-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathbicluster_newsgroups.html
396 lines (327 loc) · 33.5 KB
/
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
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>Biclustering documents with the Spectral Co-clustering algorithm — scikit-learn 0.17.1 documentation</title>
<!-- htmltitle is before nature.css - we use this hack to load bootstrap first -->
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="stylesheet" href="../../_static/css/bootstrap.min.css" media="screen" />
<link rel="stylesheet" href="../../_static/css/bootstrap-responsive.css"/>
<link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../_static/gallery.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../',
VERSION: '0.17.1',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true
};
</script>
<script type="text/javascript" src="../../_static/jquery.js"></script>
<script type="text/javascript" src="../../_static/underscore.js"></script>
<script type="text/javascript" src="../../_static/doctools.js"></script>
<script type="text/javascript" src="../../_static/js/copybutton.js"></script>
<link rel="shortcut icon" href="../../_static/favicon.ico"/>
<link rel="author" title="About these documents" href="../../about.html" />
<link rel="top" title="scikit-learn 0.17.1 documentation" href="../../index.html" />
<link rel="up" title="Examples" href="../index.html" />
<link rel="next" title="Comparison of Calibration of Classifiers" href="../calibration/plot_compare_calibration.html" />
<link rel="prev" title="A demo of the Spectral Biclustering algorithm" href="plot_spectral_biclustering.html" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<script src="../../_static/js/bootstrap.min.js" type="text/javascript"></script>
<link rel="canonical" href="https://scikit-learn.org/stable/auto_examples/bicluster/bicluster_newsgroups.html" />
<script type="text/javascript">
$("div.buttonNext, div.buttonPrevious").hover(
function () {
$(this).css('background-color', '#FF9C34');
},
function () {
$(this).css('background-color', '#A7D6E2');
}
);
</script>
</head>
<body role="document">
<div class="header-wrapper">
<div class="header">
<p class="logo"><a href="../../index.html">
<img src="../../_static/scikit-learn-logo-small.png" alt="Logo"/>
</a>
</p><div class="navbar">
<ul>
<li><a href="../../index.html">Home</a></li>
<li><a href="../../install.html">Installation</a></li>
<li class="btn-li"><div class="btn-group">
<a href="../../documentation.html">Documentation</a>
<a class="btn dropdown-toggle" data-toggle="dropdown">
<span class="caret"></span>
</a>
<ul class="dropdown-menu">
<li class="link-title">Scikit-learn 0.17 (stable)</li>
<li><a href="../../tutorial/index.html">Tutorials</a></li>
<li><a href="../../user_guide.html">User guide</a></li>
<li><a href="../../modules/classes.html">API</a></li>
<li><a href="../../faq.html">FAQ</a></li>
<li><a href="../../developers/contributing.html">Contributing</a></li>
<li class="divider"></li>
<li><a href="http://scikit-learn.org/dev/documentation.html">Scikit-learn 0.18 (development)</a></li>
<li><a href="http://scikit-learn.org/0.16/documentation.html">Scikit-learn 0.16</a></li>
<li><a href="../../_downloads/scikit-learn-docs.pdf">PDF documentation</a></li>
</ul>
</div>
</li>
<li><a href="../index.html">Examples</a></li>
</ul>
<div class="search_form">
<div id="cse" style="width: 100%;"></div>
</div>
</div> <!-- end navbar --></div>
</div>
<!-- Github "fork me" ribbon -->
<a href="https://github.com/scikit-learn/scikit-learn">
<img class="fork-me"
style="position: absolute; top: 0; right: 0; border: 0;"
src="../../_static/img/forkme.png"
alt="Fork me on GitHub" />
</a>
<div class="content-wrapper">
<div class="sphinxsidebar">
<div class="sphinxsidebarwrapper">
<div class="rel">
<!-- rellinks[1:] is an ugly hack to avoid link to module
index -->
<div class="rellink">
<a href="plot_spectral_biclustering.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
A demo of the...
