From ecfb3127670c7f15e3a15e7f51fa578532480cda Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Thu, 23 Jul 2015 10:32:11 -0700
Subject: [PATCH] [SPARK-9243] [Documentation] null -> zero in crosstab doc
We forgot to update doc. brkyvz
Author: Xiangrui Meng <meng@databricks.com>
Closes #7608 from mengxr/SPARK-9243 and squashes the following commits:
0ea3236 [Xiangrui Meng] null -> zero in crosstab doc
---
R/pkg/R/DataFrame.R | 2 +-
python/pyspark/sql/dataframe.py | 2 +-
.../scala/org/apache/spark/sql/DataFrameStatFunctions.scala | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 06dd6b75df..f4c93d3c7d 100644
--- a/R/pkg/R/DataFrame.R
+++ b/R/pkg/R/DataFrame.R
@@ -1566,7 +1566,7 @@ setMethod("fillna",
#' @return a local R data.frame representing the contingency table. 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.
+#' occurrences will have zero as their counts.
#'
#' @rdname statfunctions
#' @export
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 83e02b85f0..d76e051bd7 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -1130,7 +1130,7 @@ class DataFrame(object):
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.
+ Pairs that have no occurrences will have zero 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
index 587869e57f..4ec58082e7 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala
@@ -77,7 +77,7 @@ final class DataFrameStatFunctions private[sql](df: DataFrame) {
* 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`. Counts
- * will be returned as `Long`s. Pairs that have no occurrences will have `null` as their counts.
+ * will be returned as `Long`s. Pairs that have no occurrences will have zero as their counts.
* Null elements will be replaced by "null", and back ticks will be dropped from elements if they
* exist.
*
--
GitLab