DEPR: unit->input_unit in to_datetime, to_timedelta

Author: jbrockmendel

asv_bench/benchmarks/categoricals.py

@@ -79,7 +79,8 @@ def setup(self):
             "int": np.random.randint(2**16, size=154),
             "float": sys.maxsize * np.random.random((38,)),
             "timestamp": [
-                pd.Timestamp(x, unit="s") for x in np.random.randint(2**18, size=578)
+                pd.Timestamp(x, input_unit="s")
+                for x in np.random.randint(2**18, size=578)
             ],
         }
 

asv_bench/benchmarks/groupby.py

@@ -1130,7 +1130,7 @@ def setup(self):
         index = MultiIndex.from_product(
             [
                 np.arange(num_groups),
-                to_timedelta(np.arange(num_timedeltas), unit="s"),
+                to_timedelta(np.arange(num_timedeltas), input_unit="s"),
             ],
             names=["groups", "timedeltas"],
         )

asv_bench/benchmarks/inference.py

@@ -118,22 +118,22 @@ def setup(self):
     # speed of int64, uint64 and float64 paths should be comparable
 
     def time_nanosec_int64(self):
-        to_datetime(self.ts_nanosec, unit="ns")
+        to_datetime(self.ts_nanosec, input_unit="ns")
 
     def time_nanosec_uint64(self):
-        to_datetime(self.ts_nanosec_uint, unit="ns")
+        to_datetime(self.ts_nanosec_uint, input_unit="ns")
 
     def time_nanosec_float64(self):
-        to_datetime(self.ts_nanosec_float, unit="ns")
+        to_datetime(self.ts_nanosec_float, input_unit="ns")
 
     def time_sec_uint64(self):
-        to_datetime(self.ts_sec_uint, unit="s")
+        to_datetime(self.ts_sec_uint, input_unit="s")
 
     def time_sec_int64(self):
-        to_datetime(self.ts_sec, unit="s")
+        to_datetime(self.ts_sec, input_unit="s")
 
     def time_sec_float64(self):
-        to_datetime(self.ts_sec_float, unit="s")
+        to_datetime(self.ts_sec_float, input_unit="s")
 
 
 class ToDatetimeYYYYMMDD:
@@ -250,10 +250,10 @@ def setup(self, cache):
         self.dup_string_with_tz = ["2000-02-11 15:00:00-0800"] * N
 
     def time_unique_seconds_and_unit(self, cache):
-        to_datetime(self.unique_numeric_seconds, unit="s", cache=cache)
+        to_datetime(self.unique_numeric_seconds, input_unit="s", cache=cache)
 
     def time_dup_seconds_and_unit(self, cache):
-        to_datetime(self.dup_numeric_seconds, unit="s", cache=cache)
+        to_datetime(self.dup_numeric_seconds, input_unit="s", cache=cache)
 
     def time_dup_string_dates(self, cache):
         to_datetime(self.dup_string_dates, cache=cache)
@@ -275,7 +275,7 @@ def setup(self):
             self.str_seconds.append(f"00:00:{i:02d}")
 
     def time_convert_int(self):
-        to_timedelta(self.ints, unit="s")
+        to_timedelta(self.ints, input_unit="s")
 
     def time_convert_string_days(self):
         to_timedelta(self.str_days)

asv_bench/benchmarks/tslibs/timedelta.py

@@ -14,13 +14,13 @@ class TimedeltaConstructor:
     def setup(self):
         self.nptimedelta64 = np.timedelta64(3600)
         self.dttimedelta = datetime.timedelta(seconds=3600)
-        self.td = Timedelta(3600, unit="s")
+        self.td = Timedelta(3600, input_unit="s")
 
     def time_from_int(self):
         Timedelta(123456789)
 
     def time_from_unit(self):
-        Timedelta(1, unit="D")
+        Timedelta(1, input_unit="D")
 
     def time_from_components(self):
         Timedelta(

doc/source/user_guide/timedeltas.rst

@@ -35,7 +35,7 @@ You can construct a ``Timedelta`` scalar through various arguments, including `I
    pd.Timedelta(days=1, seconds=1)
 
    # integers with a unit
-   pd.Timedelta(1, unit="D")
+   pd.Timedelta(1, input_unit="D")
 
    # from a datetime.timedelta/np.timedelta64
    pd.Timedelta(datetime.timedelta(days=1, seconds=1))
@@ -93,8 +93,8 @@ is numeric:
 
 .. ipython:: python
 
-   pd.to_timedelta(np.arange(5), unit="s")
-   pd.to_timedelta(np.arange(5), unit="D")
+   pd.to_timedelta(np.arange(5), input_unit="s")
+   pd.to_timedelta(np.arange(5), input_unit="D")
 
