spark-instrumented-optimizer/python/pyspark/testing/mllibutils.py
Bryan Cutler a2fc48c28c [SPARK-26034][PYTHON][TESTS] Break large mllib/tests.py file into smaller files
## What changes were proposed in this pull request?

This PR breaks down the large mllib/tests.py file that contains all Python MLlib unit tests into several smaller test files to be easier to read and maintain.

The tests are broken down as follows:
```
pyspark
├── __init__.py
...
├── mllib
│   ├── __init__.py
...
│   ├── tests
│   │   ├── __init__.py
│   │   ├── test_algorithms.py
│   │   ├── test_feature.py
│   │   ├── test_linalg.py
│   │   ├── test_stat.py
│   │   ├── test_streaming_algorithms.py
│   │   └── test_util.py
...
├── testing
...
│   ├── mllibutils.py
...
```

## How was this patch tested?

Ran tests manually by module to ensure test count was the same, and ran `python/run-tests --modules=pyspark-mllib` to verify all passing with Python 2.7 and Python 3.6. Also installed scipy to include optional tests in test_linalg.

Closes #23056 from BryanCutler/python-test-breakup-mllib-SPARK-26034.

Authored-by: Bryan Cutler <cutlerb@gmail.com>
Signed-off-by: hyukjinkwon <gurwls223@apache.org>
2018-11-17 00:12:17 +08:00

45 lines
1.4 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.
#
import sys
if sys.version_info[:2] <= (2, 6):
try:
import unittest2 as unittest
except ImportError:
sys.stderr.write('Please install unittest2 to test with Python 2.6 or earlier')
sys.exit(1)
else:
import unittest
from pyspark import SparkContext
from pyspark.serializers import PickleSerializer
from pyspark.sql import SparkSession
def make_serializer():
return PickleSerializer()
class MLlibTestCase(unittest.TestCase):
def setUp(self):
self.sc = SparkContext('local[4]', "MLlib tests")
self.spark = SparkSession(self.sc)
def tearDown(self):
self.spark.stop()