1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
|
<!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.ml.classification — PySpark 1.5.0 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: '1.5.0',
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 1.5.0 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 1.5.0 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.ml.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">pyspark.ml.util</span> <span class="kn">import</span> <span class="n">keyword_only</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">JavaModel</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.param.shared</span> <span class="kn">import</span> <span class="o">*</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.regression</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">RandomForestParams</span><span class="p">,</span> <span class="n">DecisionTreeModel</span><span class="p">,</span> <span class="n">TreeEnsembleModels</span><span class="p">)</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s">'LogisticRegression'</span><span class="p">,</span> <span class="s">'LogisticRegressionModel'</span><span class="p">,</span> <span class="s">'DecisionTreeClassifier'</span><span class="p">,</span>
<span class="s">'DecisionTreeClassificationModel'</span><span class="p">,</span> <span class="s">'GBTClassifier'</span><span class="p">,</span> <span class="s">'GBTClassificationModel'</span><span class="p">,</span>
<span class="s">'RandomForestClassifier'</span><span class="p">,</span> <span class="s">'RandomForestClassificationModel'</span><span class="p">,</span> <span class="s">'NaiveBayes'</span><span class="p">,</span>
<span class="s">'NaiveBayesModel'</span><span class="p">]</span>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="LogisticRegression"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegression</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">HasRegParam</span><span class="p">,</span> <span class="n">HasTol</span><span class="p">,</span> <span class="n">HasProbabilityCol</span><span class="p">,</span> <span class="n">HasRawPredictionCol</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Logistic regression.</span>
<span class="sd"> Currently, this class only supports binary classification.</span>
<span class="sd"> >>> from pyspark.sql import Row</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> df = sc.parallelize([</span>
<span class="sd"> ... Row(label=1.0, features=Vectors.dense(1.0)),</span>
<span class="sd"> ... Row(label=0.0, features=Vectors.sparse(1, [], []))]).toDF()</span>
<span class="sd"> >>> lr = LogisticRegression(maxIter=5, regParam=0.01)</span>
<span class="sd"> >>> model = lr.fit(df)</span>
<span class="sd"> >>> model.weights</span>
<span class="sd"> DenseVector([5.5...])</span>
<span class="sd"> >>> model.intercept</span>
<span class="sd"> -2.68...</span>
<span class="sd"> >>> test0 = sc.parallelize([Row(features=Vectors.dense(-1.0))]).toDF()</span>
<span class="sd"> >>> result = model.transform(test0).head()</span>
<span class="sd"> >>> result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> result.probability</span>
<span class="sd"> DenseVector([0.99..., 0.00...])</span>
<span class="sd"> >>> result.rawPrediction</span>
<span class="sd"> DenseVector([8.22..., -8.22...])</span>
<span class="sd"> >>> test1 = sc.parallelize([Row(features=Vectors.sparse(1, [0], [1.0]))]).toDF()</span>
<span class="sd"> >>> model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> >>> lr.setParams("vector")</span>
<span class="sd"> Traceback (most recent call last):</span>
<span class="sd"> ...</span>
<span class="sd"> TypeError: Method setParams forces keyword arguments.</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">elasticNetParam</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"elasticNetParam"</span><span class="p">,</span>
<span class="s">"the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, "</span> <span class="o">+</span>
<span class="s">"the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty."</span><span class="p">)</span>
<span class="n">fitIntercept</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"fitIntercept"</span><span class="p">,</span> <span class="s">"whether to fit an intercept term."</span><span class="p">)</span>
<span class="n">thresholds</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"thresholds"</span><span class="p">,</span>
<span class="s">"Thresholds in multi-class classification"</span> <span class="o">+</span>
<span class="s">" to adjust the probability of predicting each class."</span> <span class="o">+</span>
<span class="s">" Array must have length equal to the number of classes, with values >= 0."</span> <span class="o">+</span>
<span class="s">" The class with largest value p/t is predicted, where p is the original"</span> <span class="o">+</span>
<span class="s">" probability of that class and t is the class' threshold."</span><span class="p">)</span>
<span class="n">threshold</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"threshold"</span><span class="p">,</span>
<span class="s">"Threshold in binary classification prediction, in range [0, 1]."</span> <span class="o">+</span>
<span class="s">" If threshold and thresholds are both set, they must match."</span><span class="p">)</span>
<span class="nd">@keyword_only</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">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">elasticNetParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span> <span class="n">fitIntercept</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
<span class="n">threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">thresholds</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \</span>
<span class="sd"> threshold=0.5, thresholds=None, \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction")</span>
<span class="sd"> If the threshold and thresholds Params are both set, they must be equivalent.</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LogisticRegression</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s">"org.apache.spark.ml.classification.LogisticRegression"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="c">#: param for the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty</span>
<span class="c"># is an L2 penalty. For alpha = 1, it is an L1 penalty.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">elasticNetParam</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"elasticNetParam"</span><span class="p">,</span>
