-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathwikipedia_principal_eigenvector.html
535 lines (470 loc) · 52.7 KB
/
wikipedia_principal_eigenvector.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
<!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="generator" content="Docutils 0.19: https://docutils.sourceforge.io/" />
<meta property="og:title" content="Wikipedia principal eigenvector" />
<meta property="og:type" content="website" />
<meta property="og:url" content="https://scikit-learn/stable/auto_examples/applications/wikipedia_principal_eigenvector.html" />
<meta property="og:site_name" content="scikit-learn" />
<meta property="og:description" content="A classical way to assert the relative importance of vertices in a graph is to compute the principal eigenvector of the adjacency matrix so as to assign to each vertex the values of the components ..." />
<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="A classical way to assert the relative importance of vertices in a graph is to compute the principal eigenvector of the adjacency matrix so as to assign to each vertex the values of the components ..." />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Wikipedia principal eigenvector — scikit-learn 1.2.2 documentation</title>
<link rel="canonical" href="http://scikit-learn.org/stable/auto_examples/applications/wikipedia_principal_eigenvector.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/plot_directive.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>
</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/v1.2.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/v1.2.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_stock_market.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Visualizing the stock market structure">Prev</a><a href="index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Examples based on real world datasets">Up</a>
<a href="../feature_selection/index.html" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="Feature Selection">Next</a>
</div>
<div class="alert alert-danger p-1 mb-2" role="alert">
<p class="text-center mb-0">
<strong>scikit-learn 1.2.2</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="#">Wikipedia principal eigenvector</a><ul>
<li><a class="reference internal" href="#download-data-if-not-already-on-disk">Download data, if not already on disk</a></li>
<li><a class="reference internal" href="#loading-the-redirect-files">Loading the redirect files</a></li>
<li><a class="reference internal" href="#computing-the-adjacency-matrix">Computing the Adjacency matrix</a></li>
<li><a class="reference internal" href="#computing-principal-singular-vector-using-randomized-svd">Computing Principal Singular Vector using Randomized SVD</a></li>
<li><a class="reference internal" href="#computing-centrality-scores">Computing Centrality scores</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div>
<div id="sk-page-content-wrapper">
<div class="sk-page-content container-fluid body px-md-3" role="main">
<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-applications-wikipedia-principal-eigenvector-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>
<section class="sphx-glr-example-title" id="wikipedia-principal-eigenvector">
<span id="sphx-glr-auto-examples-applications-wikipedia-principal-eigenvector-py"></span><h1>Wikipedia principal eigenvector<a class="headerlink" href="#wikipedia-principal-eigenvector" title="Permalink to this heading">¶</a></h1>
<p>A classical way to assert the relative importance of vertices in a
graph is to compute the principal eigenvector of the adjacency matrix
so as to assign to each vertex the values of the components of the first
eigenvector as a centrality score:</p>
<blockquote>
<div><p><a class="reference external" href="https://en.wikipedia.org/wiki/Eigenvector_centrality">https://en.wikipedia.org/wiki/Eigenvector_centrality</a></p>
</div></blockquote>
<p>On the graph of webpages and links those values are called the PageRank
scores by Google.</p>
<p>The goal of this example is to analyze the graph of links inside
wikipedia articles to rank articles by relative importance according to
this eigenvector centrality.</p>
<p>The traditional way to compute the principal eigenvector is to use the
power iteration method:</p>
<blockquote>
<div><p><a class="reference external" href="https://en.wikipedia.org/wiki/Power_iteration">https://en.wikipedia.org/wiki/Power_iteration</a></p>
</div></blockquote>
<p>Here the computation is achieved thanks to Martinsson’s Randomized SVD
algorithm implemented in scikit-learn.</p>
<p>The graph data is fetched from the DBpedia dumps. DBpedia is an extraction
of the latent structured data of the Wikipedia content.</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Author: Olivier Grisel <[email protected]></span>
<span class="c1"># License: BSD 3 clause</span>
<span class="kn">from</span> <span class="nn">bz2</span> <span class="kn">import</span> <a href="https://docs.python.org/3/library/bz2.html#bz2.BZ2File" title="bz2.BZ2File" class="sphx-glr-backref-module-bz2 sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">BZ2File</span></a>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span>
