-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathplot_bicluster_newsgroups.html
494 lines (429 loc) · 47.7 KB
/
plot_bicluster_newsgroups.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
<!DOCTYPE html>
<!-- data-theme below is forced to be "light" but should be changed if we use pydata-theme-sphinx in the future -->
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" data-content_root="../../" data-theme="light"> <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" data-content_root="../../" data-theme="light"> <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta property="og:title" content="Biclustering documents with the Spectral Co-clustering algorithm" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://scikit-learn/stable/auto_examples/bicluster/plot_bicluster_newsgroups.html" />
<meta property="og:site_name" content="scikit-learn" />
<meta property="og:description" content="This example demonstrates the Spectral Co-clustering algorithm on the twenty newsgroups dataset. The ‘comp.os.ms-windows.misc’ category is excluded because it contains many posts containing nothing..." />
<meta property="og:image" content="https://scikit-learn.org/stable/_static/scikit-learn-logo-small.png" />
<meta property="og:image:alt" content="scikit-learn" />
<meta name="description" content="This example demonstrates the Spectral Co-clustering algorithm on the twenty newsgroups dataset. The ‘comp.os.ms-windows.misc’ category is excluded because it contains many posts containing nothing..." />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Biclustering documents with the Spectral Co-clustering algorithm — scikit-learn 1.4.2 documentation</title>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/bicluster/plot_bicluster_newsgroups.html" />
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="stylesheet" href="../../_static/css/vendor/bootstrap.min.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../_static/copybutton.css" type="text/css" />
<link rel="stylesheet" href="../../_static/plot_directive.css" type="text/css" />
<link rel="stylesheet" href="../../https://fonts.googleapis.com/css?family=Vibur" type="text/css" />
<link rel="stylesheet" href="../../_static/jupyterlite_sphinx.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-binder.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-dataframe.css" type="text/css" />
<link rel="stylesheet" href="../../_static/sg_gallery-rendered-html.css" type="text/css" />
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
<script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
<script src="../../_static/js/vendor/jquery-3.6.3.slim.min.js"></script>
<script src="../../_static/js/details-permalink.js"></script>
</head>
<body>
<nav id="navbar" class="sk-docs-navbar navbar navbar-expand-md navbar-light bg-light py-0">
<div class="container-fluid sk-docs-container px-0">
<a class="navbar-brand py-0" href="../../index.html">
<img
class="sk-brand-img"
src="../../_static/scikit-learn-logo-small.png"
alt="logo"/>
</a>
<button
id="sk-navbar-toggler"
class="navbar-toggler"
type="button"
data-toggle="collapse"
data-target="#navbarSupportedContent"
aria-controls="navbarSupportedContent"
aria-expanded="false"
aria-label="Toggle navigation"
>
<span class="navbar-toggler-icon"></span>
</button>
<div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav mr-auto">
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../install.html">Install</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../user_guide.html">User Guide</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../../modules/classes.html">API</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" href="../index.html">Examples</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://blog.scikit-learn.org/">Community</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../getting_started.html" >Getting Started</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../tutorial/index.html" >Tutorial</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../whats_new/v1.4.html" >What's new</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../glossary.html" >Glossary</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../faq.html" >FAQ</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../support.html" >Support</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../related_projects.html" >Related packages</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../roadmap.html" >Roadmap</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../governance.html" >Governance</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="../../about.html" >About us</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
</li>
<li class="nav-item">
<a class="sk-nav-link nav-link nav-more-item-mobile-items" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</li>
<li class="nav-item dropdown nav-more-item-dropdown">
<a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a>
<div class="dropdown-menu" aria-labelledby="navbarDropdown">
<a class="sk-nav-dropdown-item dropdown-item" href="../../getting_started.html" >Getting Started</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../tutorial/index.html" >Tutorial</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../whats_new/v1.4.html" >What's new</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../glossary.html" >Glossary</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/developers/index.html" target="_blank" rel="noopener noreferrer">Development</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../faq.html" >FAQ</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../support.html" >Support</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../related_projects.html" >Related packages</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../roadmap.html" >Roadmap</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../governance.html" >Governance</a>
<a class="sk-nav-dropdown-item dropdown-item" href="../../about.html" >About us</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://github.com/scikit-learn/scikit-learn" >GitHub</a>
<a class="sk-nav-dropdown-item dropdown-item" href="https://scikit-learn.org/dev/versions.html" >Other Versions and Download</a>
</div>
</li>
</ul>
<div id="searchbox" role="search">
<div class="searchformwrapper">
<form class="search" action="../../search.html" method="get">
<input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
<input class="sk-search-text-btn" type="submit" value="Go" />
</form>
</div>
</div>
</div>
</div>
</nav>
<div class="d-flex" id="sk-doc-wrapper">
<input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
<label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
<div id="sk-sidebar-wrapper" class="border-right">
<div class="sk-sidebar-toc-wrapper">
<div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
<a href="plot_spectral_coclustering.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="A demo of the Spectral Co-Clustering algorithm">Prev</a><a href="index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Biclustering">Up</a>
<a href="../calibration/index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Calibration">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 1.4.2</strong><br/>
<a href="https://scikit-learn.org/dev/versions.html">Other versions</a>
</p>
</div>
<div class="alert alert-warning p-1 mb-2" role="alert">
<p class="text-center mb-0">
Please <a class="font-weight-bold" href="../../about.html#citing-scikit-learn"><string>cite us</string></a> if you use the software.
