pyspark/sql/__init__.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019 Important classes of Spark SQL and DataFrames:
0020
0021     - :class:`pyspark.sql.SparkSession`
0022       Main entry point for :class:`DataFrame` and SQL functionality.
0023     - :class:`pyspark.sql.DataFrame`
0024       A distributed collection of data grouped into named columns.
0025     - :class:`pyspark.sql.Column`
0026       A column expression in a :class:`DataFrame`.
0027     - :class:`pyspark.sql.Row`
0028       A row of data in a :class:`DataFrame`.
0029     - :class:`pyspark.sql.GroupedData`
0030       Aggregation methods, returned by :func:`DataFrame.groupBy`.
0031     - :class:`pyspark.sql.DataFrameNaFunctions`
0032       Methods for handling missing data (null values).
0033     - :class:`pyspark.sql.DataFrameStatFunctions`
0034       Methods for statistics functionality.
0035     - :class:`pyspark.sql.functions`
0036       List of built-in functions available for :class:`DataFrame`.
0037     - :class:`pyspark.sql.types`
0038       List of data types available.
0039     - :class:`pyspark.sql.Window`
0040       For working with window functions.
0041 """
0042 from __future__ import absolute_import
0043
0044
0045 from pyspark.sql.types import Row
0046 from pyspark.sql.context import SQLContext, HiveContext, UDFRegistration
0047 from pyspark.sql.session import SparkSession
0048 from pyspark.sql.column import Column
0049 from pyspark.sql.catalog import Catalog
0050 from pyspark.sql.dataframe import DataFrame, DataFrameNaFunctions, DataFrameStatFunctions
0051 from pyspark.sql.group import GroupedData
0052 from pyspark.sql.readwriter import DataFrameReader, DataFrameWriter
0053 from pyspark.sql.window import Window, WindowSpec
0054 from pyspark.sql.pandas.group_ops import PandasCogroupedOps
0055
0056
0057 __all__ = [
0058     'SparkSession', 'SQLContext', 'HiveContext', 'UDFRegistration',
0059     'DataFrame', 'GroupedData', 'Column', 'Catalog', 'Row',
0060     'DataFrameNaFunctions', 'DataFrameStatFunctions', 'Window', 'WindowSpec',
0061     'DataFrameReader', 'DataFrameWriter', 'PandasCogroupedOps'
0062 ]