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
|
<!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.feature — 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.feature</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="sd">"""</span>
<span class="sd">Python package for feature in MLlib.</span>
<span class="sd">"""</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">absolute_import</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">import</span> <span class="nn">binascii</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">basestring</span> <span class="o">=</span> <span class="nb">str</span>
<span class="nb">unicode</span> <span class="o">=</span> <span class="nb">str</span>
<span class="kn">from</span> <span class="nn">py4j.protocol</span> <span class="kn">import</span> <span class="n">Py4JJavaError</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">callMLlibFunc</span><span class="p">,</span> <span class="n">JavaModelWrapper</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">Vector</span><span class="p">,</span> <span class="n">Vectors</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">,</span> <span class="n">_convert_to_vector</span><span class="p">)</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.util</span> <span class="kn">import</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">JavaSaveable</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'Normalizer'</span><span class="p">,</span> <span class="s">'StandardScalerModel'</span><span class="p">,</span> <span class="s">'StandardScaler'</span><span class="p">,</span>
<span class="s">'HashingTF'</span><span class="p">,</span> <span class="s">'IDFModel'</span><span class="p">,</span> <span class="s">'IDF'</span><span class="p">,</span> <span class="s">'Word2Vec'</span><span class="p">,</span> <span class="s">'Word2VecModel'</span><span class="p">,</span>
<span class="s">'ChiSqSelector'</span><span class="p">,</span> <span class="s">'ChiSqSelectorModel'</span><span class="p">,</span> <span class="s">'ElementwiseProduct'</span><span class="p">]</span>
<span class="k">class</span> <span class="nc">VectorTransformer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: DeveloperApi</span>
<span class="sd"> Base class for transformation of a vector or RDD of vector</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Applies transformation on a vector.</span>
<span class="sd"> :param vector: vector to be transformed.</span>
<span class="sd"> """</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span>
<div class="viewcode-block" id="Normalizer"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Normalizer">[docs]</a><span class="k">class</span> <span class="nc">Normalizer</span><span class="p">(</span><span class="n">VectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Normalizes samples individually to unit L\ :sup:`p`\ norm</span>
<span class="sd"> For any 1 <= `p` < float('inf'), normalizes samples using</span>
<span class="sd"> sum(abs(vector) :sup:`p`) :sup:`(1/p)` as norm.</span>
<span class="sd"> For `p` = float('inf'), max(abs(vector)) will be used as norm for</span>
<span class="sd"> normalization.</span>
<span class="sd"> :param p: Normalization in L^p^ space, p = 2 by default.</span>
<span class="sd"> >>> v = Vectors.dense(range(3))</span>
<span class="sd"> >>> nor = Normalizer(1)</span>
<span class="sd"> >>> nor.transform(v)</span>
<span class="sd"> DenseVector([0.0, 0.3333, 0.6667])</span>
<span class="sd"> >>> rdd = sc.parallelize([v])</span>
<span class="sd"> >>> nor.transform(rdd).collect()</span>
<span class="sd"> [DenseVector([0.0, 0.3333, 0.6667])]</span>
<span class="sd"> >>> nor2 = Normalizer(float("inf"))</span>
<span class="sd"> >>> nor2.transform(v)</span>
<span class="sd"> DenseVector([0.0, 0.5, 1.0])</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">p</span><span class="o">=</span><span class="mf">2.0</span><span class="p">):</span>
<span class="k">assert</span> <span class="n">p</span> <span class="o">>=</span> <span class="mf">1.0</span><span class="p">,</span> <span class="s">"p should be greater than 1.0"</span>
<span class="bp">self</span><span class="o">.</span><span class="n">p</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
<div class="viewcode-block" id="Normalizer.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Normalizer.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Applies unit length normalization on a vector.</span>
<span class="sd"> :param vector: vector or RDD of vector to be normalized.</span>
<span class="sd"> :return: normalized vector. If the norm of the input is zero, it</span>
<span class="sd"> will return the input vector.</span>
<span class="sd"> """</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span>
<span class="k">assert</span> <span class="n">sc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">,</span> <span class="s">"SparkContext should be initialized first"</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">vector</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="k">else</span><span class="p">:</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"normalizeVector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span>
</div></div>
<span class="k">class</span> <span class="nc">JavaVectorTransformer</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">VectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Wrapper for the model in JVM</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Applies transformation on a vector or an RDD[Vector].</span>
<span class="sd"> Note: In Python, transform cannot currently be used within</span>
<span class="sd"> an RDD transformation or action.</span>
<span class="sd"> Call transform directly on the RDD instead.</span>
<span class="sd"> :param vector: Vector or RDD of Vector to be transformed.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">vector</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="k">else</span><span class="p">:</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</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">"transform"</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span>
