From 4bc3bb29a4b6ab24b6b7e1f8df26414c41c80ace Mon Sep 17 00:00:00 2001 From: Jeremy Freeman Date: Fri, 1 Aug 2014 22:33:25 -0700 Subject: StatCounter on NumPy arrays [PYSPARK][SPARK-2012] These changes allow StatCounters to work properly on NumPy arrays, to fix the issue reported here (https://issues.apache.org/jira/browse/SPARK-2012). If NumPy is installed, the NumPy functions ``maximum``, ``minimum``, and ``sqrt``, which work on arrays, are used to merge statistics. If not, we fall back on scalar operators, so it will work on arrays with NumPy, but will also work without NumPy. New unit tests added, along with a check for NumPy in the tests. Author: Jeremy Freeman Closes #1725 from freeman-lab/numpy-max-statcounter and squashes the following commits: fe973b1 [Jeremy Freeman] Avoid duplicate array import in tests 7f0e397 [Jeremy Freeman] Refactored check for numpy 8e764dd [Jeremy Freeman] Explicit numpy imports 875414c [Jeremy Freeman] Fixed indents 1c8a832 [Jeremy Freeman] Unit tests for StatCounter with NumPy arrays 176a127 [Jeremy Freeman] Use numpy arrays in StatCounter --- python/pyspark/tests.py | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'python/pyspark/tests.py') diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py index c29deb9574..16fb5a9256 100644 --- a/python/pyspark/tests.py +++ b/python/pyspark/tests.py @@ -38,12 +38,19 @@ from pyspark.serializers import read_int from pyspark.shuffle import Aggregator, InMemoryMerger, ExternalMerger _have_scipy = False +_have_numpy = False try: import scipy.sparse _have_scipy = True except: # No SciPy, but that's okay, we'll skip those tests pass +try: + import numpy as np + _have_numpy = True +except: + # No NumPy, but that's okay, we'll skip those tests + pass SPARK_HOME = os.environ["SPARK_HOME"] @@ -914,9 +921,26 @@ class SciPyTests(PySparkTestCase): self.assertEqual(expected, observed) +@unittest.skipIf(not _have_numpy, "NumPy not installed") +class NumPyTests(PySparkTestCase): + """General PySpark tests that depend on numpy """ + + def test_statcounter_array(self): + x = self.sc.parallelize([np.array([1.0,1.0]), np.array([2.0,2.0]), np.array([3.0,3.0])]) + s = x.stats() + self.assertSequenceEqual([2.0,2.0], s.mean().tolist()) + self.assertSequenceEqual([1.0,1.0], s.min().tolist()) + self.assertSequenceEqual([3.0,3.0], s.max().tolist()) + self.assertSequenceEqual([1.0,1.0], s.sampleStdev().tolist()) + + if __name__ == "__main__": if not _have_scipy: print "NOTE: Skipping SciPy tests as it does not seem to be installed" + if not _have_numpy: + print "NOTE: Skipping NumPy tests as it does not seem to be installed" unittest.main() if not _have_scipy: print "NOTE: SciPy tests were skipped as it does not seem to be installed" + if not _have_numpy: + print "NOTE: NumPy tests were skipped as it does not seem to be installed" -- cgit v1.2.3