6378d4bc06
### What changes were proposed in this pull request? - Remove SQLContext.createExternalTable and Catalog.createExternalTable, deprecated in favor of createTable since 2.2.0, plus tests of deprecated methods - Remove HiveContext, deprecated in 2.0.0, in favor of `SparkSession.builder.enableHiveSupport` - Remove deprecated KinesisUtils.createStream methods, plus tests of deprecated methods, deprecate in 2.2.0 - Remove deprecated MLlib (not Spark ML) linear method support, mostly utility constructors and 'train' methods, and associated docs. This includes methods in LinearRegression, LogisticRegression, Lasso, RidgeRegression. These have been deprecated since 2.0.0 - Remove deprecated Pyspark MLlib linear method support, including LogisticRegressionWithSGD, LinearRegressionWithSGD, LassoWithSGD - Remove 'runs' argument in KMeans.train() method, which has been a no-op since 2.0.0 - Remove deprecated ChiSqSelector isSorted protected method - Remove deprecated 'yarn-cluster' and 'yarn-client' master argument in favor of 'yarn' and deploy mode 'cluster', etc Notes: - I was not able to remove deprecated DataFrameReader.json(RDD) in favor of DataFrameReader.json(Dataset); the former was deprecated in 2.2.0, but, it is still needed to support Pyspark's .json() method, which can't use a Dataset. - Looks like SQLContext.createExternalTable was not actually deprecated in Pyspark, but, almost certainly was meant to be? Catalog.createExternalTable was. - I afterwards noted that the toDegrees, toRadians functions were almost removed fully in SPARK-25908, but Felix suggested keeping just the R version as they hadn't been technically deprecated. I'd like to revisit that. Do we really want the inconsistency? I'm not against reverting it again, but then that implies leaving SQLContext.createExternalTable just in Pyspark too, which seems weird. - I *kept* LogisticRegressionWithSGD, LinearRegressionWithSGD, LassoWithSGD, RidgeRegressionWithSGD in Pyspark, though deprecated, as it is hard to remove them (still used by StreamingLogisticRegressionWithSGD?) and they are not fully removed in Scala. Maybe should not have been deprecated. ### Why are the changes needed? Deprecated items are easiest to remove in a major release, so we should do so as much as possible for Spark 3. This does not target items deprecated 'recently' as of Spark 2.3, which is still 18 months old. ### Does this PR introduce any user-facing change? Yes, in that deprecated items are removed from some public APIs. ### How was this patch tested? Existing tests. Closes #25684 from srowen/SPARK-28980. Lead-authored-by: Sean Owen <sean.owen@databricks.com> Co-authored-by: HyukjinKwon <gurwls223@apache.org> Signed-off-by: Sean Owen <sean.owen@databricks.com>
79 lines
3.2 KiB
Python
79 lines
3.2 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 Row
|
|
from pyspark.testing.utils import QuietTest
|
|
|
|
|
|
class ImageFileFormatTest(SparkSessionTestCase):
|
|
|
|
def test_read_images(self):
|
|
data_path = 'data/mllib/images/origin/kittens'
|
|
df = self.spark.read.format("image") \
|
|
.option("dropInvalid", True) \
|
|
.option("recursiveFileLookup", True) \
|
|
.load(data_path)
|
|
self.assertEqual(df.count(), 4)
|
|
first_row = df.take(1)[0][0]
|
|
# compare `schema.simpleString()` instead of directly compare schema,
|
|
# because the df loaded from datasouce may change schema column nullability.
|
|
self.assertEqual(df.schema.simpleString(), ImageSchema.imageSchema.simpleString())
|
|
self.assertEqual(df.schema["image"].dataType.simpleString(),
|
|
ImageSchema.columnSchema.simpleString())
|
|
array = ImageSchema.toNDArray(first_row)
|
|
self.assertEqual(len(array), first_row[1])
|
|
self.assertEqual(ImageSchema.toImage(array, origin=first_row[0]), first_row)
|
|
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"))
|
|
|
|
|
|
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)
|