diff options
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index f30a92dfc8..17448b38c3 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -934,10 +934,11 @@ class DataFrame(object): def crosstab(self, col1, col2): """ Computes a pair-wise frequency table of the given columns. Also known as a contingency - table. The number of distinct values for each column should be less than 1e4. The first - column of each row will be the distinct values of `col1` and the column names will be the - distinct values of `col2`. The name of the first column will be `$col1_$col2`. Pairs that - have no occurrences will have `null` as their counts. + table. The number of distinct values for each column should be less than 1e4. At most 1e6 + non-zero pair frequencies will be returned. + The first column of each row will be the distinct values of `col1` and the column names + will be the distinct values of `col2`. The name of the first column will be `$col1_$col2`. + Pairs that have no occurrences will have `null` as their counts. :func:`DataFrame.crosstab` and :func:`DataFrameStatFunctions.crosstab` are aliases. :param col1: The name of the first column. Distinct items will make the first item of |