76791b89f5
Follow up from https://github.com/apache/spark/pull/24981 incorporating some comments from HyukjinKwon. Specifically: - Adding `CoGroupedData` to `pyspark/sql/__init__.py __all__` so that documentation is generated. - Added pydoc, including example, for the use case whereby the user supplies a cogrouping function including a key. - Added the boilerplate for doctests to cogroup.py. Note that cogroup.py only contains the apply() function which has doctests disabled as per the other Pandas Udfs. - Restricted the newly exposed RelationalGroupedDataset constructor parameters to access only by the sql package. - Some minor formatting tweaks. This was tested by running the appropriate unit tests. I'm unsure as to how to check that my change will cause the documentation to be generated correctly, but it someone can describe how I can do this I'd be happy to check. Closes #25939 from d80tb7/SPARK-27463-fixes. Authored-by: Chris Martin <chris@cmartinit.co.uk> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
63 lines
2.5 KiB
Python
63 lines
2.5 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
"""
|
|
Important classes of Spark SQL and DataFrames:
|
|
|
|
- :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.
|
|
- :class:`pyspark.sql.Column`
|
|
A column expression in a :class:`DataFrame`.
|
|
- :class:`pyspark.sql.Row`
|
|
A row of data in a :class:`DataFrame`.
|
|
- :class:`pyspark.sql.GroupedData`
|
|
Aggregation methods, returned by :func:`DataFrame.groupBy`.
|
|
- :class:`pyspark.sql.DataFrameNaFunctions`
|
|
Methods for handling missing data (null values).
|
|
- :class:`pyspark.sql.DataFrameStatFunctions`
|
|
Methods for statistics functionality.
|
|
- :class:`pyspark.sql.functions`
|
|
List of built-in functions available for :class:`DataFrame`.
|
|
- :class:`pyspark.sql.types`
|
|
List of data types available.
|
|
- :class:`pyspark.sql.Window`
|
|
For working with window functions.
|
|
"""
|
|
from __future__ import absolute_import
|
|
|
|
|
|
from pyspark.sql.types import Row
|
|
from pyspark.sql.context import SQLContext, UDFRegistration
|
|
from pyspark.sql.session import SparkSession
|
|
from pyspark.sql.column import Column
|
|
from pyspark.sql.catalog import Catalog
|
|
from pyspark.sql.dataframe import DataFrame, DataFrameNaFunctions, DataFrameStatFunctions
|
|
from pyspark.sql.group import GroupedData
|
|
from pyspark.sql.readwriter import DataFrameReader, DataFrameWriter
|
|
from pyspark.sql.window import Window, WindowSpec
|
|
from pyspark.sql.cogroup import CoGroupedData
|
|
|
|
|
|
__all__ = [
|
|
'SparkSession', 'SQLContext', 'UDFRegistration',
|
|
'DataFrame', 'GroupedData', 'Column', 'Catalog', 'Row',
|
|
'DataFrameNaFunctions', 'DataFrameStatFunctions', 'Window', 'WindowSpec',
|
|
'DataFrameReader', 'DataFrameWriter', 'CoGroupedData'
|
|
]
|