LuciferYang commented on code in PR #44436:
URL: https://github.com/apache/spark/pull/44436#discussion_r1433690859
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -12993,14 +13051,66 @@ def array_insert(arr: "ColumnOrName", pos:
Union["ColumnOrName", int], value: An
Examples
--------
- >>> df = spark.createDataFrame(
- ... [(['a', 'b', 'c'], 2, 'd'), (['c', 'b', 'a'], -2, 'd')],
- ... ['data', 'pos', 'val']
- ... )
- >>> df.select(array_insert(df.data, df.pos.cast('integer'),
df.val).alias('data')).collect()
- [Row(data=['a', 'd', 'b', 'c']), Row(data=['c', 'b', 'd', 'a'])]
- >>> df.select(array_insert(df.data, 5, 'hello').alias('data')).collect()
- [Row(data=['a', 'b', 'c', None, 'hello']), Row(data=['c', 'b', 'a', None,
'hello'])]
+ Example 1: Inserting a value at a specific position
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([(['a', 'b', 'c'],)], ['data'])
+ >>> df.select(sf.array_insert(df.data, 2, 'd')).show()
+ +------------------------+
+ |array_insert(data, 2, d)|
+ +------------------------+
+ | [a, d, b, c]|
+ +------------------------+
+
+ Example 2: Inserting a value at a negative position
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([(['a', 'b', 'c'],)], ['data'])
+ >>> df.select(sf.array_insert(df.data, -2, 'd')).show()
+ +-------------------------+
+ |array_insert(data, -2, d)|
+ +-------------------------+
+ | [a, b, d, c]|
+ +-------------------------+
+
+ Example 3: Inserting a value at a position greater than the array size
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([(['a', 'b', 'c'],)], ['data'])
+ >>> df.select(sf.array_insert(df.data, 5, 'e')).show()
+ +------------------------+
+ |array_insert(data, 5, e)|
+ +------------------------+
+ | [a, b, c, NULL, e]|
+ +------------------------+
+
+ Example 4: Inserting a NULL value
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.sql.types import StringType
+ >>> df = spark.createDataFrame([(['a', 'b', 'c'],)], ['data'])
+ >>> df.select(sf.array_insert(df.data, 2, sf.lit(None).cast(StringType()))
+ ... .alias("result")).show()
+ +---------------+
Review Comment:
It seems that the headers of the results from the connect and sql tests are
inconsistent, try giving it an `alias`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
