diff options
Diffstat (limited to 'python/pyspark/sql/functions.py')
-rw-r--r-- | python/pyspark/sql/functions.py | 25 |
1 files changed, 24 insertions, 1 deletions
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index 555c2fa5e7..241f821757 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -67,7 +67,6 @@ _functions = { 'sumDistinct': 'Aggregate function: returns the sum of distinct values in the expression.', } - for _name, _doc in _functions.items(): globals()[_name] = _create_function(_name, _doc) del _name, _doc @@ -75,6 +74,30 @@ __all__ += _functions.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``. |