Match Scala/Python/R changes

HyukjinKwon · HyukjinKwon · commit 5f0ebddc36bb · 2017-03-25T16:15:59.000+09:00
diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R
@@ -2632,8 +2632,8 @@ setMethod("date_sub", signature(y = "Column", x = "numeric"),
 
 #' format_number
 #'
-#' Formats numeric column y to a format like '#,###,###.##', rounded to x decimal places,
-#' and returns the result as a string column.
+#' Formats numeric column y to a format like '#,###,###.##', rounded to x decimal places
+#' with HALF_EVEN round mode, and returns the result as a string column.
 #'
 #' If x is 0, the result has no decimal point or fractional part.
 #' If x < 0, the result will be null.
@@ -3548,7 +3548,7 @@ setMethod("row_number",
 
 #' array_contains
 #'
-#' Returns true if the array contain the value.
+#' Returns null if the array is null, true if the array contains the value, and false otherwise.
 #'
 #' @param x A Column
 #' @param value A value to be checked if contained in the column
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
@@ -1327,8 +1327,8 @@ def encode(col, charset):
 @since(1.5)
 def format_number(col, d):
     """
-    Formats the number X to a format like '#,--#,--#.--', rounded to d decimal places,
-    and returns the result as a string.
+    Formats the number X to a format like '#,--#,--#.--', rounded to d decimal places
+    with HALF_EVEN round mode, and returns the result as a string.
 
     :param col: the column name of the numeric value to be formatted
     :param d: the N decimal places
@@ -1675,15 +1675,18 @@ def array(*cols):
 @since(1.5)
 def array_contains(col, value):
     """
-    Collection function: returns True if the array contains the given value. The collection
-    elements and value must be of the same type.
+    Collection function: returns null if the array is null, true if the array contains the
+    given value, and false otherwise.
 
     :param col: name of column containing array
     :param value: value to check for in array
 
     >>> df = spark.createDataFrame([(["a", "b", "c"],), ([],)], ['data'])
     >>> df.select(array_contains(df.data, "a")).collect()
     [Row(array_contains(data, a)=True), Row(array_contains(data, a)=False)]
+    >>> df = spark.createDataFrame([(["1", "2", "3"],), ([],)], ['data'])
+    >>> df.select(array_contains(df.data, 1)).collect()
+    [Row(array_contains(data, 1)=True), Row(array_contains(data, 1)=False)]
     """
     sc = SparkContext._active_spark_context
     return Column(sc._jvm.functions.array_contains(_to_java_column(col), value))
