-
Notifications
You must be signed in to change notification settings - Fork 28k
/
tree.py
434 lines (360 loc) · 13.4 KB
/
tree.py
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
#
# 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.
#
from typing import List, Sequence, TypeVar, TYPE_CHECKING
from pyspark import since
from pyspark.ml.linalg import Vector
from pyspark.ml.param import Params
from pyspark.ml.param.shared import (
HasCheckpointInterval,
HasSeed,
HasWeightCol,
Param,
TypeConverters,
HasMaxIter,
HasStepSize,
HasValidationIndicatorCol,
)
from pyspark.ml.wrapper import JavaPredictionModel
from pyspark.ml.common import inherit_doc
if TYPE_CHECKING:
from pyspark.ml._typing import P
T = TypeVar("T")
@inherit_doc
class _DecisionTreeModel(JavaPredictionModel[T]):
"""
Abstraction for Decision Tree models.
.. versionadded:: 1.5.0
"""
@property # type: ignore[misc]
@since("1.5.0")
def numNodes(self) -> int:
"""Return number of nodes of the decision tree."""
return self._call_java("numNodes")
@property # type: ignore[misc]
@since("1.5.0")
def depth(self) -> int:
"""Return depth of the decision tree."""
return self._call_java("depth")
@property # type: ignore[misc]
@since("2.0.0")
def toDebugString(self) -> str:
"""Full description of model."""
return self._call_java("toDebugString")
@since("3.0.0")
def predictLeaf(self, value: Vector) -> float:
"""
Predict the indices of the leaves corresponding to the feature vector.
"""
return self._call_java("predictLeaf", value)
class _DecisionTreeParams(HasCheckpointInterval, HasSeed, HasWeightCol):
"""
Mixin for Decision Tree parameters.
"""
leafCol: Param[str] = Param(
Params._dummy(),
"leafCol",
"Leaf indices column name. Predicted leaf "
+ "index of each instance in each tree by preorder.",
typeConverter=TypeConverters.toString,
)
maxDepth: Param[int] = 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. "
+ "Must be in range [0, 30].",
typeConverter=TypeConverters.toInt,
)
maxBins: Param[int] = Param(
Params._dummy(),
"maxBins",
"Max number of bins for discretizing continuous "
+ "features. Must be >=2 and >= number of categories for any categorical "
+ "feature.",
typeConverter=TypeConverters.toInt,
)
minInstancesPerNode: Param[int] = 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.",
typeConverter=TypeConverters.toInt,
)
minWeightFractionPerNode: Param[float] = Param(
Params._dummy(),
"minWeightFractionPerNode",
"Minimum "
"fraction of the weighted sample count that each child "
"must have after split. If a split causes the fraction "
"of the total weight in the left or right child to be "
"less than minWeightFractionPerNode, the split will be "
"discarded as invalid. Should be in interval [0.0, 0.5).",
typeConverter=TypeConverters.toFloat,
)
minInfoGain: Param[float] = Param(
Params._dummy(),
"minInfoGain",
"Minimum information gain for a split " + "to be considered at a tree node.",
typeConverter=TypeConverters.toFloat,
)
maxMemoryInMB: Param[int] = Param(
Params._dummy(),
"maxMemoryInMB",
"Maximum memory in MB allocated to "
+ "histogram aggregation. If too small, then 1 node will be split per "
+ "iteration, and its aggregates may exceed this size.",
typeConverter=TypeConverters.toInt,
)
cacheNodeIds: Param[bool] = 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.",
typeConverter=TypeConverters.toBoolean,
)
def __init__(self) -> None:
super(_DecisionTreeParams, self).__init__()
def setLeafCol(self: "P", value: str) -> "P":
"""
Sets the value of :py:attr:`leafCol`.
"""
return self._set(leafCol=value)
def getLeafCol(self) -> str:
"""
Gets the value of leafCol or its default value.
"""
return self.getOrDefault(self.leafCol)
def getMaxDepth(self) -> int:
"""
Gets the value of maxDepth or its default value.
"""
return self.getOrDefault(self.maxDepth)
def getMaxBins(self) -> int:
"""
Gets the value of maxBins or its default value.
"""
return self.getOrDefault(self.maxBins)
def getMinInstancesPerNode(self) -> int:
"""
Gets the value of minInstancesPerNode or its default value.
"""
return self.getOrDefault(self.minInstancesPerNode)
def getMinWeightFractionPerNode(self) -> float:
"""
Gets the value of minWeightFractionPerNode or its default value.
"""
return self.getOrDefault(self.minWeightFractionPerNode)
def getMinInfoGain(self) -> float:
"""
Gets the value of minInfoGain or its default value.
"""
return self.getOrDefault(self.minInfoGain)
def getMaxMemoryInMB(self) -> int:
"""
Gets the value of maxMemoryInMB or its default value.
"""
return self.getOrDefault(self.maxMemoryInMB)
def getCacheNodeIds(self) -> bool:
"""
Gets the value of cacheNodeIds or its default value.
"""
return self.getOrDefault(self.cacheNodeIds)
@inherit_doc
class _TreeEnsembleModel(JavaPredictionModel[T]):
"""
(private abstraction)
Represents a tree ensemble model.