</p>
</div>
<div class="sk-sidebar-toc">
<ul>
<li><a class="reference internal" href="#">Biclustering documents with the Spectral Co-clustering algorithm</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><a class="reference internal" href="#sphx-glr-download-auto-examples-bicluster-plot-bicluster-newsgroups-py"><span class="std std-ref">Go to the end</span></a>
to download the full example code or to run this example in your browser via JupyterLite or Binder</p>
</div>
<section class="sphx-glr-example-title" id="biclustering-documents-with-the-spectral-co-clustering-algorithm">
<span id="sphx-glr-auto-examples-bicluster-plot-bicluster-newsgroups-py"></span><h1>Biclustering documents with the Spectral Co-clustering algorithm<a class="headerlink" href="#biclustering-documents-with-the-spectral-co-clustering-algorithm" title="Link to this heading">¶</a></h1>
<p>This example demonstrates the Spectral Co-clustering algorithm on the
twenty newsgroups dataset. The ‘comp.os.ms-windows.misc’ category is
excluded because it contains many posts containing nothing but data.</p>
<p>The TF-IDF vectorized posts form a word frequency matrix, which is
then biclustered using Dhillon’s Spectral Co-Clustering algorithm. The
resulting document-word biclusters indicate subsets words used more
often in those subsets documents.</p>
<p>For a few of the best biclusters, its most common document categories
and its ten most important words get printed. The best biclusters are
determined by their normalized cut. The best words are determined by
comparing their sums inside and outside the bicluster.</p>
<p>For comparison, the documents are also clustered using
MiniBatchKMeans. The document clusters derived from the biclusters
achieve a better V-measure than clusters found by MiniBatchKMeans.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Vectorizing...
Coclustering...
Done in 1.31s. V-measure: 0.4415
MiniBatchKMeans...