<div class="viewcode-block" id="StandardScalerModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScalerModel">[docs]</a><span class="k">class</span> <span class="nc">StandardScalerModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Represents a StandardScaler model that can transform vectors.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="StandardScalerModel.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScalerModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Applies standardization transformation on a vector.</span>
<span class="sd"> Note: In Python, transform cannot currently be used within</span>
<span class="sd"> an RDD transformation or action.</span>
<span class="sd"> Call transform directly on the RDD instead.</span>
<span class="sd"> :param vector: Vector or RDD of Vector to be standardized.</span>
<span class="sd"> :return: Standardized vector. If the variance of a column is</span>
<span class="sd"> zero, it will return default `0.0` for the column with</span>
<span class="sd"> zero variance.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="StandardScalerModel.setWithMean"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScalerModel.setWithMean">[docs]</a> <span class="k">def</span> <span class="nf">setWithMean</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">withMean</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Setter of the boolean which decides</span>
<span class="sd"> whether it uses mean or not</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"setWithMean"</span><span class="p">,</span> <span class="n">withMean</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StandardScalerModel.setWithStd"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScalerModel.setWithStd">[docs]</a> <span class="k">def</span> <span class="nf">setWithStd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">withStd</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Setter of the boolean which decides</span>
<span class="sd"> whether it uses std or not</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s">"setWithStd"</span><span class="p">,</span> <span class="n">withStd</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div></div>
<div class="viewcode-block" id="StandardScaler"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScaler">[docs]</a><span class="k">class</span> <span class="nc">StandardScaler</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"> Standardizes features by removing the mean and scaling to unit</span>
<span class="sd"> variance using column summary statistics on the samples in the</span>
<span class="sd"> training set.</span>
<span class="sd"> :param withMean: False by default. Centers the data with mean</span>
<span class="sd"> before scaling. It will build a dense output, so this</span>
<span class="sd"> does not work on sparse input and will raise an</span>
<span class="sd"> exception.</span>
<span class="sd"> :param withStd: True by default. Scales the data to unit</span>
<span class="sd"> standard deviation.</span>
<span class="sd"> >>> vs = [Vectors.dense([-2.0, 2.3, 0]), Vectors.dense([3.8, 0.0, 1.9])]</span>
<span class="sd"> >>> dataset = sc.parallelize(vs)</span>
<span class="sd"> >>> standardizer = StandardScaler(True, True)</span>
<span class="sd"> >>> model = standardizer.fit(dataset)</span>
<span class="sd"> >>> result = model.transform(dataset)</span>
<span class="sd"> >>> for r in result.collect(): r</span>
<span class="sd"> DenseVector([-0.7071, 0.7071, -0.7071])</span>
<span class="sd"> DenseVector([0.7071, -0.7071, 0.7071])</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">withMean</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">withStd</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">withMean</span> <span class="ow">or</span> <span class="n">withStd</span><span class="p">):</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s">"Both withMean and withStd are false. The model does nothing."</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">withMean</span> <span class="o">=</span> <span class="n">withMean</span>
<span class="bp">self</span><span class="o">.</span><span class="n">withStd</span> <span class="o">=</span> <span class="n">withStd</span>
<div class="viewcode-block" id="StandardScaler.fit"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.StandardScaler.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Computes the mean and variance and stores as a model to be used</span>
<span class="sd"> for later scaling.</span>
<span class="sd"> :param dataset: The data used to compute the mean and variance</span>
<span class="sd"> to build the transformation model.</span>
<span class="sd"> :return: a StandardScalarModel</span>
<span class="sd"> """</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">dataset</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">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"fitStandardScaler"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">withMean</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">withStd</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span>
<span class="k">return</span> <span class="n">StandardScalerModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="ChiSqSelectorModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ChiSqSelectorModel">[docs]</a><span class="k">class</span> <span class="nc">ChiSqSelectorModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Represents a Chi Squared selector model.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ChiSqSelectorModel.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ChiSqSelectorModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Applies transformation on a vector.</span>
<span class="sd"> :param vector: Vector or RDD of Vector to be transformed.</span>
