2013-01-01 16:52:14 -05:00
|
|
|
"""
|
|
|
|
PySpark is a Python API for Spark.
|
|
|
|
|
|
|
|
Public classes:
|
|
|
|
|
|
|
|
- L{SparkContext<pyspark.context.SparkContext>}
|
|
|
|
Main entry point for Spark functionality.
|
|
|
|
- L{RDD<pyspark.rdd.RDD>}
|
|
|
|
A Resilient Distributed Dataset (RDD), the basic abstraction in Spark.
|
2013-01-20 04:57:44 -05:00
|
|
|
- L{Broadcast<pyspark.broadcast.Broadcast>}
|
|
|
|
A broadcast variable that gets reused across tasks.
|
|
|
|
- L{Accumulator<pyspark.accumulators.Accumulator>}
|
|
|
|
An "add-only" shared variable that tasks can only add values to.
|
2013-01-21 19:42:24 -05:00
|
|
|
- L{SparkFiles<pyspark.files.SparkFiles>}
|
|
|
|
Access files shipped with jobs.
|
2013-01-01 16:52:14 -05:00
|
|
|
"""
|
2012-12-28 01:47:37 -05:00
|
|
|
import sys
|
|
|
|
import os
|
2013-01-01 17:48:45 -05:00
|
|
|
sys.path.insert(0, os.path.join(os.environ["SPARK_HOME"], "python/lib/py4j0.7.egg"))
|
2012-12-29 01:51:28 -05:00
|
|
|
|
|
|
|
|
|
|
|
from pyspark.context import SparkContext
|
2013-01-01 16:52:14 -05:00
|
|
|
from pyspark.rdd import RDD
|
2013-01-21 19:42:24 -05:00
|
|
|
from pyspark.files import SparkFiles
|
2012-12-29 01:51:28 -05:00
|
|
|
|
|
|
|
|
2013-01-21 19:42:24 -05:00
|
|
|
__all__ = ["SparkContext", "RDD", "SparkFiles"]
|