<span class="s">"the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, "</span> <span class="o">+</span>
<span class="s">"the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty."</span><span class="p">)</span>
<span class="c">#: param for whether to fit an intercept term.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fitIntercept</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"fitIntercept"</span><span class="p">,</span> <span class="s">"whether to fit an intercept term."</span><span class="p">)</span>
<span class="c">#: param for threshold in binary classification, in range [0, 1].</span>
<span class="bp">self</span><span class="o">.</span><span class="n">threshold</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"threshold"</span><span class="p">,</span>
<span class="s">"Threshold in binary classification prediction, in range [0, 1]."</span> <span class="o">+</span>
<span class="s">" If threshold and thresholds are both set, they must match."</span><span class="p">)</span>
<span class="c">#: param for thresholds or cutoffs in binary or multiclass classification</span>
<span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"thresholds"</span><span class="p">,</span>
<span class="s">"Thresholds in multi-class classification"</span> <span class="o">+</span>
<span class="s">" to adjust the probability of predicting each class."</span> <span class="o">+</span>
<span class="s">" Array must have length equal to the number of classes, with values >= 0."</span> <span class="o">+</span>
<span class="s">" The class with largest value p/t is predicted, where p is the original"</span> <span class="o">+</span>
<span class="s">" probability of that class and t is the class' threshold."</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">elasticNetParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">1E-6</span><span class="p">,</span>
<span class="n">fitIntercept</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_checkThresholdConsistency</span><span class="p">()</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="LogisticRegression.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">elasticNetParam</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">tol</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span> <span class="n">fitIntercept</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
<span class="n">threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">thresholds</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \</span>
<span class="sd"> threshold=0.5, thresholds=None, \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction")</span>
<span class="sd"> Sets params for logistic regression.</span>
<span class="sd"> If the threshold and thresholds Params are both set, they must be equivalent.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_checkThresholdConsistency</span><span class="p">()</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">LogisticRegressionModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="LogisticRegression.setElasticNetParam"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.setElasticNetParam">[docs]</a> <span class="k">def</span> <span class="nf">setElasticNetParam</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"> Sets the value of :py:attr:`elasticNetParam`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">elasticNetParam</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="LogisticRegression.getElasticNetParam"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.getElasticNetParam">[docs]</a> <span class="k">def</span> <span class="nf">getElasticNetParam</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of elasticNetParam or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">elasticNetParam</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="LogisticRegression.setFitIntercept"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.setFitIntercept">[docs]</a> <span class="k">def</span> <span class="nf">setFitIntercept</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"> Sets the value of :py:attr:`fitIntercept`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">fitIntercept</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="LogisticRegression.getFitIntercept"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.getFitIntercept">[docs]</a> <span class="k">def</span> <span class="nf">getFitIntercept</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of fitIntercept or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fitIntercept</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="LogisticRegression.setThreshold"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.setThreshold">[docs]</a> <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"> Sets the value of :py:attr:`threshold`.</span>
<span class="sd"> Clears value of :py:attr:`thresholds` if it has been set.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">):</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">]</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="LogisticRegression.getThreshold"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.getThreshold">[docs]</a> <span class="k">def</span> <span class="nf">getThreshold</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of threshold or its default value.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_checkThresholdConsistency</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">):</span>
<span class="n">ts</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">ts</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Logistic Regression getThreshold only applies to"</span> <span class="o">+</span>
<span class="s">" binary classification, but thresholds has length != 2."</span> <span class="o">+</span>
<span class="s">" thresholds: "</span> <span class="o">+</span> <span class="s">","</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">ts</span><span class="p">))</span>
<span class="k">return</span> <span class="mf">1.0</span><span class="o">/</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">+</span> <span class="n">ts</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">/</span><span class="n">ts</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="LogisticRegression.setThresholds"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.setThresholds">[docs]</a> <span class="k">def</span> <span class="nf">setThresholds</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"> Sets the value of :py:attr:`thresholds`.</span>
