Fix tests

pandas-dev · mroeschke · Aug 12, 2024 · Jun 24, 2024 · Jun 24, 2024 · Jun 25, 2024
commit 10df94e66236ef62f712825c15c44157d5a32143
diff --git a/doc/source/user_guide/timeseries.rst b/doc/source/user_guide/timeseries.rst
@@ -2569,7 +2569,7 @@ Ambiguous times when localizing
 because daylight savings time (DST) in a local time zone causes some times to occur
 twice within one day ("clocks fall back"). The following options are available:
 
-* ``'raise'``: Raises a ``pytz.AmbiguousTimeError`` (the default behavior)
+* ``'raise'``: Raises a ``ValueError`` (the default behavior)
 * ``'infer'``: Attempt to determine the correct offset base on the monotonicity of the timestamps
 * ``'NaT'``: Replaces ambiguous times with ``NaT``
 * ``bool``: ``True`` represents a DST time, ``False`` represents non-DST time. An array-like of ``bool`` values is supported for a sequence of times.
@@ -2604,7 +2604,7 @@ A DST transition may also shift the local time ahead by 1 hour creating nonexist
 local times ("clocks spring forward"). The behavior of localizing a timeseries with nonexistent times
 can be controlled by the ``nonexistent`` argument. The following options are available:
 
-* ``'raise'``: Raises a ``pytz.NonExistentTimeError`` (the default behavior)
+* ``'raise'``: Raises a ``ValueError`` (the default behavior)
 * ``'NaT'``: Replaces nonexistent times with ``NaT``
 * ``'shift_forward'``: Shifts nonexistent times forward to the closest real time
 * ``'shift_backward'``: Shifts nonexistent times backward to the closest real time

diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -251,7 +251,7 @@ with the pip extra ``pip install pandas[timezone]``.
 
 
 Additionally, pandas no longer throws ``pytz`` exceptions for timezone operations leading to ambiguous or nonexistent
-times. These operations will now yield
+times. These cases will now raise a ``ValueError``.
 
 .. _whatsnew_300.api_breaking.other:
 

diff --git a/pandas/_libs/tslibs/conversion.pyx b/pandas/_libs/tslibs/conversion.pyx
@@ -744,9 +744,15 @@ cdef datetime _localize_pydatetime(datetime dt, tzinfo tz):
         It also assumes that the `tz` input is not None.
     """
     if treat_tz_as_pytz(tz):
+        import pytz
+
         # datetime.replace with pytz may be incorrect result
         # TODO: try to respect `fold` attribute
-        return tz.localize(dt, is_dst=None)
+        try:
+            return tz.localize(dt, is_dst=None)
+        except (pytz.AmbiguousTimeError, pytz.NonExistentTimeError) as err:
+            # As of pandas 3.0, we raise ValueErrors instead of pytz exceptions
+            raise ValueError(str(err)) from err
     else:
         return dt.replace(tzinfo=tz)
 

diff --git a/pandas/_libs/tslibs/nattype.pyx b/pandas/_libs/tslibs/nattype.pyx
@@ -1018,7 +1018,7 @@ class NaTType(_NaT):
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -1031,7 +1031,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns
@@ -1119,7 +1119,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -1132,7 +1132,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Raises
@@ -1214,7 +1214,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -1227,7 +1227,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Raises
@@ -1378,7 +1378,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : 'shift_forward', 'shift_backward, 'NaT', timedelta, \
 default 'raise'
@@ -1393,7 +1393,7 @@ default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns

diff --git a/pandas/_libs/tslibs/timestamps.pyx b/pandas/_libs/tslibs/timestamps.pyx
@@ -2084,7 +2084,7 @@ class Timestamp(_Timestamp):
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -2097,7 +2097,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns
@@ -2187,7 +2187,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -2200,7 +2200,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Raises
@@ -2282,7 +2282,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : {'raise', 'shift_forward', 'shift_backward, 'NaT', \
 timedelta}, default 'raise'
@@ -2295,7 +2295,7 @@ timedelta}, default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Raises
@@ -2410,7 +2410,7 @@ timedelta}, default 'raise'
             * bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates).
             * 'NaT' will return NaT for an ambiguous time.
-            * 'raise' will raise an AmbiguousTimeError for an ambiguous time.
+            * 'raise' will raise a ValueError for an ambiguous time.
 
         nonexistent : 'shift_forward', 'shift_backward, 'NaT', timedelta, \
 default 'raise'
@@ -2425,7 +2425,7 @@ default 'raise'
               closest existing time.
             * 'NaT' will return NaT where there are nonexistent times.
             * timedelta objects will shift nonexistent times by the timedelta.
-            * 'raise' will raise an NonExistentTimeError if there are
+            * 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns

diff --git a/pandas/core/arrays/datetimelike.py b/pandas/core/arrays/datetimelike.py
@@ -1780,7 +1780,7 @@ def strftime(self, date_format: str) -> npt.NDArray[np.object_]:
           a non-DST time (note that this flag is only applicable for
           ambiguous times)
         - 'NaT' will return NaT where there are ambiguous times
-        - 'raise' will raise an AmbiguousTimeError if there are ambiguous
+        - 'raise' will raise a ValueError if there are ambiguous
           times.
 
     nonexistent : 'shift_forward', 'shift_backward', 'NaT', timedelta, default 'raise'
@@ -1793,7 +1793,7 @@ def strftime(self, date_format: str) -> npt.NDArray[np.object_]:
           closest existing time
         - 'NaT' will return NaT where there are nonexistent times
         - timedelta objects will shift nonexistent times by the timedelta
-        - 'raise' will raise an NonExistentTimeError if there are
+        - 'raise' will raise a ValueError if there are
           nonexistent times.
 
