spark-instrumented-optimizer/python/pyspark/ml/tests/test_stat.py

51 lines
2 KiB
Python
Raw Normal View History

#
# 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 unittest
from pyspark.ml.linalg import Vectors
from pyspark.ml.stat import ChiSquareTest
from pyspark.sql import DataFrame
from pyspark.testing.mlutils import SparkSessionTestCase
class ChiSquareTestTests(SparkSessionTestCase):
def test_chisquaretest(self):
data = [[0, Vectors.dense([0, 1, 2])],
[1, Vectors.dense([1, 1, 1])],
[2, Vectors.dense([2, 1, 0])]]
df = self.spark.createDataFrame(data, ['label', 'feat'])
res = ChiSquareTest.test(df, 'feat', 'label')
# This line is hitting the collect bug described in #17218, commented for now.
# pValues = res.select("degreesOfFreedom").collect())
self.assertIsInstance(res, DataFrame)
fieldNames = set(field.name for field in res.schema.fields)
expectedFields = ["pValues", "degreesOfFreedom", "statistics"]
self.assertTrue(all(field in fieldNames for field in expectedFields))
if __name__ == "__main__":
from pyspark.ml.tests.test_stat import *
try:
import xmlrunner
[SPARK-28130][PYTHON] Print pretty messages for skipped tests when xmlrunner is available in PySpark ## What changes were proposed in this pull request? Currently, pretty skipped message added by https://github.com/apache/spark/commit/f7435bec6a9348cfbbe26b13c230c08545d16067 mechanism seems not working when xmlrunner is installed apparently. This PR fixes two things: 1. When `xmlrunner` is installed, seems `xmlrunner` does not respect `vervosity` level in unittests (default is level 1). So the output looks as below ``` Running tests... ---------------------------------------------------------------------- SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS ---------------------------------------------------------------------- ``` So it is not caught by our message detection mechanism. 2. If we manually set the `vervocity` level to `xmlrunner`, it prints messages as below: ``` test_mixed_udf (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) test_mixed_udf_and_sql (pyspark.sql.tests.test_pandas_udf_scalar.ScalarPandasUDFTests) ... SKIP (0.000s) ... ``` This is different in our Jenkins machine: ``` test_createDataFrame_column_name_encoding (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' test_createDataFrame_does_not_modify_input (pyspark.sql.tests.test_arrow.ArrowTests) ... skipped 'Pandas >= 0.23.2 must be installed; however, it was not found.' ... ``` Note that last `SKIP` is different. This PR fixes the regular expression to catch `SKIP` case as well. ## How was this patch tested? Manually tested. **Before:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (0s) ... Tests passed in 562 seconds ======================================================================== ... ``` **After:** ``` Starting test(python2.7): pyspark.... Finished test(python2.7): pyspark.... (48s) ... 93 tests were skipped ... Tests passed in 560 seconds Skipped tests pyspark.... with python2.7: pyspark...(...) ... SKIP (0.000s) ... ======================================================================== ... ``` Closes #24927 from HyukjinKwon/SPARK-28130. Authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2019-06-23 20:58:17 -04:00
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
except ImportError:
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)