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
|
<!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.classification — 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.classification</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">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">exp</span>
<span class="kn">import</span> <span class="nn">numpy</span>
<span class="kn">from</span> <span class="nn">numpy</span> <span class="kn">import</span> <span class="n">array</span>
<span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">RDD</span>
<span class="kn">from</span> <span class="nn">pyspark.streaming</span> <span class="kn">import</span> <span class="n">DStream</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">_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">DenseVector</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">,</span> <span class="n">_convert_to_vector</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">LabeledPoint</span><span class="p">,</span> <span class="n">LinearModel</span><span class="p">,</span> <span class="n">_regression_train_wrapper</span><span class="p">,</span>
<span class="n">StreamingLinearAlgorithm</span><span class="p">)</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="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'LogisticRegressionModel'</span><span class="p">,</span> <span class="s">'LogisticRegressionWithSGD'</span><span class="p">,</span> <span class="s">'LogisticRegressionWithLBFGS'</span><span class="p">,</span>
<span class="s">'SVMModel'</span><span class="p">,</span> <span class="s">'SVMWithSGD'</span><span class="p">,</span> <span class="s">'NaiveBayesModel'</span><span class="p">,</span> <span class="s">'NaiveBayes'</span><span class="p">,</span>
<span class="s">'StreamingLogisticRegressionWithSGD'</span><span class="p">]</span>
<span class="k">class</span> <span class="nc">LinearClassificationModel</span><span class="p">(</span><span class="n">LinearModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A private abstract class representing a multiclass classification</span>
<span class="sd"> model. The categories are represented by int values: 0, 1, 2, etc.</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">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LinearClassificationModel</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">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">def</span> <span class="nf">setThreshold</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Sets the threshold that separates positive predictions from</span>
<span class="sd"> negative predictions. An example with prediction score greater</span>
<span class="sd"> than or equal to this threshold is identified as an positive,</span>
<span class="sd"> and negative otherwise. It is used for binary classification</span>
<span class="sd"> only.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="n">value</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">threshold</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Returns the threshold (if any) used for converting raw</span>
<span class="sd"> prediction scores into 0/1 predictions. It is used for</span>
<span class="sd"> binary classification only.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span>
<span class="k">def</span> <span class="nf">clearThreshold</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> .. note:: Experimental</span>
<span class="sd"> Clears the threshold so that `predict` will output raw</span>
<span class="sd"> prediction scores. It is used for binary classification only.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="bp">None</span>
<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">test</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Predict values for a single data point or an RDD of points</span>
<span class="sd"> using the model trained.</span>
<span class="sd"> """</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span>
<div class="viewcode-block" id="LogisticRegressionModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionModel</span><span class="p">(</span><span class="n">LinearClassificationModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Classification model trained using Multinomial/Binary Logistic</span>
<span class="sd"> Regression.</span>
<span class="sd"> :param weights: Weights computed for every feature.</span>
<span class="sd"> :param intercept: Intercept computed for this model. (Only used</span>
<span class="sd"> in Binary Logistic Regression. In Multinomial Logistic</span>
<span class="sd"> Regression, the intercepts will not be a single value,</span>
<span class="sd"> so the intercepts will be part of the weights.)</span>
<span class="sd"> :param numFeatures: the dimension of the features.</span>
<span class="sd"> :param numClasses: the number of possible outcomes for k classes</span>
<span class="sd"> classification problem in Multinomial Logistic Regression.</span>
<span class="sd"> By default, it is binary logistic regression so numClasses</span>
<span class="sd"> will be set to 2.</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(data), iterations=10)</span>
<span class="sd"> >>> lrm.predict([1.0, 0.0])</span>
<span class="sd"> 1</span>
<span class="sd"> >>> lrm.predict([0.0, 1.0])</span>
<span class="sd"> 0</span>
<span class="sd"> >>> lrm.predict(sc.parallelize([[1.0, 0.0], [0.0, 1.0]])).collect()</span>
<span class="sd"> [1, 0]</span>
<span class="sd"> >>> lrm.clearThreshold()</span>
<span class="sd"> >>> lrm.predict([0.0, 1.0])</span>
<span class="sd"> 0.279...</span>