<span class="kn">from</span> <span class="nn">pprint</span> <span class="kn">import</span> <a href="https://docs.python.org/3/library/pprint.html#pprint.pprint" title="pprint.pprint" class="sphx-glr-backref-module-pprint sphx-glr-backref-type-py-function"><span class="n">pprint</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">scipy</span> <span class="kn">import</span> <span class="n">sparse</span>
<span class="kn">from</span> <span class="nn">sklearn.decomposition</span> <span class="kn">import</span> <span class="n">randomized_svd</span>
<span class="kn">from</span> <span class="nn">urllib.request</span> <span class="kn">import</span> <a href="https://docs.python.org/3/library/urllib.request.html#urllib.request.urlopen" title="urllib.request.urlopen" class="sphx-glr-backref-module-urllib-request sphx-glr-backref-type-py-function"><span class="n">urlopen</span></a>
</pre></div>
</div>
<section id="download-data-if-not-already-on-disk">
<h2>Download data, if not already on disk<a class="headerlink" href="#download-data-if-not-already-on-disk" title="Permalink to this heading">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">redirects_url</span> <span class="o">=</span> <span class="s2">"http://downloads.dbpedia.org/3.5.1/en/redirects_en.nt.bz2"</span>
<span class="n">redirects_filename</span> <span class="o">=</span> <span class="n">redirects_url</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">"/"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
<span class="n">page_links_url</span> <span class="o">=</span> <span class="s2">"http://downloads.dbpedia.org/3.5.1/en/page_links_en.nt.bz2"</span>
<span class="n">page_links_filename</span> <span class="o">=</span> <span class="n">page_links_url</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">"/"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
<span class="n">resources</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">(</span><span class="n">redirects_url</span><span class="p">,</span> <span class="n">redirects_filename</span><span class="p">),</span>
<span class="p">(</span><span class="n">page_links_url</span><span class="p">,</span> <span class="n">page_links_filename</span><span class="p">),</span>
<span class="p">]</span>
<span class="k">for</span> <span class="n">url</span><span class="p">,</span> <span class="n">filename</span> <span class="ow">in</span> <span class="n">resources</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <a href="https://docs.python.org/3/library/os.path.html#os.path.exists" title="os.path.exists" class="sphx-glr-backref-module-os-path sphx-glr-backref-type-py-function"><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span></a><span class="p">(</span><span class="n">filename</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Downloading data from '</span><span class="si">%s</span><span class="s2">', please wait..."</span> <span class="o">%</span> <span class="n">url</span><span class="p">)</span>
<span class="n">opener</span> <span class="o">=</span> <a href="https://docs.python.org/3/library/urllib.request.html#urllib.request.urlopen" title="urllib.request.urlopen" class="sphx-glr-backref-module-urllib-request sphx-glr-backref-type-py-function"><span class="n">urlopen</span></a><span class="p">(</span><span class="n">url</span><span class="p">)</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s2">"wb"</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">opener</span><span class="o">.</span><span class="n">read</span><span class="p">())</span>
<span class="nb">print</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="loading-the-redirect-files">
<h2>Loading the redirect files<a class="headerlink" href="#loading-the-redirect-files" title="Permalink to this heading">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">index</span><span class="p">(</span><span class="n">redirects</span><span class="p">,</span> <span class="n">index_map</span><span class="p">,</span> <span class="n">k</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Find the index of an article name after redirect resolution"""</span>
<span class="n">k</span> <span class="o">=</span> <span class="n">redirects</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">k</span><span class="p">)</span>
<span class="k">return</span> <span class="n">index_map</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">index_map</span><span class="p">))</span>
<span class="n">DBPEDIA_RESOURCE_PREFIX_LEN</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="s2">"http://dbpedia.org/resource/"</span><span class="p">)</span>
<span class="n">SHORTNAME_SLICE</span> <span class="o">=</span> <span class="nb">slice</span><span class="p">(</span><span class="n">DBPEDIA_RESOURCE_PREFIX_LEN</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">short_name</span><span class="p">(</span><span class="n">nt_uri</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Remove the < and > URI markers and the common URI prefix"""</span>
