From 9ab296ecdceef88ebca523ed62848fbeb5df353b Mon Sep 17 00:00:00 2001
From: gatorsmile <gatorsmile@gmail.com>
Date: Sun, 27 Dec 2015 23:18:48 -0800
Subject: [PATCH] [SPARK-12520] [PYSPARK] Correct Descriptions and Add Use
Cases in Equi-Join
After reading the JIRA https://issues.apache.org/jira/browse/SPARK-12520, I double checked the code.
For example, users can do the Equi-Join like
```df.join(df2, 'name', 'outer').select('name', 'height').collect()```
- There exists a bug in 1.5 and 1.4. The code just ignores the third parameter (join type) users pass. However, the join type we called is `Inner`, even if the user-specified type is the other type (e.g., `Outer`).
- After a PR: https://github.com/apache/spark/pull/8600, the 1.6 does not have such an issue, but the description has not been updated.
Plan to submit another PR to fix 1.5 and issue an error message if users specify a non-inner join type when using Equi-Join.
Author: gatorsmile <gatorsmile@gmail.com>
Closes #10477 from gatorsmile/pyOuterJoin.
---
python/pyspark/sql/dataframe.py | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 4b3791e1b8..ad621df910 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -608,13 +608,16 @@ class DataFrame(object):
:param on: a string for join column name, a list of column names,
, a join expression (Column) or a list of Columns.
If `on` is a string or a list of string indicating the name of the join column(s),
- the column(s) must exist on both sides, and this performs an inner equi-join.
+ the column(s) must exist on both sides, and this performs an equi-join.
:param how: str, default 'inner'.
One of `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
>>> df.join(df2, df.name == df2.name, 'outer').select(df.name, df2.height).collect()
[Row(name=None, height=80), Row(name=u'Alice', height=None), Row(name=u'Bob', height=85)]
+ >>> df.join(df2, 'name', 'outer').select('name', 'height').collect()
+ [Row(name=u'Tom', height=80), Row(name=u'Alice', height=None), Row(name=u'Bob', height=85)]
+
>>> cond = [df.name == df3.name, df.age == df3.age]
>>> df.join(df3, cond, 'outer').select(df.name, df3.age).collect()
[Row(name=u'Bob', age=5), Row(name=u'Alice', age=2)]
--
GitLab