diff options
Diffstat (limited to 'python')
-rw-r--r-- | python/pyspark/sql/context.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py index 599c9ac579..dc239226e6 100644 --- a/python/pyspark/sql/context.py +++ b/python/pyspark/sql/context.py @@ -86,7 +86,8 @@ class SQLContext(object): >>> df.registerTempTable("allTypes") >>> sqlContext.sql('select i+1, d+1, not b, list[1], dict["s"], time, row.a ' ... 'from allTypes where b and i > 0').collect() - [Row(c0=2, c1=2.0, c2=False, c3=2, c4=0, time=datetime.datetime(2014, 8, 1, 14, 1, 5), a=1)] + [Row(_c0=2, _c1=2.0, _c2=False, _c3=2, _c4=0, \ + time=datetime.datetime(2014, 8, 1, 14, 1, 5), a=1)] >>> df.map(lambda x: (x.i, x.s, x.d, x.l, x.b, x.time, x.row.a, x.list)).collect() [(1, u'string', 1.0, 1, True, datetime.datetime(2014, 8, 1, 14, 1, 5), 1, [1, 2, 3])] """ @@ -176,17 +177,17 @@ class SQLContext(object): >>> sqlContext.registerFunction("stringLengthString", lambda x: len(x)) >>> sqlContext.sql("SELECT stringLengthString('test')").collect() - [Row(c0=u'4')] + [Row(_c0=u'4')] >>> from pyspark.sql.types import IntegerType >>> sqlContext.registerFunction("stringLengthInt", lambda x: len(x), IntegerType()) >>> sqlContext.sql("SELECT stringLengthInt('test')").collect() - [Row(c0=4)] + [Row(_c0=4)] >>> from pyspark.sql.types import IntegerType >>> sqlContext.udf.register("stringLengthInt", lambda x: len(x), IntegerType()) >>> sqlContext.sql("SELECT stringLengthInt('test')").collect() - [Row(c0=4)] + [Row(_c0=4)] """ func = lambda _, it: map(lambda x: f(*x), it) ser = AutoBatchedSerializer(PickleSerializer()) |