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>
127 lines
4 KiB
Python
127 lines
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 overload
|
|
from typing import Dict, Optional, Tuple
|
|
from pyspark.mllib._typing import VectorLike
|
|
from pyspark.rdd import RDD
|
|
from pyspark.mllib.common import JavaModelWrapper
|
|
from pyspark.mllib.regression import LabeledPoint
|
|
from pyspark.mllib.util import JavaLoader, JavaSaveable
|
|
|
|
class TreeEnsembleModel(JavaModelWrapper, JavaSaveable):
|
|
@overload
|
|
def predict(self, x: VectorLike) -> float: ...
|
|
@overload
|
|
def predict(self, x: RDD[VectorLike]) -> RDD[VectorLike]: ...
|
|
def numTrees(self) -> int: ...
|
|
def totalNumNodes(self) -> int: ...
|
|
def toDebugString(self) -> str: ...
|
|
|
|
class DecisionTreeModel(JavaModelWrapper, JavaSaveable, JavaLoader[DecisionTreeModel]):
|
|
@overload
|
|
def predict(self, x: VectorLike) -> float: ...
|
|
@overload
|
|
def predict(self, x: RDD[VectorLike]) -> RDD[VectorLike]: ...
|
|
def numNodes(self) -> int: ...
|
|
def depth(self) -> int: ...
|
|
def toDebugString(self) -> str: ...
|
|
|
|
class DecisionTree:
|
|
@classmethod
|
|
def trainClassifier(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
numClasses: int,
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
impurity: str = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
minInstancesPerNode: int = ...,
|
|
minInfoGain: float = ...,
|
|
) -> DecisionTreeModel: ...
|
|
@classmethod
|
|
def trainRegressor(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
impurity: str = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
minInstancesPerNode: int = ...,
|
|
minInfoGain: float = ...,
|
|
) -> DecisionTreeModel: ...
|
|
|
|
class RandomForestModel(TreeEnsembleModel, JavaLoader[RandomForestModel]): ...
|
|
|
|
class RandomForest:
|
|
supportedFeatureSubsetStrategies: Tuple[str, ...]
|
|
@classmethod
|
|
def trainClassifier(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
numClasses: int,
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
numTrees: int,
|
|
featureSubsetStrategy: str = ...,
|
|
impurity: str = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
seed: Optional[int] = ...,
|
|
) -> RandomForestModel: ...
|
|
@classmethod
|
|
def trainRegressor(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
numTrees: int,
|
|
featureSubsetStrategy: str = ...,
|
|
impurity: str = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
seed: Optional[int] = ...,
|
|
) -> RandomForestModel: ...
|
|
|
|
class GradientBoostedTreesModel(
|
|
TreeEnsembleModel, JavaLoader[GradientBoostedTreesModel]
|
|
): ...
|
|
|
|
class GradientBoostedTrees:
|
|
@classmethod
|
|
def trainClassifier(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
loss: str = ...,
|
|
numIterations: int = ...,
|
|
learningRate: float = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
) -> GradientBoostedTreesModel: ...
|
|
@classmethod
|
|
def trainRegressor(
|
|
cls,
|
|
data: RDD[LabeledPoint],
|
|
categoricalFeaturesInfo: Dict[int, int],
|
|
loss: str = ...,
|
|
numIterations: int = ...,
|
|
learningRate: float = ...,
|
|
maxDepth: int = ...,
|
|
maxBins: int = ...,
|
|
) -> GradientBoostedTreesModel: ...
|