This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
-
-
Notifications
You must be signed in to change notification settings - Fork 37
/
clustering.pyi
437 lines (413 loc) · 14.2 KB
/
clustering.pyi
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
#
# 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:https://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 Any, List, Optional
from pyspark.ml.linalg import Matrix, Vector
from pyspark.ml.util import (
GeneralJavaMLWritable,
HasTrainingSummary,
JavaMLReadable,
JavaMLWritable,
)
from pyspark.ml.wrapper import JavaEstimator, JavaModel, JavaParams, JavaWrapper
from pyspark.ml.param.shared import (
HasAggregationDepth,
HasCheckpointInterval,
HasDistanceMeasure,
HasFeaturesCol,
HasMaxIter,
HasPredictionCol,
HasProbabilityCol,
HasSeed,
HasTol,
HasWeightCol,
)
from pyspark.ml.param import Param
from pyspark.ml.stat import MultivariateGaussian
from pyspark.sql.dataframe import DataFrame
from numpy import ndarray # type: ignore[import]
class ClusteringSummary(JavaWrapper):
@property
def predictionCol(self) -> str: ...
@property
def predictions(self) -> DataFrame: ...
@property
def featuresCol(self) -> str: ...
@property
def k(self) -> int: ...
@property
def cluster(self) -> DataFrame: ...
@property
def clusterSizes(self) -> List[int]: ...
@property
def numIter(self) -> int: ...
class _GaussianMixtureParams(
HasMaxIter,
HasFeaturesCol,
HasSeed,
HasPredictionCol,
HasProbabilityCol,
HasTol,
HasAggregationDepth,
HasWeightCol,
):
k: Param[int]
def __init__(self, *args: Any): ...
def getK(self) -> int: ...
class GaussianMixtureModel(
JavaModel,
_GaussianMixtureParams,
JavaMLWritable,
JavaMLReadable[GaussianMixtureModel],
HasTrainingSummary[GaussianMixtureSummary],
):
def setFeaturesCol(self, value: str) -> GaussianMixtureModel: ...
def setPredictionCol(self, value: str) -> GaussianMixtureModel: ...
def setProbabilityCol(self, value: str) -> GaussianMixtureModel: ...
@property
def weights(self) -> List[float]: ...
@property
def gaussians(self) -> List[MultivariateGaussian]: ...
@property
def gaussiansDF(self) -> DataFrame: ...
@property
def summary(self) -> GaussianMixtureSummary: ...
def predict(self, value: Vector) -> int: ...
def predictProbability(self, value: Vector) -> Vector: ...
class GaussianMixture(
JavaEstimator[GaussianMixtureModel],
_GaussianMixtureParams,
JavaMLWritable,
JavaMLReadable[GaussianMixture],
):
def __init__(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
k: int = ...,
probabilityCol: str = ...,
tol: float = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
aggregationDepth: int = ...,
weightCol: Optional[str] = ...
) -> None: ...
def setParams(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
k: int = ...,
probabilityCol: str = ...,
tol: float = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
aggregationDepth: int = ...,
weightCol: Optional[str] = ...
) -> GaussianMixture: ...
def setK(self, value: int) -> GaussianMixture: ...
def setMaxIter(self, value: int) -> GaussianMixture: ...
def setFeaturesCol(self, value: str) -> GaussianMixture: ...
def setPredictionCol(self, value: str) -> GaussianMixture: ...
def setProbabilityCol(self, value: str) -> GaussianMixture: ...
def setWeightCol(self, value: str) -> GaussianMixture: ...
def setSeed(self, value: int) -> GaussianMixture: ...
def setTol(self, value: float) -> GaussianMixture: ...
def setAggregationDepth(self, value: int) -> GaussianMixture: ...
class GaussianMixtureSummary(ClusteringSummary):
@property
def probabilityCol(self) -> str: ...
@property
def probability(self) -> DataFrame: ...
@property
def logLikelihood(self) -> float: ...
class KMeansSummary(ClusteringSummary):
def trainingCost(self) -> float: ...
class _KMeansParams(
HasMaxIter,
HasFeaturesCol,
HasSeed,
HasPredictionCol,
HasTol,
HasDistanceMeasure,
HasWeightCol,
):
k: Param[int]
initMode: Param[str]
initSteps: Param[int]
def __init__(self, *args: Any): ...
def getK(self) -> int: ...
def getInitMode(self) -> str: ...
def getInitSteps(self) -> int: ...
class KMeansModel(
JavaModel,
_KMeansParams,
GeneralJavaMLWritable,
JavaMLReadable[KMeansModel],
HasTrainingSummary[KMeansSummary],
):
def setFeaturesCol(self, value: str) -> KMeansModel: ...
def setPredictionCol(self, value: str) -> KMeansModel: ...
def clusterCenters(self) -> List[ndarray]: ...
