diff options
Diffstat (limited to 'python/pyspark/sql')
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index b09422aade..033b31983f 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -931,6 +931,8 @@ class DataFrame(object): """Return a new :class:`DataFrame` with duplicate rows removed, optionally only considering certain columns. + :func:`drop_duplicates` is an alias for :func:`dropDuplicates`. + >>> from pyspark.sql import Row >>> df = sc.parallelize([ \ Row(name='Alice', age=5, height=80), \ |