31a16fbb40
### What changes were proposed in this pull request? This PR proposes migration of [`pyspark-stubs`](https://github.com/zero323/pyspark-stubs) into Spark codebase. ### Why are the changes needed? ### Does this PR introduce _any_ user-facing change? Yes. This PR adds type annotations directly to Spark source. This can impact interaction with development tools for users, which haven't used `pyspark-stubs`. ### How was this patch tested? - [x] MyPy tests of the PySpark source ``` mypy --no-incremental --config python/mypy.ini python/pyspark ``` - [x] MyPy tests of Spark examples ``` MYPYPATH=python/ mypy --no-incremental --config python/mypy.ini examples/src/main/python/ml examples/src/main/python/sql examples/src/main/python/sql/streaming ``` - [x] Existing Flake8 linter - [x] Existing unit tests Tested against: - `mypy==0.790+dev.e959952d9001e9713d329a2f9b196705b028f894` - `mypy==0.782` Closes #29591 from zero323/SPARK-32681. Authored-by: zero323 <mszymkiewicz@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
51 lines
2 KiB
Python
51 lines
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
|
|
|
|
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 * # noqa: F401
|
|
|
|
try:
|
|
import xmlrunner # type: ignore[import]
|
|
testRunner = xmlrunner.XMLTestRunner(output='target/test-reports', verbosity=2)
|
|
except ImportError:
|
|
testRunner = None
|
|
unittest.main(testRunner=testRunner, verbosity=2)
|