Fix Python again...

Author: rxin

python/pyspark/sql.py

@@ -2035,7 +2035,7 @@ def isCheckpointed(self):
 
     def getCheckpointFile(self):
         checkpointFile = self._jschema_rdd.getCheckpointFile()
-        if checkpointFile.isPresent():
+        if checkpointFile.isDefined():
             return checkpointFile.get()
 
     def coalesce(self, numPartitions, shuffle=False):

sql/core/src/main/scala/org/apache/spark/sql/SchemaRDD.scala

@@ -476,13 +476,18 @@ class SchemaRDD(
                        (implicit ord: Ordering[Row] = null): SchemaRDD =
     applySchema(super.coalesce(numPartitions, shuffle)(ord))
 
-  override def distinct(): SchemaRDD =
-    applySchema(super.distinct())
+  def coalesce(numPartitions: Int, shuffle: Boolean): SchemaRDD =
+    applySchema(super.coalesce(numPartitions, shuffle)(null))
+
+  override def distinct(): SchemaRDD = applySchema(super.distinct())
 
   override def distinct(numPartitions: Int)
                        (implicit ord: Ordering[Row] = null): SchemaRDD =
     applySchema(super.distinct(numPartitions)(ord))
 
+  def distinct(numPartitions: Int): SchemaRDD =
+    applySchema(super.distinct(numPartitions)(null))
+
   override def filter(f: Row => Boolean): SchemaRDD =
     applySchema(super.filter(f))
 
@@ -500,6 +505,9 @@ class SchemaRDD(
                           (implicit ord: Ordering[Row] = null): SchemaRDD =
     applySchema(super.repartition(numPartitions)(ord))
 
+  def repartition(numPartitions: Int): SchemaRDD =
+    applySchema(super.repartition(numPartitions)(null))
+
   override def subtract(other: RDD[Row]): SchemaRDD =
     applySchema(super.subtract(other))