REF: remove infer_datetimelike_array (pandas-dev#49608)

Author: jbrockmendel

pandas/_libs/lib.pyi

@@ -169,9 +169,6 @@ def ensure_string_array(
     copy: bool = ...,
     skipna: bool = ...,
 ) -> npt.NDArray[np.object_]: ...
-def infer_datetimelike_array(
-    arr: npt.NDArray[np.object_],
-) -> str: ...
 def convert_nans_to_NA(
     arr: npt.NDArray[np.object_],
 ) -> npt.NDArray[np.object_]: ...

pandas/_libs/lib.pyx

@@ -1565,99 +1565,6 @@ def infer_dtype(value: object, skipna: bool = True) -> str:
     return "mixed"
 
 
-def infer_datetimelike_array(arr: ndarray[object]) -> tuple[str, bool]:
-    """
-    Infer if we have a datetime or timedelta array.
-    - date: we have *only* date and maybe strings, nulls
-    - datetime: we have *only* datetimes and maybe strings, nulls
-    - timedelta: we have *only* timedeltas and maybe strings, nulls
-    - nat: we do not have *any* date, datetimes or timedeltas, but do have
-      at least a NaT
-    - mixed: other objects (strings, a mix of tz-aware and tz-naive, or
-                            actual objects)
-
-    Parameters
-    ----------
-    arr : ndarray[object]
-
-    Returns
-    -------
-    str: {datetime, timedelta, date, nat, mixed}
-    """
-    cdef:
-        Py_ssize_t i, n = len(arr)
-        bint seen_timedelta = False, seen_date = False, seen_datetime = False
-        bint seen_tz_aware = False, seen_tz_naive = False
-        bint seen_nat = False
-        bint seen_period = False, seen_interval = False
-        object v
-
-    for i in range(n):
-        v = arr[i]
-        if isinstance(v, str):
-            return "mixed"
-
-        elif v is None or util.is_nan(v):
-            # nan or None
-            pass
-        elif v is NaT:
-            seen_nat = True
-        elif PyDateTime_Check(v):
-            # datetime
-            seen_datetime = True
-
-            # disambiguate between tz-naive and tz-aware
-            if v.tzinfo is None:
-                seen_tz_naive = True
-            else:
-                seen_tz_aware = True
-
-            if seen_tz_naive and seen_tz_aware:
-                return "mixed"
-        elif util.is_datetime64_object(v):
-            # np.datetime64
-            seen_datetime = True
-        elif PyDate_Check(v):
-            seen_date = True
-        elif is_timedelta(v):
-            # timedelta, or timedelta64
-            seen_timedelta = True
-        elif is_period_object(v):
-            seen_period = True
-            break
-        elif is_interval(v):
-            seen_interval = True
-            break
-        else:
-            return "mixed"
-
-    if seen_period:
-        if is_period_array(arr):
-            return "period"
-        return "mixed"
-
-    if seen_interval:
-        if is_interval_array(arr):
-            return "interval"
-        return "mixed"
-
-    if seen_date:
-        if not seen_datetime and not seen_timedelta:
-            return "date"
-        return "mixed"
-
-    elif seen_datetime and not seen_timedelta:
-        return "datetime"
-    elif seen_timedelta and not seen_datetime:
-        return "timedelta"
-    elif seen_datetime and seen_timedelta:
-        return "mixed"
-    elif seen_nat:
-        return "nat"
-
-    return "mixed"
-
-
 cdef inline bint is_timedelta(object o):
     return PyDelta_Check(o) or util.is_timedelta64_object(o)
 

pandas/io/parsers/base_parser.py

@@ -771,7 +771,7 @@ def _infer_types(
                 result = BooleanArray(result, bool_mask)
             elif result.dtype == np.object_ and use_nullable_dtypes:
                 # read_excel sends array of datetime objects
-                inferred_type = lib.infer_datetimelike_array(result)
+                inferred_type = lib.infer_dtype(result)
                 if inferred_type != "datetime":
                     result = StringDtype().construct_array_type()._from_sequence(values)
 

pandas/tests/dtypes/test_inference.py

@@ -1354,79 +1354,6 @@ def test_infer_dtype_period_with_na(self, na_value):
         arr = np.array([na_value, Period("2011-01", freq="D"), na_value])
         assert lib.infer_dtype(arr, skipna=True) == "period"
 
