aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/__init__.py
diff options
context:
space:
mode:
Diffstat (limited to 'python/pyspark/__init__.py')
-rw-r--r--python/pyspark/__init__.py20
1 files changed, 20 insertions, 0 deletions
diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py
new file mode 100644
index 0000000000..c595ae0842
--- /dev/null
+++ b/python/pyspark/__init__.py
@@ -0,0 +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"], "python/lib/py4j0.7.egg"))
+
+
+from pyspark.context import SparkContext
+from pyspark.rdd import RDD
+
+
+__all__ = ["SparkContext", "RDD"]