From 735bc3d042b1e3e12de57b66f166af14254ad314 Mon Sep 17 00:00:00 2001 From: 云峤 Date: Tue, 5 May 2015 13:23:53 -0700 Subject: [SPARK-7294][SQL] ADD BETWEEN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Author: 云峤 Author: kaka1992 Closes #5839 from kaka1992/master and squashes the following commits: b15360d [kaka1992] Fix python unit test in sql/test. =_= I forget to commit this file last time. f928816 [kaka1992] Fix python style in sql/test. d2e7f72 [kaka1992] Fix python style in sql/test. c54d904 [kaka1992] Fix empty map bug. 7e64d1e [云峤] Update 7b9b858 [云峤] undo f080f8d [云峤] update pep8 76f0c51 [云峤] Merge remote-tracking branch 'remotes/upstream/master' 7d62368 [云峤] [SPARK-7294] ADD BETWEEN baf839b [云峤] [SPARK-7294] ADD BETWEEN d11d5b9 [云峤] [SPARK-7294] ADD BETWEEN --- python/pyspark/sql/dataframe.py | 7 +++++++ python/pyspark/sql/tests.py | 8 ++++++++ 2 files changed, 15 insertions(+) (limited to 'python/pyspark/sql') diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 17448b38c3..24f370543d 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -1405,6 +1405,13 @@ class Column(object): raise TypeError("unexpected type: %s" % type(dataType)) return Column(jc) + @ignore_unicode_prefix + def between(self, lowerBound, upperBound): + """ A boolean expression that is evaluated to true if the value of this + expression is between the given columns. + """ + return (self >= lowerBound) & (self <= upperBound) + def __repr__(self): return 'Column<%s>' % self._jc.toString().encode('utf8') diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 7ea6656d31..46c4c88e98 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -453,6 +453,14 @@ class SQLTests(ReusedPySparkTestCase): for row in rndn: assert row[1] >= -4.0 and row[1] <= 4.0, "got: %s" % row[1] + def test_between_function(self): + df = self.sc.parallelize([ + Row(a=1, b=2, c=3), + Row(a=2, b=1, c=3), + Row(a=4, b=1, c=4)]).toDF() + self.assertEqual([Row(a=2, b=1, c=3), Row(a=4, b=1, c=4)], + df.filter(df.a.between(df.b, df.c)).collect()) + def test_save_and_load(self): df = self.df tmpPath = tempfile.mkdtemp() -- cgit v1.2.3