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
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# DO NOT MODIFY THIS FILE! It was generated by _shared_params_code_gen.py.
from pyspark.ml.param import Param, Params
class HasMaxIter(Params):
"""
Mixin for param maxIter: max number of iterations (>= 0).
"""
# a placeholder to make it appear in the generated doc
maxIter = Param(Params._dummy(), "maxIter", "max number of iterations (>= 0).")
def __init__(self):
super(HasMaxIter, self).__init__()
#: param for max number of iterations (>= 0).
self.maxIter = Param(self, "maxIter", "max number of iterations (>= 0).")
def setMaxIter(self, value):
"""
Sets the value of :py:attr:`maxIter`.
"""
self._paramMap[self.maxIter] = value
return self
def getMaxIter(self):
"""
Gets the value of maxIter or its default value.
"""
return self.getOrDefault(self.maxIter)
class HasRegParam(Params):
"""
Mixin for param regParam: regularization parameter (>= 0).
"""
# a placeholder to make it appear in the generated doc
regParam = Param(Params._dummy(), "regParam", "regularization parameter (>= 0).")
def __init__(self):
super(HasRegParam, self).__init__()
#: param for regularization parameter (>= 0).
self.regParam = Param(self, "regParam", "regularization parameter (>= 0).")
def setRegParam(self, value):
"""
Sets the value of :py:attr:`regParam`.
"""
self._paramMap[self.regParam] = value
return self
def getRegParam(self):
"""
Gets the value of regParam or its default value.
"""
return self.getOrDefault(self.regParam)
class HasFeaturesCol(Params):
"""
Mixin for param featuresCol: features column name.
"""
# a placeholder to make it appear in the generated doc
featuresCol = Param(Params._dummy(), "featuresCol", "features column name.")
def __init__(self):
super(HasFeaturesCol, self).__init__()
#: param for features column name.
self.featuresCol = Param(self, "featuresCol", "features column name.")
self._setDefault(featuresCol='features')
def setFeaturesCol(self, value):
"""
Sets the value of :py:attr:`featuresCol`.
"""
self._paramMap[self.featuresCol] = value
return self
def getFeaturesCol(self):
"""
Gets the value of featuresCol or its default value.
"""
return self.getOrDefault(self.featuresCol)
class HasLabelCol(Params):
"""
Mixin for param labelCol: label column name.
"""
# a placeholder to make it appear in the generated doc
labelCol = Param(Params._dummy(), "labelCol", "label column name.")
def __init__(self):
super(HasLabelCol, self).__init__()
#: param for label column name.
self.labelCol = Param(self, "labelCol", "label column name.")
self._setDefault(labelCol='label')
def setLabelCol(self, value):
"""
Sets the value of :py:attr:`labelCol`.
"""
self._paramMap[self.labelCol] = value
return self
def getLabelCol(self):
"""
Gets the value of labelCol or its default value.
"""
return self.getOrDefault(self.labelCol)
class HasPredictionCol(Params):
"""
Mixin for param predictionCol: prediction column name.
"""
# a placeholder to make it appear in the generated doc
predictionCol = Param(Params._dummy(), "predictionCol", "prediction column name.")
def __init__(self):
super(HasPredictionCol, self).__init__()
#: param for prediction column name.
self.predictionCol = Param(self, "predictionCol", "prediction column name.")
self._setDefault(predictionCol='prediction')
def setPredictionCol(self, value):
"""
Sets the value of :py:attr:`predictionCol`.
"""
self._paramMap[self.predictionCol] = value
return self
def getPredictionCol(self):
"""
Gets the value of predictionCol or its default value.
"""
return self.getOrDefault(self.predictionCol)
class HasProbabilityCol(Params):
"""
Mixin for param probabilityCol: Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.
"""
# a placeholder to make it appear in the generated doc
probabilityCol = Param(Params._dummy(), "probabilityCol", "Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.")
def __init__(self):
super(HasProbabilityCol, self).__init__()
#: param for Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.
self.probabilityCol = Param(self, "probabilityCol", "Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.")
self._setDefault(probabilityCol='probability')
def setProbabilityCol(self, value):
"""
Sets the value of :py:attr:`probabilityCol`.
