Repository: spark Updated Branches: refs/heads/branch-1.4 116f61187 -> e5a994f21
[SPARK-9691] [SQL] PySpark SQL rand function treats seed 0 as no seed https://issues.apache.org/jira/browse/SPARK-9691 jkbradley rxin Author: Yin Huai <yh...@databricks.com> Closes #7999 from yhuai/pythonRand and squashes the following commits: 4187e0c [Yin Huai] Regression test. a985ef9 [Yin Huai] Use "if seed is not None" instead "if seed" because "if seed" returns false when seed is 0. (cherry picked from commit baf4587a569b49e39020c04c2785041bdd00789b) Signed-off-by: Reynold Xin <r...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e5a994f2 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e5a994f2 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e5a994f2 Branch: refs/heads/branch-1.4 Commit: e5a994f21f85b1f8522e89629eb1379d22454ba9 Parents: 116f611 Author: Yin Huai <yh...@databricks.com> Authored: Thu Aug 6 17:03:14 2015 -0700 Committer: Reynold Xin <r...@databricks.com> Committed: Thu Aug 6 17:28:37 2015 -0700 ---------------------------------------------------------------------- python/pyspark/sql/functions.py | 4 ++-- python/pyspark/sql/tests.py | 10 ++++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/e5a994f2/python/pyspark/sql/functions.py ---------------------------------------------------------------------- diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index bbf465a..0fc50c8 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -329,7 +329,7 @@ def rand(seed=None): """Generates a random column with i.i.d. samples from U[0.0, 1.0]. """ sc = SparkContext._active_spark_context - if seed: + if seed is not None: jc = sc._jvm.functions.rand(seed) else: jc = sc._jvm.functions.rand() @@ -341,7 +341,7 @@ def randn(seed=None): """Generates a column with i.i.d. samples from the standard normal distribution. """ sc = SparkContext._active_spark_context - if seed: + if seed is not None: jc = sc._jvm.functions.randn(seed) else: jc = sc._jvm.functions.randn() http://git-wip-us.apache.org/repos/asf/spark/blob/e5a994f2/python/pyspark/sql/tests.py ---------------------------------------------------------------------- diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 75ad223..5818487 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -498,6 +498,16 @@ class SQLTests(ReusedPySparkTestCase): for row in rndn: assert row[1] >= -4.0 and row[1] <= 4.0, "got: %s" % row[1] + # If the specified seed is 0, we should use it. + # https://issues.apache.org/jira/browse/SPARK-9691 + rnd1 = df.select('key', functions.rand(0)).collect() + rnd2 = df.select('key', functions.rand(0)).collect() + self.assertEqual(sorted(rnd1), sorted(rnd2)) + + rndn1 = df.select('key', functions.randn(0)).collect() + rndn2 = df.select('key', functions.randn(0)).collect() + self.assertEqual(sorted(rndn1), sorted(rndn2)) + def test_between_function(self): df = self.sc.parallelize([ Row(a=1, b=2, c=3), --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
