665817bd4f
### What changes were proposed in this pull request? This pull request: - Adds following flags to the main mypy configuration: - [`strict_optional`](https://mypy.readthedocs.io/en/stable/config_file.html#confval-strict_optional) - [`no_implicit_optional`](https://mypy.readthedocs.io/en/stable/config_file.html#confval-no_implicit_optional) - [`disallow_untyped_defs`](https://mypy.readthedocs.io/en/stable/config_file.html#confval-disallow_untyped_calls) These flags are enabled only for public API and disabled for tests and internal modules. Additionally, these PR fixes missing annotations. ### Why are the changes needed? Primary reason to propose this changes is to use standard configuration as used by typeshed project. This will allow us to be more strict, especially when interacting with JVM code. See for example https://github.com/apache/spark/pull/29122#pullrequestreview-513112882 Additionally, it will allow us to detect cases where annotations have unintentionally omitted. ### Does this PR introduce _any_ user-facing change? Annotations only. ### How was this patch tested? `dev/lint-python`. Closes #30382 from zero323/SPARK-33457. Authored-by: zero323 <mszymkiewicz@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
199 lines
6.6 KiB
Python
199 lines
6.6 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 List, NamedTuple, Optional, Tuple, TypeVar
|
|
|
|
import array
|
|
|
|
from numpy import float64, int64, ndarray # type: ignore[import]
|
|
from py4j.java_gateway import JavaObject # type: ignore[import]
|
|
|
|
from pyspark.mllib._typing import VectorLike
|
|
from pyspark.context import SparkContext
|
|
from pyspark.rdd import RDD
|
|
from pyspark.mllib.common import JavaModelWrapper
|
|
from pyspark.mllib.stat.distribution import MultivariateGaussian
|
|
from pyspark.mllib.util import Saveable, Loader, JavaLoader, JavaSaveable
|
|
from pyspark.streaming.dstream import DStream
|
|
|
|
T = TypeVar("T")
|
|
|
|
class BisectingKMeansModel(JavaModelWrapper):
|
|
centers: List[ndarray]
|
|
def __init__(self, java_model: JavaObject) -> None: ...
|
|
@property
|
|
def clusterCenters(self) -> List[ndarray]: ...
|
|
@property
|
|
def k(self) -> int: ...
|
|
@overload
|
|
def predict(self, x: VectorLike) -> int: ...
|
|
@overload
|
|
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
|
|
@overload
|
|
def computeCost(self, x: VectorLike) -> float: ...
|
|
@overload
|
|
def computeCost(self, x: RDD[VectorLike]) -> float: ...
|
|
|
|
class BisectingKMeans:
|
|
@classmethod
|
|
def train(
|
|
self,
|
|
rdd: RDD[VectorLike],
|
|
k: int = ...,
|
|
maxIterations: int = ...,
|
|
minDivisibleClusterSize: float = ...,
|
|
seed: int = ...,
|
|
) -> BisectingKMeansModel: ...
|
|
|
|
class KMeansModel(Saveable, Loader[KMeansModel]):
|
|
centers: List[ndarray]
|
|
def __init__(self, centers: List[VectorLike]) -> None: ...
|
|
@property
|
|
def clusterCenters(self) -> List[ndarray]: ...
|
|
@property
|
|
def k(self) -> int: ...
|
|
@overload
|
|
def predict(self, x: VectorLike) -> int: ...
|
|
@overload
|
|
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
|
|
def computeCost(self, rdd: RDD[VectorLike]) -> float: ...
|
|
def save(self, sc: SparkContext, path: str) -> None: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> KMeansModel: ...
|
|
|
|
class KMeans:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
rdd: RDD[VectorLike],
|
|
k: int,
|
|
maxIterations: int = ...,
|
|
initializationMode: str = ...,
|
|
seed: Optional[int] = ...,
|
|
initializationSteps: int = ...,
|
|
epsilon: float = ...,
|
|
initialModel: Optional[KMeansModel] = ...,
|
|
) -> KMeansModel: ...
|
|
|
|
class GaussianMixtureModel(
|
|
JavaModelWrapper, JavaSaveable, JavaLoader[GaussianMixtureModel]
|
|
):
|
|
@property
|
|
def weights(self) -> ndarray: ...
|
|
@property
|
|
def gaussians(self) -> List[MultivariateGaussian]: ...
