diff options
Diffstat (limited to 'python/pyspark/sql')
| -rw-r--r-- | python/pyspark/sql/context.py | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py index 5a85ac3102..a49c1b58d0 100644 --- a/python/pyspark/sql/context.py +++ b/python/pyspark/sql/context.py @@ -195,14 +195,15 @@ class SQLContext(object): @ignore_unicode_prefix @since(1.2) def registerFunction(self, name, f, returnType=StringType()): - """Registers a lambda function as a UDF so it can be used in SQL statements. + """Registers a python function (including lambda function) as a UDF + so it can be used in SQL statements. In addition to a name and the function itself, the return type can be optionally specified. When the return type is not given it default to a string and conversion will automatically be done. For any other return type, the produced object must match the specified type. :param name: name of the UDF - :param samplingRatio: lambda function + :param f: python function :param returnType: a :class:`DataType` object >>> sqlContext.registerFunction("stringLengthString", lambda x: len(x)) |