This repository has been archived by the owner on Nov 22, 2022.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
196 lines (179 loc) · 6.51 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
#
# 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 overload
from typing import List, NamedTuple, Optional, Tuple, TypeVar
import array
from numpy import float64, int64, ndarray # type: ignore[import]
from py4j.java_gateway import JavaObject # type: ignore[import]
from pyspark.mllib._typing import VectorLike
from pyspark.context import SparkContext
from pyspark.rdd import RDD
from pyspark.mllib.common import JavaModelWrapper
from pyspark.mllib.stat.distribution import MultivariateGaussian
from pyspark.mllib.util import Saveable, Loader, JavaLoader, JavaSaveable
from pyspark.streaming.dstream import DStream
T = TypeVar("T")
class BisectingKMeansModel(JavaModelWrapper):
centers: List[ndarray]
def __init__(self, java_model: JavaObject) -> None: ...
@property
def clusterCenters(self) -> List[ndarray]: ...
@property
def k(self) -> int: ...
@overload
def predict(self, x: VectorLike) -> int: ...
@overload
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
@overload
def computeCost(self, x: VectorLike) -> float: ...
@overload
def computeCost(self, x: RDD[VectorLike]) -> float: ...
class BisectingKMeans:
@classmethod
def train(
self,
rdd: RDD[VectorLike],
k: int = ...,
maxIterations: int = ...,
minDivisibleClusterSize: float = ...,
seed: int = ...,
) -> BisectingKMeansModel: ...
class KMeansModel(Saveable, Loader[KMeansModel]):
centers: List[ndarray]
def __init__(self, centers: List[ndarray]) -> None: ...
@property
def clusterCenters(self) -> List[ndarray]: ...
@property
def k(self) -> int: ...
@overload
def predict(self, x: VectorLike) -> int: ...
@overload
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
def computeCost(self, rdd: RDD[VectorLike]) -> float: ...
def save(self, sc: SparkContext, path: str) -> None: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> KMeansModel: ...
class KMeans:
@classmethod
def train(
cls,
rdd: RDD[VectorLike],
k: int,
maxIterations: int = ...,
initializationMode: str = ...,
seed: Optional[int] = ...,
initializationSteps: int = ...,
epsilon: float = ...,
initialModel: Optional[KMeansModel] = ...,
) -> KMeansModel: ...
class GaussianMixtureModel(
JavaModelWrapper, JavaSaveable, JavaLoader[GaussianMixtureModel]
):
@property
def weights(self) -> ndarray: ...
@property
def gaussians(self) -> List[MultivariateGaussian]: ...
@property
def k(self) -> int: ...
@overload
def predict(self, x: VectorLike) -> int64: ...
@overload
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
@overload
def predictSoft(self, x: VectorLike) -> ndarray: ...
@overload
def predictSoft(self, x: RDD[VectorLike]) -> RDD[array.array]: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> GaussianMixtureModel: ...
class GaussianMixture:
@classmethod
def train(
cls,
rdd: RDD[VectorLike],
k: int,
convergenceTol: float = ...,
maxIterations: int = ...,
seed: Optional[int] = ...,
initialModel: Optional[GaussianMixtureModel] = ...,
) -> GaussianMixtureModel: ...
class PowerIterationClusteringModel(
JavaModelWrapper, JavaSaveable, JavaLoader[PowerIterationClusteringModel]
):
@property
def k(self) -> int: ...
def assignments(self) -> RDD[PowerIterationClustering.Assignment]: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> PowerIterationClusteringModel: ...
class PowerIterationClustering:
@classmethod
def train(
cls,
rdd: RDD[Tuple[int, int, float]],
k: int,
maxIterations: int = ...,
initMode: str = ...,
) -> PowerIterationClusteringModel: ...
class Assignment(NamedTuple("Assignment", [("id", int), ("cluster", int)])): ...
class StreamingKMeansModel(KMeansModel):
def __init__(self, clusterCenters, clusterWeights) -> None: ...
@property
def clusterWeights(self) -> List[float64]: ...
centers: ndarray
def update(
self, data: RDD[VectorLike], decayFactor: float, timeUnit: str
) -> StreamingKMeansModel: ...
class StreamingKMeans:
def __init__(
self, k: int = ..., decayFactor: float = ..., timeUnit: str = ...
) -> None: ...
def latestModel(self) -> StreamingKMeansModel: ...
def setK(self, k: int) -> StreamingKMeans: ...
def setDecayFactor(self, decayFactor: float) -> StreamingKMeans: ...
def setHalfLife(self, halfLife: float, timeUnit: str) -> StreamingKMeans: ...
def setInitialCenters(
self, centers: List[VectorLike], weights: List[float]
) -> StreamingKMeans: ...
def setRandomCenters(
self, dim: int, weight: float, seed: int
) -> StreamingKMeans: ...
def trainOn(self, dstream: DStream[VectorLike]) -> None: ...
def predictOn(self, dstream: DStream[VectorLike]) -> DStream[int]: ...
def predictOnValues(
self, dstream: DStream[Tuple[T, VectorLike]]
) -> DStream[Tuple[T, int]]: ...
class LDAModel(JavaModelWrapper, JavaSaveable, Loader[LDAModel]):
def topicsMatrix(self) -> ndarray: ...
def vocabSize(self) -> int: ...
def describeTopics(
self, maxTermsPerTopic: Optional[int] = ...
) -> List[Tuple[List[int], List[float]]]: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> LDAModel: ...
class LDA:
@classmethod
def train(
cls,
rdd: RDD[Tuple[int, VectorLike]],
k: int = ...,
maxIterations: int = ...,
docConcentration: float = ...,
topicConcentration: float = ...,
seed: Optional[int] = ...,
checkpointInterval: int = ...,
optimizer: str = ...,
) -> LDAModel: ...