@property
def summary(self) -> KMeansSummary: ...
def predict(self, value: Vector) -> int: ...
class KMeans(
JavaEstimator[KMeansModel], _KMeansParams, JavaMLWritable, JavaMLReadable[KMeans]
):
def __init__(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
k: int = ...,
initMode: str = ...,
initSteps: int = ...,
tol: float = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
distanceMeasure: str = ...,
weightCol: Optional[str] = ...
) -> None: ...
def setParams(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
k: int = ...,
initMode: str = ...,
initSteps: int = ...,
tol: float = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
distanceMeasure: str = ...,
weightCol: Optional[str] = ...
) -> KMeans: ...
def setK(self, value: int) -> KMeans: ...
def setInitMode(self, value: str) -> KMeans: ...
def setInitSteps(self, value: int) -> KMeans: ...
def setDistanceMeasure(self, value: str) -> KMeans: ...
def setMaxIter(self, value: int) -> KMeans: ...
def setFeaturesCol(self, value: str) -> KMeans: ...
def setPredictionCol(self, value: str) -> KMeans: ...
def setSeed(self, value: int) -> KMeans: ...
def setTol(self, value: float) -> KMeans: ...
def setWeightCol(self, value: str) -> KMeans: ...
class _BisectingKMeansParams(
HasMaxIter,
HasFeaturesCol,
HasSeed,
HasPredictionCol,
HasDistanceMeasure,
HasWeightCol,
):
k: Param[int]
minDivisibleClusterSize: Param[float]
def __init__(self, *args: Any): ...
def getK(self) -> int: ...
def getMinDivisibleClusterSize(self) -> float: ...
class BisectingKMeansModel(
JavaModel,
_BisectingKMeansParams,
JavaMLWritable,
JavaMLReadable[BisectingKMeansModel],
HasTrainingSummary[BisectingKMeansSummary],
):
def setFeaturesCol(self, value: str) -> BisectingKMeansModel: ...
def setPredictionCol(self, value: str) -> BisectingKMeansModel: ...
def clusterCenters(self) -> List[ndarray]: ...
def computeCost(self, dataset: DataFrame) -> float: ...
@property
def summary(self) -> BisectingKMeansSummary: ...
def predict(self, value: Vector) -> int: ...
class BisectingKMeans(
JavaEstimator[BisectingKMeansModel],
_BisectingKMeansParams,
JavaMLWritable,
JavaMLReadable[BisectingKMeans],
):
def __init__(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
k: int = ...,
minDivisibleClusterSize: float = ...,
distanceMeasure: str = ...,
weightCol: Optional[str] = ...
) -> None: ...
def setParams(
self,
*,
featuresCol: str = ...,
predictionCol: str = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
k: int = ...,
minDivisibleClusterSize: float = ...,
distanceMeasure: str = ...,
weightCol: Optional[str] = ...
) -> BisectingKMeans: ...
def setK(self, value: int) -> BisectingKMeans: ...
def setMinDivisibleClusterSize(self, value: float) -> BisectingKMeans: ...
def setDistanceMeasure(self, value: str) -> BisectingKMeans: ...
def setMaxIter(self, value: int) -> BisectingKMeans: ...
def setFeaturesCol(self, value: str) -> BisectingKMeans: ...
def setPredictionCol(self, value: str) -> BisectingKMeans: ...
def setSeed(self, value: int) -> BisectingKMeans: ...
def setWeightCol(self, value: str) -> BisectingKMeans: ...
class BisectingKMeansSummary(ClusteringSummary):
@property
def trainingCost(self) -> float: ...
class _LDAParams(HasMaxIter, HasFeaturesCol, HasSeed, HasCheckpointInterval):
k: Param[int]
optimizer: Param[str]
learningOffset: Param[float]
learningDecay: Param[float]
subsamplingRate: Param[float]
optimizeDocConcentration: Param[bool]
docConcentration: Param[List[float]]
topicConcentration: Param[float]
topicDistributionCol: Param[str]
keepLastCheckpoint: Param[bool]
def __init__(self, *args: Any): ...
def setK(self, value: int) -> LDA: ...
def getOptimizer(self) -> str: ...
def getLearningOffset(self) -> float: ...
def getLearningDecay(self) -> float: ...
def getSubsamplingRate(self) -> float: ...
def getOptimizeDocConcentration(self) -> bool: ...
def getDocConcentration(self) -> List[float]: ...
def getTopicConcentration(self) -> float: ...
def getTopicDistributionCol(self) -> str: ...