     Returns

diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
@@ -972,7 +972,7 @@ def tz_localize(
               non-DST time (note that this flag is only applicable for
               ambiguous times)
             - 'NaT' will return NaT where there are ambiguous times
-            - 'raise' will raise an AmbiguousTimeError if there are ambiguous
+            - 'raise' will raise a ValueError if there are ambiguous
               times.
 
         nonexistent : 'shift_forward', 'shift_backward, 'NaT', timedelta, \
@@ -986,7 +986,7 @@ def tz_localize(
               closest existing time
             - 'NaT' will return NaT where there are nonexistent times
             - timedelta objects will shift nonexistent times by the timedelta
-            - 'raise' will raise an NonExistentTimeError if there are
+            - 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -10554,7 +10554,7 @@ def tz_localize(
               a non-DST time (note that this flag is only applicable for
               ambiguous times)
             - 'NaT' will return NaT where there are ambiguous times
-            - 'raise' will raise an AmbiguousTimeError if there are ambiguous
+            - 'raise' will raise a ValueError if there are ambiguous
               times.
         nonexistent : str, default 'raise'
             A nonexistent time does not exist in a particular timezone
@@ -10566,7 +10566,7 @@ def tz_localize(
               closest existing time
             - 'NaT' will return NaT where there are nonexistent times
             - timedelta objects will shift nonexistent times by the timedelta
-            - 'raise' will raise an NonExistentTimeError if there are
+            - 'raise' will raise a ValueError if there are
               nonexistent times.
 
         Returns

diff --git a/pandas/core/indexes/datetimes.py b/pandas/core/indexes/datetimes.py
@@ -6,7 +6,6 @@
 import warnings
 
 import numpy as np
-import pytz
 
 from pandas._libs import (
     NaT,
@@ -162,7 +161,7 @@ class DatetimeIndex(DatetimeTimedeltaMixin):
           non-DST time (note that this flag is only applicable for ambiguous
           times)
         - 'NaT' will return NaT where there are ambiguous times
-        - 'raise' will raise an AmbiguousTimeError if there are ambiguous times.
+        - 'raise' will raise a ValueError if there are ambiguous times.
     dayfirst : bool, default False
         If True, parse dates in `data` with the day first order.
     yearfirst : bool, default False
@@ -591,7 +590,7 @@ def get_loc(self, key):
         elif isinstance(key, str):
             try:
                 parsed, reso = self._parse_with_reso(key)
-            except (ValueError, pytz.NonExistentTimeError) as err:
+            except ValueError as err:
                 raise KeyError(key) from err
             self._disallow_mismatched_indexing(parsed)
 

diff --git a/pandas/tests/indexes/datetimes/methods/test_tz_localize.py b/pandas/tests/indexes/datetimes/methods/test_tz_localize.py
@@ -9,7 +9,6 @@
 from dateutil.tz import gettz
 import numpy as np
 import pytest
-import pytz
 
 from pandas import (
     DatetimeIndex,
@@ -69,10 +68,10 @@ def test_dti_tz_localize_nonexistent_raise_coerce(self):
         times = ["2015-03-08 01:00", "2015-03-08 02:00", "2015-03-08 03:00"]
         index = DatetimeIndex(times)
         tz = "US/Eastern"
-        with pytest.raises(pytz.NonExistentTimeError, match="|".join(times)):
+        with pytest.raises(ValueError, match="|".join(times)):
             index.tz_localize(tz=tz)
 
-        with pytest.raises(pytz.NonExistentTimeError, match="|".join(times)):
+        with pytest.raises(ValueError, match="|".join(times)):
             index.tz_localize(tz=tz, nonexistent="raise")
 
         result = index.tz_localize(tz=tz, nonexistent="NaT")
@@ -85,7 +84,7 @@ def test_dti_tz_localize_ambiguous_infer(self, tz):
         # November 6, 2011, fall back, repeat 2 AM hour
         # With no repeated hours, we cannot infer the transition
         dr = date_range(datetime(2011, 11, 6, 0), periods=5, freq=offsets.Hour())
-        with pytest.raises(pytz.AmbiguousTimeError, match="Cannot infer dst time"):
+        with pytest.raises(ValueError, match="Cannot infer dst time"):
             dr.tz_localize(tz)
 
     def test_dti_tz_localize_ambiguous_infer2(self, tz, unit):
@@ -117,7 +116,7 @@ def test_dti_tz_localize_ambiguous_infer3(self, tz):
     def test_dti_tz_localize_ambiguous_times(self, tz):
         # March 13, 2011, spring forward, skip from 2 AM to 3 AM
         dr = date_range(datetime(2011, 3, 13, 1, 30), periods=3, freq=offsets.Hour())
-        with pytest.raises(pytz.NonExistentTimeError, match="2011-03-13 02:30:00"):
+        with pytest.raises(ValueError, match="2011-03-13 02:30:00"):
             dr.tz_localize(tz)
 
