This is an automated email from the ASF dual-hosted git repository.
gurwls223 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 3fd987606be4 [SPARK-46556][PYTHON][DOCS] Refine docstring for
DataFrame.createGlobalTempView/createOrReplaceGlobalTempView
3fd987606be4 is described below
commit 3fd987606be4ce262faf055d8e71faea731513e6
Author: Hyukjin Kwon <[email protected]>
AuthorDate: Tue Jan 2 16:10:36 2024 +0900
[SPARK-46556][PYTHON][DOCS] Refine docstring for
DataFrame.createGlobalTempView/createOrReplaceGlobalTempView
### What changes were proposed in this pull request?
This PR proposes to improve the docstring of
`DataFrame.createGlobalTempView` and `DataFrame.createOrReplaceGlobalTempView`.
### Why are the changes needed?
For better usability.
### Does this PR introduce _any_ user-facing change?
Yes, it improves user-facing documentation.
### How was this patch tested?
Manually ran the tests via:
```bash
python/run-tests --python-executable=python3 --testnames
'pyspark.sql.dataframe'
```
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #44552 from HyukjinKwon/SPARK-46556.
Authored-by: Hyukjin Kwon <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
python/pyspark/sql/dataframe.py | 44 ++++++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 16 deletions(-)
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 35caf3b68b7e..f138b817bd22 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -407,9 +407,6 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
def createOrReplaceTempView(self, name: str) -> None:
"""Creates or replaces a local temporary view with this
:class:`DataFrame`.
- The lifetime of this temporary table is tied to the
:class:`SparkSession`
- that was used to create this :class:`DataFrame`.
-
.. versionadded:: 2.0.0
.. versionchanged:: 3.4.0
@@ -420,6 +417,11 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
name : str
Name of the view.
+ Notes
+ -----
+ The lifetime of this temporary table is tied to the
:class:`SparkSession`
+ that was used to create this :class:`DataFrame`.
+
Examples
--------
Example 1: Creating a local temporary view named 'people'.
@@ -448,10 +450,6 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
def createGlobalTempView(self, name: str) -> None:
"""Creates a global temporary view with this :class:`DataFrame`.
- The lifetime of this temporary view is tied to this Spark application.
- throws :class:`TempTableAlreadyExistsException`, if the view name
already exists in the
- catalog.
-
.. versionadded:: 2.1.0
.. versionchanged:: 3.4.0
@@ -462,25 +460,38 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
name : str
Name of the view.
+ Notes
+ -----
+ The lifetime of this temporary view is tied to this Spark application.
+ throws :class:`TempTableAlreadyExistsException`, if the view name
already exists in the
+ catalog.
+
Examples
--------
- Create a global temporary view.
+ Example 1: Creating and querying a global temporary view
>>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")],
schema=["age", "name"])
>>> df.createGlobalTempView("people")
>>> df2 = spark.sql("SELECT * FROM global_temp.people")
- >>> sorted(df.collect()) == sorted(df2.collect())
- True
+ >>> df2.show()
+ +---+-----+
+ |age| name|
+ +---+-----+
+ | 2|Alice|
+ | 5| Bob|
+ +---+-----+
- Throws an exception if the global temporary view already exists.
+ Example 2: Attempting to create a duplicate global temporary view
>>> df.createGlobalTempView("people") # doctest:
+IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
AnalysisException: "Temporary table 'people' already exists;"
+
+ Example 3: Dropping a global temporary view
+
>>> spark.catalog.dropGlobalTempView("people")
True
-
"""
self._jdf.createGlobalTempView(name)
@@ -501,21 +512,22 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
Examples
--------
- Create a global temporary view.
+ Example 1: Creating a global temporary view with a DataFrame
>>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")],
schema=["age", "name"])
>>> df.createOrReplaceGlobalTempView("people")
- Replace the global temporary view.
+ Example 2: Replacing a global temporary view with a filtered DataFrame
>>> df2 = df.filter(df.age > 3)
>>> df2.createOrReplaceGlobalTempView("people")
- >>> df3 = spark.sql("SELECT * FROM global_temp.people")
+ >>> df3 = spark.table("global_temp.people")
>>> sorted(df3.collect()) == sorted(df2.collect())
True
+
+ Example 3: Dropping a global temporary view
>>> spark.catalog.dropGlobalTempView("people")
True
-
"""
self._jdf.createOrReplaceGlobalTempView(name)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