<span class="sd"> :return: transformed vector.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="ChiSqSelector"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ChiSqSelector">[docs]</a><span class="k">class</span> <span class="nc">ChiSqSelector</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"> Creates a ChiSquared feature selector.</span>
<span class="sd"> :param numTopFeatures: number of features that selector will select.</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(3, {0: 8.0, 1: 7.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(3, {1: 9.0, 2: 6.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, [0.0, 9.0, 8.0]),</span>
<span class="sd"> ... LabeledPoint(2.0, [8.0, 9.0, 5.0])</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> model = ChiSqSelector(1).fit(sc.parallelize(data))</span>
<span class="sd"> >>> model.transform(SparseVector(3, {1: 9.0, 2: 6.0}))</span>
<span class="sd"> SparseVector(1, {0: 6.0})</span>
<span class="sd"> >>> model.transform(DenseVector([8.0, 9.0, 5.0]))</span>
<span class="sd"> DenseVector([5.0])</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">numTopFeatures</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numTopFeatures</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">numTopFeatures</span><span class="p">)</span>
<div class="viewcode-block" id="ChiSqSelector.fit"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ChiSqSelector.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</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="sd">"""</span>
<span class="sd"> Returns a ChiSquared feature selector.</span>
<span class="sd"> :param data: an `RDD[LabeledPoint]` containing the labeled dataset</span>
<span class="sd"> with categorical features. Real-valued features will be</span>
<span class="sd"> treated as categorical for each distinct value.</span>
<span class="sd"> Apply feature discretizer before using this function.</span>
<span class="sd"> """</span>
<span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"fitChiSqSelector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numTopFeatures</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ChiSqSelectorModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
</div></div>
<span class="k">class</span> <span class="nc">PCAModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.</span>
<span class="sd"> """</span>
<span class="k">class</span> <span class="nc">PCA</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A feature transformer that projects vectors to a low-dimensional space using PCA.</span>
<span class="sd"> >>> data = [Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),</span>
<span class="sd"> ... Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),</span>
<span class="sd"> ... Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0])]</span>
<span class="sd"> >>> model = PCA(2).fit(sc.parallelize(data))</span>
<span class="sd"> >>> pcArray = model.transform(Vectors.sparse(5, [(1, 1.0), (3, 7.0)])).toArray()</span>
<span class="sd"> >>> pcArray[0]</span>
<span class="sd"> 1.648...</span>
<span class="sd"> >>> pcArray[1]</span>
<span class="sd"> -4.013...</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="p">):</span>
<span class="sd">"""</span>
<span class="sd"> :param k: number of principal components.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">k</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">k</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">fit</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="sd">"""</span>
<span class="sd"> Computes a [[PCAModel]] that contains the principal components of the input vectors.</span>
<span class="sd"> :param data: source vectors</span>
<span class="sd"> """</span>
<span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"fitPCA"</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">data</span><span class="p">)</span>
<span class="k">return</span> <span class="n">PCAModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
<div class="viewcode-block" id="HashingTF"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.HashingTF">[docs]</a><span class="k">class</span> <span class="nc">HashingTF</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"> Maps a sequence of terms to their term frequencies using the hashing</span>
<span class="sd"> trick.</span>
<span class="sd"> Note: the terms must be hashable (can not be dict/set/list...).</span>
<span class="sd"> :param numFeatures: number of features (default: 2^20)</span>
<span class="sd"> >>> htf = HashingTF(100)</span>
<span class="sd"> >>> doc = "a a b b c d".split(" ")</span>
<span class="sd"> >>> htf.transform(doc)</span>
<span class="sd"> SparseVector(100, {...})</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">numFeatures</span><span class="o">=</span><span class="mi">1</span> <span class="o"><<</span> <span class="mi">20</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span> <span class="o">=</span> <span class="n">numFeatures</span>
<div class="viewcode-block" id="HashingTF.indexOf"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.HashingTF.indexOf">[docs]</a> <span class="k">def</span> <span class="nf">indexOf</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">term</span><span class="p">):</span>
<span class="sd">""" Returns the index of the input term. """</span>
<span class="k">return</span> <span class="nb">hash</span><span class="p">(</span><span class="n">term</span><span class="p">)</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span>
</div>
<div class="viewcode-block" id="HashingTF.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.HashingTF.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">document</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Transforms the input document (list of terms) to term frequency</span>
<span class="sd"> vectors, or transform the RDD of document to RDD of term</span>
<span class="sd"> frequency vectors.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">document</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="k">return</span> <span class="n">document</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">transform</span><span class="p">)</span>
