From 962e9bcf94da6f5134983f2bf1e56c5cd84f2bf7 Mon Sep 17 00:00:00 2001 From: Wenchen Fan Date: Wed, 13 Jan 2016 22:43:28 -0800 Subject: [SPARK-12756][SQL] use hash expression in Exchange This PR makes bucketing and exchange share one common hash algorithm, so that we can guarantee the data distribution is same between shuffle and bucketed data source, which enables us to only shuffle one side when join a bucketed table and a normal one. This PR also fixes the tests that are broken by the new hash behaviour in shuffle. Author: Wenchen Fan Closes #10703 from cloud-fan/use-hash-expr-in-shuffle. --- python/pyspark/sql/dataframe.py | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'python/pyspark/sql/dataframe.py') diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index a7bc288e38..90a6b5d9c0 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -403,10 +403,10 @@ class DataFrame(object): +---+-----+ |age| name| +---+-----+ - | 2|Alice| - | 2|Alice| | 5| Bob| | 5| Bob| + | 2|Alice| + | 2|Alice| +---+-----+ >>> data = data.repartition(7, "age") >>> data.show() @@ -552,7 +552,7 @@ class DataFrame(object): >>> df_as2 = df.alias("df_as2") >>> joined_df = df_as1.join(df_as2, col("df_as1.name") == col("df_as2.name"), 'inner') >>> joined_df.select(col("df_as1.name"), col("df_as2.name"), col("df_as2.age")).collect() - [Row(name=u'Alice', name=u'Alice', age=2), Row(name=u'Bob', name=u'Bob', age=5)] + [Row(name=u'Bob', name=u'Bob', age=5), Row(name=u'Alice', name=u'Alice', age=2)] """ assert isinstance(alias, basestring), "alias should be a string" return DataFrame(getattr(self._jdf, "as")(alias), self.sql_ctx) @@ -573,14 +573,14 @@ class DataFrame(object): 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)] + [Row(name=None, height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)] >>> 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)] + [Row(name=u'Tom', height=80), Row(name=u'Bob', height=85), Row(name=u'Alice', height=None)] >>> 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)] + [Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)] >>> df.join(df2, 'name').select(df.name, df2.height).collect() [Row(name=u'Bob', height=85)] @@ -880,9 +880,9 @@ class DataFrame(object): >>> df.groupBy().avg().collect() [Row(avg(age)=3.5)] - >>> df.groupBy('name').agg({'age': 'mean'}).collect() + >>> sorted(df.groupBy('name').agg({'age': 'mean'}).collect()) [Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)] - >>> df.groupBy(df.name).avg().collect() + >>> sorted(df.groupBy(df.name).avg().collect()) [Row(name=u'Alice', avg(age)=2.0), Row(name=u'Bob', avg(age)=5.0)] >>> df.groupBy(['name', df.age]).count().collect() [Row(name=u'Bob', age=5, count=1), Row(name=u'Alice', age=2, count=1)] @@ -901,11 +901,11 @@ class DataFrame(object): +-----+----+-----+ | name| age|count| +-----+----+-----+ - |Alice|null| 1| + |Alice| 2| 1| | Bob| 5| 1| | Bob|null| 1| | null|null| 2| - |Alice| 2| 1| + |Alice|null| 1| +-----+----+-----+ """ jgd = self._jdf.rollup(self._jcols(*cols)) @@ -923,12 +923,12 @@ class DataFrame(object): | name| age|count| +-----+----+-----+ | null| 2| 1| - |Alice|null| 1| + |Alice| 2| 1| | Bob| 5| 1| - | Bob|null| 1| | null| 5| 1| + | Bob|null| 1| | null|null| 2| - |Alice| 2| 1| + |Alice|null| 1| +-----+----+-----+ """ jgd = self._jdf.cube(self._jcols(*cols)) -- cgit v1.2.3