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>
90 lines
3.1 KiB
Python
90 lines
3.1 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 Optional
|
|
|
|
from pyspark.ml.linalg import Matrix, Vector
|
|
from pyspark.ml.wrapper import JavaWrapper
|
|
from pyspark.sql.column import Column
|
|
from pyspark.sql.dataframe import DataFrame
|
|
|
|
from py4j.java_gateway import JavaObject # type: ignore[import]
|
|
|
|
class ChiSquareTest:
|
|
@staticmethod
|
|
def test(
|
|
dataset: DataFrame, featuresCol: str, labelCol: str, flatten: bool = ...
|
|
) -> DataFrame: ...
|
|
|
|
class Correlation:
|
|
@staticmethod
|
|
def corr(dataset: DataFrame, column: str, method: str = ...) -> DataFrame: ...
|
|
|
|
class KolmogorovSmirnovTest:
|
|
@staticmethod
|
|
def test(
|
|
dataset: DataFrame, sampleCol: str, distName: str, *params: float
|
|
) -> DataFrame: ...
|
|
|
|
class Summarizer:
|
|
@staticmethod
|
|
def mean(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def sum(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def variance(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def std(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def count(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def numNonZeros(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def max(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def min(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def normL1(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def normL2(col: Column, weightCol: Optional[Column] = ...) -> Column: ...
|
|
@staticmethod
|
|
def metrics(*metrics: str) -> SummaryBuilder: ...
|
|
|
|
class SummaryBuilder(JavaWrapper):
|
|
def __init__(self, jSummaryBuilder: JavaObject) -> None: ...
|
|
def summary(
|
|
self, featuresCol: Column, weightCol: Optional[Column] = ...
|
|
) -> Column: ...
|
|
|
|
class MultivariateGaussian:
|
|
mean: Vector
|
|
cov: Matrix
|
|
def __init__(self, mean: Vector, cov: Matrix) -> None: ...
|
|
|
|
class ANOVATest:
|
|
@staticmethod
|
|
def test(
|
|
dataset: DataFrame, featuresCol: str, labelCol: str, flatten: bool = ...
|
|
) -> DataFrame: ...
|
|
|
|
class FValueTest:
|
|
@staticmethod
|
|
def test(
|
|
dataset: DataFrame, featuresCol: str, labelCol: str, flatten: bool = ...
|
|
) -> DataFrame: ...
|