This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch branch-3.2
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.2 by this push:
new bcd2812 [SPARK-36226][PYTHON][DOCS] Improve python docstring links to
other classes
bcd2812 is described below
commit bcd2812fd25488522443fec520e37df5ce2bad25
Author: Dominik Gehl <[email protected]>
AuthorDate: Fri Jul 23 19:17:51 2021 +0900
[SPARK-36226][PYTHON][DOCS] Improve python docstring links to other classes
### What changes were proposed in this pull request?
additional links to other classes in python documentation
### Why are the changes needed?
python docstring syntax wasn't fully used everywhere
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Documentation change only
Closes #33440 from dominikgehl/feature/python-docstrings.
Authored-by: Dominik Gehl <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
(cherry picked from commit 701756ac957b517464cecbea3aa0799404c4b159)
Signed-off-by: Hyukjin Kwon <[email protected]>
---
python/pyspark/sql/group.py | 4 ++--
python/pyspark/sql/session.py | 14 +++++++-------
python/pyspark/sql/types.py | 14 +++++++-------
3 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/python/pyspark/sql/group.py b/python/pyspark/sql/group.py
index d3cbf92..ab0566e 100644
--- a/python/pyspark/sql/group.py
+++ b/python/pyspark/sql/group.py
@@ -208,7 +208,7 @@ class GroupedData(PandasGroupedOpsMixin):
@df_varargs_api
def sum(self, *cols):
- """Compute the sum for each numeric columns for each group.
+ """Computes the sum for each numeric columns for each group.
.. versionadded:: 1.3.0
@@ -238,7 +238,7 @@ class GroupedData(PandasGroupedOpsMixin):
----------
pivot_col : str
Name of the column to pivot.
- values :
+ values : list, optional
List of values that will be translated to columns in the output
DataFrame.
Examples
diff --git a/python/pyspark/sql/session.py b/python/pyspark/sql/session.py
index 740ceb3..cc4f176 100644
--- a/python/pyspark/sql/session.py
+++ b/python/pyspark/sql/session.py
@@ -73,7 +73,7 @@ class SparkSession(SparkConversionMixin):
A SparkSession can be used create :class:`DataFrame`, register
:class:`DataFrame` as
tables, execute SQL over tables, cache tables, and read parquet files.
- To create a SparkSession, use the following builder pattern:
+ To create a :class:`SparkSession`, use the following builder pattern:
.. autoattribute:: builder
:annotation:
@@ -280,8 +280,8 @@ class SparkSession(SparkConversionMixin):
@since(2.0)
def newSession(self):
"""
- Returns a new SparkSession as new session, that has separate SQLConf,
- registered temporary views and UDFs, but shared SparkContext and
+ Returns a new :class:`SparkSession` as new session, that has separate
SQLConf,
+ registered temporary views and UDFs, but shared :class:`SparkContext`
and
table cache.
"""
return self.__class__(self._sc, self._jsparkSession.newSession())
@@ -289,7 +289,7 @@ class SparkSession(SparkConversionMixin):
@classmethod
def getActiveSession(cls):
"""
- Returns the active SparkSession for the current thread, returned by
the builder
+ Returns the active :class:`SparkSession` for the current thread,
returned by the builder
.. versionadded:: 3.0.0
@@ -528,9 +528,9 @@ class SparkSession(SparkConversionMixin):
@staticmethod
def _create_shell_session():
"""
- Initialize a SparkSession for a pyspark shell session. This is called
from shell.py
- to make error handling simpler without needing to declare local
variables in that
- script, which would expose those to users.
+ Initialize a :class:`SparkSession` for a pyspark shell session. This
is called from
+ shell.py to make error handling simpler without needing to declare
local variables in
+ that script, which would expose those to users.
"""
import py4j
from pyspark.conf import SparkConf
diff --git a/python/pyspark/sql/types.py b/python/pyspark/sql/types.py
index 78c7732..4b5632b 100644
--- a/python/pyspark/sql/types.py
+++ b/python/pyspark/sql/types.py
@@ -398,9 +398,9 @@ class StructField(DataType):
name of the field.
dataType : :class:`DataType`
:class:`DataType` of the field.
- nullable : bool
+ nullable : bool, optional
whether the field can be null (None) or not.
- metadata : dict
+ metadata : dict, optional
a dict from string to simple type that can be toInternald to JSON
automatically
Examples
@@ -498,20 +498,20 @@ class StructType(DataType):
def add(self, field, data_type=None, nullable=True, metadata=None):
"""
- Construct a StructType by adding new elements to it, to define the
schema.
+ Construct a :class:`StructType` by adding new elements to it, to
define the schema.
The method accepts either:
- a) A single parameter which is a StructField object.
+ a) A single parameter which is a :class:`StructField` object.
b) Between 2 and 4 parameters as (name, data_type, nullable
(optional),
metadata(optional). The data_type parameter may be either a
String or a
- DataType object.
+ :class:`DataType` object.
Parameters
----------
field : str or :class:`StructField`
- Either the name of the field or a StructField object
+ Either the name of the field or a :class:`StructField` object
data_type : :class:`DataType`, optional
- If present, the DataType of the StructField to create
+ If present, the DataType of the :class:`StructField` to create
nullable : bool, optional
Whether the field to add should be nullable (default True)
metadata : dict, optional
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