<span class="sd"> >>> sparse_data = [</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 1.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> lrm = LogisticRegressionWithSGD.train(sc.parallelize(sparse_data), iterations=10)</span>
<span class="sd"> >>> lrm.predict(array([0.0, 1.0]))</span>
<span class="sd"> 1</span>
<span class="sd"> >>> lrm.predict(array([1.0, 0.0]))</span>
<span class="sd"> 0</span>
<span class="sd"> >>> lrm.predict(SparseVector(2, {1: 1.0}))</span>
<span class="sd"> 1</span>
<span class="sd"> >>> lrm.predict(SparseVector(2, {0: 1.0}))</span>
<span class="sd"> 0</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> lrm.save(sc, path)</span>
<span class="sd"> >>> sameModel = LogisticRegressionModel.load(sc, path)</span>
<span class="sd"> >>> sameModel.predict(array([0.0, 1.0]))</span>
<span class="sd"> 1</span>
<span class="sd"> >>> sameModel.predict(SparseVector(2, {0: 1.0}))</span>
<span class="sd"> 0</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except:</span>
<span class="sd"> ... pass</span>
<span class="sd"> >>> multi_class_data = [</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0, 0.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0, 0.0]),</span>
<span class="sd"> ... LabeledPoint(2.0, [0.0, 0.0, 1.0])</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> data = sc.parallelize(multi_class_data)</span>
<span class="sd"> >>> mcm = LogisticRegressionWithLBFGS.train(data, iterations=10, numClasses=3)</span>
<span class="sd"> >>> mcm.predict([0.0, 0.5, 0.0])</span>
<span class="sd"> 0</span>
<span class="sd"> >>> mcm.predict([0.8, 0.0, 0.0])</span>
<span class="sd"> 1</span>
<span class="sd"> >>> mcm.predict([0.0, 0.0, 0.3])</span>
<span class="sd"> 2</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">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">,</span> <span class="n">numClasses</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LogisticRegressionModel</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">weights</span><span class="p">,</span> <span class="n">intercept</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="nb">int</span><span class="p">(</span><span class="n">numFeatures</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">numClasses</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="mf">0.5</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span> <span class="o">=</span> <span class="bp">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span> <span class="o">=</span> <span class="bp">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="o">.</span><span class="n">size</span> <span class="o">/</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">numFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numFeatures</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">numClasses</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span>
<div class="viewcode-block" id="LogisticRegressionModel.predict"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionModel.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"> Predict values for a single data point or an RDD of points</span>
<span class="sd"> using the model trained.</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="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</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">v</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">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">margin</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_intercept</span>
<span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
<span class="n">prob</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="n">margin</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">exp_margin</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">margin</span><span class="p">)</span>
<span class="n">prob</span> <span class="o">=</span> <span class="n">exp_margin</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">exp_margin</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="n">prob</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">prob</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="k">else</span> <span class="mi">0</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">best_class</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">max_margin</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="k">if</span> <span class="n">x</span><span class="o">.</span><span class="n">size</span> <span class="o">+</span> <span class="mi">1</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataWithBiasSize</span><span class="p">:</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="n">margin</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">:</span><span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">])</span> <span class="o">+</span> \
<span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">]</span>
<span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="n">max_margin</span><span class="p">:</span>
<span class="n">max_margin</span> <span class="o">=</span> <span class="n">margin</span>
<span class="n">best_class</span> <span class="o">=</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
<span class="n">margin</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_weightsMatrix</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
<span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="n">max_margin</span><span class="p">:</span>
<span class="n">max_margin</span> <span class="o">=</span> <span class="n">margin</span>
<span class="n">best_class</span> <span class="o">=</span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">best_class</span>
</div>
