This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 5056a17919ac [SPARK-46897][PYTHON][DOCS] Refine docstring of
`bit_and/bit_or/bit_xor`
5056a17919ac is described below
commit 5056a17919ac88d35475dd13ae4167e783f9504a
Author: yangjie01 <yangji...@baidu.com>
AuthorDate: Sun Jan 28 21:33:39 2024 -0800
[SPARK-46897][PYTHON][DOCS] Refine docstring of `bit_and/bit_or/bit_xor`
### What changes were proposed in this pull request?
This pr refine docstring of `bit_and/bit_or/bit_xor` and add some new
examples.
### Why are the changes needed?
To improve PySpark documentation
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Pass Github Actions
### Was this patch authored or co-authored using generative AI tooling?
No
Closes #44923 from LuciferYang/SPARK-46897.
Authored-by: yangjie01 <yangji...@baidu.com>
Signed-off-by: Dongjoon Hyun <dh...@apple.com>
---
python/pyspark/sql/functions/builtin.py | 138 ++++++++++++++++++++++++++++++--
1 file changed, 132 insertions(+), 6 deletions(-)
diff --git a/python/pyspark/sql/functions/builtin.py
b/python/pyspark/sql/functions/builtin.py
index d3a94fe4b9e9..0932ac1c2843 100644
--- a/python/pyspark/sql/functions/builtin.py
+++ b/python/pyspark/sql/functions/builtin.py
@@ -3790,9 +3790,51 @@ def bit_and(col: "ColumnOrName") -> Column:
Examples
--------
+ Example 1: Bitwise AND with all non-null values
+
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([[1],[1],[2]], ["c"])
- >>> df.select(bit_and("c")).first()
- Row(bit_and(c)=0)
+ >>> df.select(sf.bit_and("c")).show()
+ +----------+
+ |bit_and(c)|
+ +----------+
+ | 0|
+ +----------+
+
+ Example 2: Bitwise AND with null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[1],[None],[2]], ["c"])
+ >>> df.select(sf.bit_and("c")).show()
+ +----------+
+ |bit_and(c)|
+ +----------+
+ | 0|
+ +----------+
+
+ Example 3: Bitwise AND with all null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.sql.types import IntegerType, StructType, StructField
+ >>> schema = StructType([StructField("c", IntegerType(), True)])
+ >>> df = spark.createDataFrame([[None],[None],[None]], schema=schema)
+ >>> df.select(sf.bit_and("c")).show()
+ +----------+
+ |bit_and(c)|
+ +----------+
+ | NULL|
+ +----------+
+
+ Example 4: Bitwise AND with single input value
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[5]], ["c"])
+ >>> df.select(sf.bit_and("c")).show()
+ +----------+
+ |bit_and(c)|
+ +----------+
+ | 5|
+ +----------+
"""
return _invoke_function_over_columns("bit_and", col)
@@ -3816,9 +3858,51 @@ def bit_or(col: "ColumnOrName") -> Column:
Examples
--------
+ Example 1: Bitwise OR with all non-null values
+
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([[1],[1],[2]], ["c"])
- >>> df.select(bit_or("c")).first()
- Row(bit_or(c)=3)
+ >>> df.select(sf.bit_or("c")).show()
+ +---------+
+ |bit_or(c)|
+ +---------+
+ | 3|
+ +---------+
+
+ Example 2: Bitwise OR with some null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[1],[None],[2]], ["c"])
+ >>> df.select(sf.bit_or("c")).show()
+ +---------+
+ |bit_or(c)|
+ +---------+
+ | 3|
+ +---------+
+
+ Example 3: Bitwise OR with all null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.sql.types import IntegerType, StructType, StructField
+ >>> schema = StructType([StructField("c", IntegerType(), True)])
+ >>> df = spark.createDataFrame([[None],[None],[None]], schema=schema)
+ >>> df.select(sf.bit_or("c")).show()
+ +---------+
+ |bit_or(c)|
+ +---------+
+ | NULL|
+ +---------+
+
+ Example 4: Bitwise OR with single input value
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[5]], ["c"])
+ >>> df.select(sf.bit_or("c")).show()
+ +---------+
+ |bit_or(c)|
+ +---------+
+ | 5|
+ +---------+
"""
return _invoke_function_over_columns("bit_or", col)
@@ -3842,9 +3926,51 @@ def bit_xor(col: "ColumnOrName") -> Column:
Examples
--------
+ Example 1: Bitwise XOR with all non-null values
+
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([[1],[1],[2]], ["c"])
- >>> df.select(bit_xor("c")).first()
- Row(bit_xor(c)=2)
+ >>> df.select(sf.bit_xor("c")).show()
+ +----------+
+ |bit_xor(c)|
+ +----------+
+ | 2|
+ +----------+
+
+ Example 2: Bitwise XOR with some null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[1],[None],[2]], ["c"])
+ >>> df.select(sf.bit_xor("c")).show()
+ +----------+
+ |bit_xor(c)|
+ +----------+
+ | 3|
+ +----------+
+
+ Example 3: Bitwise XOR with all null values
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.sql.types import IntegerType, StructType, StructField
+ >>> schema = StructType([StructField("c", IntegerType(), True)])
+ >>> df = spark.createDataFrame([[None],[None],[None]], schema=schema)
+ >>> df.select(sf.bit_xor("c")).show()
+ +----------+
+ |bit_xor(c)|
+ +----------+
+ | NULL|
+ +----------+
+
+ Example 4: Bitwise XOR with single input value
+
+ >>> from pyspark.sql import functions as sf
+ >>> df = spark.createDataFrame([[5]], ["c"])
+ >>> df.select(sf.bit_xor("c")).show()
+ +----------+
+ |bit_xor(c)|
+ +----------+
+ | 5|
+ +----------+
"""
return _invoke_function_over_columns("bit_xor", col)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