<span class="n">freq</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">term</span> <span class="ow">in</span> <span class="n">document</span><span class="p">:</span>
<span class="n">i</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">indexOf</span><span class="p">(</span><span class="n">term</span><span class="p">)</span>
<span class="n">freq</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">freq</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1.0</span>
<span class="k">return</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">sparse</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numFeatures</span><span class="p">,</span> <span class="n">freq</span><span class="o">.</span><span class="n">items</span><span class="p">())</span>
</div></div>
<div class="viewcode-block" id="IDFModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.IDFModel">[docs]</a><span class="k">class</span> <span class="nc">IDFModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Represents an IDF model that can transform term frequency vectors.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="IDFModel.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.IDFModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</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"> Transforms term frequency (TF) vectors to TF-IDF vectors.</span>
<span class="sd"> If `minDocFreq` was set for the IDF calculation,</span>
<span class="sd"> the terms which occur in fewer than `minDocFreq`</span>
<span class="sd"> documents will have an entry of 0.</span>
<span class="sd"> Note: In Python, transform cannot currently be used within</span>
<span class="sd"> an RDD transformation or action.</span>
<span class="sd"> Call transform directly on the RDD instead.</span>
<span class="sd"> :param x: an RDD of term frequency vectors or a term frequency</span>
<span class="sd"> vector</span>
<span class="sd"> :return: an RDD of TF-IDF vectors or a TF-IDF vector</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">JavaVectorTransformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="IDFModel.idf"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.IDFModel.idf">[docs]</a> <span class="k">def</span> <span class="nf">idf</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the current IDF vector.</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">'idf'</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="IDF"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.IDF">[docs]</a><span class="k">class</span> <span class="nc">IDF</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"> Inverse document frequency (IDF).</span>
<span class="sd"> The standard formulation is used: `idf = log((m + 1) / (d(t) + 1))`,</span>
<span class="sd"> where `m` is the total number of documents and `d(t)` is the number</span>
<span class="sd"> of documents that contain term `t`.</span>
<span class="sd"> This implementation supports filtering out terms which do not appear</span>
<span class="sd"> in a minimum number of documents (controlled by the variable</span>
<span class="sd"> `minDocFreq`). For terms that are not in at least `minDocFreq`</span>
<span class="sd"> documents, the IDF is found as 0, resulting in TF-IDFs of 0.</span>
<span class="sd"> :param minDocFreq: minimum of documents in which a term</span>
<span class="sd"> should appear for filtering</span>
<span class="sd"> >>> n = 4</span>
<span class="sd"> >>> freqs = [Vectors.sparse(n, (1, 3), (1.0, 2.0)),</span>
<span class="sd"> ... Vectors.dense([0.0, 1.0, 2.0, 3.0]),</span>
<span class="sd"> ... Vectors.sparse(n, [1], [1.0])]</span>
<span class="sd"> >>> data = sc.parallelize(freqs)</span>
<span class="sd"> >>> idf = IDF()</span>
<span class="sd"> >>> model = idf.fit(data)</span>
<span class="sd"> >>> tfidf = model.transform(data)</span>
<span class="sd"> >>> for r in tfidf.collect(): r</span>
<span class="sd"> SparseVector(4, {1: 0.0, 3: 0.5754})</span>
<span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span>
<span class="sd"> SparseVector(4, {1: 0.0})</span>
<span class="sd"> >>> model.transform(Vectors.dense([0.0, 1.0, 2.0, 3.0]))</span>
<span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span>
<span class="sd"> >>> model.transform([0.0, 1.0, 2.0, 3.0])</span>
<span class="sd"> DenseVector([0.0, 0.0, 1.3863, 0.863])</span>
<span class="sd"> >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))</span>
<span class="sd"> SparseVector(4, {1: 0.0, 3: 0.5754})</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">minDocFreq</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">minDocFreq</span> <span class="o">=</span> <span class="n">minDocFreq</span>
<div class="viewcode-block" id="IDF.fit"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.IDF.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Computes the inverse document frequency.</span>
<span class="sd"> :param dataset: an RDD of term frequency vectors</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">dataset</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">"dataset should be an RDD of term frequency vectors"</span><span class="p">)</span>
<span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"fitIDF"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">minDocFreq</span><span class="p">,</span> <span class="n">dataset</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="k">return</span> <span class="n">IDFModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="Word2VecModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2VecModel">[docs]</a><span class="k">class</span> <span class="nc">Word2VecModel</span><span class="p">(</span><span class="n">JavaVectorTransformer</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"> class for Word2Vec model</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="Word2VecModel.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2VecModel.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">word</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Transforms a word to its vector representation</span>
