31a16fbb40
### What changes were proposed in this pull request? This PR proposes migration of [`pyspark-stubs`](https://github.com/zero323/pyspark-stubs) into Spark codebase. ### Why are the changes needed? ### Does this PR introduce _any_ user-facing change? Yes. This PR adds type annotations directly to Spark source. This can impact interaction with development tools for users, which haven't used `pyspark-stubs`. ### How was this patch tested? - [x] MyPy tests of the PySpark source ``` mypy --no-incremental --config python/mypy.ini python/pyspark ``` - [x] MyPy tests of Spark examples ``` MYPYPATH=python/ mypy --no-incremental --config python/mypy.ini examples/src/main/python/ml examples/src/main/python/sql examples/src/main/python/sql/streaming ``` - [x] Existing Flake8 linter - [x] Existing unit tests Tested against: - `mypy==0.790+dev.e959952d9001e9713d329a2f9b196705b028f894` - `mypy==0.782` Closes #29591 from zero323/SPARK-32681. Authored-by: zero323 <mszymkiewicz@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
#
|
|
# 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, 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: ...
|