diff options
Diffstat (limited to 'python/pyspark')
| -rw-r--r-- | python/pyspark/sql/functions.py | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index acdb01d3d3..cfa87aeea1 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -35,6 +35,7 @@ from pyspark.sql.column import Column, _to_java_column, _to_seq __all__ = [ 'array', 'approxCountDistinct', + 'bin', 'coalesce', 'countDistinct', 'explode', @@ -231,6 +232,19 @@ def approxCountDistinct(col, rsd=None): return Column(jc) +@ignore_unicode_prefix +@since(1.5) +def bin(col): + """Returns the string representation of the binary value of the given column. + + >>> df.select(bin(df.age).alias('c')).collect() + [Row(c=u'10'), Row(c=u'101')] + """ + sc = SparkContext._active_spark_context + jc = sc._jvm.functions.bin(_to_java_column(col)) + return Column(jc) + + @since(1.4) def coalesce(*cols): """Returns the first column that is not null. |