         # after dst transition, it works
@@ -127,7 +126,7 @@ def test_dti_tz_localize_ambiguous_times(self, tz):
 
         # November 6, 2011, fall back, repeat 2 AM hour
         dr = date_range(datetime(2011, 11, 6, 1, 30), periods=3, freq=offsets.Hour())
-        with pytest.raises(pytz.AmbiguousTimeError, match="Cannot infer dst time"):
+        with pytest.raises(ValueError, match="Cannot infer dst time"):
             dr.tz_localize(tz)
 
         # UTC is OK
@@ -163,11 +162,11 @@ def test_dti_tz_localize(self, prefix):
         tm.assert_numpy_array_equal(dti3.values, dti_utc.values)
 
         dti = date_range(start="11/6/2011 1:59", end="11/6/2011 2:00", freq="ms")
-        with pytest.raises(pytz.AmbiguousTimeError, match="Cannot infer dst time"):
+        with pytest.raises(ValueError, match="Cannot infer dst time"):
             dti.tz_localize(tzstr)
 
         dti = date_range(start="3/13/2011 1:59", end="3/13/2011 2:00", freq="ms")
-        with pytest.raises(pytz.NonExistentTimeError, match="2011-03-13 02:00:00"):
+        with pytest.raises(ValueError, match="2011-03-13 02:00:00"):
             dti.tz_localize(tzstr)
 
     def test_dti_tz_localize_utc_conversion(self, tz):
@@ -184,7 +183,7 @@ def test_dti_tz_localize_utc_conversion(self, tz):
         # DST ambiguity, this should fail
         rng = date_range("3/11/2012", "3/12/2012", freq="30min")
         # Is this really how it should fail??
-        with pytest.raises(pytz.NonExistentTimeError, match="2012-03-11 02:00:00"):
+        with pytest.raises(ValueError, match="2012-03-11 02:00:00"):
             rng.tz_localize(tz)
 
     def test_dti_tz_localize_roundtrip(self, tz_aware_fixture):

diff --git a/pandas/tests/indexes/datetimes/test_constructors.py b/pandas/tests/indexes/datetimes/test_constructors.py
@@ -14,7 +14,6 @@
 from dateutil.tz import gettz
 import numpy as np
 import pytest
-import pytz
 
 from pandas._libs.tslibs import (
     astype_overflowsafe,
@@ -750,7 +749,7 @@ def test_disallow_setting_tz(self):
         [
             None,
             "America/Los_Angeles",
-            pytz.timezone("America/Los_Angeles"),
+            zoneinfo.ZoneInfo("America/Los_Angeles"),
             Timestamp("2000", tz="America/Los_Angeles").tz,
         ],
     )
@@ -765,8 +764,8 @@ def test_constructor_start_end_with_tz(self, tz):
             freq="D",
         )
         tm.assert_index_equal(result, expected)
-        # Especially assert that the timezone is consistent for pytz
-        assert pytz.timezone("America/Los_Angeles") is result.tz
+        # Especially assert that the timezone is consistent for zoneinfo
+        assert zoneinfo.ZoneInfo("America/Los_Angeles") is result.tz
 
     @pytest.mark.parametrize("tz", ["US/Pacific", "US/Eastern", "Asia/Tokyo"])
     def test_constructor_with_non_normalized_pytz(self, tz):
@@ -984,6 +983,7 @@ def test_dti_ambiguous_matches_timestamp(self, tz, use_str, box_cls, request):
         # GH#47471 check that we get the same raising behavior in the DTI
         # constructor and Timestamp constructor
         if isinstance(tz, str) and tz.startswith("pytz/"):
+            pytz = pytest.importorskip("pytz")
             tz = pytz.timezone(tz.removeprefix("pytz/"))
         dtstr = "2013-11-03 01:59:59.999999"
         item = dtstr
@@ -1000,7 +1000,7 @@ def test_dti_ambiguous_matches_timestamp(self, tz, use_str, box_cls, request):
             mark = pytest.mark.xfail(reason="We implicitly get fold=0.")
             request.applymarker(mark)
 
-        with pytest.raises(pytz.AmbiguousTimeError, match=dtstr):
+        with pytest.raises(ValueError, match=dtstr):
             box_cls(item, tz=tz)
 
     @pytest.mark.parametrize("tz", [None, "UTC", "US/Pacific"])