diff options
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 22 |
1 files changed, 11 insertions, 11 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 3a8c8305ee..3104e41407 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -887,8 +887,8 @@ class DataFrame(object): [Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)] >>> sorted(df.groupBy(df.name).avg().collect()) [Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)] - >>> df.groupBy(['name', df.age]).count().collect() - [Row(name=u'Bob', age=5, count=1), Row(name=u'Alice', age=2, count=1)] + >>> sorted(df.groupBy(['name', df.age]).count().collect()) + [Row(name=u'Alice', age=2, count=1), Row(name=u'Bob', age=5, count=1)] """ jgd = self._jdf.groupBy(self._jcols(*cols)) from pyspark.sql.group import GroupedData @@ -900,15 +900,15 @@ class DataFrame(object): Create a multi-dimensional rollup for the current :class:`DataFrame` using the specified columns, so we can run aggregation on them. - >>> df.rollup('name', df.age).count().show() + >>> df.rollup("name", df.age).count().orderBy("name", "age").show() +-----+----+-----+ | name| age|count| +-----+----+-----+ - |Alice| 2| 1| - | Bob| 5| 1| - | Bob|null| 1| | null|null| 2| |Alice|null| 1| + |Alice| 2| 1| + | Bob|null| 1| + | Bob| 5| 1| +-----+----+-----+ """ jgd = self._jdf.rollup(self._jcols(*cols)) @@ -921,17 +921,17 @@ class DataFrame(object): Create a multi-dimensional cube for the current :class:`DataFrame` using the specified columns, so we can run aggregation on them. - >>> df.cube('name', df.age).count().show() + >>> df.cube("name", df.age).count().orderBy("name", "age").show() +-----+----+-----+ | name| age|count| +-----+----+-----+ + | null|null| 2| | null| 2| 1| - |Alice| 2| 1| - | Bob| 5| 1| | null| 5| 1| - | Bob|null| 1| - | null|null| 2| |Alice|null| 1| + |Alice| 2| 1| + | Bob|null| 1| + | Bob| 5| 1| +-----+----+-----+ """ jgd = self._jdf.cube(self._jcols(*cols)) |