<span class="sd"> Clears value of :py:attr:`threshold` if it has been set.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">):</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">]</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="LogisticRegression.getThresholds"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegression.getThresholds">[docs]</a> <span class="k">def</span> <span class="nf">getThresholds</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> If :py:attr:`thresholds` is set, return its value.</span>
<span class="sd"> Otherwise, if :py:attr:`threshold` is set, return the equivalent thresholds for binary</span>
<span class="sd"> classification: (1-threshold, threshold).</span>
<span class="sd"> If neither are set, throw an error.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_checkThresholdConsistency</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">):</span>
<span class="n">t</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="mf">1.0</span><span class="o">-</span><span class="n">t</span><span class="p">,</span> <span class="n">t</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_checkThresholdConsistency</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">isSet</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">):</span>
<span class="n">ts</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getParam</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">thresholds</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">ts</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Logistic Regression getThreshold only applies to"</span> <span class="o">+</span>
<span class="s">" binary classification, but thresholds has length != 2."</span> <span class="o">+</span>
<span class="s">" thresholds: "</span> <span class="o">+</span> <span class="s">","</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">ts</span><span class="p">))</span>
<span class="n">t</span> <span class="o">=</span> <span class="mf">1.0</span><span class="o">/</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">+</span> <span class="n">ts</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">/</span><span class="n">ts</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="n">t2</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">getParam</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">threshold</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">abs</span><span class="p">(</span><span class="n">t2</span> <span class="o">-</span> <span class="n">t</span><span class="p">)</span> <span class="o">>=</span> <span class="mf">1E-5</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s">"Logistic Regression getThreshold found inconsistent values for"</span> <span class="o">+</span>
<span class="s">" threshold (</span><span class="si">%g</span><span class="s">) and thresholds (equivalent to </span><span class="si">%g</span><span class="s">)"</span> <span class="o">%</span> <span class="p">(</span><span class="n">t2</span><span class="p">,</span> <span class="n">t</span><span class="p">))</span>
</div>
<div class="viewcode-block" id="LogisticRegressionModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.LogisticRegressionModel">[docs]</a><span class="k">class</span> <span class="nc">LogisticRegressionModel</span><span class="p">(</span><span class="n">JavaModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by LogisticRegression.</span>
<span class="sd"> """</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">weights</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model weights.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"weights"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">intercept</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model intercept.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"intercept"</span><span class="p">)</span>
</div>
<span class="k">class</span> <span class="nc">TreeClassifierParams</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Private class to track supported impurity measures.</span>
<span class="sd"> """</span>
<span class="n">supportedImpurities</span> <span class="o">=</span> <span class="p">[</span><span class="s">"entropy"</span><span class="p">,</span> <span class="s">"gini"</span><span class="p">]</span>
<span class="k">class</span> <span class="nc">GBTParams</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Private class to track supported GBT params.</span>
<span class="sd"> """</span>
<span class="n">supportedLossTypes</span> <span class="o">=</span> <span class="p">[</span><span class="s">"logistic"</span><span class="p">]</span>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="DecisionTreeClassifier"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier">[docs]</a><span class="k">class</span> <span class="nc">DecisionTreeClassifier</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span>
<span class="n">HasProbabilityCol</span><span class="p">,</span> <span class="n">HasRawPredictionCol</span><span class="p">,</span> <span class="n">DecisionTreeParams</span><span class="p">,</span>
<span class="n">HasCheckpointInterval</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> `http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree`</span>
<span class="sd"> learning algorithm for classification.</span>
<span class="sd"> It supports both binary and multiclass labels, as well as both continuous and categorical</span>
<span class="sd"> features.</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> from pyspark.ml.feature import StringIndexer</span>
<span class="sd"> >>> df = sqlContext.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], ["label", "features"])</span>
<span class="sd"> >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed")</span>
<span class="sd"> >>> si_model = stringIndexer.fit(df)</span>
<span class="sd"> >>> td = si_model.transform(df)</span>
<span class="sd"> >>> dt = DecisionTreeClassifier(maxDepth=2, labelCol="indexed")</span>
<span class="sd"> >>> model = dt.fit(td)</span>
<span class="sd"> >>> model.numNodes</span>
<span class="sd"> 3</span>
<span class="sd"> >>> model.depth</span>
<span class="sd"> 1</span>
<span class="sd"> >>> test0 = sqlContext.createDataFrame([(Vectors.dense(-1.0),)], ["features"])</span>
<span class="sd"> >>> result = model.transform(test0).head()</span>
