deleted old implementation of Rand

python/pyspark/sql/functions.py

@@ -44,20 +44,6 @@ def _(col):
     return _
 
 
-def _create_zero_arg_function(name, doc=""):
-    """ Create a zero arg function by name"""
-    def _(val=None):
-        sc = SparkContext._active_spark_context
-        if val:
-            jc = getattr(sc._jvm.functions, name)(val)
-        else:
-            jc = getattr(sc._jvm.functions, name)()
-        return Column(jc)
-    _.__name__ = name
-    _.__doc__ = doc
-    return _
-
-
 _functions = {
     'lit': 'Creates a :class:`Column` of literal value.',
     'col': 'Returns a :class:`Column` based on the given column name.',
@@ -81,21 +67,37 @@ def _(val=None):
     'sumDistinct': 'Aggregate function: returns the sum of distinct values in the expression.',
 }
 
-_randfunctions = {
-    'rand': 'Generate a random column with i.i.d. samples from U[0.0, 1.0].',
-    'randn': 'Generate a column with i.i.d. samples from the standard normal distribution.'
-}
-
 for _name, _doc in _functions.items():
     globals()[_name] = _create_function(_name, _doc)
-for _name, _doc in _randfunctions.items():
-    globals()[_name] = _create_zero_arg_function(_name, _doc)
 del _name, _doc
 __all__ += _functions.keys()
-__all__ += _randfunctions.keys()
 __all__.sort()
 
 
+def rand(seed=None):
+    """
+    Generate a random column with i.i.d. samples from U[0.0, 1.0].
+    """
+    sc = SparkContext._active_spark_context
+    if seed:
+        jc = sc._jvm.functions.rand(seed)
+    else:
+        jc = sc._jvm.functions.rand()
+    return Column(jc)
+
+
+def randn(seed=None):
+    """
+    Generate a column with i.i.d. samples from the standard normal distribution.
+    """
+    sc = SparkContext._active_spark_context
+    if seed:
+        jc = sc._jvm.functions.randn(seed)
+    else:
+        jc = sc._jvm.functions.randn()
+    return Column(jc)
+
+
 def approxCountDistinct(col, rsd=None):
     """Returns a new :class:`Column` for approximate distinct count of ``col``.
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randfuncs/random.scala → sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/random.scala

@@ -15,11 +15,10 @@
  * limitations under the License.
  */
 
-package org.apache.spark.sql.catalyst.expressions.randfuncs
+package org.apache.spark.sql.catalyst.expressions
 
 import org.apache.spark.TaskContext
-import org.apache.spark.sql.catalyst.expressions._
-import org.apache.spark.sql.types.{DoubleType, DataType}
+import org.apache.spark.sql.types.{DataType, DoubleType}
 import org.apache.spark.util.random.XORShiftRandom
 
 /**
@@ -29,7 +28,7 @@ import org.apache.spark.util.random.XORShiftRandom
  *
  * Since this expression is stateful, it cannot be a case object.
  */
-private[sql] abstract class RDG(seed: Long) extends LeafExpression with Serializable { 
+abstract class RDG(seed: Long) extends LeafExpression with Serializable {
   self: Product =>
 
   /**
@@ -52,11 +51,11 @@ private[sql] abstract class RDG(seed: Long) extends LeafExpression with Serializ
 }
 
 /** Generate a random column with i.i.d. uniformly distributed values in [0, 1). */
-private[sql] case class Rand(seed: Long) extends RDG(seed) {
+case class Rand(seed: Long) extends RDG(seed) {
   override def generateNumber(random: XORShiftRandom): Double = random.nextDouble()
 }
 
 /** Generate a random column with i.i.d. gaussian random distribution. */
-private[sql] case class Randn(seed: Long) extends RDG(seed) {
+case class Randn(seed: Long) extends RDG(seed) {
   override def generateNumber(random: XORShiftRandom): Double = random.nextGaussian()
 }

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

@@ -24,7 +24,6 @@ import org.apache.spark.annotation.Experimental
 import org.apache.spark.sql.catalyst.ScalaReflection
 import org.apache.spark.sql.catalyst.analysis.{UnresolvedFunction, Star}
 import org.apache.spark.sql.catalyst.expressions._
-import org.apache.spark.sql.catalyst.expressions.randfuncs.{Randn, Rand}
 import org.apache.spark.sql.types._
 import org.apache.spark.util.Utils