<div class="viewcode-block" id="LogisticRegressionModel.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionModel.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_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">classification</span><span class="o">.</span><span class="n">LogisticRegressionModel</span><span class="p">(</span>
<span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</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="bp">self</span><span class="o">.</span><span class="n">numClasses</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="LogisticRegressionModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionModel.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">classification</span><span class="o">.</span><span class="n">LogisticRegressionModel</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="n">weights</span> <span class="o">=</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">weights</span><span class="p">())</span>
<span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span>
<span class="n">numFeatures</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">numFeatures</span><span class="p">()</span>
<span class="n">numClasses</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">numClasses</span><span class="p">()</span>
<span class="n">threshold</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">getThreshold</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">LogisticRegressionModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">,</span> <span class="n">numClasses</span><span class="p">)</span>
<span class="n">model</span><span class="o">.</span><span class="n">setThreshold</span><span class="p">(</span><span class="n">threshold</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
</div></div>
<div class="viewcode-block" id="LogisticRegressionWithSGD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionWithSGD">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionWithSGD</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="LogisticRegressionWithSGD.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionWithSGD.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">data</span><span class="p">,</span> <span class="n">iterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">step</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">miniBatchFraction</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">initialWeights</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">regType</span><span class="o">=</span><span class="s">"l2"</span><span class="p">,</span> <span class="n">intercept</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
<span class="n">validateData</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Train a logistic regression model on the given data.</span>
<span class="sd"> :param data: The training data, an RDD of</span>
<span class="sd"> LabeledPoint.</span>
<span class="sd"> :param iterations: The number of iterations</span>
<span class="sd"> (default: 100).</span>
<span class="sd"> :param step: The step parameter used in SGD</span>
<span class="sd"> (default: 1.0).</span>
<span class="sd"> :param miniBatchFraction: Fraction of data to be used for each</span>
<span class="sd"> SGD iteration (default: 1.0).</span>
<span class="sd"> :param initialWeights: The initial weights (default: None).</span>
<span class="sd"> :param regParam: The regularizer parameter</span>
<span class="sd"> (default: 0.01).</span>
<span class="sd"> :param regType: The type of regularizer used for</span>
<span class="sd"> training our model.</span>
<span class="sd"> :Allowed values:</span>
<span class="sd"> - "l1" for using L1 regularization</span>
<span class="sd"> - "l2" for using L2 regularization</span>
<span class="sd"> - None for no regularization</span>
<span class="sd"> (default: "l2")</span>
<span class="sd"> :param intercept: Boolean parameter which indicates the</span>
<span class="sd"> use or not of the augmented representation</span>
<span class="sd"> for training data (i.e. whether bias</span>
<span class="sd"> features are activated or not,</span>
<span class="sd"> default: False).</span>
<span class="sd"> :param validateData: Boolean parameter which indicates if</span>
<span class="sd"> the algorithm should validate data</span>
<span class="sd"> before training. (default: True)</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">i</span><span class="p">):</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainLogisticRegressionModelWithSGD"</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span>
<span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> <span class="n">i</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> <span class="n">regType</span><span class="p">,</span>
<span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">))</span>
<span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LogisticRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="LogisticRegressionWithLBFGS"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionWithLBFGS">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionWithLBFGS</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="LogisticRegressionWithLBFGS.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.LogisticRegressionWithLBFGS.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">data</span><span class="p">,</span> <span class="n">iterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">initialWeights</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">regType</span><span class="o">=</span><span class="s">"l2"</span><span class="p">,</span>
