7c05f61514
## What changes were proposed in this pull request?
Currently, pretty skipped message added by f7435bec6a
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>
64 lines
2.7 KiB
Python
64 lines
2.7 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 unittest
|
|
|
|
import numpy as np
|
|
|
|
from pyspark.ml.evaluation import ClusteringEvaluator, RegressionEvaluator
|
|
from pyspark.ml.linalg import Vectors
|
|
from pyspark.sql import Row
|
|
from pyspark.testing.mlutils import SparkSessionTestCase
|
|
|
|
|
|
class EvaluatorTests(SparkSessionTestCase):
|
|
|
|
def test_java_params(self):
|
|
"""
|
|
This tests a bug fixed by SPARK-18274 which causes multiple copies
|
|
of a Params instance in Python to be linked to the same Java instance.
|
|
"""
|
|
evaluator = RegressionEvaluator(metricName="r2")
|
|
df = self.spark.createDataFrame([Row(label=1.0, prediction=1.1)])
|
|
evaluator.evaluate(df)
|
|
self.assertEqual(evaluator._java_obj.getMetricName(), "r2")
|
|
evaluatorCopy = evaluator.copy({evaluator.metricName: "mae"})
|
|
evaluator.evaluate(df)
|
|
evaluatorCopy.evaluate(df)
|
|
self.assertEqual(evaluator._java_obj.getMetricName(), "r2")
|
|
self.assertEqual(evaluatorCopy._java_obj.getMetricName(), "mae")
|
|
|
|
def test_clustering_evaluator_with_cosine_distance(self):
|
|
featureAndPredictions = map(lambda x: (Vectors.dense(x[0]), x[1]),
|
|
[([1.0, 1.0], 1.0), ([10.0, 10.0], 1.0), ([1.0, 0.5], 2.0),
|
|
([10.0, 4.4], 2.0), ([-1.0, 1.0], 3.0), ([-100.0, 90.0], 3.0)])
|
|
dataset = self.spark.createDataFrame(featureAndPredictions, ["features", "prediction"])
|
|
evaluator = ClusteringEvaluator(predictionCol="prediction", distanceMeasure="cosine")
|
|
self.assertEqual(evaluator.getDistanceMeasure(), "cosine")
|
|
self.assertTrue(np.isclose(evaluator.evaluate(dataset), 0.992671213, atol=1e-5))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pyspark.ml.tests.test_evaluation import *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|