"""
self._paramMap[self.probabilityCol] = value
return self
def getProbabilityCol(self):
"""
Gets the value of probabilityCol or its default value.
"""
return self.getOrDefault(self.probabilityCol)
class HasRawPredictionCol(Params):
"""
Mixin for param rawPredictionCol: raw prediction (a.k.a. confidence) column name.
"""
# a placeholder to make it appear in the generated doc
rawPredictionCol = Param(Params._dummy(), "rawPredictionCol", "raw prediction (a.k.a. confidence) column name.")
def __init__(self):
super(HasRawPredictionCol, self).__init__()
#: param for raw prediction (a.k.a. confidence) column name.
self.rawPredictionCol = Param(self, "rawPredictionCol", "raw prediction (a.k.a. confidence) column name.")
self._setDefault(rawPredictionCol='rawPrediction')
def setRawPredictionCol(self, value):
"""
Sets the value of :py:attr:`rawPredictionCol`.
"""
self._paramMap[self.rawPredictionCol] = value
return self
def getRawPredictionCol(self):
"""
Gets the value of rawPredictionCol or its default value.
"""
return self.getOrDefault(self.rawPredictionCol)
class HasInputCol(Params):
"""
Mixin for param inputCol: input column name.
"""
# a placeholder to make it appear in the generated doc
inputCol = Param(Params._dummy(), "inputCol", "input column name.")
def __init__(self):
super(HasInputCol, self).__init__()
#: param for input column name.
self.inputCol = Param(self, "inputCol", "input column name.")
def setInputCol(self, value):
"""
Sets the value of :py:attr:`inputCol`.
"""
self._paramMap[self.inputCol] = value
return self
def getInputCol(self):
"""
Gets the value of inputCol or its default value.
"""
return self.getOrDefault(self.inputCol)
class HasInputCols(Params):
"""
Mixin for param inputCols: input column names.
"""
# a placeholder to make it appear in the generated doc
inputCols = Param(Params._dummy(), "inputCols", "input column names.")
def __init__(self):
super(HasInputCols, self).__init__()
#: param for input column names.
self.inputCols = Param(self, "inputCols", "input column names.")
def setInputCols(self, value):
"""
Sets the value of :py:attr:`inputCols`.
"""
self._paramMap[self.inputCols] = value
return self
def getInputCols(self):
"""
Gets the value of inputCols or its default value.
"""
return self.getOrDefault(self.inputCols)
class HasOutputCol(Params):
"""
Mixin for param outputCol: output column name.
"""
# a placeholder to make it appear in the generated doc
outputCol = Param(Params._dummy(), "outputCol", "output column name.")
def __init__(self):
super(HasOutputCol, self).__init__()
#: param for output column name.
self.outputCol = Param(self, "outputCol", "output column name.")
self._setDefault(outputCol=self.uid + '__output')
def setOutputCol(self, value):
"""
Sets the value of :py:attr:`outputCol`.
"""
self._paramMap[self.outputCol] = value
return self
def getOutputCol(self):
"""
Gets the value of outputCol or its default value.
"""
return self.getOrDefault(self.outputCol)
class HasNumFeatures(Params):
"""
Mixin for param numFeatures: number of features.
"""
# a placeholder to make it appear in the generated doc
numFeatures = Param(Params._dummy(), "numFeatures", "number of features.")
def __init__(self):
super(HasNumFeatures, self).__init__()
#: param for number of features.
self.numFeatures = Param(self, "numFeatures", "number of features.")
def setNumFeatures(self, value):
"""
Sets the value of :py:attr:`numFeatures`.
"""
self._paramMap[self.numFeatures] = value
return self
def getNumFeatures(self):
"""
Gets the value of numFeatures or its default value.
"""
return self.getOrDefault(self.numFeatures)
class HasCheckpointInterval(Params):
"""
Mixin for param checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.