<span class="n">intercept</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">corrections</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">,</span> <span class="n">validateData</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">numClasses</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Train a logistic regression model on the given data.</span>
<span class="sd"> :param data: The training data, an RDD of</span>
<span class="sd"> LabeledPoint.</span>
<span class="sd"> :param iterations: The number of iterations</span>
<span class="sd"> (default: 100).</span>
<span class="sd"> :param initialWeights: The initial weights (default: None).</span>
<span class="sd"> :param regParam: The regularizer parameter</span>
<span class="sd"> (default: 0.01).</span>
<span class="sd"> :param regType: The type of regularizer used for</span>
<span class="sd"> training our model.</span>
<span class="sd"> :Allowed values:</span>
<span class="sd"> - "l1" for using L1 regularization</span>
<span class="sd"> - "l2" for using L2 regularization</span>
<span class="sd"> - None for no regularization</span>
<span class="sd"> (default: "l2")</span>
<span class="sd"> :param intercept: Boolean parameter which indicates the</span>
<span class="sd"> use or not of the augmented representation</span>
<span class="sd"> for training data (i.e. whether bias</span>
<span class="sd"> features are activated or not,</span>
<span class="sd"> default: False).</span>
<span class="sd"> :param corrections: The number of corrections used in the</span>
<span class="sd"> LBFGS update (default: 10).</span>
<span class="sd"> :param tolerance: The convergence tolerance of iterations</span>
<span class="sd"> for L-BFGS (default: 1e-4).</span>
<span class="sd"> :param validateData: Boolean parameter which indicates if the</span>
<span class="sd"> algorithm should validate data before</span>
<span class="sd"> training. (default: True)</span>
<span class="sd"> :param numClasses: The number of classes (i.e., outcomes) a</span>
<span class="sd"> label can take in Multinomial Logistic</span>
<span class="sd"> Regression (default: 2).</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> lrm = LogisticRegressionWithLBFGS.train(sc.parallelize(data), iterations=10)</span>
<span class="sd"> >>> lrm.predict([1.0, 0.0])</span>
<span class="sd"> 1</span>
<span class="sd"> >>> lrm.predict([0.0, 1.0])</span>
<span class="sd"> 0</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">i</span><span class="p">):</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainLogisticRegressionModelWithLBFGS"</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> <span class="n">i</span><span class="p">,</span>
<span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> <span class="n">regType</span><span class="p">,</span> <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">corrections</span><span class="p">),</span>
<span class="nb">float</span><span class="p">(</span><span class="n">tolerance</span><span class="p">),</span> <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numClasses</span><span class="p">))</span>
<span class="k">if</span> <span class="n">initialWeights</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">numClasses</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">intercept</span><span class="p">:</span>
<span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">initialWeights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">numClasses</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LogisticRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="SVMModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMModel">[docs]</a><span class="k">class</span> <span class="nc">SVMModel</span><span class="p">(</span><span class="n">LinearClassificationModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model for Support Vector Machines (SVMs).</span>
<span class="sd"> :param weights: Weights computed for every feature.</span>
<span class="sd"> :param intercept: Intercept computed for this model.</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [1.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [2.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [3.0])</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> svm = SVMWithSGD.train(sc.parallelize(data), iterations=10)</span>
<span class="sd"> >>> svm.predict([1.0])</span>
<span class="sd"> 1</span>
<span class="sd"> >>> svm.predict(sc.parallelize([[1.0]])).collect()</span>
<span class="sd"> [1]</span>
<span class="sd"> >>> svm.clearThreshold()</span>
<span class="sd"> >>> svm.predict(array([1.0]))</span>
<span class="sd"> 1.44...</span>
<span class="sd"> >>> sparse_data = [</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: -1.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> svm = SVMWithSGD.train(sc.parallelize(sparse_data), iterations=10)</span>
<span class="sd"> >>> svm.predict(SparseVector(2, {1: 1.0}))</span>
<span class="sd"> 1</span>
<span class="sd"> >>> svm.predict(SparseVector(2, {0: -1.0}))</span>
<span class="sd"> 0</span>
<span class="sd"> >>> import os, tempfile</span>
<span class="sd"> >>> path = tempfile.mkdtemp()</span>
<span class="sd"> >>> svm.save(sc, path)</span>
<span class="sd"> >>> sameModel = SVMModel.load(sc, path)</span>
<span class="sd"> >>> sameModel.predict(SparseVector(2, {1: 1.0}))</span>
<span class="sd"> 1</span>
<span class="sd"> >>> sameModel.predict(SparseVector(2, {0: -1.0}))</span>
<span class="sd"> 0</span>
<span class="sd"> >>> from shutil import rmtree</span>
<span class="sd"> >>> try:</span>
<span class="sd"> ... rmtree(path)</span>
