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>
111 lines
4.2 KiB
Python
111 lines
4.2 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 py4j
|
|
|
|
from pyspark.ml.image import ImageSchema
|
|
from pyspark.testing.mlutils import PySparkTestCase, SparkSessionTestCase
|
|
from pyspark.sql import HiveContext, Row
|
|
from pyspark.testing.utils import QuietTest
|
|
|
|
|
|
class ImageReaderTest(SparkSessionTestCase):
|
|
|
|
def test_read_images(self):
|
|
data_path = 'data/mllib/images/origin/kittens'
|
|
df = ImageSchema.readImages(data_path, recursive=True, dropImageFailures=True)
|
|
self.assertEqual(df.count(), 4)
|
|
first_row = df.take(1)[0][0]
|
|
array = ImageSchema.toNDArray(first_row)
|
|
self.assertEqual(len(array), first_row[1])
|
|
self.assertEqual(ImageSchema.toImage(array, origin=first_row[0]), first_row)
|
|
self.assertEqual(df.schema, ImageSchema.imageSchema)
|
|
self.assertEqual(df.schema["image"].dataType, ImageSchema.columnSchema)
|
|
expected = {'CV_8UC3': 16, 'Undefined': -1, 'CV_8U': 0, 'CV_8UC1': 0, 'CV_8UC4': 24}
|
|
self.assertEqual(ImageSchema.ocvTypes, expected)
|
|
expected = ['origin', 'height', 'width', 'nChannels', 'mode', 'data']
|
|
self.assertEqual(ImageSchema.imageFields, expected)
|
|
self.assertEqual(ImageSchema.undefinedImageType, "Undefined")
|
|
|
|
with QuietTest(self.sc):
|
|
self.assertRaisesRegexp(
|
|
TypeError,
|
|
"image argument should be pyspark.sql.types.Row; however",
|
|
lambda: ImageSchema.toNDArray("a"))
|
|
|
|
with QuietTest(self.sc):
|
|
self.assertRaisesRegexp(
|
|
ValueError,
|
|
"image argument should have attributes specified in",
|
|
lambda: ImageSchema.toNDArray(Row(a=1)))
|
|
|
|
with QuietTest(self.sc):
|
|
self.assertRaisesRegexp(
|
|
TypeError,
|
|
"array argument should be numpy.ndarray; however, it got",
|
|
lambda: ImageSchema.toImage("a"))
|
|
|
|
|
|
class ImageReaderTest2(PySparkTestCase):
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
super(ImageReaderTest2, cls).setUpClass()
|
|
cls.hive_available = True
|
|
# Note that here we enable Hive's support.
|
|
cls.spark = None
|
|
try:
|
|
cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
|
|
except py4j.protocol.Py4JError:
|
|
cls.tearDownClass()
|
|
cls.hive_available = False
|
|
except TypeError:
|
|
cls.tearDownClass()
|
|
cls.hive_available = False
|
|
if cls.hive_available:
|
|
cls.spark = HiveContext._createForTesting(cls.sc)
|
|
|
|
def setUp(self):
|
|
if not self.hive_available:
|
|
self.skipTest("Hive is not available.")
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
super(ImageReaderTest2, cls).tearDownClass()
|
|
if cls.spark is not None:
|
|
cls.spark.sparkSession.stop()
|
|
cls.spark = None
|
|
|
|
def test_read_images_multiple_times(self):
|
|
# This test case is to check if `ImageSchema.readImages` tries to
|
|
# initiate Hive client multiple times. See SPARK-22651.
|
|
data_path = 'data/mllib/images/origin/kittens'
|
|
ImageSchema.readImages(data_path, recursive=True, dropImageFailures=True)
|
|
ImageSchema.readImages(data_path, recursive=True, dropImageFailures=True)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pyspark.ml.tests.test_image import *
|
|
|
|
try:
|
|
import xmlrunner
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|