fix test

Author: brkyvz

python/pyspark/sql/dataframe.py

@@ -915,7 +915,7 @@ 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`. Pairs that have no occurrences will have `null` as their values.
+        distinct values of `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

python/pyspark/sql/tests.py

@@ -408,7 +408,7 @@ def test_cov(self):
     def test_crosstab(self):
         df = self.sc.parallelize([Row(a=i % 3, b=i % 2) for i in range(1, 7)]).toDF()
         ct = df.stat.crosstab("a", "b").collect()
-        ct = sorted(ct, lambda r: r[0])
+        ct = sorted(ct, key=lambda x: x[0])
         for i, row in enumerate(ct):
             self.assertEqual(row[0], str(i))
             self.assertTrue(row[1], 1)

sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala

@@ -68,7 +68,7 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) {
    * 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`. Counts will be returned as `Long`s. Pairs that have no occurrences
-   * will have `null` as their values.
+   * will have `null` as their counts.
    *
    * @param col1 The name of the first column. Distinct items will make the first item of
    *             each row.