<span class="sd"> ... except:</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">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">SVMModel</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">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="o">=</span> <span class="mf">0.0</span>
<div class="viewcode-block" id="SVMModel.predict"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMModel.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"> Predict values for a single data point or an RDD of points</span>
<span class="sd"> using the model trained.</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="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</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">v</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="n">margin</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">return</span> <span class="n">margin</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">margin</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_threshold</span> <span class="k">else</span> <span class="mi">0</span>
</div>
<div class="viewcode-block" id="SVMModel.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMModel.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_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">classification</span><span class="o">.</span><span class="n">SVMModel</span><span class="p">(</span>
<span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</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="SVMModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMModel.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">classification</span><span class="o">.</span><span class="n">SVMModel</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="n">weights</span> <span class="o">=</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">weights</span><span class="p">())</span>
<span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span>
<span class="n">threshold</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">getThreshold</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">SVMModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span>
<span class="n">model</span><span class="o">.</span><span class="n">setThreshold</span><span class="p">(</span><span class="n">threshold</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
</div></div>
<div class="viewcode-block" id="SVMWithSGD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMWithSGD">[docs]</a><span class="k">class</span> <span class="nc">SVMWithSGD</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="SVMWithSGD.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.SVMWithSGD.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">data</span><span class="p">,</span> <span class="n">iterations</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">step</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span>
<span class="n">miniBatchFraction</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">initialWeights</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">regType</span><span class="o">=</span><span class="s">"l2"</span><span class="p">,</span>
<span class="n">intercept</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">validateData</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Train a support vector machine on the given data.</span>
<span class="sd"> :param data: The training data, an RDD of</span>
<span class="sd"> LabeledPoint.</span>
<span class="sd"> :param iterations: The number of iterations</span>
<span class="sd"> (default: 100).</span>
<span class="sd"> :param step: The step parameter used in SGD</span>
<span class="sd"> (default: 1.0).</span>
<span class="sd"> :param regParam: The regularizer parameter</span>
<span class="sd"> (default: 0.01).</span>
<span class="sd"> :param miniBatchFraction: Fraction of data to be used for each</span>
<span class="sd"> SGD iteration (default: 1.0).</span>
<span class="sd"> :param initialWeights: The initial weights (default: None).</span>
<span class="sd"> :param regType: The type of regularizer used for</span>
<span class="sd"> training our model.</span>
<span class="sd"> :Allowed values:</span>
<span class="sd"> - "l1" for using L1 regularization</span>
<span class="sd"> - "l2" for using L2 regularization</span>
<span class="sd"> - None for no regularization</span>
<span class="sd"> (default: "l2")</span>
<span class="sd"> :param intercept: Boolean parameter which indicates the</span>
<span class="sd"> use or not of the augmented representation</span>
<span class="sd"> for training data (i.e. whether bias</span>
<span class="sd"> features are activated or not,</span>
<span class="sd"> default: False).</span>
<span class="sd"> :param validateData: Boolean parameter which indicates if</span>
<span class="sd"> the algorithm should validate data</span>
<span class="sd"> before training. (default: True)</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">i</span><span class="p">):</span>
<span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainSVMModelWithSGD"</span><span class="p">,</span> <span class="n">rdd</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span>
<span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> <span class="n">i</span><span class="p">,</span> <span class="n">regType</span><span class="p">,</span>
<span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">))</span>
<span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">SVMModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="NaiveBayesModel"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayesModel">[docs]</a><span class="k">class</span> <span class="nc">NaiveBayesModel</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">"""</span>