-    @pytest.mark.parametrize(
-        "data",
-        [
-            [datetime(2017, 6, 12, 19, 30), datetime(2017, 3, 11, 1, 15)],
-            [Timestamp("20170612"), Timestamp("20170311")],
-            [
-                Timestamp("20170612", tz="US/Eastern"),
-                Timestamp("20170311", tz="US/Eastern"),
-            ],
-            [np.datetime64("2017-06-12"), np.datetime64("2017-03-11")],
-            [np.datetime64("2017-06-12"), datetime(2017, 3, 11, 1, 15)],
-        ],
-    )
-    def test_infer_datetimelike_array_datetime(self, data):
-        assert lib.infer_datetimelike_array(data) == "datetime"
-
-    def test_infer_datetimelike_array_date_mixed(self):
-        # GH49341 pre-2.0 we these were inferred as "datetime" and "timedelta",
-        #  respectively
-        data = [date(2017, 6, 12), Timestamp("20170311", tz="US/Eastern")]
-        assert lib.infer_datetimelike_array(data) == "mixed"
-
-        data = ([timedelta(2017, 6, 12), date(2017, 3, 11)],)
-        assert lib.infer_datetimelike_array(data) == "mixed"
-
-    @pytest.mark.parametrize(
-        "data",
-        [
-            [timedelta(2017, 6, 12), timedelta(2017, 3, 11)],
-            [np.timedelta64(2017, "D"), np.timedelta64(6, "s")],
-            [np.timedelta64(2017, "D"), timedelta(2017, 3, 11)],
-        ],
-    )
-    def test_infer_datetimelike_array_timedelta(self, data):
-        assert lib.infer_datetimelike_array(data) == "timedelta"
-
-    def test_infer_datetimelike_array_date(self):
-        arr = [date(2017, 6, 12), date(2017, 3, 11)]
-        assert lib.infer_datetimelike_array(arr) == "date"
-
-    @pytest.mark.parametrize(
-        "data",
-        [
-            ["2017-06-12", "2017-03-11"],
-            [20170612, 20170311],
-            [20170612.5, 20170311.8],
-            [Dummy(), Dummy()],
-            [Timestamp("20170612"), Timestamp("20170311", tz="US/Eastern")],
-            [Timestamp("20170612"), 20170311],
-            [timedelta(2017, 6, 12), Timestamp("20170311", tz="US/Eastern")],
-        ],
-    )
-    def test_infer_datetimelike_array_mixed(self, data):
-        assert lib.infer_datetimelike_array(data) == "mixed"
-
-    @pytest.mark.parametrize(
-        "first, expected",
-        [
-            [[None], "mixed"],
-            [[np.nan], "mixed"],
-            [[pd.NaT], "nat"],
-            [[datetime(2017, 6, 12, 19, 30), pd.NaT], "datetime"],
-            [[np.datetime64("2017-06-12"), pd.NaT], "datetime"],
-            [[date(2017, 6, 12), pd.NaT], "date"],
-            [[timedelta(2017, 6, 12), pd.NaT], "timedelta"],
-            [[np.timedelta64(2017, "D"), pd.NaT], "timedelta"],
-        ],
-    )
-    @pytest.mark.parametrize("second", [None, np.nan])
-    def test_infer_datetimelike_array_nan_nat_like(self, first, second, expected):
-        first.append(second)
-        assert lib.infer_datetimelike_array(first) == expected
-
     def test_infer_dtype_all_nan_nat_like(self):
         arr = np.array([np.nan, np.nan])
         assert lib.infer_dtype(arr, skipna=True) == "floating"