1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
|
<!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>pyspark.mllib.clustering — PySpark master documentation</title>
<link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../../',
VERSION: 'master',
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>
<link rel="top" title="PySpark master documentation" href="../../../index.html" />
<link rel="up" title="Module code" href="../../index.html" />
</head>
<body role="document">
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> »</li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for pyspark.mllib.clustering</h1><div class="highlight"><pre>
<span class="c">#</span>
<span class="c"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c"># this work for additional information regarding copyright ownership.</span>
<span class="c"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c"># (the "License"); you may not use this file except in compliance with</span>
<span class="c"># the License. You may obtain a copy of the License at</span>
<span class="c">#</span>
<span class="c"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c">#</span>
<span class="c"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c"># distributed under the License is distributed on an "AS IS" BASIS,</span>
<span class="c"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c"># See the License for the specific language governing permissions and</span>
<span class="c"># limitations under the License.</span>
<span class="c">#</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">array</span> <span class="kn">as</span> <span class="nn">pyarray</span>
<span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version</span> <span class="o">></span> <span class="s">'3'</span><span class="p">:</span>
<span class="nb">xrange</span> <span class="o">=</span> <span class="nb">range</span>
<span class="nb">basestring</span> <span class="o">=</span> <span class="nb">str</span>
<span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">exp</span><span class="p">,</span> <span class="n">log</span>
<span class="kn">from</span> <span class="nn">numpy</span> <span class="kn">import</span> <span class="n">array</span><span class="p">,</span> <span class="n">random</span><span class="p">,</span> <span class="n">tile</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">namedtuple</span>
<span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">RDD</span><span class="p">,</span> <span class="n">ignore_unicode_prefix</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span><span class="p">,</span> <span class="n">callJavaFunc</span><span class="p">,</span> <span class="n">_py2java</span><span class="p">,</span> <span class="n">_java2py</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">SparseVector</span><span class="p">,</span> <span class="n">_convert_to_vector</span><span class="p">,</span> <span class="n">DenseVector</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.stat.distribution</span> <span class="kn">import</span> <span class="n">MultivariateGaussian</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span><span class="p">,</span> <span class="n">inherit_doc</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">JavaSaveable</span>
<span class="kn">from</span> <span class="nn">pyspark.streaming</span> <span class="kn">import</span> <span class="n">DStream</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'KMeansModel'</span><span class="p">,</span> <span class="s">'KMeans'</span><span class="p">,</span> <span class="s">'GaussianMixtureModel'</span><span class="p">,</span> <span class="s">'GaussianMixture'</span><span class="p">,</span>
<span class="s">'PowerIterationClusteringModel'</span><span class="p">,</span> <span class="s">'PowerIterationClustering'</span><span class="p">,</span>
<span class="s">'StreamingKMeans'</span><span class="p">,</span> <span class="s">'StreamingKMeansModel'</span><span class="p">,</span>
<span class="s">'LDA'</span><span class="p">,</span> <span class="s">'LDAModel'</span><span class="p">]</span>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="KMeansModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeansModel">[docs]</a><span class="k">class</span> <span class="nc">KMeansModel</span><span class="p">(</span><span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span><span class="p">):</span>
<span class="sd">"""A clustering model derived from the k-means method.</span>
<span class="sd"> >>> data = array([0.0,0.0, 1.0,1.0, 9.0,8.0, 8.0,9.0]).reshape(4, 2)</span>
<span class="sd"> >>> model = KMeans.train(</span>
<span class="sd"> ... sc.parallelize(data), 2, maxIterations=10, runs=30, initializationMode="random",</span>
<span class="sd"> ... seed=50, initializationSteps=5, epsilon=1e-4)</span>
<span class="sd"> >>> model.predict(array([0.0, 0.0])) == model.predict(array([1.0, 1.0]))</span>
<span class="sd"> True</span>
<span class="sd"> >>> model.predict(array([8.0, 9.0])) == model.predict(array([9.0, 8.0]))</span>
<span class="sd"> True</span>
<span class="sd"> >>> model.k</span>
<span class="sd"> 2</span>
<span class="sd"> >>> model.computeCost(sc.parallelize(data))</span>
<span class="sd"> 2.0000000000000004</span>
<span class="sd"> >>> model = KMeans.train(sc.parallelize(data), 2)</span>
<span class="sd"> >>> sparse_data = [</span>
<span class="sd"> ... SparseVector(3, {1: 1.0}),</span>
<span class="sd"> ... SparseVector(3, {1: 1.1}),</span>
<span class="sd"> ... SparseVector(3, {2: 1.0}),</span>
<span class="sd"> ... SparseVector(3, {2: 1.1})</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> model = KMeans.train(sc.parallelize(sparse_data), 2, initializationMode="k-means||",</span>
<span class="sd"> ... seed=50, initializationSteps=5, epsilon=1e-4)</span>
<span class="sd"> >>> model.predict(array([0., 1., 0.])) == model.predict(array([0, 1.1, 0.]))</span>
<span class="sd"> True</span>
<span class="sd"> >>> model.predict(array([0., 0., 1.])) == model.predict(array([0, 0, 1.1]))</span>
<span class="sd"> True</span>
<span class="sd"> >>> model.predict(sparse_data[0]) == model.predict(sparse_data[1])</span>
<span class="sd"> True</span>
<span class="sd"> >>> model.predict(sparse_data[2]) == model.predict(sparse_data[3])</span>
<span class="sd"> True</span>
<span class="sd"> >>> isinstance(model.clusterCenters, list)</span>
<span class="sd"> True</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> model.save(sc, path)</span>
<span class="sd"> >>> sameModel = KMeansModel.load(sc, path)</span>
<span class="sd"> >>> sameModel.predict(sparse_data[0]) == model.predict(sparse_data[0])</span>
