|
| 1 | +# Copyright 2026 Google LLC |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +import operator |
| 16 | +import pathlib |
| 17 | +from typing import Generator |
| 18 | + |
| 19 | +import pandas as pd |
| 20 | +import pytest |
| 21 | + |
| 22 | +import bigframes |
| 23 | +import bigframes.pandas as bpd |
| 24 | +from bigframes.testing.utils import assert_frame_equal, convert_pandas_dtypes |
| 25 | + |
| 26 | +pytest.importorskip("polars") |
| 27 | +pytest.importorskip("pandas", minversion="3.0.0") |
| 28 | + |
| 29 | + |
| 30 | +CURRENT_DIR = pathlib.Path(__file__).parent |
| 31 | +DATA_DIR = CURRENT_DIR.parent / "data" |
| 32 | + |
| 33 | + |
| 34 | +@pytest.fixture(scope="module", autouse=True) |
| 35 | +def session() -> Generator[bigframes.Session, None, None]: |
| 36 | + import bigframes.core.global_session |
| 37 | + from bigframes.testing import polars_session |
| 38 | + |
| 39 | + session = polars_session.TestSession() |
| 40 | + with bigframes.core.global_session._GlobalSessionContext(session): |
| 41 | + yield session |
| 42 | + |
| 43 | + |
| 44 | +@pytest.fixture(scope="module") |
| 45 | +def scalars_pandas_df_index() -> pd.DataFrame: |
| 46 | + """pd.DataFrame pointing at test data.""" |
| 47 | + |
| 48 | + df = pd.read_json( |
| 49 | + DATA_DIR / "scalars.jsonl", |
| 50 | + lines=True, |
| 51 | + ) |
| 52 | + convert_pandas_dtypes(df, bytes_col=True) |
| 53 | + |
| 54 | + df = df.set_index("rowindex", drop=False) |
| 55 | + df.index.name = None |
| 56 | + return df.set_index("rowindex").sort_index() |
| 57 | + |
| 58 | + |
| 59 | +@pytest.fixture(scope="module") |
| 60 | +def scalars_df_index( |
| 61 | + session: bigframes.Session, scalars_pandas_df_index |
| 62 | +) -> bpd.DataFrame: |
| 63 | + return session.read_pandas(scalars_pandas_df_index) |
| 64 | + |
| 65 | + |
| 66 | +@pytest.fixture(scope="module") |
| 67 | +def scalars_df_2_index( |
| 68 | + session: bigframes.Session, scalars_pandas_df_index |
| 69 | +) -> bpd.DataFrame: |
| 70 | + return session.read_pandas(scalars_pandas_df_index) |
| 71 | + |
| 72 | + |
| 73 | +@pytest.fixture(scope="module") |
| 74 | +def scalars_dfs( |
| 75 | + scalars_df_index, |
| 76 | + scalars_pandas_df_index, |
| 77 | +): |
| 78 | + return scalars_df_index, scalars_pandas_df_index |
| 79 | + |
| 80 | + |
| 81 | +@pytest.mark.parametrize( |
| 82 | + ("op",), |
| 83 | + [ |
| 84 | + (operator.invert,), |
| 85 | + ], |
| 86 | +) |
| 87 | +def test_pd_col_unary_operators(scalars_dfs, op): |
| 88 | + scalars_df, scalars_pandas_df = scalars_dfs |
| 89 | + bf_kwargs = { |
| 90 | + "result": op(bpd.col("float64_col")), |
| 91 | + } |
| 92 | + pd_kwargs = { |
| 93 | + "result": op(pd.col("float64_col")), # type: ignore |
| 94 | + } |
| 95 | + df = scalars_df.assign(**bf_kwargs) |
| 96 | + bf_result = df.to_pandas() |
| 97 | + pd_result = scalars_pandas_df.assign(**pd_kwargs) |
| 98 | + |
| 99 | + assert_frame_equal(bf_result, pd_result) |
| 100 | + |
| 101 | + |
| 102 | +@pytest.mark.parametrize( |
| 103 | + ("op",), |
| 104 | + [ |
| 105 | + (operator.add,), |
| 106 | + (operator.sub,), |
| 107 | + (operator.mul,), |
| 108 | + (operator.truediv,), |
| 109 | + (operator.floordiv,), |
| 110 | + (operator.gt,), |
| 111 | + (operator.lt,), |
| 112 | + (operator.ge,), |
| 113 | + (operator.le,), |
| 114 | + (operator.eq,), |
| 115 | + (operator.mod,), |
| 116 | + ], |
| 117 | +) |
| 118 | +def test_pd_col_binary_operators(scalars_dfs, op): |
| 119 | + scalars_df, scalars_pandas_df = scalars_dfs |
| 120 | + bf_kwargs = { |
| 121 | + "result": op(bpd.col("float64_col"), 2.4), |
| 122 | + "reverse_result": op(2.4, bpd.col("float64_col")), |
| 123 | + } |
| 124 | + pd_kwargs = { |
| 125 | + "result": op(pd.col("float64_col"), 2.4), # type: ignore |
| 126 | + "reverse_result": op(2.4, pd.col("float64_col")), # type: ignore |
| 127 | + } |
| 128 | + df = scalars_df.assign(**bf_kwargs) |
| 129 | + bf_result = df.to_pandas() |
| 130 | + pd_result = scalars_pandas_df.assign(**pd_kwargs) |
| 131 | + |
| 132 | + assert_frame_equal(bf_result, pd_result) |
| 133 | + |
| 134 | + |
| 135 | +@pytest.mark.parametrize( |
| 136 | + ("op",), |
| 137 | + [ |
| 138 | + (operator.and_,), |
| 139 | + (operator.or_,), |
| 140 | + (operator.xor,), |
| 141 | + ], |
| 142 | +) |
| 143 | +def test_pd_col_binary_bool_operators(scalars_dfs, op): |
| 144 | + scalars_df, scalars_pandas_df = scalars_dfs |
| 145 | + bf_kwargs = { |
| 146 | + "result": op(bpd.col("bool_col"), True), |
| 147 | + "reverse_result": op(False, bpd.col("bool_col")), |
| 148 | + } |
| 149 | + pd_kwargs = { |
| 150 | + "result": op(pd.col("bool_col"), True), # type: ignore |
| 151 | + "reverse_result": op(False, pd.col("bool_col")), # type: ignore |
| 152 | + } |
| 153 | + df = scalars_df.assign(**bf_kwargs) |
| 154 | + bf_result = df.to_pandas() |
| 155 | + pd_result = scalars_pandas_df.assign(**pd_kwargs) |
| 156 | + |
| 157 | + assert_frame_equal(bf_result, pd_result) |
0 commit comments