<span class="k">return</span> <span class="n">nt_uri</span><span class="p">[</span><span class="n">SHORTNAME_SLICE</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">get_redirects</span><span class="p">(</span><span class="n">redirects_filename</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Parse the redirections and build a transitively closed map out of it"""</span>
<span class="n">redirects</span> <span class="o">=</span> <span class="p">{}</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Parsing the NT redirect file"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">l</span><span class="p">,</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><a href="https://docs.python.org/3/library/bz2.html#bz2.BZ2File" title="bz2.BZ2File" class="sphx-glr-backref-module-bz2 sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">BZ2File</span></a><span class="p">(</span><span class="n">redirects_filename</span><span class="p">)):</span>
<span class="n">split</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">split</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">4</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"ignoring malformed line: "</span> <span class="o">+</span> <span class="n">line</span><span class="p">)</span>
<span class="k">continue</span>
<span class="n">redirects</span><span class="p">[</span><span class="n">short_name</span><span class="p">(</span><span class="n">split</span><span class="p">[</span><span class="mi">0</span><span class="p">])]</span> <span class="o">=</span> <span class="n">short_name</span><span class="p">(</span><span class="n">split</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span>
<span class="k">if</span> <span class="n">l</span> <span class="o">%</span> <span class="mi">1000000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"[</span><span class="si">%s</span><span class="s2">] line: </span><span class="si">%08d</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">isoformat</span><span class="p">(),</span> <span class="n">l</span><span class="p">))</span>
<span class="c1"># compute the transitive closure</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Computing the transitive closure of the redirect relation"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">l</span><span class="p">,</span> <span class="n">source</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">redirects</span><span class="o">.</span><span class="n">keys</span><span class="p">()):</span>
<span class="n">transitive_target</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">target</span> <span class="o">=</span> <span class="n">redirects</span><span class="p">[</span><span class="n">source</span><span class="p">]</span>
<span class="n">seen</span> <span class="o">=</span> <span class="p">{</span><span class="n">source</span><span class="p">}</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">transitive_target</span> <span class="o">=</span> <span class="n">target</span>
<span class="n">target</span> <span class="o">=</span> <span class="n">redirects</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
<span class="k">if</span> <span class="n">target</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">target</span> <span class="ow">in</span> <span class="n">seen</span><span class="p">:</span>
<span class="k">break</span>
<span class="n">seen</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
<span class="n">redirects</span><span class="p">[</span><span class="n">source</span><span class="p">]</span> <span class="o">=</span> <span class="n">transitive_target</span>
<span class="k">if</span> <span class="n">l</span> <span class="o">%</span> <span class="mi">1000000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"[</span><span class="si">%s</span><span class="s2">] line: </span><span class="si">%08d</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">isoformat</span><span class="p">(),</span> <span class="n">l</span><span class="p">))</span>
<span class="k">return</span> <span class="n">redirects</span>
</pre></div>
</div>
</section>
<section id="computing-the-adjacency-matrix">
<h2>Computing the Adjacency matrix<a class="headerlink" href="#computing-the-adjacency-matrix" title="Permalink to this heading">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">get_adjacency_matrix</span><span class="p">(</span><span class="n">redirects_filename</span><span class="p">,</span> <span class="n">page_links_filename</span><span class="p">,</span> <span class="n">limit</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Extract the adjacency graph as a scipy sparse matrix</span>
<span class="sd"> Redirects are resolved first.</span>
<span class="sd"> Returns X, the scipy sparse adjacency matrix, redirects as python</span>
<span class="sd"> dict from article names to article names and index_map a python dict</span>
<span class="sd"> from article names to python int (article indexes).</span>
<span class="sd"> """</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Computing the redirect map"</span><span class="p">)</span>
<span class="n">redirects</span> <span class="o">=</span> <span class="n">get_redirects</span><span class="p">(</span><span class="n">redirects_filename</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Computing the integer index map"</span><span class="p">)</span>