<span class="sd"> True</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except OSError:</span>
<span class="sd"> ... pass</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">centers</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">centers</span> <span class="o">=</span> <span class="n">centers</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">clusterCenters</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Get the cluster centers, represented as a list of NumPy arrays."""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">centers</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">k</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Total number of clusters."""</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">)</span>
<div class="viewcode-block" id="KMeansModel.predict"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeansModel.predict">[docs]</a> <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="sd">"""Find the cluster to which x belongs in this model."""</span>
<span class="n">best</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">best_distance</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="s">"inf"</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">xrange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">)):</span>
<span class="n">distance</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">squared_distance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
<span class="k">if</span> <span class="n">distance</span> <span class="o"><</span> <span class="n">best_distance</span><span class="p">:</span>
<span class="n">best</span> <span class="o">=</span> <span class="n">i</span>
<span class="n">best_distance</span> <span class="o">=</span> <span class="n">distance</span>
<span class="k">return</span> <span class="n">best</span>
</div>
<div class="viewcode-block" id="KMeansModel.computeCost"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeansModel.computeCost">[docs]</a> <span class="k">def</span> <span class="nf">computeCost</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rdd</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the K-means cost (sum of squared distances of points to</span>
<span class="sd"> their nearest center) for this model on the given data.</span>
<span class="sd"> """</span>
<span class="n">cost</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"computeCostKmeansModel"</span><span class="p">,</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span>
<span class="p">[</span><span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">])</span>
<span class="k">return</span> <span class="n">cost</span>
</div>
<div class="viewcode-block" id="KMeansModel.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeansModel.save">[docs]</a> <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="n">java_centers</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="p">[</span><span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">])</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">clustering</span><span class="o">.</span><span class="n">KMeansModel</span><span class="p">(</span><span class="n">java_centers</span><span class="p">)</span>
<span class="n">java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>
</div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="KMeansModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeansModel.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">clustering</span><span class="o">.</span><span class="n">KMeansModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>
<span class="k">return</span> <span class="n">KMeansModel</span><span class="p">(</span><span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">clusterCenters</span><span class="p">()))</span>
</div></div>
<div class="viewcode-block" id="KMeans"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeans">[docs]</a><span class="k">class</span> <span class="nc">KMeans</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="KMeans.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.KMeans.train">[docs]</a> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">maxIterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">runs</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">initializationMode</span><span class="o">=</span><span class="s">"k-means||"</span><span class="p">,</span>
<span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">initializationSteps</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">):</span>
<span class="sd">"""Train a k-means clustering model."""</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainKMeansModel"</span><span class="p">,</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span> <span class="n">k</span><span class="p">,</span> <span class="n">maxIterations</span><span class="p">,</span>
<span class="n">runs</span><span class="p">,</span> <span class="n">initializationMode</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">initializationSteps</span><span class="p">,</span> <span class="n">epsilon</span><span class="p">)</span>
<span class="n">centers</span> <span class="o">=</span> <span class="n">callJavaFunc</span><span class="p">(</span><span class="n">rdd</span><span class="o">.</span><span class="n">context</span><span class="p">,</span> <span class="n">model</span><span class="o">.</span><span class="n">clusterCenters</span><span class="p">)</span>
<span class="k">return</span> <span class="n">KMeansModel</span><span class="p">([</span><span class="n">c</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">centers</span><span class="p">])</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="GaussianMixtureModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixtureModel">[docs]</a><span class="k">class</span> <span class="nc">GaussianMixtureModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> A clustering model derived from the Gaussian Mixture Model method.</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors, DenseMatrix</span>
<span class="sd"> >>> from numpy.testing import assert_equal</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> clusterdata_1 = sc.parallelize(array([-0.1,-0.05,-0.01,-0.1,</span>
<span class="sd"> ... 0.9,0.8,0.75,0.935,</span>
<span class="sd"> ... -0.83,-0.68,-0.91,-0.76 ]).reshape(6, 2))</span>
<span class="sd"> >>> model = GaussianMixture.train(clusterdata_1, 3, convergenceTol=0.0001,</span>
<span class="sd"> ... maxIterations=50, seed=10)</span>
<span class="sd"> >>> labels = model.predict(clusterdata_1).collect()</span>
<span class="sd"> >>> labels[0]==labels[1]</span>
<span class="sd"> False</span>
