aboutsummaryrefslogtreecommitdiff
path: root/pyspark/pyspark/__init__.py
diff options
context:
space:
mode:
authorJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-01 13:52:14 -0800
committerJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-01 13:52:14 -0800
commit170e451fbdd308ae77065bd9c0f2bd278abf0cb7 (patch)
treeda3df59e2262dac4b381227d5bc712502249d746 /pyspark/pyspark/__init__.py
parent6f6a6b79c4c3f3555f8ff427c91e714d02afe8fa (diff)
downloadspark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.tar.gz
spark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.tar.bz2
spark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.zip
Minor documentation and style fixes for PySpark.
Diffstat (limited to 'pyspark/pyspark/__init__.py')
-rw-r--r--pyspark/pyspark/__init__.py13
1 files changed, 12 insertions, 1 deletions
diff --git a/pyspark/pyspark/__init__.py b/pyspark/pyspark/__init__.py
index 8f8402b62b..1ab360a666 100644
--- a/pyspark/pyspark/__init__.py
+++ b/pyspark/pyspark/__init__.py
@@ -1,9 +1,20 @@
+"""
+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.
+"""
import sys
import os
sys.path.insert(0, os.path.join(os.environ["SPARK_HOME"], "pyspark/lib/py4j0.7.egg"))
from pyspark.context import SparkContext
+from pyspark.rdd import RDD
-__all__ = ["SparkContext"]
+__all__ = ["SparkContext", "RDD"]