venv

venv/lib/python3.12/site-packages/pandas/tests/arrays/period/test_arrow_compat.py

@@ -0,0 +1,130 @@
+import pytest
+
+from pandas.compat.pyarrow import pa_version_under10p1
+
+from pandas.core.dtypes.dtypes import PeriodDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import (
+    PeriodArray,
+    period_array,
+)
+
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+
+
+pa = pytest.importorskip("pyarrow")
+
+
+def test_arrow_extension_type():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    p1 = ArrowPeriodType("D")
+    p2 = ArrowPeriodType("D")
+    p3 = ArrowPeriodType("M")
+
+    assert p1.freq == "D"
+    assert p1 == p2
+    assert p1 != p3
+    assert hash(p1) == hash(p2)
+    assert hash(p1) != hash(p3)
+
+
+@pytest.mark.xfail(not pa_version_under10p1, reason="Wrong behavior with pyarrow 10")
+@pytest.mark.parametrize(
+    "data, freq",
+    [
+        (pd.date_range("2017", periods=3), "D"),
+        (pd.date_range("2017", periods=3, freq="YE"), "Y-DEC"),
+    ],
+)
+def test_arrow_array(data, freq):
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    periods = period_array(data, freq=freq)
+    result = pa.array(periods)
+    assert isinstance(result.type, ArrowPeriodType)
+    assert result.type.freq == freq
+    expected = pa.array(periods.asi8, type="int64")
+    assert result.storage.equals(expected)
+
+    # convert to its storage type
+    result = pa.array(periods, type=pa.int64())
+    assert result.equals(expected)
+
+    # unsupported conversions
+    msg = "Not supported to convert PeriodArray to 'double' type"
+    with pytest.raises(TypeError, match=msg):
+        pa.array(periods, type="float64")
+
+    with pytest.raises(TypeError, match="different 'freq'"):
+        pa.array(periods, type=ArrowPeriodType("T"))
+
+
+def test_arrow_array_missing():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([1, 2, 3], dtype="period[D]")
+    arr[1] = pd.NaT
+
+    result = pa.array(arr)
+    assert isinstance(result.type, ArrowPeriodType)
+    assert result.type.freq == "D"
+    expected = pa.array([1, None, 3], type="int64")
+    assert result.storage.equals(expected)
+
+
+def test_arrow_table_roundtrip():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([1, 2, 3], dtype="period[D]")
+    arr[1] = pd.NaT
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    assert isinstance(table.field("a").type, ArrowPeriodType)
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)
+
+    table2 = pa.concat_tables([table, table])
+    result = table2.to_pandas()
+    expected = pd.concat([df, df], ignore_index=True)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_arrow_load_from_zero_chunks():
+    # GH-41040
+
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([], dtype="period[D]")
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    assert isinstance(table.field("a").type, ArrowPeriodType)
+    table = pa.table(
+        [pa.chunked_array([], type=table.column(0).type)], schema=table.schema
+    )
+
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)
+
+
+def test_arrow_table_roundtrip_without_metadata():
+    arr = PeriodArray([1, 2, 3], dtype="period[h]")
+    arr[1] = pd.NaT
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    # remove the metadata
+    table = table.replace_schema_metadata()
+    assert table.schema.metadata is None
+
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)