<span class="sd"> >>> labels[1]==labels[2]</span>
<span class="sd"> True</span>
<span class="sd"> >>> labels[4]==labels[5]</span>
<span class="sd"> True</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> model.save(sc, path)</span>
<span class="sd"> >>> sameModel = GaussianMixtureModel.load(sc, path)</span>
<span class="sd"> >>> assert_equal(model.weights, sameModel.weights)</span>
<span class="sd"> >>> mus, sigmas = list(</span>
<span class="sd"> ... zip(*[(g.mu, g.sigma) for g in model.gaussians]))</span>
<span class="sd"> >>> sameMus, sameSigmas = list(</span>
<span class="sd"> ... zip(*[(g.mu, g.sigma) for g in sameModel.gaussians]))</span>
<span class="sd"> >>> mus == sameMus</span>
<span class="sd"> True</span>
<span class="sd"> >>> sigmas == sameSigmas</span>
<span class="sd"> True</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except OSError:</span>
<span class="sd"> ... pass</span>
<span class="sd"> >>> data = array([-5.1971, -2.5359, -3.8220,</span>
<span class="sd"> ... -5.2211, -5.0602, 4.7118,</span>
<span class="sd"> ... 6.8989, 3.4592, 4.6322,</span>
<span class="sd"> ... 5.7048, 4.6567, 5.5026,</span>
<span class="sd"> ... 4.5605, 5.2043, 6.2734])</span>
<span class="sd"> >>> clusterdata_2 = sc.parallelize(data.reshape(5,3))</span>
<span class="sd"> >>> model = GaussianMixture.train(clusterdata_2, 2, convergenceTol=0.0001,</span>
<span class="sd"> ... maxIterations=150, seed=10)</span>
<span class="sd"> >>> labels = model.predict(clusterdata_2).collect()</span>
<span class="sd"> >>> labels[0]==labels[1]==labels[2]</span>
<span class="sd"> True</span>
<span class="sd"> >>> labels[3]==labels[4]</span>
<span class="sd"> True</span>
<span class="sd"> """</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weights</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Weights for each Gaussian distribution in the mixture, where weights[i] is</span>
<span class="sd"> the weight for Gaussian i, and weights.sum == 1.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"weights"</span><span class="p">))</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">gaussians</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Array of MultivariateGaussian where gaussians[i] represents</span>
<span class="sd"> the Multivariate Gaussian (Normal) Distribution for Gaussian i.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">[</span>
<span class="n">MultivariateGaussian</span><span class="p">(</span><span class="n">gaussian</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">gaussian</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="k">for</span> <span class="n">gaussian</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"gaussians"</span><span class="p">))]</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">k</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Number of gaussians in mixture."""</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="p">)</span>
<div class="viewcode-block" id="GaussianMixtureModel.predict"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixtureModel.predict">[docs]</a> <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Find the cluster to which the points in 'x' has maximum membership</span>
<span class="sd"> in this model.</span>
<span class="sd"> :param x: RDD of data points.</span>
<span class="sd"> :return: cluster_labels. RDD of cluster labels.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">cluster_labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predictSoft</span><span class="p">(</span><span class="n">x</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">z</span><span class="p">:</span> <span class="n">z</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="nb">max</span><span class="p">(</span><span class="n">z</span><span class="p">)))</span>
<span class="k">return</span> <span class="n">cluster_labels</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"x should be represented by an RDD, "</span>
<span class="s">"but got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
</div>
<div class="viewcode-block" id="GaussianMixtureModel.predictSoft"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixtureModel.predictSoft">[docs]</a> <span class="k">def</span> <span class="nf">predictSoft</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Find the membership of each point in 'x' to all mixture components.</span>
<span class="sd"> :param x: RDD of data points.</span>
<span class="sd"> :return: membership_matrix. RDD of array of double values.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">means</span><span class="p">,</span> <span class="n">sigmas</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="p">[(</span><span class="n">g</span><span class="o">.</span><span class="n">mu</span><span class="p">,</span> <span class="n">g</span><span class="o">.</span><span class="n">sigma</span><span class="p">)</span> <span class="k">for</span> <span class="n">g</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">gaussians</span><span class="p">])</span>
<span class="n">membership_matrix</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"predictSoftGMM"</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span>
<span class="n">_convert_to_vector</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="p">),</span> <span class="n">means</span><span class="p">,</span> <span class="n">sigmas</span><span class="p">)</span>
<span class="k">return</span> <span class="n">membership_matrix</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">pyarray</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="s">'d'</span><span class="p">,</span> <span class="n">x</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"x should be represented by an RDD, "</span>
<span class="s">"but got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
</div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="GaussianMixtureModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixtureModel.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">"""Load the GaussianMixtureModel from disk.</span>
<span class="sd"> :param sc: SparkContext</span>
<span class="sd"> :param path: str, path to where the model is stored.</span>
<span class="sd"> """</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="n">wrapper</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">GaussianMixtureModelWrapper</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
