diff options
Diffstat (limited to 'python/pyspark/sql')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 7 | ||||
-rw-r--r-- | python/pyspark/sql/tests.py | 8 |
2 files changed, 15 insertions, 0 deletions
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() |