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>
95 lines
3.5 KiB
Python
95 lines
3.5 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, Tuple, TypeVar
|
|
from pyspark.rdd import RDD
|
|
from pyspark.mllib.common import JavaModelWrapper
|
|
from pyspark.mllib.linalg import Matrix
|
|
|
|
T = TypeVar("T")
|
|
|
|
class BinaryClassificationMetrics(JavaModelWrapper):
|
|
def __init__(self, scoreAndLabels: RDD[Tuple[float, float]]) -> None: ...
|
|
@property
|
|
def areaUnderROC(self) -> float: ...
|
|
@property
|
|
def areaUnderPR(self) -> float: ...
|
|
def unpersist(self) -> None: ...
|
|
|
|
class RegressionMetrics(JavaModelWrapper):
|
|
def __init__(self, predictionAndObservations: RDD[Tuple[float, float]]) -> None: ...
|
|
@property
|
|
def explainedVariance(self) -> float: ...
|
|
@property
|
|
def meanAbsoluteError(self) -> float: ...
|
|
@property
|
|
def meanSquaredError(self) -> float: ...
|
|
@property
|
|
def rootMeanSquaredError(self) -> float: ...
|
|
@property
|
|
def r2(self) -> float: ...
|
|
|
|
class MulticlassMetrics(JavaModelWrapper):
|
|
def __init__(self, predictionAndLabels: RDD[Tuple[float, float]]) -> None: ...
|
|
def confusionMatrix(self) -> Matrix: ...
|
|
def truePositiveRate(self, label: float) -> float: ...
|
|
def falsePositiveRate(self, label: float) -> float: ...
|
|
def precision(self, label: float = ...) -> float: ...
|
|
def recall(self, label: float = ...) -> float: ...
|
|
def fMeasure(self, label: float = ..., beta: Optional[float] = ...) -> float: ...
|
|
@property
|
|
def accuracy(self) -> float: ...
|
|
@property
|
|
def weightedTruePositiveRate(self) -> float: ...
|
|
@property
|
|
def weightedFalsePositiveRate(self) -> float: ...
|
|
@property
|
|
def weightedRecall(self) -> float: ...
|
|
@property
|
|
def weightedPrecision(self) -> float: ...
|
|
def weightedFMeasure(self, beta: Optional[float] = ...) -> float: ...
|
|
|
|
class RankingMetrics(JavaModelWrapper):
|
|
def __init__(self, predictionAndLabels: RDD[Tuple[List[T], List[T]]]) -> None: ...
|
|
def precisionAt(self, k: int) -> float: ...
|
|
@property
|
|
def meanAveragePrecision(self) -> float: ...
|
|
def meanAveragePrecisionAt(self, k: int) -> float: ...
|
|
def ndcgAt(self, k: int) -> float: ...
|
|
def recallAt(self, k: int) -> float: ...
|
|
|
|
class MultilabelMetrics(JavaModelWrapper):
|
|
def __init__(
|
|
self, predictionAndLabels: RDD[Tuple[List[float], List[float]]]
|
|
) -> None: ...
|
|
def precision(self, label: Optional[float] = ...) -> float: ...
|
|
def recall(self, label: Optional[float] = ...) -> float: ...
|
|
def f1Measure(self, label: Optional[float] = ...) -> float: ...
|
|
@property
|
|
def microPrecision(self) -> float: ...
|
|
@property
|
|
def microRecall(self) -> float: ...
|
|
@property
|
|
def microF1Measure(self) -> float: ...
|
|
@property
|
|
def hammingLoss(self) -> float: ...
|
|
@property
|
|
def subsetAccuracy(self) -> float: ...
|
|
@property
|
|
def accuracy(self) -> float: ...
|