<span class="sd"> Model for Naive Bayes classifiers.</span>
<span class="sd"> :param labels: list of labels.</span>
<span class="sd"> :param pi: log of class priors, whose dimension is C,</span>
<span class="sd"> number of labels.</span>
<span class="sd"> :param theta: log of class conditional probabilities, whose</span>
<span class="sd"> dimension is C-by-D, where D is number of features.</span>
<span class="sd"> >>> data = [</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0, 0.0]),</span>
<span class="sd"> ... LabeledPoint(0.0, [0.0, 1.0]),</span>
<span class="sd"> ... LabeledPoint(1.0, [1.0, 0.0]),</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> model = NaiveBayes.train(sc.parallelize(data))</span>
<span class="sd"> >>> model.predict(array([0.0, 1.0]))</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> model.predict(array([1.0, 0.0]))</span>
<span class="sd"> 1.0</span>
<span class="sd"> >>> model.predict(sc.parallelize([[1.0, 0.0]])).collect()</span>
<span class="sd"> [1.0]</span>
<span class="sd"> >>> sparse_data = [</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {1: 0.0})),</span>
<span class="sd"> ... LabeledPoint(0.0, SparseVector(2, {1: 1.0})),</span>
<span class="sd"> ... LabeledPoint(1.0, SparseVector(2, {0: 1.0}))</span>
<span class="sd"> ... ]</span>
<span class="sd"> >>> model = NaiveBayes.train(sc.parallelize(sparse_data))</span>
<span class="sd"> >>> model.predict(SparseVector(2, {1: 1.0}))</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> model.predict(SparseVector(2, {0: 1.0}))</span>
<span class="sd"> 1.0</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 = NaiveBayesModel.load(sc, path)</span>
<span class="sd"> >>> sameModel.predict(SparseVector(2, {0: 1.0})) == model.predict(SparseVector(2, {0: 1.0}))</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">labels</span><span class="p">,</span> <span class="n">pi</span><span class="p">,</span> <span class="n">theta</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pi</span> <span class="o">=</span> <span class="n">pi</span>
<span class="bp">self</span><span class="o">.</span><span class="n">theta</span> <span class="o">=</span> <span class="n">theta</span>
<div class="viewcode-block" id="NaiveBayesModel.predict"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayesModel.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"> Return the most likely class for a data vector</span>
<span class="sd"> or an RDD of vectors</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="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</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">v</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">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pi</span> <span class="o">+</span> <span class="n">x</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">theta</span><span class="o">.</span><span class="n">transpose</span><span class="p">()))]</span>
</div>
<div class="viewcode-block" id="NaiveBayesModel.save"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayesModel.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_labels</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="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span>
<span class="n">java_pi</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="bp">self</span><span class="o">.</span><span class="n">pi</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span>
<span class="n">java_theta</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="bp">self</span><span class="o">.</span><span class="n">theta</span><span class="o">.</span><span class="n">tolist</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">classification</span><span class="o">.</span><span class="n">NaiveBayesModel</span><span class="p">(</span>
<span class="n">java_labels</span><span class="p">,</span> <span class="n">java_pi</span><span class="p">,</span> <span class="n">java_theta</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="NaiveBayesModel.load"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayesModel.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">classification</span><span class="o">.</span><span class="n">NaiveBayesModel</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="c"># Can not unpickle array.array from Pyrolite in Python3 with "bytes"</span>
<span class="n">py_labels</span> <span class="o">=</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">labels</span><span class="p">(),</span> <span class="s">"latin1"</span><span class="p">)</span>
<span class="n">py_pi</span> <span class="o">=</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">pi</span><span class="p">(),</span> <span class="s">"latin1"</span><span class="p">)</span>
<span class="n">py_theta</span> <span class="o">=</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">theta</span><span class="p">(),</span> <span class="s">"latin1"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">NaiveBayesModel</span><span class="p">(</span><span class="n">py_labels</span><span class="p">,</span> <span class="n">py_pi</span><span class="p">,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">py_theta</span><span class="p">))</span>
</div></div>
<div class="viewcode-block" id="NaiveBayes"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayes">[docs]</a><span class="k">class</span> <span class="nc">NaiveBayes</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="NaiveBayes.train"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.NaiveBayes.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">data</span><span class="p">,</span> <span class="n">lambda_</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Train a Naive Bayes model given an RDD of (label, features)</span>
