From 3134c3fe495862b7687b5aa00d3344d09cd5e08e Mon Sep 17 00:00:00 2001 From: Reynold Xin Date: Tue, 21 Apr 2015 17:49:55 -0700 Subject: [SPARK-6953] [PySpark] speed up python tests This PR try to speed up some python tests: ``` tests.py 144s -> 103s -41s mllib/classification.py 24s -> 17s -7s mllib/regression.py 27s -> 15s -12s mllib/tree.py 27s -> 13s -14s mllib/tests.py 64s -> 31s -33s streaming/tests.py 185s -> 84s -101s ``` Considering python3, the total saving will be 558s (almost 10 minutes) (core, and streaming run three times, mllib runs twice). During testing, it will show used time for each test file: ``` Run core tests ... Running test: pyspark/rdd.py ... ok (22s) Running test: pyspark/context.py ... ok (16s) Running test: pyspark/conf.py ... ok (4s) Running test: pyspark/broadcast.py ... ok (4s) Running test: pyspark/accumulators.py ... ok (4s) Running test: pyspark/serializers.py ... ok (6s) Running test: pyspark/profiler.py ... ok (5s) Running test: pyspark/shuffle.py ... ok (1s) Running test: pyspark/tests.py ... ok (103s) 144s ``` Author: Reynold Xin Author: Xiangrui Meng Closes #5605 from rxin/python-tests-speed and squashes the following commits: d08542d [Reynold Xin] Merge pull request #14 from mengxr/SPARK-6953 89321ee [Xiangrui Meng] fix seed in tests 3ad2387 [Reynold Xin] Merge pull request #5427 from davies/python_tests --- python/pyspark/sql/tests.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'python/pyspark/sql/tests.py') diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 23e8428367..fe43c374f1 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -109,7 +109,7 @@ class SQLTests(ReusedPySparkTestCase): os.unlink(cls.tempdir.name) cls.sqlCtx = SQLContext(cls.sc) cls.testData = [Row(key=i, value=str(i)) for i in range(100)] - rdd = cls.sc.parallelize(cls.testData) + rdd = cls.sc.parallelize(cls.testData, 2) cls.df = rdd.toDF() @classmethod @@ -303,7 +303,7 @@ class SQLTests(ReusedPySparkTestCase): abstract = "byte1 short1 float1 time1 map1{} struct1(b) list1[]" schema = _parse_schema_abstract(abstract) typedSchema = _infer_schema_type(rdd.first(), schema) - df = self.sqlCtx.applySchema(rdd, typedSchema) + df = self.sqlCtx.createDataFrame(rdd, typedSchema) r = (127, -32768, 1.0, datetime(2010, 1, 1, 1, 1, 1), {"a": 1}, Row(b=2), [1, 2, 3]) self.assertEqual(r, tuple(df.first())) -- cgit v1.2.3