Merge branch 'main' into daydst2

Author: jbrockmendel

pandas/_libs/tslibs/timedeltas.pxd

@@ -4,6 +4,7 @@ from numpy cimport int64_t
 from .np_datetime cimport NPY_DATETIMEUNIT
 
 
+cpdef int64_t get_unit_for_round(freq, NPY_DATETIMEUNIT creso) except? -1
 # Exposed for tslib, not intended for outside use.
 cpdef int64_t delta_to_nanoseconds(
     delta, NPY_DATETIMEUNIT reso=*, bint round_ok=*

pandas/_libs/tslibs/timedeltas.pyi

@@ -68,6 +68,8 @@ UnitChoices: TypeAlias = Literal[
 ]
 _S = TypeVar("_S", bound=timedelta)
 
+def get_unit_for_round(freq, creso: int) -> int: ...
+def disallow_ambiguous_unit(unit: str | None) -> None: ...
 def ints_to_pytimedelta(
     arr: npt.NDArray[np.timedelta64],
     box: bool = ...,

pandas/_libs/tslibs/timedeltas.pyx

@@ -827,6 +827,14 @@ def _binary_op_method_timedeltalike(op, name):
 # ----------------------------------------------------------------------
 # Timedelta Construction
 
+cpdef disallow_ambiguous_unit(unit):
+    if unit in {"Y", "y", "M"}:
+        raise ValueError(
+            "Units 'M', 'Y', and 'y' are no longer supported, as they do not "
+            "represent unambiguous timedelta values durations."
+        )
+
+
 cdef int64_t parse_iso_format_string(str ts) except? -1:
     """
     Extracts and cleanses the appropriate values from a match object with
@@ -1815,11 +1823,7 @@ class Timedelta(_Timedelta):
                 )
                 raise OutOfBoundsTimedelta(msg) from err
 
-        if unit in {"Y", "y", "M"}:
-            raise ValueError(
-                "Units 'M', 'Y', and 'y' are no longer supported, as they do not "
-                "represent unambiguous timedelta values durations."
-            )
+        disallow_ambiguous_unit(unit)
 
         # GH 30543 if pd.Timedelta already passed, return it
         # check that only value is passed
@@ -1932,13 +1936,7 @@ class Timedelta(_Timedelta):
             int64_t result, unit
             ndarray[int64_t] arr
 
-        from pandas._libs.tslibs.offsets import to_offset
-
-        orig = freq
-        # In this context it is sufficiently clear that "D" this means 24H
-        freq = to_offset(freq)._maybe_to_hours()
-        freq.nanos  # raises on non-fixed freq
-        unit = delta_to_nanoseconds(to_offset(freq), self._creso)
+        unit = get_unit_for_round(freq, self._creso)
 
         arr = np.array([self._value], dtype="i8")
         try:
@@ -2295,3 +2293,12 @@ cdef bint _should_cast_to_timedelta(object obj):
     return (
         is_any_td_scalar(obj) or obj is None or obj is NaT or isinstance(obj, str)
     )
+
+
+cpdef int64_t get_unit_for_round(freq, NPY_DATETIMEUNIT creso) except? -1:
+    from pandas._libs.tslibs.offsets import to_offset
+
+    # In this context it is unambiguous that "D" represents 24 hours
+    freq = to_offset(freq)._maybe_to_hours()
+    freq.nanos  # raises on non-fixed freq
+    return delta_to_nanoseconds(freq, creso)

pandas/_libs/tslibs/timestamps.pyx

@@ -107,7 +107,7 @@ from pandas._libs.tslibs.np_datetime import (
 from pandas._libs.tslibs.offsets cimport to_offset
 from pandas._libs.tslibs.timedeltas cimport (
     _Timedelta,
-    delta_to_nanoseconds,
+    get_unit_for_round,
     is_any_td_scalar,
 )
 
@@ -1895,19 +1895,15 @@ class Timestamp(_Timestamp):
         cdef:
             int64_t nanos
 
-        # In this context it is sufficiently clear that "D" this means 24H
-        freq = to_offset(freq, is_period=False)._maybe_to_hours()
-        freq.nanos  # raises on non-fixed freq
-        nanos = delta_to_nanoseconds(freq, self._creso)
+        freq = to_offset(freq, is_period=False)
+        nanos = get_unit_for_round(freq, self._creso)
         if nanos == 0:
             if freq.nanos == 0:
                 raise ValueError("Division by zero in rounding")
 
             # e.g. self.unit == "s" and sub-second freq
             return self
 
-        # TODO: problem if nanos==0
-
         if self.tz is not None:
             value = self.tz_localize(None)._value
         else:

pandas/core/arrays/datetimelike.py

@@ -37,7 +37,6 @@
     Timedelta,
     Timestamp,
     astype_overflowsafe,
-    delta_to_nanoseconds,
     get_unit_from_dtype,
     iNaT,
     ints_to_pydatetime,
@@ -50,6 +49,7 @@
     round_nsint64,
 )
 from pandas._libs.tslibs.np_datetime import compare_mismatched_resolutions
+from pandas._libs.tslibs.timedeltas import get_unit_for_round
 from pandas._libs.tslibs.timestamps import integer_op_not_supported
 from pandas._typing import (
     ArrayLike,
@@ -2149,13 +2149,7 @@ def _round(self, freq, mode, ambiguous, nonexistent):
 
         values = self.view("i8")
         values = cast(np.ndarray, values)
-        offset = to_offset(freq)
-
-        # In this context it is clear "D" means "24H"
-        offset = offset._maybe_to_hours()
-
-        offset.nanos  # raises on non-fixed frequencies
-        nanos = delta_to_nanoseconds(offset, self._creso)
+        nanos = get_unit_for_round(freq, self._creso)
         if nanos == 0:
             # GH 52761
             return self.copy()

pandas/core/indexes/timedeltas.py

@@ -14,6 +14,7 @@
     Timedelta,
     to_offset,
 )
+from pandas._libs.tslibs.timedeltas import disallow_ambiguous_unit
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.common import (
@@ -171,11 +172,7 @@ def __new__(
         if is_scalar(data):
             cls._raise_scalar_data_error(data)
 
-        if unit in {"Y", "y", "M"}:
-            raise ValueError(
-                "Units 'M', 'Y', and 'y' are no longer supported, as they do not "
-                "represent unambiguous timedelta values durations."
-            )
+        disallow_ambiguous_unit(unit)
         if dtype is not None:
             dtype = pandas_dtype(dtype)
 

pandas/core/tools/timedeltas.py

@@ -17,6 +17,7 @@
 )
 from pandas._libs.tslibs.timedeltas import (
     Timedelta,
+    disallow_ambiguous_unit,
     parse_timedelta_unit,
 )
 
@@ -178,16 +179,11 @@ def to_timedelta(
     """
     if unit is not None:
         unit = parse_timedelta_unit(unit)
+        disallow_ambiguous_unit(unit)
 
     if errors not in ("ignore", "raise", "coerce"):
         raise ValueError("errors must be one of 'ignore', 'raise', or 'coerce'.")
 
-    if unit in {"Y", "y", "M"}:
-        raise ValueError(
-            "Units 'M', 'Y', and 'y' are no longer supported, as they do not "
-            "represent unambiguous timedelta values durations."
-        )
-
     if arg is None:
         return arg
     elif isinstance(arg, ABCSeries):