From 1fcefef06950e2f03477282368ca835bbf40ff24 Mon Sep 17 00:00:00 2001 From: Liang-Chi Hsieh Date: Mon, 21 Sep 2015 23:46:00 -0700 Subject: [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 Closes #8600 from viirya/usingcolumns_df. --- python/pyspark/sql/dataframe.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'python/pyspark/sql/dataframe.py') 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: -- cgit v1.2.3