diff options
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index adf549dd02..8ff9403d59 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -613,16 +613,16 @@ class DataFrame(object): def join(self, other, on=None, how=None): """Joins with another :class:`DataFrame`, using the given join expression. - The following performs a full outer join between ``df1`` and ``df2``. - :param other: Right side of the join - :param on: a string for join column name, a list of column names, - , a join expression (Column) or a list of Columns. - If `on` is a string or a list of string indicating the name of the join column(s), + :param on: a string for the join column name, a list of column names, + a join expression (Column), or a list of Columns. + If `on` is a string or a list of strings indicating the name of the join column(s), the column(s) must exist on both sides, and this performs an equi-join. :param how: str, default 'inner'. One of `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`. + The following performs a full outer join between ``df1`` and ``df2``. + >>> df.join(df2, df.name == df2.name, 'outer').select(df.name, df2.height).collect() [Row(name=None, height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)] |