<span class="sd"> >>> result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> result.probability</span>
<span class="sd"> DenseVector([1.0, 0.0])</span>
<span class="sd"> >>> result.rawPrediction</span>
<span class="sd"> DenseVector([1.0, 0.0])</span>
<span class="sd"> >>> test1 = sqlContext.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], ["features"])</span>
<span class="sd"> >>> model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">impurity</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"impurity"</span><span class="p">,</span>
<span class="s">"Criterion used for information gain calculation (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">TreeClassifierParams</span><span class="o">.</span><span class="n">supportedImpurities</span><span class="p">))</span>
<span class="nd">@keyword_only</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">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DecisionTreeClassifier</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s">"org.apache.spark.ml.classification.DecisionTreeClassifier"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="c">#: param for Criterion used for information gain calculation (case-insensitive).</span>
<span class="bp">self</span><span class="o">.</span><span class="n">impurity</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"impurity"</span><span class="p">,</span>
<span class="s">"Criterion used for information gain calculation (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">TreeClassifierParams</span><span class="o">.</span><span class="n">supportedImpurities</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="DecisionTreeClassifier.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")</span>
<span class="sd"> Sets params for the DecisionTreeClassifier.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">DecisionTreeClassificationModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="DecisionTreeClassifier.setImpurity"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier.setImpurity">[docs]</a> <span class="k">def</span> <span class="nf">setImpurity</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"> Sets the value of :py:attr:`impurity`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">impurity</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="DecisionTreeClassifier.getImpurity"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier.getImpurity">[docs]</a> <span class="k">def</span> <span class="nf">getImpurity</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of impurity or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">impurity</span><span class="p">)</span>
</div></div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="DecisionTreeClassificationModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassificationModel">[docs]</a><span class="k">class</span> <span class="nc">DecisionTreeClassificationModel</span><span class="p">(</span><span class="n">DecisionTreeModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by DecisionTreeClassifier.</span>
<span class="sd"> """</span>
</div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="RandomForestClassifier"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier">[docs]</a><span class="k">class</span> <span class="nc">RandomForestClassifier</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasSeed</span><span class="p">,</span>
<span class="n">HasRawPredictionCol</span><span class="p">,</span> <span class="n">HasProbabilityCol</span><span class="p">,</span>
<span class="n">DecisionTreeParams</span><span class="p">,</span> <span class="n">HasCheckpointInterval</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> `http://en.wikipedia.org/wiki/Random_forest Random Forest`</span>
<span class="sd"> learning algorithm for classification.</span>
<span class="sd"> It supports both binary and multiclass labels, as well as both continuous and categorical</span>
<span class="sd"> features.</span>
<span class="sd"> >>> import numpy</span>
<span class="sd"> >>> from numpy import allclose</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> from pyspark.ml.feature import StringIndexer</span>
<span class="sd"> >>> df = sqlContext.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], ["label", "features"])</span>
<span class="sd"> >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed")</span>
<span class="sd"> >>> si_model = stringIndexer.fit(df)</span>
<span class="sd"> >>> td = si_model.transform(df)</span>
<span class="sd"> >>> rf = RandomForestClassifier(numTrees=3, maxDepth=2, labelCol="indexed", seed=42)</span>
<span class="sd"> >>> model = rf.fit(td)</span>
<span class="sd"> >>> allclose(model.treeWeights, [1.0, 1.0, 1.0])</span>
<span class="sd"> True</span>
<span class="sd"> >>> test0 = sqlContext.createDataFrame([(Vectors.dense(-1.0),)], ["features"])</span>
<span class="sd"> >>> result = model.transform(test0).head()</span>
<span class="sd"> >>> result.prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> numpy.argmax(result.probability)</span>
<span class="sd"> 0</span>
<span class="sd"> >>> numpy.argmax(result.rawPrediction)</span>
<span class="sd"> 0</span>
<span class="sd"> >>> test1 = sqlContext.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], ["features"])</span>
<span class="sd"> >>> model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">impurity</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"impurity"</span><span class="p">,</span>
<span class="s">"Criterion used for information gain calculation (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">TreeClassifierParams</span><span class="o">.</span><span class="n">supportedImpurities</span><span class="p">))</span>
<span class="n">subsamplingRate</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"subsamplingRate"</span><span class="p">,</span>
<span class="s">"Fraction of the training data used for learning each decision tree, "</span> <span class="o">+</span>
<span class="s">"in range (0, 1]."</span><span class="p">)</span>
<span class="n">numTrees</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"numTrees"</span><span class="p">,</span> <span class="s">"Number of trees to train (>= 1)"</span><span class="p">)</span>
<span class="n">featureSubsetStrategy</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"featureSubsetStrategy"</span><span class="p">,</span>
<span class="s">"The number of features to consider for splits at each tree node. Supported "</span> <span class="o">+</span>
