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>
77 lines
2.5 KiB
Python
77 lines
2.5 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 Any, Dict, TypeVar, Union
|
|
from typing_extensions import Literal
|
|
|
|
import pyspark.ml.base
|
|
import pyspark.ml.param
|
|
import pyspark.ml.util
|
|
import pyspark.ml.wrapper
|
|
|
|
ParamMap = Dict[pyspark.ml.param.Param, Any]
|
|
PipelineStage = Union[pyspark.ml.base.Estimator, pyspark.ml.base.Transformer]
|
|
|
|
T = TypeVar("T")
|
|
P = TypeVar("P", bound=pyspark.ml.param.Params)
|
|
M = TypeVar("M", bound=pyspark.ml.base.Transformer)
|
|
JM = TypeVar("JM", bound=pyspark.ml.wrapper.JavaTransformer)
|
|
|
|
BinaryClassificationEvaluatorMetricType = Union[
|
|
Literal["areaUnderROC"], Literal["areaUnderPR"]
|
|
]
|
|
RegressionEvaluatorMetricType = Union[
|
|
Literal["rmse"], Literal["mse"], Literal["r2"], Literal["mae"], Literal["var"]
|
|
]
|
|
MulticlassClassificationEvaluatorMetricType = Union[
|
|
Literal["f1"],
|
|
Literal["accuracy"],
|
|
Literal["weightedPrecision"],
|
|
Literal["weightedRecall"],
|
|
Literal["weightedTruePositiveRate"],
|
|
Literal["weightedFalsePositiveRate"],
|
|
Literal["weightedFMeasure"],
|
|
Literal["truePositiveRateByLabel"],
|
|
Literal["falsePositiveRateByLabel"],
|
|
Literal["precisionByLabel"],
|
|
Literal["recallByLabel"],
|
|
Literal["fMeasureByLabel"],
|
|
]
|
|
MultilabelClassificationEvaluatorMetricType = Union[
|
|
Literal["subsetAccuracy"],
|
|
Literal["accuracy"],
|
|
Literal["hammingLoss"],
|
|
Literal["precision"],
|
|
Literal["recall"],
|
|
Literal["f1Measure"],
|
|
Literal["precisionByLabel"],
|
|
Literal["recallByLabel"],
|
|
Literal["f1MeasureByLabel"],
|
|
Literal["microPrecision"],
|
|
Literal["microRecall"],
|
|
Literal["microF1Measure"],
|
|
]
|
|
ClusteringEvaluatorMetricType = Union[Literal["silhouette"]]
|
|
RankingEvaluatorMetricType = Union[
|
|
Literal["meanAveragePrecision"],
|
|
Literal["meanAveragePrecisionAtK"],
|
|
Literal["precisionAtK"],
|
|
Literal["ndcgAtK"],
|
|
Literal["recallAtK"],
|
|
]
|