<span class="k">return</span> <span class="n">cls</span><span class="p">(</span><span class="n">wrapper</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="GaussianMixture"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixture">[docs]</a><span class="k">class</span> <span class="nc">GaussianMixture</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Learning algorithm for Gaussian Mixtures using the expectation-maximization algorithm.</span>
<span class="sd"> :param data: RDD of data points</span>
<span class="sd"> :param k: Number of components</span>
<span class="sd"> :param convergenceTol: Threshold value to check the convergence criteria. Defaults to 1e-3</span>
<span class="sd"> :param maxIterations: Number of iterations. Default to 100</span>
<span class="sd"> :param seed: Random Seed</span>
<span class="sd"> :param initialModel: GaussianMixtureModel for initializing learning</span>
<span class="sd"> """</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="GaussianMixture.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.GaussianMixture.train">[docs]</a> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">convergenceTol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">maxIterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">initialModel</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Train a Gaussian Mixture clustering model."""</span>
<span class="n">initialModelWeights</span> <span class="o">=</span> <span class="bp">None</span>
<span class="n">initialModelMu</span> <span class="o">=</span> <span class="bp">None</span>
<span class="n">initialModelSigma</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">if</span> <span class="n">initialModel</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">initialModel</span><span class="o">.</span><span class="n">k</span> <span class="o">!=</span> <span class="n">k</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s">"Mismatched cluster count, initialModel.k = </span><span class="si">%s</span><span class="s">, however k = </span><span class="si">%s</span><span class="s">"</span>
<span class="o">%</span> <span class="p">(</span><span class="n">initialModel</span><span class="o">.</span><span class="n">k</span><span class="p">,</span> <span class="n">k</span><span class="p">))</span>
<span class="n">initialModelWeights</span> <span class="o">=</span> <span class="n">initialModel</span><span class="o">.</span><span class="n">weights</span>
<span class="n">initialModelMu</span> <span class="o">=</span> <span class="p">[</span><span class="n">initialModel</span><span class="o">.</span><span class="n">gaussians</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">mu</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">initialModel</span><span class="o">.</span><span class="n">k</span><span class="p">)]</span>
<span class="n">initialModelSigma</span> <span class="o">=</span> <span class="p">[</span><span class="n">initialModel</span><span class="o">.</span><span class="n">gaussians</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">sigma</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">initialModel</span><span class="o">.</span><span class="n">k</span><span class="p">)]</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainGaussianMixtureModel"</span><span class="p">,</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span>
<span class="n">k</span><span class="p">,</span> <span class="n">convergenceTol</span><span class="p">,</span> <span class="n">maxIterations</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span>
<span class="n">initialModelWeights</span><span class="p">,</span> <span class="n">initialModelMu</span><span class="p">,</span> <span class="n">initialModelSigma</span><span class="p">)</span>
<span class="k">return</span> <span class="n">GaussianMixtureModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="PowerIterationClusteringModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClusteringModel">[docs]</a><span class="k">class</span> <span class="nc">PowerIterationClusteringModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Model produced by [[PowerIterationClustering]].</span>
<span class="sd"> >>> data = [(0, 1, 1.0), (0, 2, 1.0), (0, 3, 1.0), (1, 2, 1.0), (1, 3, 1.0),</span>
<span class="sd"> ... (2, 3, 1.0), (3, 4, 0.1), (4, 5, 1.0), (4, 15, 1.0), (5, 6, 1.0),</span>
<span class="sd"> ... (6, 7, 1.0), (7, 8, 1.0), (8, 9, 1.0), (9, 10, 1.0), (10, 11, 1.0),</span>
<span class="sd"> ... (11, 12, 1.0), (12, 13, 1.0), (13, 14, 1.0), (14, 15, 1.0)]</span>
<span class="sd"> >>> rdd = sc.parallelize(data, 2)</span>
<span class="sd"> >>> model = PowerIterationClustering.train(rdd, 2, 100)</span>
<span class="sd"> >>> model.k</span>
<span class="sd"> 2</span>
<span class="sd"> >>> result = sorted(model.assignments().collect(), key=lambda x: x.id)</span>
<span class="sd"> >>> result[0].cluster == result[1].cluster == result[2].cluster == result[3].cluster</span>
<span class="sd"> True</span>
<span class="sd"> >>> result[4].cluster == result[5].cluster == result[6].cluster == result[7].cluster</span>
<span class="sd"> True</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> model.save(sc, path)</span>
<span class="sd"> >>> sameModel = PowerIterationClusteringModel.load(sc, path)</span>
<span class="sd"> >>> sameModel.k</span>
<span class="sd"> 2</span>
<span class="sd"> >>> result = sorted(model.assignments().collect(), key=lambda x: x.id)</span>
<span class="sd"> >>> result[0].cluster == result[1].cluster == result[2].cluster == result[3].cluster</span>
<span class="sd"> True</span>
<span class="sd"> >>> result[4].cluster == result[5].cluster == result[6].cluster == result[7].cluster</span>
<span class="sd"> True</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except OSError:</span>
<span class="sd"> ... pass</span>
<span class="sd"> """</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">k</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the number of clusters.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"k"</span><span class="p">)</span>
<div class="viewcode-block" id="PowerIterationClusteringModel.assignments"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClusteringModel.assignments">[docs]</a> <span class="k">def</span> <span class="nf">assignments</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the cluster assignments of this model.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"getAssignments"</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="p">(</span><span class="n">PowerIterationClustering</span><span class="o">.</span><span class="n">Assignment</span><span class="p">(</span><span class="o">*</span><span class="n">x</span><span class="p">)))</span>
