python API for dataframe

zhzhan · Jan 27, 2015 · 4ae51ea · 4ae51ea
1 parent 1e5e454
commit 4ae51ea
Show file tree

Hide file tree

Showing 5 changed files with 648 additions and 318 deletions.
diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py
@@ -111,10 +111,9 @@ def run(self):
     java_import(gateway.jvm, "org.apache.spark.api.java.*")
     java_import(gateway.jvm, "org.apache.spark.api.python.*")
     java_import(gateway.jvm, "org.apache.spark.mllib.api.python.*")
-    java_import(gateway.jvm, "org.apache.spark.sql.SQLContext")
-    java_import(gateway.jvm, "org.apache.spark.sql.hive.HiveContext")
-    java_import(gateway.jvm, "org.apache.spark.sql.hive.LocalHiveContext")
-    java_import(gateway.jvm, "org.apache.spark.sql.hive.TestHiveContext")
+    # TODO(davies): move into sql
+    java_import(gateway.jvm, "org.apache.spark.sql.*")
+    java_import(gateway.jvm, "org.apache.spark.sql.hive.*")
     java_import(gateway.jvm, "scala.Tuple2")
 
     return gateway