"""
@property # type: ignore[misc]
@since("2.0.0")
def trees(self) -> Sequence["_DecisionTreeModel"]:
"""Trees in this ensemble. Warning: These have null parent Estimators."""
return [_DecisionTreeModel(m) for m in list(self._call_java("trees"))]
@property # type: ignore[misc]
@since("2.0.0")
def getNumTrees(self) -> int:
"""Number of trees in ensemble."""
return self._call_java("getNumTrees")
@property # type: ignore[misc]
@since("1.5.0")
def treeWeights(self) -> List[float]:
"""Return the weights for each tree"""
return list(self._call_java("javaTreeWeights"))
@property # type: ignore[misc]
@since("2.0.0")
def totalNumNodes(self) -> int:
"""Total number of nodes, summed over all trees in the ensemble."""
return self._call_java("totalNumNodes")
@property # type: ignore[misc]
@since("2.0.0")
def toDebugString(self) -> str:
"""Full description of model."""
return self._call_java("toDebugString")
@since("3.0.0")
def predictLeaf(self, value: Vector) -> float:
"""
Predict the indices of the leaves corresponding to the feature vector.
"""
return self._call_java("predictLeaf", value)
class _TreeEnsembleParams(_DecisionTreeParams):
"""
Mixin for Decision Tree-based ensemble algorithms parameters.
"""
subsamplingRate: Param[float] = Param(
Params._dummy(),
"subsamplingRate",
"Fraction of the training data " + "used for learning each decision tree, in range (0, 1].",
typeConverter=TypeConverters.toFloat,
)
supportedFeatureSubsetStrategies: List[str] = ["auto", "all", "onethird", "sqrt", "log2"]
featureSubsetStrategy: Param[str] = Param(
Params._dummy(),
"featureSubsetStrategy",
"The number of features to consider for splits at each tree node. Supported "
+ "options: 'auto' (choose automatically for task: If numTrees == 1, set to "
+ "'all'. If numTrees > 1 (forest), set to 'sqrt' for classification and to "
+ "'onethird' for regression), 'all' (use all features), 'onethird' (use "
+ "1/3 of the features), 'sqrt' (use sqrt(number of features)), 'log2' (use "
+ "log2(number of features)), 'n' (when n is in the range (0, 1.0], use "
+ "n * number of features. When n is in the range (1, number of features), use"
+ " n features). default = 'auto'",
typeConverter=TypeConverters.toString,
)
def __init__(self) -> None:
super(_TreeEnsembleParams, self).__init__()
@since("1.4.0")
def getSubsamplingRate(self) -> float:
"""
Gets the value of subsamplingRate or its default value.
"""
return self.getOrDefault(self.subsamplingRate)
@since("1.4.0")
def getFeatureSubsetStrategy(self) -> str:
"""
Gets the value of featureSubsetStrategy or its default value.
"""
return self.getOrDefault(self.featureSubsetStrategy)
class _RandomForestParams(_TreeEnsembleParams):
"""
Private class to track supported random forest parameters.
"""
numTrees: Param[int] = Param(
Params._dummy(),
"numTrees",
"Number of trees to train (>= 1).",
typeConverter=TypeConverters.toInt,
)
bootstrap: Param[bool] = Param(
Params._dummy(),
"bootstrap",
"Whether bootstrap samples are used " "when building trees.",
typeConverter=TypeConverters.toBoolean,
)
def __init__(self) -> None:
super(_RandomForestParams, self).__init__()
@since("1.4.0")
def getNumTrees(self) -> int:
"""
Gets the value of numTrees or its default value.
"""
return self.getOrDefault(self.numTrees)
@since("3.0.0")
def getBootstrap(self) -> bool:
"""
Gets the value of bootstrap or its default value.
"""
return self.getOrDefault(self.bootstrap)
class _GBTParams(_TreeEnsembleParams, HasMaxIter, HasStepSize, HasValidationIndicatorCol):
"""
Private class to track supported GBT params.
"""
stepSize: Param[float] = Param(
Params._dummy(),
"stepSize",
"Step size (a.k.a. learning rate) in interval (0, 1] for shrinking "
+ "the contribution of each estimator.",
typeConverter=TypeConverters.toFloat,
)
validationTol: Param[float] = Param(
Params._dummy(),
"validationTol",
"Threshold for stopping early when fit with validation is used. "
+ "If the error rate on the validation input changes by less than the "
+ "validationTol, then learning will stop early (before `maxIter`). "
+ "This parameter is ignored when fit without validation is used.",
typeConverter=TypeConverters.toFloat,
)
@since("3.0.0")
def getValidationTol(self) -> float:
"""
Gets the value of validationTol or its default value.
"""
return self.getOrDefault(self.validationTol)
class _HasVarianceImpurity(Params):
"""
Private class to track supported impurity measures.
"""
supportedImpurities: List[str] = ["variance"]
impurity: Param[str] = Param(
Params._dummy(),
"impurity",
"Criterion used for information gain calculation (case-insensitive). "
+ "Supported options: "
+ ", ".join(supportedImpurities),
typeConverter=TypeConverters.toString,
)
def __init__(self) -> None:
super(_HasVarianceImpurity, self).__init__()
@since("1.4.0")
def getImpurity(self) -> str:
"""
Gets the value of impurity or its default value.
"""
return self.getOrDefault(self.impurity)
class _TreeClassifierParams(Params):
"""
Private class to track supported impurity measures.
.. versionadded:: 1.4.0
"""
supportedImpurities: List[str] = ["entropy", "gini"]
impurity: Param[str] = Param(
Params._dummy(),
"impurity",
"Criterion used for information gain calculation (case-insensitive). "
+ "Supported options: "
+ ", ".join(supportedImpurities),
typeConverter=TypeConverters.toString,
)
def __init__(self) -> None:
super(_TreeClassifierParams, self).__init__()
@since("1.6.0")
def getImpurity(self) -> str:
"""
Gets the value of impurity or its default value.
"""
return self.getOrDefault(self.impurity)
class _TreeRegressorParams(_HasVarianceImpurity):
"""
Private class to track supported impurity measures.
"""
pass