<span class="n">index_map</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="n">links</span> <span class="o">=</span> <span class="nb">list</span><span class="p">()</span>
<span class="k">for</span> <span class="n">l</span><span class="p">,</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><a href="https://docs.python.org/3/library/bz2.html#bz2.BZ2File" title="bz2.BZ2File" class="sphx-glr-backref-module-bz2 sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">BZ2File</span></a><span class="p">(</span><span class="n">page_links_filename</span><span class="p">)):</span>
<span class="n">split</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">split</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">4</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"ignoring malformed line: "</span> <span class="o">+</span> <span class="n">line</span><span class="p">)</span>
<span class="k">continue</span>
<span class="n">i</span> <span class="o">=</span> <span class="n">index</span><span class="p">(</span><span class="n">redirects</span><span class="p">,</span> <span class="n">index_map</span><span class="p">,</span> <span class="n">short_name</span><span class="p">(</span><span class="n">split</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span>
<span class="n">j</span> <span class="o">=</span> <span class="n">index</span><span class="p">(</span><span class="n">redirects</span><span class="p">,</span> <span class="n">index_map</span><span class="p">,</span> <span class="n">short_name</span><span class="p">(</span><span class="n">split</span><span class="p">[</span><span class="mi">2</span><span class="p">]))</span>
<span class="n">links</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">))</span>
<span class="k">if</span> <span class="n">l</span> <span class="o">%</span> <span class="mi">1000000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"[</span><span class="si">%s</span><span class="s2">] line: </span><span class="si">%08d</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">isoformat</span><span class="p">(),</span> <span class="n">l</span><span class="p">))</span>
<span class="k">if</span> <span class="n">limit</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">l</span> <span class="o">>=</span> <span class="n">limit</span> <span class="o">-</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">break</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Computing the adjacency matrix"</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <a href="https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.lil_matrix.html#scipy.sparse.lil_matrix" title="scipy.sparse.lil_matrix" class="sphx-glr-backref-module-scipy-sparse sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sparse</span><span class="o">.</span><span class="n">lil_matrix</span></a><span class="p">((</span><span class="nb">len</span><span class="p">(</span><span class="n">index_map</span><span class="p">),</span> <span class="nb">len</span><span class="p">(</span><span class="n">index_map</span><span class="p">)),</span> <span class="n">dtype</span><span class="o">=</span><a href="https://numpy.org/doc/stable/reference/arrays.scalars.html#numpy.float32" title="numpy.float32" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-attribute"><span class="n">np</span><span class="o">.</span><span class="n">float32</span></a><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">links</span><span class="p">:</span>
<span class="n">X</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="mf">1.0</span>
<span class="k">del</span> <span class="n">links</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Converting to CSR representation"</span><span class="p">)</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">tocsr</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"CSR conversion done"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">X</span><span class="p">,</span> <span class="n">redirects</span><span class="p">,</span> <span class="n">index_map</span>
<span class="c1"># stop after 5M links to make it possible to work in RAM</span>
<span class="n">X</span><span class="p">,</span> <span class="n">redirects</span><span class="p">,</span> <span class="n">index_map</span> <span class="o">=</span> <span class="n">get_adjacency_matrix</span><span class="p">(</span>
<span class="n">redirects_filename</span><span class="p">,</span> <span class="n">page_links_filename</span><span class="p">,</span> <span class="n">limit</span><span class="o">=</span><span class="mi">5000000</span>
<span class="p">)</span>
<span class="n">names</span> <span class="o">=</span> <span class="p">{</span><span class="n">i</span><span class="p">:</span> <span class="n">name</span> <span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">index_map</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
</pre></div>
</div>
</section>
<section id="computing-principal-singular-vector-using-randomized-svd">
