aboutsummaryrefslogtreecommitdiff
path: root/pyspark/pyspark/__init__.py
diff options
context:
space:
mode:
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"]