<span class="s">"options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">RandomForestParams</span><span class="o">.</span><span class="n">supportedFeatureSubsetStrategies</span><span class="p">))</span>
<span class="nd">@keyword_only</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">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">,</span>
<span class="n">numTrees</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">featureSubsetStrategy</span><span class="o">=</span><span class="s">"auto"</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \</span>
<span class="sd"> numTrees=20, featureSubsetStrategy="auto", seed=None)</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">RandomForestClassifier</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s">"org.apache.spark.ml.classification.RandomForestClassifier"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="c">#: param for Criterion used for information gain calculation (case-insensitive).</span>
<span class="bp">self</span><span class="o">.</span><span class="n">impurity</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"impurity"</span><span class="p">,</span>
<span class="s">"Criterion used for information gain calculation (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">TreeClassifierParams</span><span class="o">.</span><span class="n">supportedImpurities</span><span class="p">))</span>
<span class="c">#: param for Fraction of the training data used for learning each decision tree,</span>
<span class="c"># in range (0, 1]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"subsamplingRate"</span><span class="p">,</span>
<span class="s">"Fraction of the training data used for learning each "</span> <span class="o">+</span>
<span class="s">"decision tree, in range (0, 1]."</span><span class="p">)</span>
<span class="c">#: param for Number of trees to train (>= 1)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">numTrees</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"numTrees"</span><span class="p">,</span> <span class="s">"Number of trees to train (>= 1)"</span><span class="p">)</span>
<span class="c">#: param for The number of features to consider for splits at each tree node</span>
<span class="bp">self</span><span class="o">.</span><span class="n">featureSubsetStrategy</span> <span class="o">=</span> \
<span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"featureSubsetStrategy"</span><span class="p">,</span>
<span class="s">"The number of features to consider for splits at each tree node. Supported "</span> <span class="o">+</span>
<span class="s">"options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">RandomForestParams</span><span class="o">.</span><span class="n">supportedFeatureSubsetStrategies</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">,</span> <span class="n">numTrees</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">featureSubsetStrategy</span><span class="o">=</span><span class="s">"auto"</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="RandomForestClassifier.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">impurity</span><span class="o">=</span><span class="s">"gini"</span><span class="p">,</span> <span class="n">numTrees</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">featureSubsetStrategy</span><span class="o">=</span><span class="s">"auto"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, \</span>
<span class="sd"> impurity="gini", numTrees=20, featureSubsetStrategy="auto")</span>
<span class="sd"> Sets params for linear classification.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">RandomForestClassificationModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="RandomForestClassifier.setImpurity"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.setImpurity">[docs]</a> <span class="k">def</span> <span class="nf">setImpurity</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"> Sets the value of :py:attr:`impurity`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">impurity</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.getImpurity"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.getImpurity">[docs]</a> <span class="k">def</span> <span class="nf">getImpurity</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of impurity or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">impurity</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.setSubsamplingRate"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.setSubsamplingRate">[docs]</a> <span class="k">def</span> <span class="nf">setSubsamplingRate</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"> Sets the value of :py:attr:`subsamplingRate`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.getSubsamplingRate"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.getSubsamplingRate">[docs]</a> <span class="k">def</span> <span class="nf">getSubsamplingRate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of subsamplingRate or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.setNumTrees"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.setNumTrees">[docs]</a> <span class="k">def</span> <span class="nf">setNumTrees</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"> Sets the value of :py:attr:`numTrees`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">numTrees</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.getNumTrees"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.getNumTrees">[docs]</a> <span class="k">def</span> <span class="nf">getNumTrees</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of numTrees or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numTrees</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.setFeatureSubsetStrategy"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.setFeatureSubsetStrategy">[docs]</a> <span class="k">def</span> <span class="nf">setFeatureSubsetStrategy</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"> Sets the value of :py:attr:`featureSubsetStrategy`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">featureSubsetStrategy</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="RandomForestClassifier.getFeatureSubsetStrategy"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassifier.getFeatureSubsetStrategy">[docs]</a> <span class="k">def</span> <span class="nf">getFeatureSubsetStrategy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of featureSubsetStrategy or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">featureSubsetStrategy</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="RandomForestClassificationModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.RandomForestClassificationModel">[docs]</a><span class="k">class</span> <span class="nc">RandomForestClassificationModel</span><span class="p">(</span><span class="n">TreeEnsembleModels</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by RandomForestClassifier.</span>