</div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="PowerIterationClusteringModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClusteringModel.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="n">wrapper</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PowerIterationClusteringModelWrapper</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
<span class="k">return</span> <span class="n">PowerIterationClusteringModel</span><span class="p">(</span><span class="n">wrapper</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="PowerIterationClustering"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClustering">[docs]</a><span class="k">class</span> <span class="nc">PowerIterationClustering</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Power Iteration Clustering (PIC), a scalable graph clustering algorithm</span>
<span class="sd"> developed by [[http://www.icml2010.org/papers/387.pdf Lin and Cohen]].</span>
<span class="sd"> From the abstract: PIC finds a very low-dimensional embedding of a</span>
<span class="sd"> dataset using truncated power iteration on a normalized pair-wise</span>
<span class="sd"> similarity matrix of the data.</span>
<span class="sd"> """</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="PowerIterationClustering.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClustering.train">[docs]</a> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">maxIterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">initMode</span><span class="o">=</span><span class="s">"random"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> :param rdd: an RDD of (i, j, s,,ij,,) tuples representing the</span>
<span class="sd"> affinity matrix, which is the matrix A in the PIC paper.</span>
<span class="sd"> The similarity s,,ij,, must be nonnegative.</span>
<span class="sd"> This is a symmetric matrix and hence s,,ij,, = s,,ji,,.</span>
<span class="sd"> For any (i, j) with nonzero similarity, there should be</span>
<span class="sd"> either (i, j, s,,ij,,) or (j, i, s,,ji,,) in the input.</span>
<span class="sd"> Tuples with i = j are ignored, because we assume</span>
<span class="sd"> s,,ij,, = 0.0.</span>
<span class="sd"> :param k: Number of clusters.</span>
<span class="sd"> :param maxIterations: Maximum number of iterations of the</span>
<span class="sd"> PIC algorithm.</span>
<span class="sd"> :param initMode: Initialization mode.</span>
<span class="sd"> """</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainPowerIterationClusteringModel"</span><span class="p">,</span>
<span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">maxIterations</span><span class="p">),</span> <span class="n">initMode</span><span class="p">)</span>
<span class="k">return</span> <span class="n">PowerIterationClusteringModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="PowerIterationClustering.Assignment"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.PowerIterationClustering.Assignment">[docs]</a> <span class="k">class</span> <span class="nc">Assignment</span><span class="p">(</span><span class="n">namedtuple</span><span class="p">(</span><span class="s">"Assignment"</span><span class="p">,</span> <span class="p">[</span><span class="s">"id"</span><span class="p">,</span> <span class="s">"cluster"</span><span class="p">])):</span>
<span class="sd">"""</span>
<span class="sd"> Represents an (id, cluster) tuple.</span>
<span class="sd"> """</span>
</div></div>
<div class="viewcode-block" id="StreamingKMeansModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeansModel">[docs]</a><span class="k">class</span> <span class="nc">StreamingKMeansModel</span><span class="p">(</span><span class="n">KMeansModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Clustering model which can perform an online update of the centroids.</span>
<span class="sd"> The update formula for each centroid is given by</span>
<span class="sd"> * c_t+1 = ((c_t * n_t * a) + (x_t * m_t)) / (n_t + m_t)</span>
<span class="sd"> * n_t+1 = n_t * a + m_t</span>
<span class="sd"> where</span>
<span class="sd"> * c_t: Centroid at the n_th iteration.</span>
<span class="sd"> * n_t: Number of samples (or) weights associated with the centroid</span>
<span class="sd"> at the n_th iteration.</span>
<span class="sd"> * x_t: Centroid of the new data closest to c_t.</span>
<span class="sd"> * m_t: Number of samples (or) weights of the new data closest to c_t</span>
<span class="sd"> * c_t+1: New centroid.</span>
<span class="sd"> * n_t+1: New number of weights.</span>
<span class="sd"> * a: Decay Factor, which gives the forgetfulness.</span>
<span class="sd"> Note that if a is set to 1, it is the weighted mean of the previous</span>
<span class="sd"> and new data. If it set to zero, the old centroids are completely</span>
<span class="sd"> forgotten.</span>
<span class="sd"> :param clusterCenters: Initial cluster centers.</span>
<span class="sd"> :param clusterWeights: List of weights assigned to each cluster.</span>
<span class="sd"> >>> initCenters = [[0.0, 0.0], [1.0, 1.0]]</span>
<span class="sd"> >>> initWeights = [1.0, 1.0]</span>
<span class="sd"> >>> stkm = StreamingKMeansModel(initCenters, initWeights)</span>
<span class="sd"> >>> data = sc.parallelize([[-0.1, -0.1], [0.1, 0.1],</span>
<span class="sd"> ... [0.9, 0.9], [1.1, 1.1]])</span>
<span class="sd"> >>> stkm = stkm.update(data, 1.0, u"batches")</span>
<span class="sd"> >>> stkm.centers</span>
<span class="sd"> array([[ 0., 0.],</span>
<span class="sd"> [ 1., 1.]])</span>
<span class="sd"> >>> stkm.predict([-0.1, -0.1])</span>
<span class="sd"> 0</span>
<span class="sd"> >>> stkm.predict([0.9, 0.9])</span>
<span class="sd"> 1</span>
<span class="sd"> >>> stkm.clusterWeights</span>
<span class="sd"> [3.0, 3.0]</span>
<span class="sd"> >>> decayFactor = 0.0</span>
<span class="sd"> >>> data = sc.parallelize([DenseVector([1.5, 1.5]), DenseVector([0.2, 0.2])])</span>
<span class="sd"> >>> stkm = stkm.update(data, 0.0, u"batches")</span>
<span class="sd"> >>> stkm.centers</span>
<span class="sd"> array([[ 0.2, 0.2],</span>
<span class="sd"> [ 1.5, 1.5]])</span>
<span class="sd"> >>> stkm.clusterWeights</span>
<span class="sd"> [1.0, 1.0]</span>
<span class="sd"> >>> stkm.predict([0.2, 0.2])</span>
<span class="sd"> 0</span>
<span class="sd"> >>> stkm.predict([1.5, 1.5])</span>
<span class="sd"> 1</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">clusterCenters</span><span class="p">,</span> <span class="n">clusterWeights</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">StreamingKMeansModel</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">centers</span><span class="o">=</span><span class="n">clusterCenters</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_clusterWeights</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">clusterWeights</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">clusterWeights</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Return the cluster weights."""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_clusterWeights</span>
