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>
76 lines
2.7 KiB
Python
76 lines
2.7 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, Union
|
|
|
|
import array
|
|
from collections import namedtuple
|
|
|
|
from pyspark.context import SparkContext
|
|
from pyspark.rdd import RDD
|
|
from pyspark.mllib.common import JavaModelWrapper
|
|
from pyspark.mllib.util import JavaLoader, JavaSaveable
|
|
|
|
class Rating(namedtuple("Rating", ["user", "product", "rating"])):
|
|
def __reduce__(self): ...
|
|
|
|
class MatrixFactorizationModel(
|
|
JavaModelWrapper, JavaSaveable, JavaLoader[MatrixFactorizationModel]
|
|
):
|
|
def predict(self, user: int, product: int) -> float: ...
|
|
def predictAll(self, user_product: RDD[Tuple[int, int]]) -> RDD[Rating]: ...
|
|
def userFeatures(self) -> RDD[Tuple[int, array.array]]: ...
|
|
def productFeatures(self) -> RDD[Tuple[int, array.array]]: ...
|
|
def recommendUsers(self, product: int, num: int) -> List[Rating]: ...
|
|
def recommendProducts(self, user: int, num: int) -> List[Rating]: ...
|
|
def recommendProductsForUsers(
|
|
self, num: int
|
|
) -> RDD[Tuple[int, Tuple[Rating, ...]]]: ...
|
|
def recommendUsersForProducts(
|
|
self, num: int
|
|
) -> RDD[Tuple[int, Tuple[Rating, ...]]]: ...
|
|
@property
|
|
def rank(self) -> int: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> MatrixFactorizationModel: ...
|
|
|
|
class ALS:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
ratings: Union[RDD[Rating], RDD[Tuple[int, int, float]]],
|
|
rank: int,
|
|
iterations: int = ...,
|
|
lambda_: float = ...,
|
|
blocks: int = ...,
|
|
nonnegative: bool = ...,
|
|
seed: Optional[int] = ...,
|
|
) -> MatrixFactorizationModel: ...
|
|
@classmethod
|
|
def trainImplicit(
|
|
cls,
|
|
ratings: Union[RDD[Rating], RDD[Tuple[int, int, float]]],
|
|
rank: int,
|
|
iterations: int = ...,
|
|
lambda_: float = ...,
|
|
blocks: int = ...,
|
|
alpha: float = ...,
|
|
nonnegative: bool = ...,
|
|
seed: Optional[int] = ...,
|
|
) -> MatrixFactorizationModel: ...
|