<span class="sd"> Note: local use only</span>
<span class="sd"> :param word: a word</span>
<span class="sd"> :return: vector representation of word(s)</span>
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</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">"transform"</span><span class="p">,</span> <span class="n">word</span><span class="p">)</span>
<span class="k">except</span> <span class="n">Py4JJavaError</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"</span><span class="si">%s</span><span class="s"> not found"</span> <span class="o">%</span> <span class="n">word</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="Word2VecModel.findSynonyms"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2VecModel.findSynonyms">[docs]</a> <span class="k">def</span> <span class="nf">findSynonyms</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">word</span><span class="p">,</span> <span class="n">num</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Find synonyms of a word</span>
<span class="sd"> :param word: a word or a vector representation of word</span>
<span class="sd"> :param num: number of synonyms to find</span>
<span class="sd"> :return: array of (word, cosineSimilarity)</span>
<span class="sd"> Note: local use only</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">word</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
<span class="n">word</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">word</span><span class="p">)</span>
<span class="n">words</span><span class="p">,</span> <span class="n">similarity</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">"findSynonyms"</span><span class="p">,</span> <span class="n">word</span><span class="p">,</span> <span class="n">num</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">zip</span><span class="p">(</span><span class="n">words</span><span class="p">,</span> <span class="n">similarity</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="Word2VecModel.getVectors"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2VecModel.getVectors">[docs]</a> <span class="k">def</span> <span class="nf">getVectors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns a map of words to their vector representations.</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">"getVectors"</span><span class="p">)</span>
</div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="Word2VecModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2VecModel.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">jmodel</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">feature</span> \
<span class="o">.</span><span class="n">Word2VecModel</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">Word2VecModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
</div></div>
<span class="nd">@ignore_unicode_prefix</span>
<div class="viewcode-block" id="Word2Vec"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec">[docs]</a><span class="k">class</span> <span class="nc">Word2Vec</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Word2Vec creates vector representation of words in a text corpus.</span>
<span class="sd"> The algorithm first constructs a vocabulary from the corpus</span>
<span class="sd"> and then learns vector representation of words in the vocabulary.</span>
<span class="sd"> The vector representation can be used as features in</span>
<span class="sd"> natural language processing and machine learning algorithms.</span>
<span class="sd"> We used skip-gram model in our implementation and hierarchical</span>
<span class="sd"> softmax method to train the model. The variable names in the</span>
<span class="sd"> implementation matches the original C implementation.</span>
<span class="sd"> For original C implementation,</span>
<span class="sd"> see https://code.google.com/p/word2vec/</span>
<span class="sd"> For research papers, see</span>
<span class="sd"> Efficient Estimation of Word Representations in Vector Space</span>
<span class="sd"> and Distributed Representations of Words and Phrases and their</span>
<span class="sd"> Compositionality.</span>
<span class="sd"> >>> sentence = "a b " * 100 + "a c " * 10</span>
<span class="sd"> >>> localDoc = [sentence, sentence]</span>
<span class="sd"> >>> doc = sc.parallelize(localDoc).map(lambda line: line.split(" "))</span>
<span class="sd"> >>> model = Word2Vec().setVectorSize(10).setSeed(42).fit(doc)</span>
<span class="sd"> >>> syms = model.findSynonyms("a", 2)</span>
<span class="sd"> >>> [s[0] for s in syms]</span>
<span class="sd"> [u'b', u'c']</span>
<span class="sd"> >>> vec = model.transform("a")</span>
<span class="sd"> >>> syms = model.findSynonyms(vec, 2)</span>
<span class="sd"> >>> [s[0] for s in syms]</span>
<span class="sd"> [u'b', u'c']</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 = Word2VecModel.load(sc, path)</span>
<span class="sd"> >>> model.transform("a") == sameModel.transform("a")</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="sd">"""</span>
<span class="sd"> Construct Word2Vec instance</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span> <span class="o">=</span> <span class="mi">100</span>
<span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span> <span class="o">=</span> <span class="mf">0.025</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span> <span class="o">=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span> <span class="o">=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxsize</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">minCount</span> <span class="o">=</span> <span class="mi">5</span>