Done in 2.07s. V-measure: 0.3015
Best biclusters:
----------------
bicluster 0 : 8 documents, 6 words
categories : 100% talk.politics.mideast
words : cosmo, angmar, alfalfa, alphalpha, proline, benson
bicluster 1 : 1948 documents, 4325 words
categories : 23% talk.politics.guns, 18% talk.politics.misc, 17% sci.med
words : gun, guns, geb, banks, gordon, clinton, pitt, cdt, surrender, veal
bicluster 2 : 1259 documents, 3534 words
categories : 27% soc.religion.christian, 25% talk.politics.mideast, 25% alt.atheism
words : god, jesus, christians, kent, sin, objective, belief, christ, faith, moral
bicluster 3 : 775 documents, 1623 words
categories : 30% comp.windows.x, 25% comp.sys.ibm.pc.hardware, 20% comp.graphics
words : scsi, nada, ide, vga, esdi, isa, kth, s3, vlb, bmug
bicluster 4 : 2180 documents, 2802 words
categories : 18% comp.sys.mac.hardware, 16% sci.electronics, 16% comp.sys.ibm.pc.hardware
words : voltage, shipping, circuit, receiver, processing, scope, mpce, analog, kolstad, umass
</pre></div>
</div>
<div class="line-block">
<div class="line"><br /></div>
</div>
<div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">operator</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <a href="https://docs.python.org/3/library/collections.html#collections.defaultdict" title="collections.defaultdict" class="sphx-glr-backref-module-collections sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">defaultdict</span></a>
<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="time.time" class="sphx-glr-backref-module-time sphx-glr-backref-type-py-function"><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="kn">from</span> <span class="nn">sklearn.cluster</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.cluster.MiniBatchKMeans.html#sklearn.cluster.MiniBatchKMeans" title="sklearn.cluster.MiniBatchKMeans" class="sphx-glr-backref-module-sklearn-cluster sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MiniBatchKMeans</span></a><span class="p">,</span> <a href="../../modules/generated/sklearn.cluster.SpectralCoclustering.html#sklearn.cluster.SpectralCoclustering" title="sklearn.cluster.SpectralCoclustering" class="sphx-glr-backref-module-sklearn-cluster sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">SpectralCoclustering</span></a>
<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="sklearn.datasets.fetch_20newsgroups" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><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="sklearn.feature_extraction.text.TfidfVectorizer" class="sphx-glr-backref-module-sklearn-feature_extraction-text sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">TfidfVectorizer</span></a>
<span class="kn">from</span> <span class="nn">sklearn.metrics.cluster</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.metrics.v_measure_score.html#sklearn.metrics.v_measure_score" title="sklearn.metrics.v_measure_score" class="sphx-glr-backref-module-sklearn-metrics sphx-glr-backref-type-py-function"><span class="n">v_measure_score</span></a>
<span class="k">def</span> <span class="nf">number_normalizer</span><span class="p">(</span><span class="n">tokens</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Map all numeric tokens to a placeholder.</span>
<span class="sd"> For many applications, tokens that begin with a number are not directly</span>
<span class="sd"> useful, but the fact that such a token exists can be relevant. By applying</span>
<span class="sd"> this form of dimensionality reduction, some methods may perform better.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span><span class="s2">"#NUMBER"</span> <span class="k">if</span> <span class="n">token</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">isdigit</span><span class="p">()</span> <span class="k">else</span> <span class="n">token</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">NumberNormalizingVectorizer</span><span class="p">(</span><a href="../../modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer" title="sklearn.feature_extraction.text.TfidfVectorizer" class="sphx-glr-backref-module-sklearn-feature_extraction-text sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">TfidfVectorizer</span></a><span class="p">):</span>
<span class="k">def</span> <span class="nf">build_tokenizer</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">tokenize</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">build_tokenizer</span><span class="p">()</span>
<span class="k">return</span> <span class="k">lambda</span> <span class="n">doc</span><span class="p">:</span> <span class="nb">list</span><span class="p">(</span><span class="n">number_normalizer</span><span class="p">(</span><span class="n">tokenize</span><span class="p">(</span><span class="n">doc</span><span class="p">)))</span>
<span class="c1"># exclude 'comp.os.ms-windows.misc'</span>
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">"alt.atheism"</span><span class="p">,</span>
<span class="s2">"comp.graphics"</span><span class="p">,</span>
<span class="s2">"comp.sys.ibm.pc.hardware"</span><span class="p">,</span>
<span class="s2">"comp.sys.mac.hardware"</span><span class="p">,</span>
<span class="s2">"comp.windows.x"</span><span class="p">,</span>
<span class="s2">"misc.forsale"</span><span class="p">,</span>
<span class="s2">"rec.autos"</span><span class="p">,</span>
<span class="s2">"rec.motorcycles"</span><span class="p">,</span>
