python/pyspark/pandas/tests/diff_frames_ops/test_arithmetic_ext.py

#
# 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 pandas as pd

from pyspark.pandas.config import set_option, reset_option
from pyspark.testing.pandasutils import PandasOnSparkTestCase
from pyspark.testing.sqlutils import SQLTestUtils
from pyspark.pandas.typedef.typehints import extension_dtypes_available
from pyspark.pandas.tests.diff_frames_ops.test_arithmetic import ArithmeticMixin


class ArithmeticExtMixin(ArithmeticMixin):
    @classmethod
    def setUpClass(cls):
        super().setUpClass()
        set_option("compute.ops_on_diff_frames", True)

    @classmethod
    def tearDownClass(cls):
        reset_option("compute.ops_on_diff_frames")
        super().tearDownClass()

    @property
    def pdf1(self):
        return pd.DataFrame(
            {"a": [1, 2, 3, 4, 5, 6, 7, 8, 9], "b": [4, 5, 6, 3, 2, 1, 0, 0, 0]},
            index=[0, 1, 3, 5, 6, 8, 9, 10, 11],
        )

    @property
    def pdf2(self):
        return pd.DataFrame(
            {"a": [9, 8, 7, 6, 5, 4, 3, 2, 1], "b": [0, 0, 0, 4, 5, 6, 1, 2, 3]},
            index=list(range(9)),
        )

    @property
    def pser1(self):
        midx = pd.MultiIndex(
            [["lama", "cow", "falcon", "koala"], ["speed", "weight", "length", "power"]],
            [[0, 3, 1, 1, 1, 2, 2, 2], [0, 2, 0, 3, 2, 0, 1, 3]],
        )
        return pd.Series([45, 200, 1.2, 30, 250, 1.5, 320, 1], index=midx)

    @property
    def pser2(self):
        midx = pd.MultiIndex(
            [["lama", "cow", "falcon"], ["speed", "weight", "length"]],
            [[0, 0, 0, 1, 1, 1, 2, 2, 2], [0, 1, 2, 0, 1, 2, 0, 1, 2]],
        )
        return pd.Series([-45, 200, -1.2, 30, -250, 1.5, 320, 1, -0.3], index=midx)

    @unittest.skipIf(not extension_dtypes_available, "pandas extension dtypes are not available")
    def test_arithmetic_extension_dtypes(self):
        self._test_arithmetic_frame(
            self.pdf1.astype("Int64"), self.pdf2.astype("Int64"), check_extension=True
        )
        self._test_arithmetic_series(
            self.pser1.astype(int).astype("Int64"),
            self.pser2.astype(int).astype("Int64"),
            check_extension=True,
        )


class ArithmeticExtTests(
    ArithmeticExtMixin,
    PandasOnSparkTestCase,
    SQLTestUtils,
):
    pass


if __name__ == "__main__":
    import unittest
    from pyspark.pandas.tests.diff_frames_ops.test_arithmetic_ext import *  # noqa: F401

    try:
        import xmlrunner

        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
    except ImportError:
        testRunner = None
    unittest.main(testRunner=testRunner, verbosity=2)