<span class="sd"> """</span>
</div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="GBTClassifier"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier">[docs]</a><span class="k">class</span> <span class="nc">GBTClassifier</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span>
<span class="n">DecisionTreeParams</span><span class="p">,</span> <span class="n">HasCheckpointInterval</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> `http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)`</span>
<span class="sd"> learning algorithm for classification.</span>
<span class="sd"> It supports binary labels, as well as both continuous and categorical features.</span>
<span class="sd"> Note: Multiclass labels are not currently supported.</span>
<span class="sd"> >>> from numpy import allclose</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> from pyspark.ml.feature import StringIndexer</span>
<span class="sd"> >>> df = sqlContext.createDataFrame([</span>
<span class="sd"> ... (1.0, Vectors.dense(1.0)),</span>
<span class="sd"> ... (0.0, Vectors.sparse(1, [], []))], ["label", "features"])</span>
<span class="sd"> >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed")</span>
<span class="sd"> >>> si_model = stringIndexer.fit(df)</span>
<span class="sd"> >>> td = si_model.transform(df)</span>
<span class="sd"> >>> gbt = GBTClassifier(maxIter=5, maxDepth=2, labelCol="indexed")</span>
<span class="sd"> >>> model = gbt.fit(td)</span>
<span class="sd"> >>> allclose(model.treeWeights, [1.0, 0.1, 0.1, 0.1, 0.1])</span>
<span class="sd"> True</span>
<span class="sd"> >>> test0 = sqlContext.createDataFrame([(Vectors.dense(-1.0),)], ["features"])</span>
<span class="sd"> >>> model.transform(test0).head().prediction</span>
<span class="sd"> 0.0</span>
<span class="sd"> >>> test1 = sqlContext.createDataFrame([(Vectors.sparse(1, [0], [1.0]),)], ["features"])</span>
<span class="sd"> >>> model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">lossType</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"lossType"</span><span class="p">,</span>
<span class="s">"Loss function which GBT tries to minimize (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">GBTParams</span><span class="o">.</span><span class="n">supportedLossTypes</span><span class="p">))</span>
<span class="n">subsamplingRate</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"subsamplingRate"</span><span class="p">,</span>
<span class="s">"Fraction of the training data used for learning each decision tree, "</span> <span class="o">+</span>
<span class="s">"in range (0, 1]."</span><span class="p">)</span>
<span class="n">stepSize</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"stepSize"</span><span class="p">,</span>
<span class="s">"Step size (a.k.a. learning rate) in interval (0, 1] for shrinking the "</span> <span class="o">+</span>
<span class="s">"contribution of each estimator"</span><span class="p">)</span>
<span class="nd">@keyword_only</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">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">lossType</span><span class="o">=</span><span class="s">"logistic"</span><span class="p">,</span>
<span class="n">maxIter</span><span class="o">=</span><span class="mi">20</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="sd">"""</span>
<span class="sd"> __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> lossType="logistic", maxIter=20, stepSize=0.1)</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">GBTClassifier</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s">"org.apache.spark.ml.classification.GBTClassifier"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="c">#: param for Loss function which GBT tries to minimize (case-insensitive).</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lossType</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"lossType"</span><span class="p">,</span>
<span class="s">"Loss function which GBT tries to minimize (case-insensitive). "</span> <span class="o">+</span>
<span class="s">"Supported options: "</span> <span class="o">+</span> <span class="s">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">GBTParams</span><span class="o">.</span><span class="n">supportedLossTypes</span><span class="p">))</span>
<span class="c">#: Fraction of the training data used for learning each decision tree, in range (0, 1].</span>
<span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"subsamplingRate"</span><span class="p">,</span>
<span class="s">"Fraction of the training data used for learning each "</span> <span class="o">+</span>
<span class="s">"decision tree, in range (0, 1]."</span><span class="p">)</span>
<span class="c">#: Step size (a.k.a. learning rate) in interval (0, 1] for shrinking the contribution of</span>
<span class="c"># each estimator</span>
<span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"stepSize"</span><span class="p">,</span>
<span class="s">"Step size (a.k.a. learning rate) in interval (0, 1] for shrinking "</span> <span class="o">+</span>
<span class="s">"the contribution of each estimator"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">lossType</span><span class="o">=</span><span class="s">"logistic"</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">20</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">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="GBTClassifier.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">maxDepth</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">maxBins</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">minInstancesPerNode</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">minInfoGain</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
<span class="n">maxMemoryInMB</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">cacheNodeIds</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">lossType</span><span class="o">=</span><span class="s">"logistic"</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">20</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="sd">"""</span>