<span class="s2">"rec.sport.baseball"</span><span class="p">,</span>
<span class="s2">"rec.sport.hockey"</span><span class="p">,</span>
<span class="s2">"sci.crypt"</span><span class="p">,</span>
<span class="s2">"sci.electronics"</span><span class="p">,</span>
<span class="s2">"sci.med"</span><span class="p">,</span>
<span class="s2">"sci.space"</span><span class="p">,</span>
<span class="s2">"soc.religion.christian"</span><span class="p">,</span>
<span class="s2">"talk.politics.guns"</span><span class="p">,</span>
<span class="s2">"talk.politics.mideast"</span><span class="p">,</span>
<span class="s2">"talk.politics.misc"</span><span class="p">,</span>
<span class="s2">"talk.religion.misc"</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">newsgroups</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.datasets.fetch_20newsgroups.html#sklearn.datasets.fetch_20newsgroups" title="sklearn.datasets.fetch_20newsgroups" class="sphx-glr-backref-module-sklearn-datasets sphx-glr-backref-type-py-function"><span class="n">fetch_20newsgroups</span></a><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">y_true</span> <span class="o">=</span> <span class="n">newsgroups</span><span class="o">.</span><span class="n">target</span>
<span class="n">vectorizer</span> <span class="o">=</span> <span class="n">NumberNormalizingVectorizer</span><span class="p">(</span><span class="n">stop_words</span><span class="o">=</span><span class="s2">"english"</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
<span class="n">cocluster</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.cluster.SpectralCoclustering.html#sklearn.cluster.SpectralCoclustering" title="sklearn.cluster.SpectralCoclustering" class="sphx-glr-backref-module-sklearn-cluster sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">SpectralCoclustering</span></a><span class="p">(</span>
<span class="n">n_clusters</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="n">svd_method</span><span class="o">=</span><span class="s2">"arpack"</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span>
<span class="p">)</span>
<span class="n">kmeans</span> <span class="o">=</span> <a href="../../modules/generated/sklearn.cluster.MiniBatchKMeans.html#sklearn.cluster.MiniBatchKMeans" title="sklearn.cluster.MiniBatchKMeans" class="sphx-glr-backref-module-sklearn-cluster sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">MiniBatchKMeans</span></a><span class="p">(</span>
<span class="n">n_clusters</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="n">batch_size</span><span class="o">=</span><span class="mi">20000</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">n_init</span><span class="o">=</span><span class="mi">3</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Vectorizing..."</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">newsgroups</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">"Coclustering..."</span><span class="p">)</span>
<span class="n">start_time</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/time.html#time.time" title="time.time" class="sphx-glr-backref-module-time sphx-glr-backref-type-py-function"><span class="n">time</span></a><span class="p">()</span>
<span class="n">cocluster</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>
<span class="n">y_cocluster</span> <span class="o">=</span> <span class="n">cocluster</span><span class="o">.</span><span class="n">row_labels_</span>
<span class="nb">print</span><span class="p">(</span>
<span class="s2">"Done in </span><span class="si">{:.2f}</span><span class="s2">s. V-measure: </span><span class="si">{:.4f}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<a href="https://docs.python.org/3/library/time.html#time.time" title="time.time" class="sphx-glr-backref-module-time sphx-glr-backref-type-py-function"><span class="n">time</span></a><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span><span class="p">,</span> <a href="../../modules/generated/sklearn.metrics.v_measure_score.html#sklearn.metrics.v_measure_score" title="sklearn.metrics.v_measure_score" class="sphx-glr-backref-module-sklearn-metrics sphx-glr-backref-type-py-function"><span class="n">v_measure_score</span></a><span class="p">(</span><span class="n">y_cocluster</span><span class="p">,</span> <span class="n">y_true</span><span class="p">)</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"MiniBatchKMeans..."</span><span class="p">)</span>
<span class="n">start_time</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/time.html#time.time" title="time.time" class="sphx-glr-backref-module-time sphx-glr-backref-type-py-function"><span class="n">time</span></a><span class="p">()</span>
<span class="n">y_kmeans</span> <span class="o">=</span> <span class="n">kmeans</span><span class="o">.</span><span class="n">fit_predict</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">{:.2f}</span><span class="s2">s. V-measure: </span><span class="si">{:.4f}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<a href="https://docs.python.org/3/library/time.html#time.time" title="time.time" class="sphx-glr-backref-module-time sphx-glr-backref-type-py-function"><span class="n">time</span></a><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span><span class="p">,</span> <a href="../../modules/generated/sklearn.metrics.v_measure_score.html#sklearn.metrics.v_measure_score" title="sklearn.metrics.v_measure_score" class="sphx-glr-backref-module-sklearn-metrics sphx-glr-backref-type-py-function"><span class="n">v_measure_score</span></a><span class="p">(</span><span class="n">y_kmeans</span><span class="p">,</span> <span class="n">y_true</span><span class="p">)</span>
