diff options
Diffstat (limited to 'python/pyspark')
-rw-r--r-- | python/pyspark/sql.py | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 1a62031db5..6789d7002b 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -360,6 +360,35 @@ class SchemaRDD(RDD): else: return None + def coalesce(self, numPartitions, shuffle=False): + rdd = self._jschema_rdd.coalesce(numPartitions, shuffle) + return SchemaRDD(rdd, self.sql_ctx) + + def distinct(self): + rdd = self._jschema_rdd.distinct() + return SchemaRDD(rdd, self.sql_ctx) + + def intersection(self, other): + if (other.__class__ is SchemaRDD): + rdd = self._jschema_rdd.intersection(other._jschema_rdd) + return SchemaRDD(rdd, self.sql_ctx) + else: + raise ValueError("Can only intersect with another SchemaRDD") + + def repartition(self, numPartitions): + rdd = self._jschema_rdd.repartition(numPartitions) + return SchemaRDD(rdd, self.sql_ctx) + + def subtract(self, other, numPartitions=None): + if (other.__class__ is SchemaRDD): + if numPartitions is None: + rdd = self._jschema_rdd.subtract(other._jschema_rdd) + else: + rdd = self._jschema_rdd.subtract(other._jschema_rdd, numPartitions) + return SchemaRDD(rdd, self.sql_ctx) + else: + raise ValueError("Can only subtract another SchemaRDD") + def _test(): import doctest from pyspark.context import SparkContext |