diff options
| author | Liang-Chi Hsieh <viirya@appier.com> | 2015-09-21 23:46:00 -0700 |
|---|---|---|
| committer | Reynold Xin <rxin@databricks.com> | 2015-09-21 23:46:00 -0700 |
| commit | 1fcefef06950e2f03477282368ca835bbf40ff24 (patch) | |
| tree | 9fd7829e91af85b3f682f677721ca00b1c96eb30 /python/pyspark/sql/dataframe.py | |
| parent | 781b21ba2a873ed29394c8dbc74fc700e3e0d17e (diff) | |
| download | spark-1fcefef06950e2f03477282368ca835bbf40ff24.tar.gz spark-1fcefef06950e2f03477282368ca835bbf40ff24.tar.bz2 spark-1fcefef06950e2f03477282368ca835bbf40ff24.zip | |
[SPARK-10446][SQL] Support to specify join type when calling join with usingColumns
JIRA: https://issues.apache.org/jira/browse/SPARK-10446
Currently the method `join(right: DataFrame, usingColumns: Seq[String])` only supports inner join. It is more convenient to have it support other join types.
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes #8600 from viirya/usingcolumns_df.
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index fb995fa3a7..80f8d8a0eb 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -567,7 +567,11 @@ class DataFrame(object): if on is None or len(on) == 0: jdf = self._jdf.join(other._jdf) elif isinstance(on[0], basestring): - jdf = self._jdf.join(other._jdf, self._jseq(on)) + if how is None: + jdf = self._jdf.join(other._jdf, self._jseq(on), "inner") + else: + assert isinstance(how, basestring), "how should be basestring" + jdf = self._jdf.join(other._jdf, self._jseq(on), how) else: assert isinstance(on[0], Column), "on should be Column or list of Column" if len(on) > 1: |