DOC/ENH: Holiday exclusion argument

doc/source/whatsnew/v3.0.0.rst

@@ -64,6 +64,7 @@ Other enhancements
 - :meth:`Series.nlargest` uses a 'stable' sort internally and will preserve original ordering.
 - :class:`ArrowDtype` now supports ``pyarrow.JsonType`` (:issue:`60958`)
 - :class:`DataFrameGroupBy` and :class:`SeriesGroupBy` methods ``sum``, ``mean``, ``median``, ``prod``, ``min``, ``max``, ``std``, ``var`` and ``sem`` now accept ``skipna`` parameter (:issue:`15675`)
+- :class:`Holiday` has gained the constructor argument and field ``exclude_dates`` to exclude specific datetimes from a custom holiday calendar (:issue:`54382`)
 - :class:`Rolling` and :class:`Expanding` now support ``nunique`` (:issue:`26958`)
 - :class:`Rolling` and :class:`Expanding` now support aggregations ``first`` and ``last`` (:issue:`33155`)
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)

pandas/tests/tseries/holiday/test_holiday.py

@@ -353,3 +353,57 @@ def test_holidays_with_timezone_specified_but_no_occurences():
     expected_results.index = expected_results.index.as_unit("ns")
 
     tm.assert_equal(test_case, expected_results)
+
+
+def test_holiday_with_exclusion():
+    # GH 54382
+    start = Timestamp("2020-05-01")
+    end = Timestamp("2025-05-31")
+    exclude = [Timestamp("2022-05-30")]  # Queen's platinum Jubilee
+    default_uk_spring_bank_holiday: Holiday = Holiday(
+        "UK Spring Bank Holiday",
+        month=5,
+        day=31,
+        offset=DateOffset(weekday=MO(-1)),
+    )
+
+    queens_jubilee_uk_spring_bank_holiday: Holiday = Holiday(
+        "Queen's Jubilee UK Spring Bank Holiday",
+        month=5,
+        day=31,
+        offset=DateOffset(weekday=MO(-1)),
+        exclude_dates=exclude,
+    )
+
+    original_dates = list(default_uk_spring_bank_holiday.dates(start, end))
+    exclusion_dates = list(queens_jubilee_uk_spring_bank_holiday.dates(start, end))
+
+    assert all(ex in original_dates for ex in exclude)
+    assert all(ex not in exclusion_dates for ex in exclude)
+    assert set(exclusion_dates).issubset(original_dates)
+
+
+def test_holiday_with_multiple_exclusions():
+    start = Timestamp("2000-01-01")
+    end = Timestamp("2100-05-31")
+    exclude = [
+        Timestamp("2025-01-01"),
+        Timestamp("2042-01-01"),
+        Timestamp("2061-01-01"),
+    ]  # Yakudoshi new year
+    default_japan_new_year: Holiday = Holiday(
+        "Japan New Year",
+        month=1,
+        day=1,
+    )
+
+    yakudoshi_new_year: Holiday = Holiday(
+        "Yakudoshi New Year", month=1, day=1, exclude_dates=exclude
+    )
+
+    original_dates = list(default_japan_new_year.dates(start, end))
+    exclusion_dates = list(yakudoshi_new_year.dates(start, end))
+
+    assert all(ex in original_dates for ex in exclude)
+    assert all(ex not in exclusion_dates for ex in exclude)
+    assert set(exclusion_dates).issubset(original_dates)

pandas/tseries/holiday.py

@@ -169,6 +169,7 @@ def __init__(
         start_date=None,
         end_date=None,
         days_of_week: tuple | None = None,
+        exclude_dates: DatetimeIndex | None = None,
     ) -> None:
         """
         Parameters
@@ -193,6 +194,8 @@ class from pandas.tseries.offsets, default None
         days_of_week : tuple of int or dateutil.relativedelta weekday strs, default None
             Provide a tuple of days e.g  (0,1,2,3,) for Monday Through Thursday
             Monday=0,..,Sunday=6
+        exclude_dates : DatetimeIndex or default None
+            Specific dates to exclude e.g. skipping a specific year's holiday
 
         Examples
         --------
@@ -257,6 +260,9 @@ class from pandas.tseries.offsets, default None
         self.observance = observance
         assert days_of_week is None or type(days_of_week) == tuple
         self.days_of_week = days_of_week
+        if exclude_dates is not None and type(exclude_dates) != DatetimeIndex:
+            raise ValueError("exclude_dates must be None or of type DatetimeIndex.")
+        self.exclude_dates = exclude_dates
 
     def __repr__(self) -> str:
         info = ""
@@ -328,6 +334,9 @@ def dates(
         holiday_dates = holiday_dates[
             (holiday_dates >= filter_start_date) & (holiday_dates <= filter_end_date)
         ]
+
+        if self.exclude_dates:
+            holiday_dates = holiday_dates.difference(self.exclude_dates)
         if return_name:
             return Series(self.name, index=holiday_dates)
         return holiday_dates