python/pyspark/pandas/tests/series/test_interpolate.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 numpy as np
import pandas as pd

import pyspark.pandas as ps
from pyspark.loose_version import LooseVersion
from pyspark.testing.pandasutils import PandasOnSparkTestCase


class SeriesInterpolateMixin:
    def _test_interpolate(self, pobj):
        psobj = ps.from_pandas(pobj)
        self.assert_eq(
            psobj.interpolate().sort_index(),
            pobj.interpolate().sort_index(),
        )
        for limit, limit_direction, limit_area in [
            (1, None, None),
            (2, "forward", "inside"),
            (3, "backward", "outside"),
            (4, "backward", "inside"),
            (5, "both", "inside"),
        ]:
            # pandas 3.0.0 can raise when limit >= len(obj) in interpolate edge cases.
            effective_limit = limit
            if LooseVersion(pd.__version__) >= "3.0.0":
                effective_limit = min(limit, len(pobj) - 1)
            with self.subTest(
                limit=effective_limit, limit_direction=limit_direction, limit_area=limit_area
            ):
                self.assert_eq(
                    psobj.interpolate(
                        limit=effective_limit,
                        limit_direction=limit_direction,
                        limit_area=limit_area,
                    ).sort_index(),
                    pobj.interpolate(
                        limit=effective_limit,
                        limit_direction=limit_direction,
                        limit_area=limit_area,
                    ).sort_index(),
                )

    def test_interpolate(self):
        pser = pd.Series(
            [
                1,
                np.nan,
                3,
            ],
            name="a",
        )
        self._test_interpolate(pser)

        pser = pd.Series(
            [
                np.nan,
                np.nan,
                np.nan,
            ],
            name="a",
        )
        self._test_interpolate(pser)

        pser = pd.Series(
            [
                np.nan,
                np.nan,
                np.nan,
                0,
                1,
                np.nan,
                np.nan,
                np.nan,
                np.nan,
                3,
                np.nan,
                np.nan,
                np.nan,
            ],
            name="a",
        )
        self._test_interpolate(pser)


class SeriesInterpolateTests(
    SeriesInterpolateMixin,
    PandasOnSparkTestCase,
):
    pass


if __name__ == "__main__":
    from pyspark.testing import main

    main()