"""
# a placeholder to make it appear in the generated doc
checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.")
def __init__(self):
super(HasCheckpointInterval, self).__init__()
#: param for set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.
self.checkpointInterval = Param(self, "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.")
def setCheckpointInterval(self, value):
"""
Sets the value of :py:attr:`checkpointInterval`.
"""
self._paramMap[self.checkpointInterval] = value
return self
def getCheckpointInterval(self):
"""
Gets the value of checkpointInterval or its default value.
"""
return self.getOrDefault(self.checkpointInterval)
class HasSeed(Params):
"""
Mixin for param seed: random seed.
"""
# a placeholder to make it appear in the generated doc
seed = Param(Params._dummy(), "seed", "random seed.")
def __init__(self):
super(HasSeed, self).__init__()
#: param for random seed.
self.seed = Param(self, "seed", "random seed.")
self._setDefault(seed=hash(type(self).__name__))
def setSeed(self, value):
"""
Sets the value of :py:attr:`seed`.
"""
self._paramMap[self.seed] = value
return self
def getSeed(self):
"""
Gets the value of seed or its default value.
"""
return self.getOrDefault(self.seed)
class HasTol(Params):
"""
Mixin for param tol: the convergence tolerance for iterative algorithms.
"""
# a placeholder to make it appear in the generated doc
tol = Param(Params._dummy(), "tol", "the convergence tolerance for iterative algorithms.")
def __init__(self):
super(HasTol, self).__init__()
#: param for the convergence tolerance for iterative algorithms.
self.tol = Param(self, "tol", "the convergence tolerance for iterative algorithms.")
def setTol(self, value):
"""
Sets the value of :py:attr:`tol`.
"""
self._paramMap[self.tol] = value
return self
def getTol(self):
"""
Gets the value of tol or its default value.
"""
return self.getOrDefault(self.tol)
class HasStepSize(Params):
"""
Mixin for param stepSize: Step size to be used for each iteration of optimization.
"""
# a placeholder to make it appear in the generated doc
stepSize = Param(Params._dummy(), "stepSize", "Step size to be used for each iteration of optimization.")
def __init__(self):
super(HasStepSize, self).__init__()
#: param for Step size to be used for each iteration of optimization.
self.stepSize = Param(self, "stepSize", "Step size to be used for each iteration of optimization.")
def setStepSize(self, value):
"""
Sets the value of :py:attr:`stepSize`.
"""
self._paramMap[self.stepSize] = value
return self
def getStepSize(self):
"""
Gets the value of stepSize or its default value.
"""
return self.getOrDefault(self.stepSize)
class HasHandleInvalid(Params):
"""
Mixin for param handleInvalid: how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.
"""
# a placeholder to make it appear in the generated doc
handleInvalid = Param(Params._dummy(), "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.")
def __init__(self):
super(HasHandleInvalid, self).__init__()
#: param for how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.
self.handleInvalid = Param(self, "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.")
def setHandleInvalid(self, value):
"""
Sets the value of :py:attr:`handleInvalid`.
"""
self._paramMap[self.handleInvalid] = value
return self
def getHandleInvalid(self):
"""
Gets the value of handleInvalid or its default value.
"""
return self.getOrDefault(self.handleInvalid)
class HasElasticNetParam(Params):
"""
Mixin for param elasticNetParam: the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.
"""
# a placeholder to make it appear in the generated doc
elasticNetParam = Param(Params._dummy(), "elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.")
def __init__(self):
super(HasElasticNetParam, self).__init__()
#: param for the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.
self.elasticNetParam = Param(self, "elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.")
self._setDefault(elasticNetParam=0.0)
def setElasticNetParam(self, value):
"""
Sets the value of :py:attr:`elasticNetParam`.
"""
self._paramMap[self.elasticNetParam] = value
return self
def getElasticNetParam(self):
"""
Gets the value of elasticNetParam or its default value.