<span class="sd"> setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \</span>
<span class="sd"> maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \</span>
<span class="sd"> lossType="logistic", maxIter=20, stepSize=0.1)</span>
<span class="sd"> Sets params for Gradient Boosted Tree Classification.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">GBTClassificationModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="GBTClassifier.setLossType"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.setLossType">[docs]</a> <span class="k">def</span> <span class="nf">setLossType</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"> Sets the value of :py:attr:`lossType`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">lossType</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="GBTClassifier.getLossType"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.getLossType">[docs]</a> <span class="k">def</span> <span class="nf">getLossType</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of lossType or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">lossType</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="GBTClassifier.setSubsamplingRate"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.setSubsamplingRate">[docs]</a> <span class="k">def</span> <span class="nf">setSubsamplingRate</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"> Sets the value of :py:attr:`subsamplingRate`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="GBTClassifier.getSubsamplingRate"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.getSubsamplingRate">[docs]</a> <span class="k">def</span> <span class="nf">getSubsamplingRate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of subsamplingRate or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">subsamplingRate</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="GBTClassifier.setStepSize"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.setStepSize">[docs]</a> <span class="k">def</span> <span class="nf">setStepSize</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"> Sets the value of :py:attr:`stepSize`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</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="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="GBTClassifier.getStepSize"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassifier.getStepSize">[docs]</a> <span class="k">def</span> <span class="nf">getStepSize</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of stepSize or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="GBTClassificationModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.GBTClassificationModel">[docs]</a><span class="k">class</span> <span class="nc">GBTClassificationModel</span><span class="p">(</span><span class="n">TreeEnsembleModels</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by GBTClassifier.</span>
<span class="sd"> """</span>
</div>
<span class="nd">@inherit_doc</span>
<div class="viewcode-block" id="NaiveBayes"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes">[docs]</a><span class="k">class</span> <span class="nc">NaiveBayes</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">HasFeaturesCol</span><span class="p">,</span> <span class="n">HasLabelCol</span><span class="p">,</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasProbabilityCol</span><span class="p">,</span>
<span class="n">HasRawPredictionCol</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Naive Bayes Classifiers.</span>
<span class="sd"> It supports both Multinomial and Bernoulli NB. Multinomial NB</span>
<span class="sd"> (`http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html`)</span>
<span class="sd"> can handle finitely supported discrete data. For example, by converting documents into</span>
<span class="sd"> TF-IDF vectors, it can be used for document classification. By making every vector a</span>
<span class="sd"> binary (0/1) data, it can also be used as Bernoulli NB</span>
<span class="sd"> (`http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html`).</span>
<span class="sd"> The input feature values must be nonnegative.</span>
<span class="sd"> >>> from pyspark.sql import Row</span>
<span class="sd"> >>> from pyspark.mllib.linalg import Vectors</span>
<span class="sd"> >>> df = sqlContext.createDataFrame([</span>
<span class="sd"> ... Row(label=0.0, features=Vectors.dense([0.0, 0.0])),</span>
<span class="sd"> ... Row(label=0.0, features=Vectors.dense([0.0, 1.0])),</span>
<span class="sd"> ... Row(label=1.0, features=Vectors.dense([1.0, 0.0]))])</span>
<span class="sd"> >>> nb = NaiveBayes(smoothing=1.0, modelType="multinomial")</span>
<span class="sd"> >>> model = nb.fit(df)</span>
<span class="sd"> >>> model.pi</span>
<span class="sd"> DenseVector([-0.51..., -0.91...])</span>
<span class="sd"> >>> model.theta</span>
<span class="sd"> DenseMatrix(2, 2, [-1.09..., -0.40..., -0.40..., -1.09...], 1)</span>
<span class="sd"> >>> test0 = sc.parallelize([Row(features=Vectors.dense([1.0, 0.0]))]).toDF()</span>
<span class="sd"> >>> result = model.transform(test0).head()</span>
<span class="sd"> >>> result.prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> >>> result.probability</span>
<span class="sd"> DenseVector([0.42..., 0.57...])</span>
<span class="sd"> >>> result.rawPrediction</span>
<span class="sd"> DenseVector([-1.60..., -1.32...])</span>
<span class="sd"> >>> test1 = sc.parallelize([Row(features=Vectors.sparse(2, [0], [1.0]))]).toDF()</span>
<span class="sd"> >>> model.transform(test1).head().prediction</span>
<span class="sd"> 1.0</span>
<span class="sd"> """</span>
<span class="c"># a placeholder to make it appear in the generated doc</span>
<span class="n">smoothing</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"smoothing"</span><span class="p">,</span> <span class="s">"The smoothing parameter, should be >= 0, "</span> <span class="o">+</span>
<span class="s">"default is 1.0"</span><span class="p">)</span>
<span class="n">modelType</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s">"modelType"</span><span class="p">,</span> <span class="s">"The model type which is a string "</span> <span class="o">+</span>
<span class="s">"(case-sensitive). Supported options: multinomial (default) and bernoulli."</span><span class="p">)</span>