<span class="p">)</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_out</span><span class="p">()</span>
<span class="n">document_names</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">newsgroups</span><span class="o">.</span><span class="n">target_names</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">newsgroups</span><span class="o">.</span><span class="n">target</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">bicluster_ncut</span><span class="p">(</span><span class="n">i</span><span class="p">):</span>
<span class="n">rows</span><span class="p">,</span> <span class="n">cols</span> <span class="o">=</span> <span class="n">cocluster</span><span class="o">.</span><span class="n">get_indices</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.any.html#numpy.any" title="numpy.any" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">any</span></a><span class="p">(</span><span class="n">rows</span><span class="p">)</span> <span class="ow">and</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.any.html#numpy.any" title="numpy.any" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">any</span></a><span class="p">(</span><span class="n">cols</span><span class="p">)):</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="k">return</span> <span class="n">sys</span><span class="o">.</span><span class="n">float_info</span><span class="o">.</span><span class="n">max</span>
<span class="n">row_complement</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.nonzero.html#numpy.nonzero" title="numpy.nonzero" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">nonzero</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.logical_not.html#numpy.logical_not" title="numpy.logical_not" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">logical_not</span></a><span class="p">(</span><span class="n">cocluster</span><span class="o">.</span><span class="n">rows_</span><span class="p">[</span><span class="n">i</span><span class="p">]))[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">col_complement</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.nonzero.html#numpy.nonzero" title="numpy.nonzero" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">nonzero</span></a><span class="p">(</span><a href="https://numpy.org/doc/stable/reference/generated/numpy.logical_not.html#numpy.logical_not" title="numpy.logical_not" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-data"><span class="n">np</span><span class="o">.</span><span class="n">logical_not</span></a><span class="p">(</span><span class="n">cocluster</span><span class="o">.</span><span class="n">columns_</span><span class="p">[</span><span class="n">i</span><span class="p">]))[</span><span class="mi">0</span><span class="p">]</span>
<span class="c1"># Note: the following is identical to X[rows[:, np.newaxis],</span>
<span class="c1"># cols].sum() but much faster in scipy <= 0.16</span>
<span class="n">weight</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="n">rows</span><span class="p">][:,</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="n">cut</span> <span class="o">=</span> <span class="n">X</span><span class="p">[</span><span class="n">row_complement</span><span class="p">][:,</span> <span class="n">cols</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">+</span> <span class="n">X</span><span class="p">[</span><span class="n">rows</span><span class="p">][:,</span> <span class="n">col_complement</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="k">return</span> <span class="n">cut</span> <span class="o">/</span> <span class="n">weight</span>
<span class="k">def</span> <span class="nf">most_common</span><span class="p">(</span><span class="n">d</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Items of a defaultdict(int) with the highest values.</span>
<span class="sd"> Like Counter.most_common in Python >=2.7.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">d</span><span class="o">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><a href="https://docs.python.org/3/library/operator.html#operator.itemgetter" title="operator.itemgetter" class="sphx-glr-backref-module-operator sphx-glr-backref-type-py-function"><span class="n">operator</span><span class="o">.</span><span class="n">itemgetter</span></a><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">bicluster_ncuts</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">bicluster_ncut</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">newsgroups</span><span class="o">.</span><span class="n">target_names</span><span class="p">)))</span>
<span class="n">best_idx</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.argsort.html#numpy.argsort" title="numpy.argsort" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">argsort</span></a><span class="p">(</span><span class="n">bicluster_ncuts</span><span class="p">)[:</span><span class="mi">5</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">"Best biclusters:"</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"----------------"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">cluster</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">best_idx</span><span class="p">):</span>