"""
return self.getOrDefault(self.elasticNetParam)
class HasFitIntercept(Params):
"""
Mixin for param fitIntercept: whether to fit an intercept term.
"""
# a placeholder to make it appear in the generated doc
fitIntercept = Param(Params._dummy(), "fitIntercept", "whether to fit an intercept term.")
def __init__(self):
super(HasFitIntercept, self).__init__()
#: param for whether to fit an intercept term.
self.fitIntercept = Param(self, "fitIntercept", "whether to fit an intercept term.")
self._setDefault(fitIntercept=True)
def setFitIntercept(self, value):
"""
Sets the value of :py:attr:`fitIntercept`.
"""
self._paramMap[self.fitIntercept] = value
return self
def getFitIntercept(self):
"""
Gets the value of fitIntercept or its default value.
"""
return self.getOrDefault(self.fitIntercept)
class HasStandardization(Params):
"""
Mixin for param standardization: whether to standardize the training features before fitting the model.
"""
# a placeholder to make it appear in the generated doc
standardization = Param(Params._dummy(), "standardization", "whether to standardize the training features before fitting the model.")
def __init__(self):
super(HasStandardization, self).__init__()
#: param for whether to standardize the training features before fitting the model.
self.standardization = Param(self, "standardization", "whether to standardize the training features before fitting the model.")
self._setDefault(standardization=True)
def setStandardization(self, value):
"""
Sets the value of :py:attr:`standardization`.
"""
self._paramMap[self.standardization] = value
return self
def getStandardization(self):
"""
Gets the value of standardization or its default value.
"""
return self.getOrDefault(self.standardization)
class HasThresholds(Params):
"""
Mixin for param thresholds: Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.
"""
# a placeholder to make it appear in the generated doc
thresholds = Param(Params._dummy(), "thresholds", "Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.")
def __init__(self):
super(HasThresholds, self).__init__()
#: param for Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.
self.thresholds = Param(self, "thresholds", "Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.")
def setThresholds(self, value):
"""
Sets the value of :py:attr:`thresholds`.
"""
self._paramMap[self.thresholds] = value
return self
def getThresholds(self):
"""
Gets the value of thresholds or its default value.
"""
return self.getOrDefault(self.thresholds)
class HasWeightCol(Params):
"""
Mixin for param weightCol: weight column name. If this is not set or empty, we treat all instance weights as 1.0.
"""
# a placeholder to make it appear in the generated doc
weightCol = Param(Params._dummy(), "weightCol", "weight column name. If this is not set or empty, we treat all instance weights as 1.0.")
def __init__(self):
super(HasWeightCol, self).__init__()
#: param for weight column name. If this is not set or empty, we treat all instance weights as 1.0.
self.weightCol = Param(self, "weightCol", "weight column name. If this is not set or empty, we treat all instance weights as 1.0.")
def setWeightCol(self, value):
"""
Sets the value of :py:attr:`weightCol`.
"""
self._paramMap[self.weightCol] = value
return self
def getWeightCol(self):
"""
Gets the value of weightCol or its default value.
"""
return self.getOrDefault(self.weightCol)
class HasSolver(Params):
"""
Mixin for param solver: the solver algorithm for optimization. If this is not set or empty, default value is 'auto'.
"""
# a placeholder to make it appear in the generated doc
solver = Param(Params._dummy(), "solver", "the solver algorithm for optimization. If this is not set or empty, default value is 'auto'.")
def __init__(self):
super(HasSolver, self).__init__()
#: param for the solver algorithm for optimization. If this is not set or empty, default value is 'auto'.
self.solver = Param(self, "solver", "the solver algorithm for optimization. If this is not set or empty, default value is 'auto'.")
self._setDefault(solver='auto')
def setSolver(self, value):
"""
Sets the value of :py:attr:`solver`.
"""
self._paramMap[self.solver] = value
return self
def getSolver(self):
"""
Gets the value of solver or its default value.
"""
return self.getOrDefault(self.solver)
class DecisionTreeParams(Params):
"""
Mixin for Decision Tree parameters.