<span class="nd">@keyword_only</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">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span> <span class="n">smoothing</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">modelType</span><span class="o">=</span><span class="s">"multinomial"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", smoothing=1.0, \</span>
<span class="sd"> modelType="multinomial")</span>
<span class="sd"> """</span>
<span class="nb">super</span><span class="p">(</span><span class="n">NaiveBayes</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span>
<span class="s">"org.apache.spark.ml.classification.NaiveBayes"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span>
<span class="c">#: param for the smoothing parameter.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">smoothing</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"smoothing"</span><span class="p">,</span> <span class="s">"The smoothing parameter, should be >= 0, "</span> <span class="o">+</span>
<span class="s">"default is 1.0"</span><span class="p">)</span>
<span class="c">#: param for the model type.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">modelType</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s">"modelType"</span><span class="p">,</span> <span class="s">"The model type which is a string "</span> <span class="o">+</span>
<span class="s">"(case-sensitive). Supported options: multinomial (default) "</span> <span class="o">+</span>
<span class="s">"and bernoulli."</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">smoothing</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">modelType</span><span class="o">=</span><span class="s">"multinomial"</span><span class="p">)</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">__init__</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@keyword_only</span>
<div class="viewcode-block" id="NaiveBayes.setParams"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes.setParams">[docs]</a> <span class="k">def</span> <span class="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span>
<span class="n">probabilityCol</span><span class="o">=</span><span class="s">"probability"</span><span class="p">,</span> <span class="n">rawPredictionCol</span><span class="o">=</span><span class="s">"rawPrediction"</span><span class="p">,</span> <span class="n">smoothing</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">modelType</span><span class="o">=</span><span class="s">"multinomial"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \</span>
<span class="sd"> probabilityCol="probability", rawPredictionCol="rawPrediction", smoothing=1.0, \</span>
<span class="sd"> modelType="multinomial")</span>
<span class="sd"> Sets params for Naive Bayes.</span>
<span class="sd"> """</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="o">.</span><span class="n">_input_kwargs</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
</div>
<span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">NaiveBayesModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span>
<div class="viewcode-block" id="NaiveBayes.setSmoothing"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes.setSmoothing">[docs]</a> <span class="k">def</span> <span class="nf">setSmoothing</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"> Sets the value of :py:attr:`smoothing`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">smoothing</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="NaiveBayes.getSmoothing"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes.getSmoothing">[docs]</a> <span class="k">def</span> <span class="nf">getSmoothing</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of smoothing or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">smoothing</span><span class="p">)</span>
</div>
<div class="viewcode-block" id="NaiveBayes.setModelType"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes.setModelType">[docs]</a> <span class="k">def</span> <span class="nf">setModelType</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"> Sets the value of :py:attr:`modelType`.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_paramMap</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">modelType</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">return</span> <span class="bp">self</span>
</div>
<div class="viewcode-block" id="NaiveBayes.getModelType"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayes.getModelType">[docs]</a> <span class="k">def</span> <span class="nf">getModelType</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Gets the value of modelType or its default value.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">modelType</span><span class="p">)</span>
</div></div>
<div class="viewcode-block" id="NaiveBayesModel"><a class="viewcode-back" href="../../../pyspark.ml.html#pyspark.ml.classification.NaiveBayesModel">[docs]</a><span class="k">class</span> <span class="nc">NaiveBayesModel</span><span class="p">(</span><span class="n">JavaModel</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Model fitted by NaiveBayes.</span>
<span class="sd"> """</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">pi</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> log of class priors.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"pi"</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">theta</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> log of class conditional probabilities.</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s">"theta"</span><span class="p">)</span>
</div>
<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="kn">import</span> <span class="nn">doctest</span>
<span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SQLContext</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="c"># The small batch size here ensures that we see multiple batches,</span>
<span class="c"># even in these small test examples:</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">"local[2]"</span><span class="p">,</span> <span class="s">"ml.classification tests"</span><span class="p">)</span>
<span class="n">sqlContext</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</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">sc</span>
<span class="n">globs</span><span class="p">[</span><span class="s">'sqlContext'</span><span class="p">]</span> <span class="o">=</span> <span class="n">sqlContext</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">sc</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>
</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 1.5.0 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>
|
