03306a6df3
## What changes were proposed in this pull request? This PR continues to break down a big large file into smaller files. See https://github.com/apache/spark/pull/23021. It targets to follow https://github.com/numpy/numpy/tree/master/numpy. Basically this PR proposes to break down `pyspark/tests.py` into ...: ``` pyspark ... ├── testing ... │ └── utils.py ├── tests │ ├── __init__.py │ ├── test_appsubmit.py │ ├── test_broadcast.py │ ├── test_conf.py │ ├── test_context.py │ ├── test_daemon.py │ ├── test_join.py │ ├── test_profiler.py │ ├── test_rdd.py │ ├── test_readwrite.py │ ├── test_serializers.py │ ├── test_shuffle.py │ ├── test_taskcontext.py │ ├── test_util.py │ └── test_worker.py ... ``` ## How was this patch tested? Existing tests should cover. `cd python` and .`/run-tests-with-coverage`. Manually checked they are actually being ran. Each test (not officially) can be ran via: ```bash SPARK_TESTING=1 ./bin/pyspark pyspark.tests.test_context ``` Note that if you're using Mac and Python 3, you might have to `OBJC_DISABLE_INITIALIZE_FORK_SAFETY=YES`. Closes #23033 from HyukjinKwon/SPARK-26036. Authored-by: hyukjinkwon <gurwls223@apache.org> Signed-off-by: hyukjinkwon <gurwls223@apache.org>
47 lines
1.8 KiB
Python
47 lines
1.8 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from pyspark.sql import Row
|
|
from pyspark.testing.sqlutils import ReusedSQLTestCase
|
|
|
|
|
|
class GroupTests(ReusedSQLTestCase):
|
|
|
|
def test_aggregator(self):
|
|
df = self.df
|
|
g = df.groupBy()
|
|
self.assertEqual([99, 100], sorted(g.agg({'key': 'max', 'value': 'count'}).collect()[0]))
|
|
self.assertEqual([Row(**{"AVG(key#0)": 49.5})], g.mean().collect())
|
|
|
|
from pyspark.sql import functions
|
|
self.assertEqual((0, u'99'),
|
|
tuple(g.agg(functions.first(df.key), functions.last(df.value)).first()))
|
|
self.assertTrue(95 < g.agg(functions.approx_count_distinct(df.key)).first()[0])
|
|
self.assertEqual(100, g.agg(functions.countDistinct(df.value)).first()[0])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.sql.tests.test_group import *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports')
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|