<h2>Computing Principal Singular Vector using Randomized SVD<a class="headerlink" href="#computing-principal-singular-vector-using-randomized-svd" title="Permalink to this heading">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="s2">"Computing the principal singular vectors using randomized_svd"</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="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">U</span><span class="p">,</span> <span class="n">s</span><span class="p">,</span> <span class="n">V</span> <span class="o">=</span> <span class="n">randomized_svd</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="n">n_iter</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">"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="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">t0</span><span class="p">))</span>
<span class="c1"># print the names of the wikipedia related strongest components of the</span>
<span class="c1"># principal singular vector which should be similar to the highest eigenvector</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Top wikipedia pages according to principal singular vectors"</span><span class="p">)</span>
<a href="https://docs.python.org/3/library/pprint.html#pprint.pprint" title="pprint.pprint" class="sphx-glr-backref-module-pprint sphx-glr-backref-type-py-function"><span class="n">pprint</span></a><span class="p">([</span><span class="n">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">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">U</span><span class="o">.</span><span class="n">T</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">10</span><span class="p">:]])</span>
<a href="https://docs.python.org/3/library/pprint.html#pprint.pprint" title="pprint.pprint" class="sphx-glr-backref-module-pprint sphx-glr-backref-type-py-function"><span class="n">pprint</span></a><span class="p">([</span><span class="n">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">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">V</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">10</span><span class="p">:]])</span>
</pre></div>
</div>
</section>
<section id="computing-centrality-scores">
<h2>Computing Centrality scores<a class="headerlink" href="#computing-centrality-scores" title="Permalink to this heading">¶</a></h2>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">centrality_scores</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">0.85</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">tol</span><span class="o">=</span><span class="mf">1e-10</span><span class="p">):</span>
<span class="w"> </span><span class="sd">"""Power iteration computation of the principal eigenvector</span>
<span class="sd"> This method is also known as Google PageRank and the implementation</span>
<span class="sd"> is based on the one from the NetworkX project (BSD licensed too)</span>
<span class="sd"> with copyrights by:</span>
<span class="sd"> Aric Hagberg <[email protected]></span>
<span class="sd"> Dan Schult <[email protected]></span>
<span class="sd"> Pieter Swart <[email protected]></span>
<span class="sd"> """</span>
<span class="n">n</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">X</span> <span class="o">=</span> <span class="n">X</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">incoming_counts</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="numpy.asarray" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</span><span class="n">X</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">1</span><span class="p">))</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Normalizing the graph"</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">incoming_counts</span><span class="o">.</span><span class="n">nonzero</span><span class="p">()[</span><span class="mi">0</span><span class="p">]:</span>
<span class="n">X</span><span class="o">.</span><span class="n">data</span><span class="p">[</span><span class="n">X</span><span class="o">.</span><span class="n">indptr</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="p">:</span> <span class="n">X</span><span class="o">.</span><span class="n">indptr</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]]</span> <span class="o">*=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="n">incoming_counts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
<span class="n">dangle</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.asarray.html#numpy.asarray" title="numpy.asarray" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</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><a href="https://numpy.org/doc/stable/reference/generated/numpy.isclose.html#numpy.isclose" title="numpy.isclose" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">isclose</span></a><span class="p">(</span><span class="n">X</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">1</span><span class="p">),</span> <span class="mi">0</span><span class="p">),</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="n">n</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span>
<span class="n">scores</span> <span class="o">=</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.full.html#numpy.full" title="numpy.full" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">full</span></a><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><a href="https://numpy.org/doc/stable/reference/arrays.scalars.html#numpy.float32" title="numpy.float32" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-attribute"><span class="n">np</span><span class="o">.</span><span class="n">float32</span></a><span class="p">)</span> <span class="c1"># initial guess</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">max_iter</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"power iteration #</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">prev_scores</span> <span class="o">=</span> <span class="n">scores</span>
<span class="n">scores</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">alpha</span> <span class="o">*</span> <span class="p">(</span><span class="n">scores</span> <span class="o">*</span> <span class="n">X</span> <span class="o">+</span> <a href="https://numpy.org/doc/stable/reference/generated/numpy.dot.html#numpy.dot" title="numpy.dot" class="sphx-glr-backref-module-numpy sphx-glr-backref-type-py-function"><span class="n">np</span><span class="o">.</span><span class="n">dot</span></a><span class="p">(</span><span class="n">dangle</span><span class="p">,</span> <span class="n">prev_scores</span><span class="p">))</span>
<span class="o">+</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">alpha</span><span class="p">)</span> <span class="o">*</span> <span class="n">prev_scores</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">/</span> <span class="n">n</span>
<span class="p">)</span>
<span class="c1"># check convergence: normalized l_inf norm</span>
<span class="n">scores_max</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">scores</span><span class="p">)</span><span class="o">.</span><span class="n">max</span><span class="p">()</span>
<span class="k">if</span> <span class="n">scores_max</span> <span class="o">==</span> <span class="mf">0.0</span><span class="p">:</span>
<span class="n">scores_max</span> <span class="o">=</span> <span class="mf">1.0</span>
<span class="n">err</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">scores</span> <span class="o">-</span> <span class="n">prev_scores</span><span class="p">)</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> <span class="o">/</span> <span class="n">scores_max</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"error: </span><span class="si">%0.6f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">err</span><span class="p">)</span>
<span class="k">if</span> <span class="n">err</span> <span class="o"><</span> <span class="n">n</span> <span class="o">*</span> <span class="n">tol</span><span class="p">:</span>
<span class="k">return</span> <span class="n">scores</span>
<span class="k">return</span> <span class="n">scores</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Computing principal eigenvector score using a power iteration method"</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="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">scores</span> <span class="o">=</span> <span class="n">centrality_scores</span><span class="p">(</span><span class="n">X</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="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="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">t0</span><span class="p">))</span>
<a href="https://docs.python.org/3/library/pprint.html#pprint.pprint" title="pprint.pprint" class="sphx-glr-backref-module-pprint sphx-glr-backref-type-py-function"><span class="n">pprint</span></a><span class="p">([</span><span class="n">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">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">scores</span><span class="p">)</span><span class="o">.</span><span class="n">argsort</span><span class="p">()[</span><span class="o">-</span><span class="mi">10</span><span class="p">:]])</span>
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 0.000 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applications-wikipedia-principal-eigenvector-py">
<div class="binder-badge docutils container">
<a class="reference external image-reference" href="https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.2.X?urlpath=lab/tree/notebooks/auto_examples/applications/wikipedia_principal_eigenvector.ipynb"><img alt="Launch binder" src="../../_images/binder_badge_logo8.svg" width="150px" /></a>
</div>
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/51bc3899ceeec0ecf99c5f72ff1fd241/wikipedia_principal_eigenvector.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">wikipedia_principal_eigenvector.py</span></code></a></p>
</div>
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/948a4dfa149766b475b1cf2515f289d1/wikipedia_principal_eigenvector.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">wikipedia_principal_eigenvector.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>
</section>
</section>
</div>
<div class="container">
<footer class="sk-content-footer">
© 2007 - 2023, scikit-learn developers (BSD License).
<a href="../../_sources/auto_examples/applications/wikipedia_principal_eigenvector.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>
$(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>');
});
});
</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>