venv/lib/python3.12/site-packages/pandas/tests/arrays/period/test_astype.py

@@ -0,0 +1,67 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import PeriodDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import period_array
+
+
+@pytest.mark.parametrize("dtype", [int, np.int32, np.int64, "uint32", "uint64"])
+def test_astype_int(dtype):
+    # We choose to ignore the sign and size of integers for
+    # Period/Datetime/Timedelta astype
+    arr = period_array(["2000", "2001", None], freq="D")
+
+    if np.dtype(dtype) != np.int64:
+        with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"):
+            arr.astype(dtype)
+        return
+
+    result = arr.astype(dtype)
+    expected = arr._ndarray.view("i8")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_astype_copies():
+    arr = period_array(["2000", "2001", None], freq="D")
+    result = arr.astype(np.int64, copy=False)
+
+    # Add the `.base`, since we now use `.asi8` which returns a view.
+    # We could maybe override it in PeriodArray to return ._ndarray directly.
+    assert result.base is arr._ndarray
+
+    result = arr.astype(np.int64, copy=True)
+    assert result is not arr._ndarray
+    tm.assert_numpy_array_equal(result, arr._ndarray.view("i8"))
+
+
+def test_astype_categorical():
+    arr = period_array(["2000", "2001", "2001", None], freq="D")
+    result = arr.astype("category")
+    categories = pd.PeriodIndex(["2000", "2001"], freq="D")
+    expected = pd.Categorical.from_codes([0, 1, 1, -1], categories=categories)
+    tm.assert_categorical_equal(result, expected)
+
+
+def test_astype_period():
+    arr = period_array(["2000", "2001", None], freq="D")
+    result = arr.astype(PeriodDtype("M"))
+    expected = period_array(["2000", "2001", None], freq="M")
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["datetime64[ns]", "timedelta64[ns]"])
+def test_astype_datetime(dtype):
+    arr = period_array(["2000", "2001", None], freq="D")
+    # slice off the [ns] so that the regex matches.
+    if dtype == "timedelta64[ns]":
+        with pytest.raises(TypeError, match=dtype[:-4]):
+            arr.astype(dtype)
+
+    else:
+        # GH#45038 allow period->dt64 because we allow dt64->period
+        result = arr.astype(dtype)
+        expected = pd.DatetimeIndex(["2000", "2001", pd.NaT], dtype=dtype)._data
+        tm.assert_datetime_array_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/arrays/period/test_constructors.py

