diff --git a/doc/source/whatsnew/v1.2.0.rst b/doc/source/whatsnew/v1.2.0.rst index ac930b3e77785..49ea516b2bfad 100644 --- a/doc/source/whatsnew/v1.2.0.rst +++ b/doc/source/whatsnew/v1.2.0.rst @@ -590,6 +590,7 @@ Datetimelike - Bug in :meth:`Series.isin` with ``datetime64[ns]`` dtype and :meth:`.DatetimeIndex.isin` failing to consider timezone-aware and timezone-naive datetimes as always different (:issue:`35728`) - Bug in :meth:`Series.isin` with ``PeriodDtype`` dtype and :meth:`PeriodIndex.isin` failing to consider arguments with different ``PeriodDtype`` as always different (:issue:`37528`) - Bug in :class:`Period` constructor now correctly handles nanoseconds in the ``value`` argument (:issue:`34621` and :issue:`17053`) +- Bug in :meth:`DataFrame.first` and :meth:`Series.first` returning two months for offset one month when first day is last calendar day (:issue:`29623`) Timedelta ^^^^^^^^^ diff --git a/pandas/core/generic.py b/pandas/core/generic.py index 4a9e020a0fe46..26a09058c1c52 100644 --- a/pandas/core/generic.py +++ b/pandas/core/generic.py @@ -8426,7 +8426,11 @@ def first(self: FrameOrSeries, offset) -> FrameOrSeries: return self offset = to_offset(offset) - end_date = end = self.index[0] + offset + if not isinstance(offset, Tick) and offset.is_on_offset(self.index[0]): + # GH#29623 if first value is end of period + end_date = end = self.index[0] + else: + end_date = end = self.index[0] + offset # Tick-like, e.g. 3 weeks if isinstance(offset, Tick): diff --git a/pandas/tests/frame/methods/test_first_and_last.py b/pandas/tests/frame/methods/test_first_and_last.py index d21e1eee54e16..4ee7016004137 100644 --- a/pandas/tests/frame/methods/test_first_and_last.py +++ b/pandas/tests/frame/methods/test_first_and_last.py @@ -3,7 +3,7 @@ """ import pytest -from pandas import DataFrame +from pandas import DataFrame, bdate_range import pandas._testing as tm @@ -69,3 +69,13 @@ def test_last_subset(self, frame_or_series): result = ts[:0].last("3M") tm.assert_equal(result, ts[:0]) + + @pytest.mark.parametrize("start, periods", [("2010-03-31", 1), ("2010-03-30", 2)]) + def test_first_with_first_day_last_of_month(self, frame_or_series, start, periods): + # GH#29623 + x = frame_or_series([1] * 100, index=bdate_range(start, periods=100)) + result = x.first("1M") + expected = frame_or_series( + [1] * periods, index=bdate_range(start, periods=periods) + ) + tm.assert_equal(result, expected)