 .. warning::
     If a string or array of strings is passed as an input then the ``unit`` keyword
@@ -199,7 +199,7 @@ You can fillna on timedeltas, passing a timedelta to get a particular value.
 .. ipython:: python
 
    y.fillna(pd.Timedelta(0))
-   y.fillna(pd.Timedelta(10, unit="s"))
+   y.fillna(pd.Timedelta(10, input_unit="s"))
    y.fillna(pd.Timedelta("-1 days, 00:00:05"))
 
 You can also negate, multiply and use ``abs`` on ``Timedeltas``:

doc/source/user_guide/timeseries.rst

@@ -353,8 +353,8 @@ as timezone-naive timestamps and then localize to the appropriate timezone:
 
    .. ipython:: python
 
-      pd.to_datetime([1490195805.433, 1490195805.433502912], unit="s")
-      pd.to_datetime(1490195805433502912, unit="ns")
+      pd.to_datetime([1490195805.433, 1490195805.433502912], input_unit="s")
+      pd.to_datetime(1490195805433502912, input_unit="ns")
 
 .. seealso::
 
@@ -389,14 +389,14 @@ of a ``DatetimeIndex``. For example, to use 1960-01-01 as the starting date:
 
 .. ipython:: python
 
-   pd.to_datetime([1, 2, 3], unit="D", origin=pd.Timestamp("1960-01-01"))
+   pd.to_datetime([1, 2, 3], input_unit="D", origin=pd.Timestamp("1960-01-01"))
 
 The default is set at ``origin='unix'``, which defaults to ``1970-01-01 00:00:00``.
 Commonly called 'unix epoch' or POSIX time.
 
 .. ipython:: python
 
-   pd.to_datetime([1, 2, 3], unit="D")
+   pd.to_datetime([1, 2, 3], input_unit="D")
 
 .. _timeseries.daterange:
 
@@ -2633,7 +2633,7 @@ Transform nonexistent times to ``NaT`` or shift the times.
     dti
     dti.tz_localize("Europe/Warsaw", nonexistent="shift_forward")
     dti.tz_localize("Europe/Warsaw", nonexistent="shift_backward")
-    dti.tz_localize("Europe/Warsaw", nonexistent=pd.Timedelta(1, unit="h"))
+    dti.tz_localize("Europe/Warsaw", nonexistent=pd.Timedelta(1, input_unit="h"))
     dti.tz_localize("Europe/Warsaw", nonexistent="NaT")
 
 

doc/source/whatsnew/v3.0.0.rst

@@ -667,6 +667,7 @@ Other Deprecations
 - Deprecated allowing ``fill_value`` that cannot be held in the original dtype (excepting NA values for integer and bool dtypes) in :meth:`Series.unstack` and :meth:`DataFrame.unstack` (:issue:`12189`, :issue:`53868`)
 - Deprecated allowing ``fill_value`` that cannot be held in the original dtype (excepting NA values for integer and bool dtypes) in :meth:`Series.shift` and :meth:`DataFrame.shift` (:issue:`53802`)
 - Deprecated slicing on a :class:`Series` or :class:`DataFrame` with a :class:`DatetimeIndex` using a ``datetime.date`` object, explicitly cast to :class:`Timestamp` instead (:issue:`35830`)
+- Deprecated the ``unit`` keyword in :meth:`to_datetime` and :meth:`to_timedelta`, use ``input_unit`` instead (:issue:`62097`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.prior_deprecations:

pandas/_libs/tslibs/conversion.pyx

@@ -117,7 +117,7 @@ def cast_from_unit_vectorized(
             #  but not clear what 2.5 "M" corresponds to, so we will
             #  disallow that case.
             raise ValueError(
-                f"Conversion of non-round float with unit={unit} "
+                f"Conversion of non-round float with input_unit={unit} "
                 "is ambiguous"
             )
 
@@ -194,7 +194,7 @@ cdef int64_t cast_from_unit(
             #  but not clear what 2.5 "M" corresponds to, so we will
             #  disallow that case.
             raise ValueError(
-                f"Conversion of non-round float with unit={unit} "
+                f"Conversion of non-round float with input_unit={unit} "
                 "is ambiguous"
             )
         # GH#47266 go through np.datetime64 to avoid weird results e.g. with "Y"

pandas/_libs/tslibs/offsets.pyx

@@ -5382,7 +5382,7 @@ cpdef to_offset(freq, bint is_period=False):
                     # For these prefixes, we have something like "3h" or
                     #  "2.5min", so we can construct a Timedelta with the
                     #  matching unit and get our offset from delta_to_tick
-                    td = Timedelta(1, unit=name)
+                    td = Timedelta(1, input_unit=name)
                     off = delta_to_tick(td)
                     offset = off * float(stride)
                     if n != 0:

pandas/_libs/tslibs/timedeltas.pyx

@@ -1132,7 +1132,7 @@ cdef class _Timedelta(timedelta):
 
         Examples
         --------
-        >>> pd.Timedelta(1, "us").value
+        >>> pd.Timedelta(1, input_unit="us").value
         1000
         """
         try:
@@ -1174,7 +1174,7 @@ cdef class _Timedelta(timedelta):
 