def getKeepLastCheckpoint(self) -> bool: ...
class LDAModel(JavaModel, _LDAParams):
def setFeaturesCol(self, value: str) -> LDAModel: ...
def setSeed(self, value: int) -> LDAModel: ...
def setTopicDistributionCol(self, value: str) -> LDAModel: ...
def isDistributed(self) -> bool: ...
def vocabSize(self) -> int: ...
def topicsMatrix(self) -> Matrix: ...
def logLikelihood(self, dataset: DataFrame) -> float: ...
def logPerplexity(self, dataset: DataFrame) -> float: ...
def describeTopics(self, maxTermsPerTopic: int = ...) -> DataFrame: ...
def estimatedDocConcentration(self) -> Vector: ...
class DistributedLDAModel(
LDAModel, JavaMLReadable[DistributedLDAModel], JavaMLWritable
):
def toLocal(self) -> LDAModel: ...
def trainingLogLikelihood(self) -> float: ...
def logPrior(self) -> float: ...
def getCheckpointFiles(self) -> List[str]: ...
class LocalLDAModel(LDAModel, JavaMLReadable[LocalLDAModel], JavaMLWritable): ...
class LDA(JavaEstimator[LDAModel], _LDAParams, JavaMLReadable[LDA], JavaMLWritable):
def __init__(
self,
*,
featuresCol: str = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
checkpointInterval: int = ...,
k: int = ...,
optimizer: str = ...,
learningOffset: float = ...,
learningDecay: float = ...,
subsamplingRate: float = ...,
optimizeDocConcentration: bool = ...,
docConcentration: Optional[List[float]] = ...,
topicConcentration: Optional[float] = ...,
topicDistributionCol: str = ...,
keepLastCheckpoint: bool = ...
) -> None: ...
def setParams(
self,
*,
featuresCol: str = ...,
maxIter: int = ...,
seed: Optional[int] = ...,
checkpointInterval: int = ...,
k: int = ...,
optimizer: str = ...,
learningOffset: float = ...,
learningDecay: float = ...,
subsamplingRate: float = ...,
optimizeDocConcentration: bool = ...,
docConcentration: Optional[List[float]] = ...,
topicConcentration: Optional[float] = ...,
topicDistributionCol: str = ...,
keepLastCheckpoint: bool = ...
) -> LDA: ...
def setCheckpointInterval(self, value: int) -> LDA: ...
def setSeed(self, value: int) -> LDA: ...
def setK(self, value: int) -> LDA: ...
def setOptimizer(self, value: str) -> LDA: ...
def setLearningOffset(self, value: float) -> LDA: ...
def setLearningDecay(self, value: float) -> LDA: ...
def setSubsamplingRate(self, value: float) -> LDA: ...
def setOptimizeDocConcentration(self, value: bool) -> LDA: ...
def setDocConcentration(self, value: List[float]) -> LDA: ...
def setTopicConcentration(self, value: float) -> LDA: ...
def setTopicDistributionCol(self, value: str) -> LDA: ...
def setKeepLastCheckpoint(self, value: bool) -> LDA: ...
def setMaxIter(self, value: int) -> LDA: ...
def setFeaturesCol(self, value: str) -> LDA: ...
class _PowerIterationClusteringParams(HasMaxIter, HasWeightCol):
k: Param[int]
initMode: Param[str]
srcCol: Param[str]
dstCol: Param[str]
def __init__(self, *args: Any): ...
def getK(self) -> int: ...
def getInitMode(self) -> str: ...
def getSrcCol(self) -> str: ...
def getDstCol(self) -> str: ...
class PowerIterationClustering(
_PowerIterationClusteringParams,
JavaParams,
JavaMLReadable[PowerIterationClustering],
JavaMLWritable,
):
def __init__(
self,
*,
k: int = ...,
maxIter: int = ...,
initMode: str = ...,
srcCol: str = ...,
dstCol: str = ...,
weightCol: Optional[str] = ...
) -> None: ...
def setParams(
self,
*,
k: int = ...,
maxIter: int = ...,
initMode: str = ...,
srcCol: str = ...,
dstCol: str = ...,
weightCol: Optional[str] = ...
) -> PowerIterationClustering: ...
def setK(self, value: int) -> PowerIterationClustering: ...
def setInitMode(self, value: str) -> PowerIterationClustering: ...
def setSrcCol(self, value: str) -> str: ...
def setDstCol(self, value: str) -> PowerIterationClustering: ...
def setMaxIter(self, value: int) -> PowerIterationClustering: ...
def setWeightCol(self, value: str) -> PowerIterationClustering: ...
def assignClusters(self, dataset: DataFrame) -> DataFrame: ...