89addd40ab
## What changes were proposed in this pull request?
```
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/__ / .__/\_,_/_/ /_/\_\ version 2.0.0-SNAPSHOT
/_/
Using Python version 2.7.5 (default, Mar 9 2014 22:15:05)
SparkSession available as 'spark'.
>>> spark
<pyspark.sql.session.SparkSession object at 0x101f3bfd0>
>>> spark.sql("SHOW TABLES").show()
...
+---------+-----------+
|tableName|isTemporary|
+---------+-----------+
| src| false|
+---------+-----------+
>>> spark.range(1, 10, 2).show()
+---+
| id|
+---+
| 1|
| 3|
| 5|
| 7|
| 9|
+---+
```
**Note**: This API is NOT complete in its current state. In particular, for now I left out the `conf` and `catalog` APIs, which were added later in Scala. These will be added later before 2.0.
## How was this patch tested?
Python tests.
Author: Andrew Or <andrew@databricks.com>
Closes #12746 from andrewor14/python-spark-session.
62 lines
2.5 KiB
Python
62 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.SQLContext`
|
|
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.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`
|
|
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, HiveContext
|
|
from pyspark.sql.session import SparkSession
|
|
from pyspark.sql.column import Column
|
|
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
|
|
|
|
|
|
__all__ = [
|
|
'SparkSession', 'SQLContext', 'HiveContext', 'DataFrame', 'GroupedData', 'Column',
|
|
'Row', 'DataFrameNaFunctions', 'DataFrameStatFunctions', 'Window', 'WindowSpec',
|
|
'DataFrameReader', 'DataFrameWriter'
|
|
]
|