def rollup(self, *cols):
"""
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()
+-----+----+-----+
| name| age|count|
+-----+----+-----+
|Alice|null| 1|
| Bob| 5| 1|
| Bob|null| 1|
| null|null| 2|
|Alice| 2| 1|
+-----+----+-----+
"""
jgd = self._jdf.rollup(self._jcols(*cols))
from pyspark.sql.group import GroupedData
return GroupedData(jgd, self.sql_ctx)
def groupBy(self, *cols):
"""Groups the :class:`DataFrame` using the specified columns,
so we can run aggregation on them. See :class:`GroupedData`
for all the available aggregate functions.
:func:`groupby` is an alias for :func:`groupBy`.
:param cols: list of columns to group by.
Each element should be a column name (string) or an expression (:class:`Column`).
>>> df.groupBy().avg().collect()
[Row(avg(age)=3.5)]
>>> df.groupBy('name').agg({'age': 'mean'}).collect()
[Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)]
>>> 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)]
"""
jgd = self._jdf.groupBy(self._jcols(*cols))
from pyspark.sql.group import GroupedData
return GroupedData(jgd, self.sql_ctx)