<span class="nd">@ignore_unicode_prefix</span>
<div class="viewcode-block" id="StreamingKMeansModel.update"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeansModel.update">[docs]</a> <span class="k">def</span> <span class="nf">update</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">decayFactor</span><span class="p">,</span> <span class="n">timeUnit</span><span class="p">):</span>
<span class="sd">"""Update the centroids, according to data</span>
<span class="sd"> :param data: Should be a RDD that represents the new data.</span>
<span class="sd"> :param decayFactor: forgetfulness of the previous centroids.</span>
<span class="sd"> :param timeUnit: Can be "batches" or "points". If points, then the</span>
<span class="sd"> decay factor is raised to the power of number of new</span>
<span class="sd"> points and if batches, it is used as it is.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"Data should be of an RDD, got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">data</span><span class="p">))</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">)</span>
<span class="n">decayFactor</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">decayFactor</span><span class="p">)</span>
<span class="k">if</span> <span class="n">timeUnit</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s">"batches"</span><span class="p">,</span> <span class="s">"points"</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s">"timeUnit should be 'batches' or 'points', got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="n">timeUnit</span><span class="p">)</span>
<span class="n">vectorCenters</span> <span class="o">=</span> <span class="p">[</span><span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">center</span><span class="p">)</span> <span class="k">for</span> <span class="n">center</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">centers</span><span class="p">]</span>
<span class="n">updatedModel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span>
<span class="s">"updateStreamingKMeansModel"</span><span class="p">,</span> <span class="n">vectorCenters</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_clusterWeights</span><span class="p">,</span>
<span class="n">data</span><span class="p">,</span> <span class="n">decayFactor</span><span class="p">,</span> <span class="n">timeUnit</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">centers</span> <span class="o">=</span> <span class="n">array</span><span class="p">(</span><span class="n">updatedModel</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_clusterWeights</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">updatedModel</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="k">return</span> <span class="bp">self</span>
</div></div>
<div class="viewcode-block" id="StreamingKMeans"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans">[docs]</a><span class="k">class</span> <span class="nc">StreamingKMeans</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Provides methods to set k, decayFactor, timeUnit to configure the</span>
<span class="sd"> KMeans algorithm for fitting and predicting on incoming dstreams.</span>
<span class="sd"> More details on how the centroids are updated are provided under the</span>
<span class="sd"> docs of StreamingKMeansModel.</span>
<span class="sd"> :param k: int, number of clusters</span>
<span class="sd"> :param decayFactor: float, forgetfulness of the previous centroids.</span>
<span class="sd"> :param timeUnit: can be "batches" or "points". If points, then the</span>
<span class="sd"> decayfactor is raised to the power of no. of new points.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">decayFactor</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">timeUnit</span><span class="o">=</span><span class="s">"batches"</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_k</span> <span class="o">=</span> <span class="n">k</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_decayFactor</span> <span class="o">=</span> <span class="n">decayFactor</span>
<span class="k">if</span> <span class="n">timeUnit</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s">"batches"</span><span class="p">,</span> <span class="s">"points"</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s">"timeUnit should be 'batches' or 'points', got </span><span class="si">%s</span><span class="s">."</span> <span class="o">%</span> <span class="n">timeUnit</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_timeUnit</span> <span class="o">=</span> <span class="n">timeUnit</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="bp">None</span>
<div class="viewcode-block" id="StreamingKMeans.latestModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.latestModel">[docs]</a> <span class="k">def</span> <span class="nf">latestModel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Return the latest model"""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span>
</div>
<span class="k">def</span> <span class="nf">_validate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s">"Initial centers should be set either by setInitialCenters "</span>
<span class="s">"or setRandomCenters."</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dstream</span><span class="p">,</span> <span class="n">DStream</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="s">"Expected dstream to be of type DStream, "</span>
<span class="s">"got type </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">dstream</span><span class="p">))</span>
<div class="viewcode-block" id="StreamingKMeans.setK"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.setK">[docs]</a> <span class="k">def</span> <span class="nf">setK</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">k</span><span class="p">):</span>
<span class="sd">"""Set number of clusters."""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_k</span> <span class="o">=</span> <span class="n">k</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.setDecayFactor"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.setDecayFactor">[docs]</a> <span class="k">def</span> <span class="nf">setDecayFactor</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">decayFactor</span><span class="p">):</span>
