47d62af2a9
### What changes were proposed in this pull request? Now that we merged the Koalas main code into the PySpark code base (#32036), we should port the Koalas internal implementation unit tests to PySpark. ### Why are the changes needed? Currently, the pandas-on-Spark modules are not tested fully. We should enable the internal implementation unit tests. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Enable internal implementation unit tests. Closes #32137 from xinrong-databricks/port.test_internal_impl. Lead-authored-by: Xinrong Meng <xinrong.meng@databricks.com> Co-authored-by: xinrong-databricks <47337188+xinrong-databricks@users.noreply.github.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
52 lines
2.1 KiB
Python
52 lines
2.1 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 pandas as pd
|
|
|
|
from pyspark import pandas as ps
|
|
from pyspark.pandas.testing.utils import ReusedSQLTestCase
|
|
|
|
|
|
class DefaultIndexTest(ReusedSQLTestCase):
|
|
def test_default_index_sequence(self):
|
|
with ps.option_context("compute.default_index_type", "sequence"):
|
|
sdf = self.spark.range(1000)
|
|
self.assert_eq(ps.DataFrame(sdf), pd.DataFrame({"id": list(range(1000))}))
|
|
|
|
def test_default_index_distributed_sequence(self):
|
|
with ps.option_context("compute.default_index_type", "distributed-sequence"):
|
|
sdf = self.spark.range(1000)
|
|
self.assert_eq(ps.DataFrame(sdf), pd.DataFrame({"id": list(range(1000))}))
|
|
|
|
def test_default_index_distributed(self):
|
|
with ps.option_context("compute.default_index_type", "distributed"):
|
|
sdf = self.spark.range(1000)
|
|
pdf = ps.DataFrame(sdf).to_pandas()
|
|
self.assertEqual(len(set(pdf.index)), len(pdf))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import unittest
|
|
from pyspark.pandas.tests.test_default_index 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)
|