         Examples
         --------
-        >>> td = pd.Timedelta(1, "d")
+        >>> td = pd.Timedelta(1, input_unit="d")
         >>> td.days
         1
 
@@ -1216,7 +1216,7 @@ cdef class _Timedelta(timedelta):
 
         **Using integer input**
 
-        >>> td = pd.Timedelta(42, unit='s')
+        >>> td = pd.Timedelta(42, input_unit='s')
         >>> td.seconds
         42
         """
@@ -1256,7 +1256,7 @@ cdef class _Timedelta(timedelta):
 
         **Using integer input**
 
-        >>> td = pd.Timedelta(42, unit='us')
+        >>> td = pd.Timedelta(42, input_unit='us')
         >>> td.microseconds
         42
         """
@@ -1308,7 +1308,8 @@ cdef class _Timedelta(timedelta):
 
         Examples
         --------
-        >>> td = pd.Timedelta(42, unit='us')
+        >>> td = pd.Timedelta(42, input_unit='us')
+        >>> ts.unit
         'ns'
         """
         return npy_unit_to_abbrev(self._creso)
@@ -1652,7 +1653,7 @@ cdef class _Timedelta(timedelta):
         >>> td.asm8
         numpy.timedelta64(3005000,'ns')
 
-        >>> td = pd.Timedelta(42, unit='ns')
+        >>> td = pd.Timedelta(42, input_unit='ns')
         >>> td.asm8
         numpy.timedelta64(42,'ns')
         """
@@ -1696,7 +1697,7 @@ cdef class _Timedelta(timedelta):
         >>> td.resolution_string
         's'
 
-        >>> td = pd.Timedelta(36, unit='us')
+        >>> td = pd.Timedelta(36, input_unit='us')
         >>> td.resolution_string
         'us'
         """
@@ -1743,7 +1744,7 @@ cdef class _Timedelta(timedelta):
 
         **Using integer input**
 
-        >>> td = pd.Timedelta(42, unit='ns')
+        >>> td = pd.Timedelta(42, input_unit='ns')
         >>> td.nanoseconds
         42
         """
@@ -1995,7 +1996,7 @@ class Timedelta(_Timedelta):
     --------
     Here we initialize Timedelta object with both value and unit
 
-    >>> td = pd.Timedelta(1, "D")
+    >>> td = pd.Timedelta(1, input_unit="D")
     >>> td
     Timedelta('1 days 00:00:00')
 
@@ -2011,7 +2012,18 @@ class Timedelta(_Timedelta):
     _req_any_kwargs_new = {"weeks", "days", "hours", "minutes", "seconds",
                            "milliseconds", "microseconds", "nanoseconds"}
 
-    def __new__(cls, object value=_no_input, unit=None, **kwargs):
+    def __new__(cls, object value=_no_input, unit=None, *, input_unit=None, **kwargs):
+        if unit is not None:
+            if input_unit is not None:
+                raise ValueError("Specify only 'input_unit', not 'unit'")
+            from pandas.errors import Pandas4Warning
+            warnings.warn(
+                "The 'unit' keyword is deprecated. Use 'input_unit' instead.",
+                Pandas4Warning,
+                stacklevel=find_stack_level(),
+            )
+            input_unit = unit
+
         unsupported_kwargs = set(kwargs)
         unsupported_kwargs.difference_update(cls._req_any_kwargs_new)
         if unsupported_kwargs or (
@@ -2066,12 +2078,12 @@ class Timedelta(_Timedelta):
                 )
                 raise OutOfBoundsTimedelta(msg) from err
 
-        disallow_ambiguous_unit(unit)
+        disallow_ambiguous_unit(input_unit)
 
         # GH 30543 if pd.Timedelta already passed, return it
         # check that only value is passed
         if isinstance(value, _Timedelta):
-            # 'unit' is benign in this case, but e.g. days or seconds
+            # 'input_unit' is benign in this case, but e.g. days or seconds
             #  doesn't make sense here.
             if len(kwargs):
                 # GH#48898
@@ -2082,8 +2094,10 @@ class Timedelta(_Timedelta):
                 )
             return value
         elif isinstance(value, str):
-            if unit is not None:
-                raise ValueError("unit must not be specified if the value is a str")
+            if input_unit is not None:
+                raise ValueError(
+                    "input_unit must not be specified if the value is a str"
+                )
             if (len(value) > 0 and value[0] == "P") or (
                 len(value) > 1 and value[:2] == "-P"
             ):
@@ -2140,8 +2154,8 @@ class Timedelta(_Timedelta):
 
         elif is_integer_object(value) or is_float_object(value):
             # unit=None is de-facto 'ns'
-            unit = parse_timedelta_unit(unit)
-            value = convert_to_timedelta64(value, unit)
+            input_unit = parse_timedelta_unit(input_unit)
+            value = convert_to_timedelta64(value, input_unit)
         elif checknull_with_nat_and_na(value):
             return NaT
         else: