-
Notifications
You must be signed in to change notification settings - Fork 81
/
Copy pathwikipedia_principal_eigenvector.html
441 lines (357 loc) · 40.3 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
<!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>Wikipedia principal eigenvector — 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="Prediction Latency" href="plot_prediction_latency.html" />
<link rel="prev" title="Visualizing the stock market structure" href="plot_stock_market.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/applications/wikipedia_principal_eigenvector.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_stock_market.html"
accesskey="P">Previous
<br/>
<span class="smallrellink">
Visualizing t...
</span>
<span class="hiddenrellink">
Visualizing the stock market structure
</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="#">Wikipedia principal eigenvector</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="wikipedia-principal-eigenvector">
<span id="example-applications-wikipedia-principal-eigenvector-py"></span><h1>Wikipedia principal eigenvector<a class="headerlink" href="#wikipedia-principal-eigenvector" title="Permalink to this headline">¶</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><a class="reference external" href="http://en.wikipedia.org/wiki/Eigenvector_centrality">http://en.wikipedia.org/wiki/Eigenvector_centrality</a></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><a class="reference external" href="http://en.wikipedia.org/wiki/Power_iteration">http://en.wikipedia.org/wiki/Power_iteration</a></div></blockquote>
<p>Here the computation is achieved thanks to Martinsson’s Randomized SVD
algorithm implemented in the scikit.</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>
<p><strong>Python source code:</strong> <a class="reference download internal" href="../../_downloads/wikipedia_principal_eigenvector.py"><code class="xref download docutils literal"><span class="pre">wikipedia_principal_eigenvector.py</span></code></a></p>
<div class="highlight-python"><div class="highlight"><pre>
<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">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="kn">from</span> <span class="nn">bz2</span> <span class="kn">import</span> <span class="n">BZ2File</span>
<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> <span class="n">pprint</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">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">sklearn.externals.joblib</span> <span class="kn">import</span> <span class="n">Memory</span>
<span class="kn">from</span> <span class="nn">sklearn.externals.six.moves.urllib.request</span> <span class="kn">import</span> <span class="n">urlopen</span>
<span class="kn">from</span> <span class="nn">sklearn.externals.six</span> <span class="kn">import</span> <span class="n">iteritems</span>
<span class="k">print</span><span class="p">(</span><span class="n">__doc__</span><span class="p">)</span>
<span class="c1">###############################################################################</span>
<span class="c1"># Where to download the data, if not already on disk</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> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">filename</span><span class="p">):</span>
<span class="k">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> <span class="n">urlopen</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
<span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s1">'wb'</span><span class="p">)</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="k">print</span><span class="p">()</span>
<span class="c1">###############################################################################</span>
<span class="c1"># Loading the redirect files</span>
<span class="n">memory</span> <span class="o">=</span> <span class="n">Memory</span><span class="p">(</span><span class="n">cachedir</span><span class="o">=</span><span class="s2">"."</span><span class="p">)</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="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="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="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="k">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><span class="n">BZ2File</span><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="k">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="k">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="k">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="bp">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="nb">set</span><span class="p">([</span><span class="n">source</span><span class="p">])</span>
<span class="k">while</span> <span class="bp">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="bp">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="k">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>
<span class="c1"># disabling joblib as the pickling of large dicts seems much too slow</span>
<span class="c1">#@memory.cache</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="bp">None</span><span class="p">):</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="k">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="k">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><span class="n">BZ2File</span><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="k">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="k">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="bp">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="k">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> <span class="n">sparse</span><span class="o">.</span><span class="n">lil_matrix</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="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><span class="n">np</span><span class="o">.</span><span class="n">float32</span><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="k">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="k">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="nb">dict</span><span class="p">((</span><span class="n">i</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">i</span> <span class="ow">in</span> <span class="n">iteritems</span><span class="p">(</span><span class="n">index_map</span><span class="p">))</span>
<span class="k">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> <span class="n">time</span><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="k">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><span class="n">time</span><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 compenents of the the</span>
<span class="c1"># principal singular vector which should be similar to the highest eigenvector</span>
<span class="k">print</span><span class="p">(</span><span class="s2">"Top wikipedia pages according to principal singular vectors"</span><span class="p">)</span>
<span class="n">pprint</span><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>
<span class="n">pprint</span><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>
<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="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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.asarray.html#numpy.asarray"><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="k">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="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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.asarray.html#numpy.asarray"><span class="n">np</span><span class="o">.</span><span class="n">asarray</span></a><span class="p">(</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">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="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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.ones.html#numpy.ones"><span class="n">np</span><span class="o">.</span><span class="n">ones</span></a><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span> <span class="o">/</span> <span class="n">n</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="k">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="http://docs.scipy.org/doc/numpy-1.6.0/reference/generated/numpy.dot.html#numpy.dot"><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="k">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="k">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> <span class="n">time</span><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="n">tol</span><span class="o">=</span><span class="mf">1e-10</span><span class="p">)</span>
<span class="k">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><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">t0</span><span class="p">))</span>
<span class="n">pprint</span><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>
</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/applications/wikipedia_principal_eigenvector.txt" rel="nofollow">Show this page source</a>
</div>
<div class="rel">
<div class="buttonPrevious">
<a href="plot_stock_market.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>