|
|
@property
|
|
def k(self) -> int: ...
|
|
@overload
|
|
def predict(self, x: VectorLike) -> int64: ...
|
|
@overload
|
|
def predict(self, x: RDD[VectorLike]) -> RDD[int]: ...
|
|
@overload
|
|
def predictSoft(self, x: VectorLike) -> ndarray: ...
|
|
@overload
|
|
def predictSoft(self, x: RDD[VectorLike]) -> RDD[array.array]: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> GaussianMixtureModel: ...
|
|
|
|
class GaussianMixture:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
rdd: RDD[VectorLike],
|
|
k: int,
|
|
convergenceTol: float = ...,
|
|
maxIterations: int = ...,
|
|
seed: Optional[int] = ...,
|
|
initialModel: Optional[GaussianMixtureModel] = ...,
|
|
) -> GaussianMixtureModel: ...
|
|
|
|
class PowerIterationClusteringModel(
|
|
JavaModelWrapper, JavaSaveable, JavaLoader[PowerIterationClusteringModel]
|
|
):
|
|
@property
|
|
def k(self) -> int: ...
|
|
def assignments(self) -> RDD[PowerIterationClustering.Assignment]: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> PowerIterationClusteringModel: ...
|
|
|
|
class PowerIterationClustering:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
rdd: RDD[Tuple[int, int, float]],
|
|
k: int,
|
|
maxIterations: int = ...,
|
|
initMode: str = ...,
|
|
) -> PowerIterationClusteringModel: ...
|
|
class Assignment(NamedTuple("Assignment", [("id", int), ("cluster", int)])): ...
|
|
|
|
class StreamingKMeansModel(KMeansModel):
|
|
def __init__(
|
|
self, clusterCenters: List[VectorLike], clusterWeights: VectorLike
|
|
) -> None: ...
|
|
@property
|
|
def clusterWeights(self) -> List[float64]: ...
|
|
centers: ndarray
|
|
def update(
|
|
self, data: RDD[VectorLike], decayFactor: float, timeUnit: str
|
|
) -> StreamingKMeansModel: ...
|
|
|
|
class StreamingKMeans:
|
|
def __init__(
|
|
self, k: int = ..., decayFactor: float = ..., timeUnit: str = ...
|
|
) -> None: ...
|
|
def latestModel(self) -> StreamingKMeansModel: ...
|
|
def setK(self, k: int) -> StreamingKMeans: ...
|
|
def setDecayFactor(self, decayFactor: float) -> StreamingKMeans: ...
|
|
def setHalfLife(self, halfLife: float, timeUnit: str) -> StreamingKMeans: ...
|
|
def setInitialCenters(
|
|
self, centers: List[VectorLike], weights: List[float]
|
|
) -> StreamingKMeans: ...
|
|
def setRandomCenters(
|
|
self, dim: int, weight: float, seed: int
|
|
) -> StreamingKMeans: ...
|
|
def trainOn(self, dstream: DStream[VectorLike]) -> None: ...
|
|
def predictOn(self, dstream: DStream[VectorLike]) -> DStream[int]: ...
|
|
def predictOnValues(
|
|
self, dstream: DStream[Tuple[T, VectorLike]]
|
|
) -> DStream[Tuple[T, int]]: ...
|
|
|
|
class LDAModel(JavaModelWrapper, JavaSaveable, Loader[LDAModel]):
|
|
def topicsMatrix(self) -> ndarray: ...
|
|
def vocabSize(self) -> int: ...
|
|
def describeTopics(
|
|
self, maxTermsPerTopic: Optional[int] = ...
|
|
) -> List[Tuple[List[int], List[float]]]: ...
|
|
@classmethod
|
|
def load(cls, sc: SparkContext, path: str) -> LDAModel: ...
|
|
|
|
class LDA:
|
|
@classmethod
|
|
def train(
|
|
cls,
|
|
rdd: RDD[Tuple[int, VectorLike]],
|
|
k: int = ...,
|
|
maxIterations: int = ...,
|
|
docConcentration: float = ...,
|
|
topicConcentration: float = ...,
|
|
seed: Optional[int] = ...,
|
|
checkpointInterval: int = ...,
|
|
optimizer: str = ...,
|
|
) -> LDAModel: ...
|