</span>
<span class="hiddenrellink">
A demo of the Spectral Biclustering algorithm
</span>
</a>
</div>
<!-- Ad a link to the 'up' page -->
<div class="spacer">
</div>
<div class="rellink">
<a href="../index.html">
Up
<br/>
<span class="smallrellink">
Examples
</span>
<span class="hiddenrellink">
Examples
</span>
</a>
</div>
</div>
<p class="doc-version">This documentation is for scikit-learn <strong>version 0.17.1</strong> — <a href="http://scikit-learn.org/stable/support.html#documentation-resources">Other versions</a></p>
<p class="citing">If you use the software, please consider <a href="../../about.html#citing-scikit-learn">citing scikit-learn</a>.</p>
<ul>
<li><a class="reference internal" href="#">Biclustering documents with the Spectral Co-clustering algorithm</a></li>
</ul>
</div>
</div>
<input type="checkbox" id="nav-trigger" class="nav-trigger" checked />
<label for="nav-trigger"></label>
<div class="content">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<div class="section" id="biclustering-documents-with-the-spectral-co-clustering-algorithm">
<span id="example-bicluster-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="Permalink to this headline">¶</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>
<p>Output:</p>
<div class="highlight-python"><div class="highlight"><pre>Vectorizing...
Coclustering...
Done in 9.53s. V-measure: 0.4455
MiniBatchKMeans...
Done in 12.00s. V-measure: 0.3309
Best biclusters:
----------------
bicluster 0 : 1951 documents, 4373 words
categories : 23% talk.politics.guns, 19% talk.politics.misc, 14% sci.med
words : gun, guns, geb, banks, firearms, drugs, gordon, clinton, cdt, amendment
bicluster 1 : 1165 documents, 3304 words
categories : 29% talk.politics.mideast, 26% soc.religion.christian, 25% alt.atheism
words : god, jesus, christians, atheists, kent, sin, morality, belief, resurrection, marriage
bicluster 2 : 2219 documents, 2830 words
categories : 18% comp.sys.mac.hardware, 16% comp.sys.ibm.pc.hardware, 16% comp.graphics
words : voltage, dsp, board, receiver, circuit, shipping, packages, stereo, compression, package
bicluster 3 : 1860 documents, 2745 words
categories : 26% rec.motorcycles, 23% rec.autos, 13% misc.forsale
words : bike, car, dod, engine, motorcycle, ride, honda, cars, bmw, bikes
bicluster 4 : 12 documents, 155 words
categories : 100% rec.sport.hockey
words : scorer, unassisted, reichel, semak, sweeney, kovalenko, ricci, audette, momesso, nedved
</pre></div>
</div>
<p><strong>Python source code:</strong> <a class="reference download internal" href="../../_downloads/bicluster_newsgroups.py"><code class="xref download docutils literal"><span class="pre">bicluster_newsgroups.py</span></code></a></p>
<div class="highlight-python"><div class="highlight"><pre><span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="k">print</span><span class="p">(</span><span class="n">__doc__</span><span class="p">)</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">defaultdict</span>
<span class="kn">import</span> <span class="nn">operator</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">time</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">sklearn.cluster.bicluster</span> <span class="kn">import</span> <span class="n">SpectralCoclustering</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"><span class="n">MiniBatchKMeans</span></a>
<span class="kn">from</span> <span class="nn">sklearn.externals.six</span> <span class="kn">import</span> <span class="n">iteritems</span>
<span class="kn">from</span> <span class="nn">sklearn.datasets.twenty_newsgroups</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.datasets.fetch_20newsgroups.html#sklearn.datasets.fetch_20newsgroups"><span class="n">fetch_20newsgroups</span></a>
<span class="kn">from</span> <span class="nn">sklearn.feature_extraction.text</span> <span class="kn">import</span> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer"><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"><span class="n">v_measure_score</span></a>
<span class="k">def</span> <span class="nf">number_aware_tokenizer</span><span class="p">(</span><span class="n">doc</span><span class="p">):</span>
<span class="sd">""" Tokenizer that maps 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="n">token_pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="s1">u'(?u)</span><span class="se">\\</span><span class="s1">b</span><span class="se">\\</span><span class="s1">w</span><span class="se">\\</span><span class="s1">w+</span><span class="se">\\</span><span class="s1">b'</span><span class="p">)</span>
<span class="n">tokens</span> <span class="o">=</span> <span class="n">token_pattern</span><span class="o">.</span><span class="n">findall</span><span class="p">(</span><span class="n">doc</span><span class="p">)</span>
<span class="n">tokens</span> <span class="o">=</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="ow">in</span> <span class="s2">"0123456789_"</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">return</span> <span class="n">tokens</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="s1">'alt.atheism'</span><span class="p">,</span> <span class="s1">'comp.graphics'</span><span class="p">,</span>
<span class="s1">'comp.sys.ibm.pc.hardware'</span><span class="p">,</span> <span class="s1">'comp.sys.mac.hardware'</span><span class="p">,</span>
<span class="s1">'comp.windows.x'</span><span class="p">,</span> <span class="s1">'misc.forsale'</span><span class="p">,</span> <span class="s1">'rec.autos'</span><span class="p">,</span>
<span class="s1">'rec.motorcycles'</span><span class="p">,</span> <span class="s1">'rec.sport.baseball'</span><span class="p">,</span>
<span class="s1">'rec.sport.hockey'</span><span class="p">,</span> <span class="s1">'sci.crypt'</span><span class="p">,</span> <span class="s1">'sci.electronics'</span><span class="p">,</span>
<span class="s1">'sci.med'</span><span class="p">,</span> <span class="s1">'sci.space'</span><span class="p">,</span> <span class="s1">'soc.religion.christian'</span><span class="p">,</span>