<div class="viewcode-block" id="Word2Vec.setVectorSize"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setVectorSize">[docs]</a> <span class="k">def</span> <span class="nf">setVectorSize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vectorSize</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets vector size (default: 100).</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span> <span class="o">=</span> <span class="n">vectorSize</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.setLearningRate"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setLearningRate">[docs]</a> <span class="k">def</span> <span class="nf">setLearningRate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">learningRate</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets initial learning rate (default: 0.025).</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span> <span class="o">=</span> <span class="n">learningRate</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.setNumPartitions"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setNumPartitions">[docs]</a> <span class="k">def</span> <span class="nf">setNumPartitions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets number of partitions (default: 1). Use a small number for</span>
<span class="sd"> accuracy.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span> <span class="o">=</span> <span class="n">numPartitions</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.setNumIterations"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setNumIterations">[docs]</a> <span class="k">def</span> <span class="nf">setNumIterations</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numIterations</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets number of iterations (default: 1), which should be smaller</span>
<span class="sd"> than or equal to number of partitions.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span> <span class="o">=</span> <span class="n">numIterations</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.setSeed"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setSeed">[docs]</a> <span class="k">def</span> <span class="nf">setSeed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">seed</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets random seed.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="n">seed</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.setMinCount"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.setMinCount">[docs]</a> <span class="k">def</span> <span class="nf">setMinCount</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">minCount</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Sets minCount, the minimum number of times a token must appear</span>
<span class="sd"> to be included in the word2vec model's vocabulary (default: 5).</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">minCount</span> <span class="o">=</span> <span class="n">minCount</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="Word2Vec.fit"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.Word2Vec.fit">[docs]</a> <span class="k">def</span> <span class="nf">fit</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="sd">"""</span>
<span class="sd"> Computes the vector representation of each word in vocabulary.</span>
<span class="sd"> :param data: training data. RDD of list of string</span>
<span class="sd"> :return: Word2VecModel instance</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 an RDD of list of string"</span><span class="p">)</span>
<span class="n">jmodel</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainWord2VecModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">vectorSize</span><span class="p">),</span>
<span class="nb">float</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">learningRate</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numPartitions</span><span class="p">),</span>
<span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">),</span>
<span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">minCount</span><span class="p">))</span>
<span class="k">return</span> <span class="n">Word2VecModel</span><span class="p">(</span><span class="n">jmodel</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="ElementwiseProduct"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ElementwiseProduct">[docs]</a><span class="k">class</span> <span class="nc">ElementwiseProduct</span><span class="p">(</span><span class="n">VectorTransformer</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Scales each column of the vector, with the supplied weight vector.</span>
<span class="sd"> i.e the elementwise product.</span>
<span class="sd"> >>> weight = Vectors.dense([1.0, 2.0, 3.0])</span>
<span class="sd"> >>> eprod = ElementwiseProduct(weight)</span>
<span class="sd"> >>> a = Vectors.dense([2.0, 1.0, 3.0])</span>
<span class="sd"> >>> eprod.transform(a)</span>
<span class="sd"> DenseVector([2.0, 2.0, 9.0])</span>
<span class="sd"> >>> b = Vectors.dense([9.0, 3.0, 4.0])</span>
<span class="sd"> >>> rdd = sc.parallelize([a, b])</span>
<span class="sd"> >>> eprod.transform(rdd).collect()</span>
<span class="sd"> [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]</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">scalingVector</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scalingVector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">scalingVector</span><span class="p">)</span>
<div class="viewcode-block" id="ElementwiseProduct.transform"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.feature.ElementwiseProduct.transform">[docs]</a> <span class="k">def</span> <span class="nf">transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vector</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Computes the Hadamard product of the vector.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vector</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">vector</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="k">else</span><span class="p">:</span>
<span class="n">vector</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"elementwiseProductVector"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">scalingVector</span><span class="p">,</span> <span class="n">vector</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">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</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">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</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>
|