@@ -0,0 +1,156 @@
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import iNaT
+from pandas._libs.tslibs.offsets import MonthEnd
+from pandas._libs.tslibs.period import IncompatibleFrequency
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import (
+    PeriodArray,
+    period_array,
+)
+
+
+@pytest.mark.parametrize(
+    "data, freq, expected",
+    [
+        ([pd.Period("2017", "D")], None, [17167]),
+        ([pd.Period("2017", "D")], "D", [17167]),
+        ([2017], "D", [17167]),
+        (["2017"], "D", [17167]),
+        ([pd.Period("2017", "D")], pd.tseries.offsets.Day(), [17167]),
+        ([pd.Period("2017", "D"), None], None, [17167, iNaT]),
+        (pd.Series(pd.date_range("2017", periods=3)), None, [17167, 17168, 17169]),
+        (pd.date_range("2017", periods=3), None, [17167, 17168, 17169]),
+        (pd.period_range("2017", periods=4, freq="Q"), None, [188, 189, 190, 191]),
+    ],
+)
+def test_period_array_ok(data, freq, expected):
+    result = period_array(data, freq=freq).asi8
+    expected = np.asarray(expected, dtype=np.int64)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_period_array_readonly_object():
+    # https://github.com/pandas-dev/pandas/issues/25403
+    pa = period_array([pd.Period("2019-01-01")])
+    arr = np.asarray(pa, dtype="object")
+    arr.setflags(write=False)
+
+    result = period_array(arr)
+    tm.assert_period_array_equal(result, pa)
+
+    result = pd.Series(arr)
+    tm.assert_series_equal(result, pd.Series(pa))
+
+    result = pd.DataFrame({"A": arr})
+    tm.assert_frame_equal(result, pd.DataFrame({"A": pa}))
+
+
+def test_from_datetime64_freq_changes():
+    # https://github.com/pandas-dev/pandas/issues/23438
+    arr = pd.date_range("2017", periods=3, freq="D")
+    result = PeriodArray._from_datetime64(arr, freq="M")
+    expected = period_array(["2017-01-01", "2017-01-01", "2017-01-01"], freq="M")
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("freq", ["2M", MonthEnd(2)])
+def test_from_datetime64_freq_2M(freq):
+    arr = np.array(
+        ["2020-01-01T00:00:00", "2020-01-02T00:00:00"], dtype="datetime64[ns]"
+    )
+    result = PeriodArray._from_datetime64(arr, freq)
+    expected = period_array(["2020-01", "2020-01"], freq=freq)
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "data, freq, msg",
+    [
+        (
+            [pd.Period("2017", "D"), pd.Period("2017", "Y")],
+            None,
+            "Input has different freq",
+        ),
+        ([pd.Period("2017", "D")], "Y", "Input has different freq"),
+    ],
+)
+def test_period_array_raises(data, freq, msg):
+    with pytest.raises(IncompatibleFrequency, match=msg):
+        period_array(data, freq)
+
+
+def test_period_array_non_period_series_raies():
+    ser = pd.Series([1, 2, 3])
+    with pytest.raises(TypeError, match="dtype"):
+        PeriodArray(ser, dtype="period[D]")
+
+
+def test_period_array_freq_mismatch():
+    arr = period_array(["2000", "2001"], freq="D")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        PeriodArray(arr, dtype="period[M]")
+
+    dtype = pd.PeriodDtype(pd.tseries.offsets.MonthEnd())
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        PeriodArray(arr, dtype=dtype)
+
+
+def test_from_sequence_disallows_i8():
+    arr = period_array(["2000", "2001"], freq="D")
+
+    msg = str(arr[0].ordinal)
+    with pytest.raises(TypeError, match=msg):
+        PeriodArray._from_sequence(arr.asi8, dtype=arr.dtype)
+
+    with pytest.raises(TypeError, match=msg):
+        PeriodArray._from_sequence(list(arr.asi8), dtype=arr.dtype)
+
+
+def test_from_td64nat_sequence_raises():
+    # GH#44507
+    td = pd.NaT.to_numpy("m8[ns]")
+
+    dtype = pd.period_range("2005-01-01", periods=3, freq="D").dtype
+
+    arr = np.array([None], dtype=object)
+    arr[0] = td
+
+    msg = "Value must be Period, string, integer, or datetime"
+    with pytest.raises(ValueError, match=msg):
+        PeriodArray._from_sequence(arr, dtype=dtype)
+
+    with pytest.raises(ValueError, match=msg):
+        pd.PeriodIndex(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.Index(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.array(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.Series(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.DataFrame(arr, dtype=dtype)
+
+
+def test_freq_deprecated():
+    # GH#52462
+    data = np.arange(5).astype(np.int64)
+    msg = "The 'freq' keyword in the PeriodArray constructor is deprecated"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        res = PeriodArray(data, freq="M")
+
+    expected = PeriodArray(data, dtype="period[M]")
+    tm.assert_equal(res, expected)
+
+
+def test_period_array_from_datetime64():
+    arr = np.array(
+        ["2020-01-01T00:00:00", "2020-02-02T00:00:00"], dtype="datetime64[ns]"
+    )
+    result = PeriodArray._from_datetime64(arr, freq=MonthEnd(2))
+
+    expected = period_array(["2020-01-01", "2020-02-01"], freq=MonthEnd(2))
+    tm.assert_period_array_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/arrays/period/test_reductions.py

@@ -0,0 +1,42 @@
+import pytest
+
+import pandas as pd
+from pandas.core.arrays import period_array
+
+
+class TestReductions:
+    def test_min_max(self):
+        arr = period_array(
+            [
+                "2000-01-03",
+                "2000-01-03",
+                "NaT",
+                "2000-01-02",
+                "2000-01-05",
+                "2000-01-04",
+            ],
+            freq="D",
+        )
+
+        result = arr.min()
+        expected = pd.Period("2000-01-02", freq="D")
+        assert result == expected
+
+        result = arr.max()
+        expected = pd.Period("2000-01-05", freq="D")
+        assert result == expected
+
+        result = arr.min(skipna=False)
+        assert result is pd.NaT
+
+        result = arr.max(skipna=False)
+        assert result is pd.NaT
+
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_min_max_empty(self, skipna):
+        arr = period_array([], freq="D")
+        result = arr.min(skipna=skipna)
+        assert result is pd.NaT
+
+        result = arr.max(skipna=skipna)
+        assert result is pd.NaT