ce0333f9a0
This PR rename random.py to rand.py to avoid the side affects of conflict with random module, but still keep the same interface as before. ``` >>> from pyspark.mllib.random import RandomRDDs ``` ``` $ pydoc pyspark.mllib.random Help on module random in pyspark.mllib: NAME random - Python package for random data generation. FILE /Users/davies/work/spark/python/pyspark/mllib/rand.py CLASSES __builtin__.object pyspark.mllib.random.RandomRDDs class RandomRDDs(__builtin__.object) | Generator methods for creating RDDs comprised of i.i.d samples from | some distribution. | | Static methods defined here: | | normalRDD(sc, size, numPartitions=None, seed=None) ``` cc mengxr reference link: http://xion.org.pl/2012/05/06/hacking-python-imports/ Author: Davies Liu <davies@databricks.com> Closes #3216 from davies/random and squashes the following commits: 7ac4e8b [Davies Liu] rename random.py to rand.py
56 lines
1.9 KiB
Python
56 lines
1.9 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
|
|
|
|
# for back compatibility
|
|
from pyspark.sql import SQLContext, HiveContext, SchemaRDD, Row
|
|
|
|
__all__ = [
|
|
"SparkConf", "SparkContext", "SparkFiles", "RDD", "StorageLevel", "Broadcast",
|
|
"Accumulator", "AccumulatorParam", "MarshalSerializer", "PickleSerializer",
|
|
]
|