diff options
author | Nicholas Chammas <nicholas.chammas@gmail.com> | 2016-07-29 14:07:03 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2016-07-29 14:07:03 -0700 |
commit | 2182e4322da6ba732f99ae75dce00f76f1cdc4d9 (patch) | |
tree | 1fbb2ec619487844e174e56dcc8c16533fb29b99 /python/pyspark | |
parent | 2c15323ad026da64caa68787c5d103a8595f63a0 (diff) | |
download | spark-2182e4322da6ba732f99ae75dce00f76f1cdc4d9.tar.gz spark-2182e4322da6ba732f99ae75dce00f76f1cdc4d9.tar.bz2 spark-2182e4322da6ba732f99ae75dce00f76f1cdc4d9.zip |
[SPARK-16772][PYTHON][DOCS] Restore "datatype string" to Python API docstrings
## What changes were proposed in this pull request?
This PR corrects [an error made in an earlier PR](https://github.com/apache/spark/pull/14393/files#r72843069).
## How was this patch tested?
```sh
$ ./dev/lint-python
PEP8 checks passed.
rm -rf _build/*
pydoc checks passed.
```
I also built the docs and confirmed that they looked good in my browser.
Author: Nicholas Chammas <nicholas.chammas@gmail.com>
Closes #14408 from nchammas/SPARK-16772.
Diffstat (limited to 'python/pyspark')
-rw-r--r-- | python/pyspark/sql/context.py | 10 | ||||
-rw-r--r-- | python/pyspark/sql/session.py | 10 |
2 files changed, 8 insertions, 12 deletions
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py index f7009fe589..4085f165f4 100644 --- a/python/pyspark/sql/context.py +++ b/python/pyspark/sql/context.py @@ -226,9 +226,8 @@ class SQLContext(object): from ``data``, which should be an RDD of :class:`Row`, or :class:`namedtuple`, or :class:`dict`. - When ``schema`` is :class:`pyspark.sql.types.DataType` or - :class:`pyspark.sql.types.StringType`, it must match the - real data, or an exception will be thrown at runtime. If the given schema is not + When ``schema`` is :class:`pyspark.sql.types.DataType` or a datatype string it must match + the real data, or an exception will be thrown at runtime. If the given schema is not :class:`pyspark.sql.types.StructType`, it will be wrapped into a :class:`pyspark.sql.types.StructType` as its only field, and the field name will be "value", each record will also be wrapped into a tuple, which can be converted to row later. @@ -239,8 +238,7 @@ class SQLContext(object): :param data: an RDD of any kind of SQL data representation(e.g. :class:`Row`, :class:`tuple`, ``int``, ``boolean``, etc.), or :class:`list`, or :class:`pandas.DataFrame`. - :param schema: a :class:`pyspark.sql.types.DataType` or a - :class:`pyspark.sql.types.StringType` or a list of + :param schema: a :class:`pyspark.sql.types.DataType` or a datatype string or a list of column names, default is None. The data type string format equals to :class:`pyspark.sql.types.DataType.simpleString`, except that top level struct type can omit the ``struct<>`` and atomic types use ``typeName()`` as their format, e.g. use @@ -251,7 +249,7 @@ class SQLContext(object): .. versionchanged:: 2.0 The ``schema`` parameter can be a :class:`pyspark.sql.types.DataType` or a - :class:`pyspark.sql.types.StringType` after 2.0. + datatype string after 2.0. If it's not a :class:`pyspark.sql.types.StructType`, it will be wrapped into a :class:`pyspark.sql.types.StructType` and each record will also be wrapped into a tuple. diff --git a/python/pyspark/sql/session.py b/python/pyspark/sql/session.py index 10bd89b03f..2dacf483fc 100644 --- a/python/pyspark/sql/session.py +++ b/python/pyspark/sql/session.py @@ -414,9 +414,8 @@ class SparkSession(object): from ``data``, which should be an RDD of :class:`Row`, or :class:`namedtuple`, or :class:`dict`. - When ``schema`` is :class:`pyspark.sql.types.DataType` or - :class:`pyspark.sql.types.StringType`, it must match the - real data, or an exception will be thrown at runtime. If the given schema is not + When ``schema`` is :class:`pyspark.sql.types.DataType` or a datatype string, it must match + the real data, or an exception will be thrown at runtime. If the given schema is not :class:`pyspark.sql.types.StructType`, it will be wrapped into a :class:`pyspark.sql.types.StructType` as its only field, and the field name will be "value", each record will also be wrapped into a tuple, which can be converted to row later. @@ -426,8 +425,7 @@ class SparkSession(object): :param data: an RDD of any kind of SQL data representation(e.g. row, tuple, int, boolean, etc.), or :class:`list`, or :class:`pandas.DataFrame`. - :param schema: a :class:`pyspark.sql.types.DataType` or a - :class:`pyspark.sql.types.StringType` or a list of + :param schema: a :class:`pyspark.sql.types.DataType` or a datatype string or a list of column names, default is ``None``. The data type string format equals to :class:`pyspark.sql.types.DataType.simpleString`, except that top level struct type can omit the ``struct<>`` and atomic types use ``typeName()`` as their format, e.g. use @@ -438,7 +436,7 @@ class SparkSession(object): .. versionchanged:: 2.0 The ``schema`` parameter can be a :class:`pyspark.sql.types.DataType` or a - :class:`pyspark.sql.types.StringType` after 2.0. If it's not a + datatype string after 2.0. If it's not a :class:`pyspark.sql.types.StructType`, it will be wrapped into a :class:`pyspark.sql.types.StructType` and each record will also be wrapped into a tuple. |