<span class="sd">"""Set decay factor."""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_decayFactor</span> <span class="o">=</span> <span class="n">decayFactor</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.setHalfLife"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.setHalfLife">[docs]</a> <span class="k">def</span> <span class="nf">setHalfLife</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">halfLife</span><span class="p">,</span> <span class="n">timeUnit</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Set number of batches after which the centroids of that</span>
<span class="sd"> particular batch has half the weightage.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_timeUnit</span> <span class="o">=</span> <span class="n">timeUnit</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_decayFactor</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">log</span><span class="p">(</span><span class="mf">0.5</span><span class="p">)</span> <span class="o">/</span> <span class="n">halfLife</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.setInitialCenters"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.setInitialCenters">[docs]</a> <span class="k">def</span> <span class="nf">setInitialCenters</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">centers</span><span class="p">,</span> <span class="n">weights</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Set initial centers. Should be set before calling trainOn.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">StreamingKMeansModel</span><span class="p">(</span><span class="n">centers</span><span class="p">,</span> <span class="n">weights</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.setRandomCenters"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.setRandomCenters">[docs]</a> <span class="k">def</span> <span class="nf">setRandomCenters</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dim</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">seed</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Set the initial centres to be random samples from</span>
<span class="sd"> a gaussian population with constant weights.</span>
<span class="sd"> """</span>
<span class="n">rng</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">RandomState</span><span class="p">(</span><span class="n">seed</span><span class="p">)</span>
<span class="n">clusterCenters</span> <span class="o">=</span> <span class="n">rng</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_k</span><span class="p">,</span> <span class="n">dim</span><span class="p">)</span>
<span class="n">clusterWeights</span> <span class="o">=</span> <span class="n">tile</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_k</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">StreamingKMeansModel</span><span class="p">(</span><span class="n">clusterCenters</span><span class="p">,</span> <span class="n">clusterWeights</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.trainOn"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.trainOn">[docs]</a> <span class="k">def</span> <span class="nf">trainOn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">):</span>
<span class="sd">"""Train the model on the incoming dstream."""</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">update</span><span class="p">(</span><span class="n">rdd</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decayFactor</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_timeUnit</span><span class="p">)</span>
<span class="n">dstream</span><span class="o">.</span><span class="n">foreachRDD</span><span class="p">(</span><span class="n">update</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.predictOn"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.predictOn">[docs]</a> <span class="k">def</span> <span class="nf">predictOn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Make predictions on a dstream.</span>
<span class="sd"> Returns a transformed dstream object</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dstream</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
</div>
<div class="viewcode-block" id="StreamingKMeans.predictOnValues"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.StreamingKMeans.predictOnValues">[docs]</a> <span class="k">def</span> <span class="nf">predictOnValues</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Make predictions on a keyed dstream.</span>
<span class="sd"> Returns a transformed dstream object.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dstream</span><span class="o">.</span><span class="n">mapValues</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
</div></div>
<div class="viewcode-block" id="LDAModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDAModel">[docs]</a><span class="k">class</span> <span class="nc">LDAModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">""" A clustering model derived from the LDA method.</span>
<span class="sd"> Latent Dirichlet Allocation (LDA), a topic model designed for text documents.</span>
<span class="sd"> Terminology</span>
<span class="sd"> - "word" = "term": an element of the vocabulary</span>
<span class="sd"> - "token": instance of a term appearing in a document</span>
<span class="sd"> - "topic": multinomial distribution over words representing some concept</span>
<span class="sd"> References:</span>
<span class="sd"> - Original LDA paper (journal version):</span>
<span class="sd"> Blei, Ng, and Jordan. "Latent Dirichlet Allocation." JMLR, 2003.</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> from numpy.testing import assert_almost_equal, assert_equal</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... [1, Vectors.dense([0.0, 1.0])],</span>
<span class="sd"> ... [2, SparseVector(2, {0: 1.0})],</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> rdd = sc.parallelize(data)</span>
<span class="sd"> >>> model = LDA.train(rdd, k=2)</span>
<span class="sd"> >>> model.vocabSize()</span>
<span class="sd"> 2</span>
<span class="sd"> >>> topics = model.topicsMatrix()</span>
<span class="sd"> >>> topics_expect = array([[0.5, 0.5], [0.5, 0.5]])</span>
<span class="sd"> >>> assert_almost_equal(topics, topics_expect, 1)</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> model.save(sc, path)</span>
<span class="sd"> >>> sameModel = LDAModel.load(sc, path)</span>
<span class="sd"> >>> assert_equal(sameModel.topicsMatrix(), model.topicsMatrix())</span>
<span class="sd"> >>> sameModel.vocabSize() == model.vocabSize()</span>
<span class="sd"> True</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except OSError:</span>
