This repository has been archived by the owner on Nov 22, 2022.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
/
_statistics.pyi
69 lines (63 loc) · 2.43 KB
/
_statistics.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
#
# 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 List, Optional, overload, Union
from typing_extensions import Literal
from numpy import ndarray # type: ignore[import]
from pyspark.mllib.common import JavaModelWrapper
from pyspark.mllib.linalg import Vector, Matrix
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.stat.test import ChiSqTestResult, KolmogorovSmirnovTestResult
from pyspark.rdd import RDD
CorrelationMethod = Union[Literal["spearman"], Literal["pearson"]]
class MultivariateStatisticalSummary(JavaModelWrapper):
def mean(self) -> ndarray: ...
def variance(self) -> ndarray: ...
def count(self) -> int: ...
def numNonzeros(self) -> ndarray: ...
def max(self) -> ndarray: ...
def min(self) -> ndarray: ...
def normL1(self) -> ndarray: ...
def normL2(self) -> ndarray: ...
class Statistics:
@staticmethod
def colStats(rdd: RDD[Vector]) -> MultivariateStatisticalSummary: ...
@overload
@staticmethod
def corr(
x: RDD[Vector], *, method: Optional[CorrelationMethod] = ...
) -> Matrix: ...
@overload
@staticmethod
def corr(
x: RDD[float], y: RDD[float], method: Optional[CorrelationMethod] = ...
) -> float: ...
@overload
@staticmethod
def chiSqTest(observed: Matrix) -> ChiSqTestResult: ...
@overload
@staticmethod
def chiSqTest(
observed: Vector, expected: Optional[Vector] = ...
) -> ChiSqTestResult: ...
@overload
@staticmethod
def chiSqTest(observed: RDD[LabeledPoint]) -> List[ChiSqTestResult]: ...
@staticmethod
def kolmogorovSmirnovTest(
data, distName: Literal["norm"] = ..., *params: float
) -> KolmogorovSmirnovTestResult: ...