<span class="n">n_rows</span><span class="p">,</span> <span class="n">n_cols</span> <span class="o">=</span> <span class="n">cocluster</span><span class="o">.</span><span class="n">get_shape</span><span class="p">(</span><span class="n">cluster</span><span class="p">)</span>
<span class="n">cluster_docs</span><span class="p">,</span> <span class="n">cluster_words</span> <span class="o">=</span> <span class="n">cocluster</span><span class="o">.</span><span class="n">get_indices</span><span class="p">(</span><span class="n">cluster</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">len</span><span class="p">(</span><span class="n">cluster_docs</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">len</span><span class="p">(</span><span class="n">cluster_words</span><span class="p">):</span>
<span class="k">continue</span>
<span class="c1"># categories</span>
<span class="n">counter</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/collections.html#collections.defaultdict" title="collections.defaultdict" class="sphx-glr-backref-module-collections sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">defaultdict</span></a><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">cluster_docs</span><span class="p">:</span>
<span class="n">counter</span><span class="p">[</span><span class="n">document_names</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="n">cat_string</span> <span class="o">=</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
<span class="s2">"</span><span class="si">{:.0f}</span><span class="s2">% </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">float</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="o">/</span> <span class="n">n_rows</span> <span class="o">*</span> <span class="mi">100</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
<span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">most_common</span><span class="p">(</span><span class="n">counter</span><span class="p">)[:</span><span class="mi">3</span><span class="p">]</span>
<span class="p">)</span>
<span class="c1"># words</span>
<span class="n">out_of_cluster_docs</span> <span class="o">=</span> <span class="n">cocluster</span><span class="o">.</span><span class="n">row_labels_</span> <span class="o">!=</span> <span class="n">cluster</span>
<span class="n">out_of_cluster_docs</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.where.html#numpy.where" title="numpy.where" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">where</span></a><span class="p">(</span><span class="n">out_of_cluster_docs</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">word_col</span> <span class="o">=</span> <span class="n">X</span><span class="p">[:,</span> <span class="n">cluster_words</span><span class="p">]</span>
<span class="n">word_scores</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.array.html#numpy.array" title="numpy.array" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">array</span></a><span class="p">(</span>
<span class="n">word_col</span><span class="p">[</span><span class="n">cluster_docs</span><span class="p">,</span> <span class="p">:]</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="o">-</span> <span class="n">word_col</span><span class="p">[</span><span class="n">out_of_cluster_docs</span><span class="p">,</span> <span class="p">:]</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">word_scores</span> <span class="o">=</span> <span class="n">word_scores</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="n">important_words</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span>
<span class="n">feature_names</span><span class="p">[</span><span class="n">cluster_words</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">word_scores</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[:</span><span class="o">-</span><span class="mi">11</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"bicluster </span><span class="si">{}</span><span class="s2"> : </span><span class="si">{}</span><span class="s2"> documents, </span><span class="si">{}</span><span class="s2"> words"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">idx</span><span class="p">,</span> <span class="n">n_rows</span><span class="p">,</span> <span class="n">n_cols</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"categories : </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">cat_string</span><span class="p">))</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"words : </span><span class="si">{}</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">format</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">important_words</span><span class="p">)))</span>
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 12.913 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-bicluster-plot-bicluster-newsgroups-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.4.X?urlpath=lab/tree/notebooks/auto_examples/bicluster/plot_bicluster_newsgroups.ipynb"><img alt="Launch binder" src="../../_images/binder_badge_logo1.svg" width="150px" /></a>
</div>
<div class="lite-badge docutils container">