<span class="s1">'talk.politics.guns'</span><span class="p">,</span> <span class="s1">'talk.politics.mideast'</span><span class="p">,</span>
<span class="s1">'talk.politics.misc'</span><span class="p">,</span> <span class="s1">'talk.religion.misc'</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"><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> <a href="../../modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer"><span class="n">TfidfVectorizer</span></a><span class="p">(</span><span class="n">stop_words</span><span class="o">=</span><span class="s1">'english'</span><span class="p">,</span> <span class="n">min_df</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">tokenizer</span><span class="o">=</span><span class="n">number_aware_tokenizer</span><span class="p">)</span>
<span class="n">cocluster</span> <span class="o">=</span> <span class="n">SpectralCoclustering</span><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="s1">'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"><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="k">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="k">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> <span class="n">time</span><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="k">print</span><span class="p">(</span><span class="s2">"Done in {:.2f}s. V-measure: {:.4f}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">time</span><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"><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="k">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> <span class="n">time</span><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="k">print</span><span class="p">(</span><span class="s2">"Done in {:.2f}s. V-measure: {:.4f}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">time</span><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"><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="n">feature_names</span> <span class="o">=</span> <span class="n">vectorizer</span><span class="o">.</span><span class="n">get_feature_names</span><span class="p">()</span>
<span class="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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.any.html#numpy.any"><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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.any.html#numpy.any"><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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.nonzero.html#numpy.nonzero"><span class="n">np</span><span class="o">.</span><span class="n">nonzero</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_not</span><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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.nonzero.html#numpy.nonzero"><span class="n">np</span><span class="o">.</span><span class="n">nonzero</span></a><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_not</span><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], cols].sum() but</span>
<span class="c1"># 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="p">(</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="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">iteritems</span><span class="p">(</span><span class="n">d</span><span class="p">),</span> <span class="n">key</span><span class="o">=</span><span class="n">operator</span><span class="o">.</span><span class="n">itemgetter</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="n">reverse</span><span class="o">=</span><span class="bp">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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.argsort.html#numpy.argsort"><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="k">print</span><span class="p">()</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Best biclusters:"</span><span class="p">)</span>
<span class="k">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> <span class="n">defaultdict</span><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">"{:.0f}% {}"</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="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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.where.html#numpy.where"><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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.array.html#numpy.array"><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="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="k">print</span><span class="p">(</span><span class="s2">"bicluster {} : {} documents, {} 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="k">print</span><span class="p">(</span><span class="s2">"categories : {}"</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="k">print</span><span class="p">(</span><span class="s2">"words : {}</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="s1">', '</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>
</div>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
</div>
<div class="footer">
© 2010 - 2014, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/bicluster/bicluster_newsgroups.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_spectral_biclustering.html">Previous
</a>
</div>
</div>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-22606712-2']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
<script src="http://www.google.com/jsapi" type="text/javascript"></script>
<script type="text/javascript"> google.load('search', '1',
{language : 'en'}); google.setOnLoadCallback(function() {
var customSearchControl = new
google.search.CustomSearchControl('016639176250731907682:tjtqbvtvij0');
customSearchControl.setResultSetSize(google.search.Search.FILTERED_CSE_RESULTSET);
var options = new google.search.DrawOptions();
options.setAutoComplete(true);
customSearchControl.draw('cse', options); }, true);
</script>
<script src="https://scikit-learn.org/versionwarning.js"></script>
</body>
</html>