3bead67d59
This PR is based on #3255 , fix conflicts and code style. Closes #3255. Author: Yandu Oppacher <yandu.oppacher@jadedpixel.com> Author: Davies Liu <davies@databricks.com> Closes #3901 from davies/refactor-python-profile-code and squashes the following commits: b4a9306 [Davies Liu] fix tests 4b79ce8 [Davies Liu] add docstring for profiler_cls 2700e47 [Davies Liu] use BasicProfiler as default 349e341 [Davies Liu] more refactor 6a5d4df [Davies Liu] refactor and fix tests 31bf6b6 [Davies Liu] fix code style 0864b5d [Yandu Oppacher] Remove unused method 76a6c37 [Yandu Oppacher] Added a profile collector to accumulate the profilers per stage 9eefc36 [Yandu Oppacher] Fix doc 9ace076 [Yandu Oppacher] Refactor of profiler, and moved tests around 8739aff [Yandu Oppacher] Code review fixes 9bda3ec [Yandu Oppacher] Refactor profiler code
58 lines
2 KiB
Python
58 lines
2 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.
|
|
- L{RDD}
|
|
A Resilient Distributed Dataset (RDD), the basic abstraction in Spark.
|
|
- L{Broadcast}
|
|
A broadcast variable that gets reused across tasks.
|
|
- L{Accumulator}
|
|
An "add-only" shared variable that tasks can only add values to.
|
|
- L{SparkConf}
|
|
For configuring Spark.
|
|
- L{SparkFiles}
|
|
Access files shipped with jobs.
|
|
- L{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.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",
|
|
"Profiler", "BasicProfiler",
|
|
]
|