<a class="reference external image-reference" href="../../lite/lab/?path=auto_examples/bicluster/plot_bicluster_newsgroups.ipynb"><img alt="Launch JupyterLite" src="../../_images/jupyterlite_badge_logo1.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/3f7191b01d0103d1886c959ed7687c4d/plot_bicluster_newsgroups.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_bicluster_newsgroups.ipynb</span></code></a></p>
</div>
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e68419b513284db108081422c73a5667/plot_bicluster_newsgroups.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_bicluster_newsgroups.py</span></code></a></p>
</div>
</div>
<p class="rubric">Related examples</p>
<div class="sphx-glr-thumbnails"><div class="sphx-glr-thumbcontainer" tooltip="This is an example showing how scikit-learn can be used to classify documents by topics using a..."><img alt="" src="../../_images/sphx_glr_plot_document_classification_20newsgroups_thumb.png" />
<p><a class="reference internal" href="../text/plot_document_classification_20newsgroups.html#sphx-glr-auto-examples-text-plot-document-classification-20newsgroups-py"><span class="std std-ref">Classification of text documents using sparse features</span></a></p>
<div class="sphx-glr-thumbnail-title">Classification of text documents using sparse features</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This is an example showing how the scikit-learn API can be used to cluster documents by topics ..."><img alt="" src="../../_images/sphx_glr_plot_document_clustering_thumb.png" />
<p><a class="reference internal" href="../text/plot_document_clustering.html#sphx-glr-auto-examples-text-plot-document-clustering-py"><span class="std std-ref">Clustering text documents using k-means</span></a></p>
<div class="sphx-glr-thumbnail-title">Clustering text documents using k-means</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In this example, semi-supervised classifiers are trained on the 20 newsgroups dataset (which wi..."><img alt="" src="../../_images/sphx_glr_plot_semi_supervised_newsgroups_thumb.png" />
<p><a class="reference internal" href="../semi_supervised/plot_semi_supervised_newsgroups.html#sphx-glr-auto-examples-semi-supervised-plot-semi-supervised-newsgroups-py"><span class="std std-ref">Semi-supervised Classification on a Text Dataset</span></a></p>
<div class="sphx-glr-thumbnail-title">Semi-supervised Classification on a Text Dataset</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="In this example we illustrate text vectorization, which is the process of representing non-nume..."><img alt="" src="../../_images/sphx_glr_plot_hashing_vs_dict_vectorizer_thumb.png" />
<p><a class="reference internal" href="../text/plot_hashing_vs_dict_vectorizer.html#sphx-glr-auto-examples-text-plot-hashing-vs-dict-vectorizer-py"><span class="std std-ref">FeatureHasher and DictVectorizer Comparison</span></a></p>
<div class="sphx-glr-thumbnail-title">FeatureHasher and DictVectorizer Comparison</div>
</div><div class="sphx-glr-thumbcontainer" tooltip="This example demonstrates how to generate a dataset and bicluster it using the Spectral Co-Clus..."><img alt="" src="../../_images/sphx_glr_plot_spectral_coclustering_thumb.png" />
<p><a class="reference internal" href="plot_spectral_coclustering.html#sphx-glr-auto-examples-bicluster-plot-spectral-coclustering-py"><span class="std std-ref">A demo of the Spectral Co-Clustering algorithm</span></a></p>
<div class="sphx-glr-thumbnail-title">A demo of the Spectral Co-Clustering algorithm</div>
</div></div><p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.github.io">Gallery generated by Sphinx-Gallery</a></p>
</section>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2024, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/bicluster/plot_bicluster_newsgroups.rst.txt" rel="nofollow">Show this page source</a>
</footer>
</div>
</div>
</div>
<script src="../../_static/js/vendor/bootstrap.min.js"></script>
<script>
window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date;
ga('create', 'UA-22606712-2', 'auto');
ga('set', 'anonymizeIp', true);
ga('send', 'pageview');
</script>
<script async src='https://www.google-analytics.com/analytics.js'></script>
<script defer data-domain="scikit-learn.org" src="https://views.scientific-python.org/js/script.js">
</script>
<script src="../../_static/clipboard.min.js"></script>
<script src="../../_static/copybutton.js"></script>
<script>
$(document).ready(function() {
/* Add a [>>>] button on the top-right corner of code samples to hide
* the >>> and ... prompts and the output and thus make the code
* copyable. */
var div = $('.highlight-python .highlight,' +
'.highlight-python3 .highlight,' +
'.highlight-pycon .highlight,' +
'.highlight-default .highlight')
var pre = div.find('pre');
// get the styles from the current theme
pre.parent().parent().css('position', 'relative');
// create and add the button to all the code blocks that contain >>>
div.each(function(index) {
var jthis = $(this);
// tracebacks (.gt) contain bare text elements that need to be
// wrapped in a span to work with .nextUntil() (see later)
jthis.find('pre:has(.gt)').contents().filter(function() {
return ((this.nodeType == 3) && (this.data.trim().length > 0));
}).wrap('<span>');
});
/*** Add permalink buttons next to glossary terms ***/
$('dl.glossary > dt[id]').append(function() {
return ('<a class="headerlink" href="#' +
this.getAttribute('id') +
'" title="Permalink to this term">¶</a>');
});
});
</script>
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>