<span class="sd"> ... pass</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="LDAModel.topicsMatrix"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDAModel.topicsMatrix">[docs]</a> <span class="k">def</span> <span class="nf">topicsMatrix</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Inferred topics, where each topic is represented by a distribution over terms."""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"topicsMatrix"</span><span class="p">)</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span>
</div>
<div class="viewcode-block" id="LDAModel.vocabSize"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDAModel.vocabSize">[docs]</a> <span class="k">def</span> <span class="nf">vocabSize</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Vocabulary size (number of terms or terms in the vocabulary)"""</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"vocabSize"</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="LDAModel.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDAModel.save">[docs]</a> <span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">"""Save the LDAModel on to disk.</span>
<span class="sd"> :param sc: SparkContext</span>
<span class="sd"> :param path: str, path to where the model needs to be stored.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">SparkContext</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"sc should be a SparkContext, got type </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">sc</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"path should be a basestring, got type </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>
</div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="LDAModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDAModel.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">"""Load the LDAModel from disk.</span>
<span class="sd"> :param sc: SparkContext</span>
<span class="sd"> :param path: str, path to where the model is stored.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">SparkContext</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"sc should be a SparkContext, got type </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">sc</span><span class="p">))</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s">"path should be a basestring, got type </span><span class="si">%s</span><span class="s">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">))</span>
<span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">clustering</span><span class="o">.</span><span class="n">DistributedLDAModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span>
<span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span>
<span class="k">return</span> <span class="n">cls</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="LDA"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDA">[docs]</a><span class="k">class</span> <span class="nc">LDA</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="LDA.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.clustering.LDA.train">[docs]</a> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIterations</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">docConcentration</span><span class="o">=-</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">topicConcentration</span><span class="o">=-</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">optimizer</span><span class="o">=</span><span class="s">"em"</span><span class="p">):</span>
<span class="sd">"""Train a LDA model.</span>
<span class="sd"> :param rdd: RDD of data points</span>
<span class="sd"> :param k: Number of clusters you want</span>
<span class="sd"> :param maxIterations: Number of iterations. Default to 20</span>
<span class="sd"> :param docConcentration: Concentration parameter (commonly named "alpha")</span>
<span class="sd"> for the prior placed on documents' distributions over topics ("theta").</span>
<span class="sd"> :param topicConcentration: Concentration parameter (commonly named "beta" or "eta")</span>
<span class="sd"> for the prior placed on topics' distributions over terms.</span>
<span class="sd"> :param seed: Random Seed</span>
<span class="sd"> :param checkpointInterval: Period (in iterations) between checkpoints.</span>
<span class="sd"> :param optimizer: LDAOptimizer used to perform the actual calculation.</span>
<span class="sd"> Currently "em", "online" are supported. Default to "em".</span>
<span class="sd"> """</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainLDAModel"</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">maxIterations</span><span class="p">,</span>
<span class="n">docConcentration</span><span class="p">,</span> <span class="n">topicConcentration</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">)</span>
<span class="k">return</span> <span class="n">LDAModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
</div></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
<span class="kn">import</span> <span class="nn">doctest</span>
<span class="kn">import</span> <span class="nn">pyspark.mllib.clustering</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">clustering</span><span class="o">.</span><span class="n">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">'local[4]'</span><span class="p">,</span> <span class="s">'PythonTest'</span><span class="p">,</span> <span class="n">batchSize</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sc'</span><span class="p">]</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
<span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
<span class="nb">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="n">__name__</span> <span class="o">==</span> <span class="s">"__main__"</span><span class="p">:</span>
<span class="n">_test</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../../index.html">
<img class="logo" src="../../../_static/spark-logo-hd.png" alt="Logo"/>
</a></p>
<div id="searchbox" style="display: none" role="search">
<h3>Quick search</h3>
<form class="search" action="../../../search.html" method="get">
<input type="text" name="q" />
<input type="submit" value="Go" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
<p class="searchtip" style="font-size: 90%">
Enter search terms or a module, class or function name.
</p>
</div>
<script type="text/javascript">$('#searchbox').show(0);</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="nav-item nav-item-0"><a href="../../../index.html">PySpark master documentation</a> »</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
</ul>
</div>
<div class="footer" role="contentinfo">
© Copyright .
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.3.1.
</div>
</body>
</html>
|
