address comments

apache · May 5, 2015 · b30ace2 · b30ace2
1 parent a417ba5
commit b30ace2
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 8 deletions.
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
@@ -934,10 +934,11 @@ def cov(self, col1, col2):
     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 returned 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

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala
@@ -65,10 +65,11 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) {
 
   /**
    * 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`. Counts will be
-   * returned as `Long`s. Pairs that have no occurrences will have `null` as their counts.
+   * The number of distinct values for each column should be less than 1e4. At most, 1e6 non-zero
+   * pair frequencies returned 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`. Counts
+   * will be returned as `Long`s. Pairs that have no occurrences will have `null` as their counts.
    *
    * @param col1 The name of the first column. Distinct items will make the first item of
    *             each row.