diff options
Diffstat (limited to 'python/pyspark/sql/tests.py')
-rw-r--r-- | python/pyspark/sql/tests.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 613efc0ac0..d652c302a5 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -394,6 +394,12 @@ class SQLTests(ReusedPySparkTestCase): self.assertTrue(95 < g.agg(functions.approxCountDistinct(df.key)).first()[0]) self.assertEqual(100, g.agg(functions.countDistinct(df.value)).first()[0]) + def test_corr(self): + import math + df = self.sc.parallelize([Row(a=i, b=math.sqrt(i)) for i in range(10)]).toDF() + corr = df.stat.corr("a", "b") + self.assertTrue(abs(corr - 0.95734012) < 1e-6) + def test_cov(self): df = self.sc.parallelize([Row(a=i, b=2 * i) for i in range(10)]).toDF() cov = df.stat.cov("a", "b") |