"""
# a placeholder to make it appear in the generated doc
maxDepth = Param(Params._dummy(), "maxDepth", "Maximum depth of the tree. (>= 0) E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes.")
maxBins = Param(Params._dummy(), "maxBins", "Max number of bins for discretizing continuous features. Must be >=2 and >= number of categories for any categorical feature.")
minInstancesPerNode = Param(Params._dummy(), "minInstancesPerNode", "Minimum number of instances each child must have after split. If a split causes the left or right child to have fewer than minInstancesPerNode, the split will be discarded as invalid. Should be >= 1.")
minInfoGain = Param(Params._dummy(), "minInfoGain", "Minimum information gain for a split to be considered at a tree node.")
maxMemoryInMB = Param(Params._dummy(), "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
cacheNodeIds = Param(Params._dummy(), "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.")
def __init__(self):
super(DecisionTreeParams, self).__init__()
#: param for Maximum depth of the tree. (>= 0) E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes.
self.maxDepth = Param(self, "maxDepth", "Maximum depth of the tree. (>= 0) E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes.")
#: param for Max number of bins for discretizing continuous features. Must be >=2 and >= number of categories for any categorical feature.
self.maxBins = Param(self, "maxBins", "Max number of bins for discretizing continuous features. Must be >=2 and >= number of categories for any categorical feature.")
#: param for Minimum number of instances each child must have after split. If a split causes the left or right child to have fewer than minInstancesPerNode, the split will be discarded as invalid. Should be >= 1.
self.minInstancesPerNode = Param(self, "minInstancesPerNode", "Minimum number of instances each child must have after split. If a split causes the left or right child to have fewer than minInstancesPerNode, the split will be discarded as invalid. Should be >= 1.")
#: param for Minimum information gain for a split to be considered at a tree node.
self.minInfoGain = Param(self, "minInfoGain", "Minimum information gain for a split to be considered at a tree node.")
#: param for Maximum memory in MB allocated to histogram aggregation.
self.maxMemoryInMB = Param(self, "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
#: param for If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.
self.cacheNodeIds = Param(self, "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.")
def setMaxDepth(self, value):
"""
Sets the value of :py:attr:`maxDepth`.
"""
self._paramMap[self.maxDepth] = value
return self
def getMaxDepth(self):
"""
Gets the value of maxDepth or its default value.
"""
return self.getOrDefault(self.maxDepth)
def setMaxBins(self, value):
"""
Sets the value of :py:attr:`maxBins`.
"""
self._paramMap[self.maxBins] = value
return self
def getMaxBins(self):
"""
Gets the value of maxBins or its default value.
"""
return self.getOrDefault(self.maxBins)
def setMinInstancesPerNode(self, value):
"""
Sets the value of :py:attr:`minInstancesPerNode`.
"""
self._paramMap[self.minInstancesPerNode] = value
return self
def getMinInstancesPerNode(self):
"""
Gets the value of minInstancesPerNode or its default value.
"""
return self.getOrDefault(self.minInstancesPerNode)
def setMinInfoGain(self, value):
"""
Sets the value of :py:attr:`minInfoGain`.
"""
self._paramMap[self.minInfoGain] = value
return self
def getMinInfoGain(self):
"""
Gets the value of minInfoGain or its default value.
"""
return self.getOrDefault(self.minInfoGain)
def setMaxMemoryInMB(self, value):
"""
Sets the value of :py:attr:`maxMemoryInMB`.
"""
self._paramMap[self.maxMemoryInMB] = value
return self
def getMaxMemoryInMB(self):
"""
Gets the value of maxMemoryInMB or its default value.
"""
return self.getOrDefault(self.maxMemoryInMB)
def setCacheNodeIds(self, value):
"""
Sets the value of :py:attr:`cacheNodeIds`.
"""
self._paramMap[self.cacheNodeIds] = value
return self
def getCacheNodeIds(self):
"""
Gets the value of cacheNodeIds or its default value.
"""
return self.getOrDefault(self.cacheNodeIds)
|