From 2dd03886173f2f3b5c20fe14e9cdbd33480c1f36 Mon Sep 17 00:00:00 2001 From: Nicholas Chammas Date: Sat, 6 Aug 2016 05:02:59 +0100 Subject: [SPARK-16772][PYTHON][DOCS] Fix API doc references to UDFRegistration + Update "important classes" ## Proposed Changes * Update the list of "important classes" in `pyspark.sql` to match 2.0. * Fix references to `UDFRegistration` so that the class shows up in the docs. It currently [doesn't](http://spark.apache.org/docs/latest/api/python/pyspark.sql.html). * Remove some unnecessary whitespace in the Python RST doc files. I reused the [existing JIRA](https://issues.apache.org/jira/browse/SPARK-16772) I created last week for similar API doc fixes. ## How was this patch tested? * I ran `lint-python` successfully. * I ran `make clean build` on the Python docs and confirmed the results are as expected locally in my browser. Author: Nicholas Chammas Closes #14496 from nchammas/SPARK-16772-UDFRegistration. --- python/pyspark/sql/__init__.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'python/pyspark/sql') diff --git a/python/pyspark/sql/__init__.py b/python/pyspark/sql/__init__.py index cff73ff192..22ec416f6c 100644 --- a/python/pyspark/sql/__init__.py +++ b/python/pyspark/sql/__init__.py @@ -18,7 +18,7 @@ """ Important classes of Spark SQL and DataFrames: - - :class:`pyspark.sql.SQLContext` + - :class:`pyspark.sql.SparkSession` Main entry point for :class:`DataFrame` and SQL functionality. - :class:`pyspark.sql.DataFrame` A distributed collection of data grouped into named columns. @@ -26,8 +26,6 @@ Important classes of Spark SQL and DataFrames: A column expression in a :class:`DataFrame`. - :class:`pyspark.sql.Row` A row of data in a :class:`DataFrame`. - - :class:`pyspark.sql.HiveContext` - Main entry point for accessing data stored in Apache Hive. - :class:`pyspark.sql.GroupedData` Aggregation methods, returned by :func:`DataFrame.groupBy`. - :class:`pyspark.sql.DataFrameNaFunctions` @@ -45,7 +43,7 @@ from __future__ import absolute_import from pyspark.sql.types import Row -from pyspark.sql.context import SQLContext, HiveContext +from pyspark.sql.context import SQLContext, HiveContext, UDFRegistration from pyspark.sql.session import SparkSession from pyspark.sql.column import Column from pyspark.sql.dataframe import DataFrame, DataFrameNaFunctions, DataFrameStatFunctions @@ -55,7 +53,8 @@ from pyspark.sql.window import Window, WindowSpec __all__ = [ - 'SparkSession', 'SQLContext', 'HiveContext', 'DataFrame', 'GroupedData', 'Column', - 'Row', 'DataFrameNaFunctions', 'DataFrameStatFunctions', 'Window', 'WindowSpec', + 'SparkSession', 'SQLContext', 'HiveContext', 'UDFRegistration', + 'DataFrame', 'GroupedData', 'Column', 'Row', + 'DataFrameNaFunctions', 'DataFrameStatFunctions', 'Window', 'WindowSpec', 'DataFrameReader', 'DataFrameWriter' ] -- cgit v1.2.3