if (hashTargetOnTop()) {
hideNavBar()
}
var prevScrollpos = window.pageYOffset;
hideOnScroll = function(lastScrollTop) {
if (($window.width() < 768) && (navBarToggler.getAttribute("aria-expanded") === 'true')) {
return;
}
if (lastScrollTop > 2 && (prevScrollpos <= lastScrollTop) || hashTargetOnTop()){
hideNavBar()
} else {
showNavBar()
}
prevScrollpos = lastScrollTop;
};
/*** high performance scroll event listener***/
var raf = window.requestAnimationFrame ||
window.webkitRequestAnimationFrame ||
window.mozRequestAnimationFrame ||
window.msRequestAnimationFrame ||
window.oRequestAnimationFrame;
var lastScrollTop = $window.scrollTop();
if (raf) {
loop();
}
function loop() {
var scrollTop = $window.scrollTop();
if (lastScrollTop === scrollTop) {
raf(loop);
return;
} else {
lastScrollTop = scrollTop;
hideOnScroll(lastScrollTop);
raf(loop);
}
}
})();
});
</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>