diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 03b01a1136e45af54bcd47305389c2507999ab45..902504df5b11baa24c5ef750a8f2a4cf2acdacb2 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -616,7 +616,19 @@ class DataFrame(object): | min| 2| | max| 5| +-------+---+ + >>> df.describe(['age', 'name']).show() + +-------+---+-----+ + |summary|age| name| + +-------+---+-----+ + | count| 2| 2| + | mean|3.5| null| + | stddev|1.5| null| + | min| 2|Alice| + | max| 5| Bob| + +-------+---+-----+ """ + if len(cols) == 1 and isinstance(cols[0], list): + cols = cols[0] jdf = self._jdf.describe(self._jseq(cols)) return DataFrame(jdf, self.sql_ctx)