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>
156 lines
5.1 KiB
Python
156 lines
5.1 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 overload
|
|
from typing import Iterable, Optional, Tuple, TypeVar
|
|
from pyspark.rdd import RDD
|
|
from pyspark.mllib._typing import VectorLike
|
|
from pyspark.context import SparkContext
|
|
from pyspark.mllib.linalg import Vector
|
|
from pyspark.mllib.util import Saveable, Loader
|
|
from pyspark.streaming.dstream import DStream
|
|
from numpy import ndarray # type: ignore[import]
|
|
|
|
K = TypeVar("K")
|
|
|
|
class LabeledPoint:
|
|
label: int
|
|
features: Vector
|
|
def __init__(self, label: float, features: Iterable[float]) -> None: ...
|
|
def __reduce__(self) -> Tuple[type, Tuple[bytes]]: ...
|
|
|
|
class LinearModel:
|
|
def __init__(self, weights: Vector, intercept: float) -> None: ...
|
|
@property
|
|
def weights(self) -> Vector: ...
|
|
@property
|
|
def intercept(self) -> float: ...
|
|
|
|
class LinearRegressionModelBase(LinearModel):
|
|
@overload
|
|
def predict(self, x: Vector) -> float: ...
|
|
@overload
|
|
def predict(self, x: RDD[Vector]) -> RDD[float]: ...
|
|
|
|
class LinearRegressionModel(LinearRegressionModelBase):
|
|
def save(self, sc: SparkContext, path: str) -> None: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> LinearRegressionModel: ...
|
|
|
|
class LinearRegressionWithSGD:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
iterations: int = ...,
|
|
step: float = ...,
|
|
miniBatchFraction: float = ...,
|
|
initialWeights: Optional[VectorLike] = ...,
|
|
regParam: float = ...,
|
|
regType: Optional[str] = ...,
|
|
intercept: bool = ...,
|
|
validateData: bool = ...,
|
|
convergenceTol: float = ...,
|
|
) -> LinearRegressionModel: ...
|
|
|
|
class LassoModel(LinearRegressionModelBase):
|
|
def save(self, sc: SparkContext, path: str) -> None: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> LassoModel: ...
|
|
|
|
class LassoWithSGD:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
iterations: int = ...,
|
|
step: float = ...,
|
|
regParam: float = ...,
|
|
miniBatchFraction: float = ...,
|
|
initialWeights: Optional[VectorLike] = ...,
|
|
intercept: bool = ...,
|
|
validateData: bool = ...,
|
|
convergenceTol: float = ...,
|
|
) -> LassoModel: ...
|
|
|
|
class RidgeRegressionModel(LinearRegressionModelBase):
|
|
def save(self, sc: SparkContext, path: str) -> None: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> RidgeRegressionModel: ...
|
|
|
|
class RidgeRegressionWithSGD:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
iterations: int = ...,
|
|
step: float = ...,
|
|
regParam: float = ...,
|
|
miniBatchFraction: float = ...,
|
|
initialWeights: Optional[VectorLike] = ...,
|
|
intercept: bool = ...,
|
|
validateData: bool = ...,
|
|
convergenceTol: float = ...,
|
|
) -> RidgeRegressionModel: ...
|
|
|
|
class IsotonicRegressionModel(Saveable, Loader[IsotonicRegressionModel]):
|
|
boundaries: ndarray
|
|
predictions: ndarray
|
|
isotonic: bool
|
|
def __init__(
|
|
self, boundaries: ndarray, predictions: ndarray, isotonic: bool
|
|
) -> None: ...
|
|
@overload
|
|
def predict(self, x: Vector) -> ndarray: ...
|
|
@overload
|
|
def predict(self, x: RDD[Vector]) -> RDD[ndarray]: ...
|
|
def save(self, sc: SparkContext, path: str) -> None: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> IsotonicRegressionModel: ...
|
|
|
|
class IsotonicRegression:
|
|
@classmethod
|
|
def train(
|
|
cls, data: RDD[VectorLike], isotonic: bool = ...
|
|
) -> IsotonicRegressionModel: ...
|
|
|
|
class StreamingLinearAlgorithm:
|
|
def __init__(self, model: LinearModel) -> None: ...
|
|
def latestModel(self) -> LinearModel: ...
|
|
def predictOn(self, dstream: DStream[VectorLike]) -> DStream[float]: ...
|
|
def predictOnValues(
|
|
self, dstream: DStream[Tuple[K, VectorLike]]
|
|
) -> DStream[Tuple[K, float]]: ...
|
|
|
|
class StreamingLinearRegressionWithSGD(StreamingLinearAlgorithm):
|
|
stepSize: float
|
|
numIterations: int
|
|
miniBatchFraction: float
|
|
convergenceTol: float
|
|
def __init__(
|
|
self,
|
|
stepSize: float = ...,
|
|
numIterations: int = ...,
|
|
miniBatchFraction: float = ...,
|
|
convergenceTol: float = ...,
|
|
) -> None: ...
|
|
def setInitialWeights(
|
|
self, initialWeights: VectorLike
|
|
) -> StreamingLinearRegressionWithSGD: ...
|
|
def trainOn(self, dstream: DStream[LabeledPoint]) -> None: ...
|