445a755b88
This patch bring the pull based progress API into Python, also a example in Python. Author: Davies Liu <davies@databricks.com> Closes #3027 from davies/progress_api and squashes the following commits: b1ba984 [Davies Liu] fix style d3b9253 [Davies Liu] add tests, mute the exception after stop 4297327 [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api 969fa9d [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api 25590c9 [Davies Liu] update with Java API 360de2d [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api c0f1021 [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api 023afb3 [Davies Liu] add Python API and example for progress API
59 lines
2.1 KiB
Python
59 lines
2.1 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.
|
|
#
|
|
|
|
"""
|
|
PySpark is the Python API for Spark.
|
|
|
|
Public classes:
|
|
|
|
- :class:`SparkContext`:
|
|
Main entry point for Spark functionality.
|
|
- :class:`RDD`:
|
|
A Resilient Distributed Dataset (RDD), the basic abstraction in Spark.
|
|
- :class:`Broadcast`:
|
|
A broadcast variable that gets reused across tasks.
|
|
- :class:`Accumulator`:
|
|
An "add-only" shared variable that tasks can only add values to.
|
|
- :class:`SparkConf`:
|
|
For configuring Spark.
|
|
- :class:`SparkFiles`:
|
|
Access files shipped with jobs.
|
|
- :class:`StorageLevel`:
|
|
Finer-grained cache persistence levels.
|
|
|
|
"""
|
|
|
|
from pyspark.conf import SparkConf
|
|
from pyspark.context import SparkContext
|
|
from pyspark.rdd import RDD
|
|
from pyspark.files import SparkFiles
|
|
from pyspark.storagelevel import StorageLevel
|
|
from pyspark.accumulators import Accumulator, AccumulatorParam
|
|
from pyspark.broadcast import Broadcast
|
|
from pyspark.serializers import MarshalSerializer, PickleSerializer
|
|
from pyspark.status import *
|
|
from pyspark.profiler import Profiler, BasicProfiler
|
|
|
|
# for back compatibility
|
|
from pyspark.sql import SQLContext, HiveContext, SchemaRDD, Row
|
|
|
|
__all__ = [
|
|
"SparkConf", "SparkContext", "SparkFiles", "RDD", "StorageLevel", "Broadcast",
|
|
"Accumulator", "AccumulatorParam", "MarshalSerializer", "PickleSerializer",
|
|
"StatusTracker", "SparkJobInfo", "SparkStageInfo", "Profiler", "BasicProfiler",
|
|
]
|