<span class="sd"> vectors.</span>
<span class="sd"> This is the Multinomial NB (U{http://tinyurl.com/lsdw6p}) which</span>
<span class="sd"> can handle all kinds of discrete data. For example, by</span>
<span class="sd"> converting documents into TF-IDF vectors, it can be used for</span>
<span class="sd"> document classification. By making every vector a 0-1 vector,</span>
<span class="sd"> it can also be used as Bernoulli NB (U{http://tinyurl.com/p7c96j6}).</span>
<span class="sd"> The input feature values must be nonnegative.</span>
<span class="sd"> :param data: RDD of LabeledPoint.</span>
<span class="sd"> :param lambda_: The smoothing parameter (default: 1.0).</span>
<span class="sd"> """</span>
<span class="n">first</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">first</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">first</span><span class="p">,</span> <span class="n">LabeledPoint</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"`data` should be an RDD of LabeledPoint"</span><span class="p">)</span>
<span class="n">labels</span><span class="p">,</span> <span class="n">pi</span><span class="p">,</span> <span class="n">theta</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s">"trainNaiveBayesModel"</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">lambda_</span><span class="p">)</span>
<span class="k">return</span> <span class="n">NaiveBayesModel</span><span class="p">(</span><span class="n">labels</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">pi</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">numpy</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">theta</span><span class="p">))</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="StreamingLogisticRegressionWithSGD"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD">[docs]</a><span class="k">class</span> <span class="nc">StreamingLogisticRegressionWithSGD</span><span class="p">(</span><span class="n">StreamingLinearAlgorithm</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Run LogisticRegression with SGD on a batch of data.</span>
<span class="sd"> The weights obtained at the end of training a stream are used as initial</span>
<span class="sd"> weights for the next batch.</span>
<span class="sd"> :param stepSize: Step size for each iteration of gradient descent.</span>
<span class="sd"> :param numIterations: Number of iterations run for each batch of data.</span>
<span class="sd"> :param miniBatchFraction: Fraction of data on which SGD is run for each</span>
<span class="sd"> iteration.</span>
<span class="sd"> :param regParam: L2 Regularization parameter.</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">stepSize</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numIterations</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">miniBatchFraction</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.01</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span> <span class="o">=</span> <span class="n">stepSize</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="bp">self</span><span class="o">.</span><span class="n">regParam</span> <span class="o">=</span> <span class="n">regParam</span>
<span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span> <span class="o">=</span> <span class="n">miniBatchFraction</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="bp">None</span>
<span class="nb">super</span><span class="p">(</span><span class="n">StreamingLogisticRegressionWithSGD</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">model</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">)</span>
<div class="viewcode-block" id="StreamingLogisticRegressionWithSGD.setInitialWeights"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.setInitialWeights">[docs]</a> <span class="k">def</span> <span class="nf">setInitialWeights</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Set the initial value of weights.</span>
<span class="sd"> This must be set before running trainOn and predictOn.</span>
<span class="sd"> """</span>
<span class="n">initialWeights</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">initialWeights</span><span class="p">)</span>
<span class="c"># LogisticRegressionWithSGD does only binary classification.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">LogisticRegressionModel</span><span class="p">(</span>
<span class="n">initialWeights</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">initialWeights</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="StreamingLogisticRegressionWithSGD.trainOn"><a class="viewcode-back" href="../../../pyspark.mllib.html#pyspark.mllib.classification.StreamingLogisticRegressionWithSGD.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="c"># LogisticRegressionWithSGD.train raises an error for an empty RDD.</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">rdd</span><span class="o">.</span><span class="n">isEmpty</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">LogisticRegressionWithSGD</span><span class="o">.</span><span class="n">train</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">numIterations</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</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">weights</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>
<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="kn">import</span> <span class="nn">pyspark.mllib.classification</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">classification</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>
|
