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>
125 lines
4.2 KiB
Python
125 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 os
|
|
import time
|
|
import unittest
|
|
|
|
from pyspark.testing.sqlutils import ReusedSQLTestCase, have_pandas, have_pyarrow, \
|
|
pandas_requirement_message, pyarrow_requirement_message
|
|
|
|
if have_pandas:
|
|
import pandas as pd
|
|
|
|
|
|
@unittest.skipIf(
|
|
not have_pandas or not have_pyarrow,
|
|
pandas_requirement_message or pyarrow_requirement_message) # type: ignore[arg-type]
|
|
class MapInPandasTests(ReusedSQLTestCase):
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
ReusedSQLTestCase.setUpClass()
|
|
|
|
# Synchronize default timezone between Python and Java
|
|
cls.tz_prev = os.environ.get("TZ", None) # save current tz if set
|
|
tz = "America/Los_Angeles"
|
|
os.environ["TZ"] = tz
|
|
time.tzset()
|
|
|
|
cls.sc.environment["TZ"] = tz
|
|
cls.spark.conf.set("spark.sql.session.timeZone", tz)
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
del os.environ["TZ"]
|
|
if cls.tz_prev is not None:
|
|
os.environ["TZ"] = cls.tz_prev
|
|
time.tzset()
|
|
ReusedSQLTestCase.tearDownClass()
|
|
|
|
def test_map_partitions_in_pandas(self):
|
|
def func(iterator):
|
|
for pdf in iterator:
|
|
assert isinstance(pdf, pd.DataFrame)
|
|
assert pdf.columns == ['id']
|
|
yield pdf
|
|
|
|
df = self.spark.range(10)
|
|
actual = df.mapInPandas(func, 'id long').collect()
|
|
expected = df.collect()
|
|
self.assertEquals(actual, expected)
|
|
|
|
def test_multiple_columns(self):
|
|
data = [(1, "foo"), (2, None), (3, "bar"), (4, "bar")]
|
|
df = self.spark.createDataFrame(data, "a int, b string")
|
|
|
|
def func(iterator):
|
|
for pdf in iterator:
|
|
assert isinstance(pdf, pd.DataFrame)
|
|
assert [d.name for d in list(pdf.dtypes)] == ['int32', 'object']
|
|
yield pdf
|
|
|
|
actual = df.mapInPandas(func, df.schema).collect()
|
|
expected = df.collect()
|
|
self.assertEquals(actual, expected)
|
|
|
|
def test_different_output_length(self):
|
|
def func(iterator):
|
|
for _ in iterator:
|
|
yield pd.DataFrame({'a': list(range(100))})
|
|
|
|
df = self.spark.range(10)
|
|
actual = df.repartition(1).mapInPandas(func, 'a long').collect()
|
|
self.assertEquals(set((r.a for r in actual)), set(range(100)))
|
|
|
|
def test_empty_iterator(self):
|
|
def empty_iter(_):
|
|
return iter([])
|
|
|
|
self.assertEqual(
|
|
self.spark.range(10).mapInPandas(empty_iter, 'a int, b string').count(), 0)
|
|
|
|
def test_empty_rows(self):
|
|
def empty_rows(_):
|
|
return iter([pd.DataFrame({'a': []})])
|
|
|
|
self.assertEqual(
|
|
self.spark.range(10).mapInPandas(empty_rows, 'a int').count(), 0)
|
|
|
|
def test_chain_map_partitions_in_pandas(self):
|
|
def func(iterator):
|
|
for pdf in iterator:
|
|
assert isinstance(pdf, pd.DataFrame)
|
|
assert pdf.columns == ['id']
|
|
yield pdf
|
|
|
|
df = self.spark.range(10)
|
|
actual = df.mapInPandas(func, 'id long').mapInPandas(func, 'id long').collect()
|
|
expected = df.collect()
|
|
self.assertEquals(actual, expected)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pyspark.sql.tests.test_pandas_map 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)
|