diff options
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 90a6b5d9c0..3a8c8305ee 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -739,6 +739,9 @@ class DataFrame(object): def head(self, n=None): """Returns the first ``n`` rows. + Note that this method should only be used if the resulting array is expected + to be small, as all the data is loaded into the driver's memory. + :param n: int, default 1. Number of rows to return. :return: If n is greater than 1, return a list of :class:`Row`. If n is 1, return a single Row. @@ -1330,6 +1333,9 @@ class DataFrame(object): def toPandas(self): """Returns the contents of this :class:`DataFrame` as Pandas ``pandas.DataFrame``. + Note that this method should only be used if the resulting Pandas's DataFrame is expected + to be small, as all the data is loaded into the driver's memory. + This is only available if Pandas is installed and available. >>> df.toPandas() # doctest: +SKIP |