Skip to content

BUG: DatetimeIndex.is_year_start breaks on custom business days frequencies bigger then 1C #58665

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions doc/source/whatsnew/v3.0.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -419,6 +419,7 @@ Interval
Indexing
^^^^^^^^
- Bug in :meth:`DataFrame.__getitem__` returning modified columns when called with ``slice`` in Python 3.12 (:issue:`57500`)
- Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` does not raise on Custom business days frequencies bigger then "1C" (:issue:`58664`)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you put this under Datetimelike?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks, updated

-

Missing
Expand Down
2 changes: 1 addition & 1 deletion pandas/_libs/tslibs/fields.pyi
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ def get_date_name_field(
def get_start_end_field(
dtindex: npt.NDArray[np.int64],
field: str,
freqstr: str | None = ...,
freq_name: str | None = ...,
month_kw: int = ...,
reso: int = ..., # NPY_DATETIMEUNIT
) -> npt.NDArray[np.bool_]: ...
Expand Down
13 changes: 6 additions & 7 deletions pandas/_libs/tslibs/fields.pyx
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ cdef bint _is_on_month(int month, int compare_month, int modby) noexcept nogil:
def get_start_end_field(
const int64_t[:] dtindex,
str field,
str freqstr=None,
str freq_name=None,
int month_kw=12,
NPY_DATETIMEUNIT reso=NPY_FR_ns,
):
Expand All @@ -223,7 +223,7 @@ def get_start_end_field(
----------
dtindex : ndarray[int64]
field : str
frestr : str or None, default None
freq_name : str or None, default None
month_kw : int, default 12
reso : NPY_DATETIMEUNIT, default NPY_FR_ns

Expand All @@ -243,18 +243,17 @@ def get_start_end_field(

out = np.zeros(count, dtype="int8")

if freqstr:
if freqstr == "C":
if freq_name:
if freq_name == "C":
raise ValueError(f"Custom business days is not supported by {field}")
is_business = freqstr[0] == "B"
is_business = freq_name[0] == "B"

# YearBegin(), BYearBegin() use month = starting month of year.
# QuarterBegin(), BQuarterBegin() use startingMonth = starting
# month of year. Other offsets use month, startingMonth as ending
# month of year.

if (freqstr[0:2] in ["MS", "QS", "YS"]) or (
freqstr[1:3] in ["MS", "QS", "YS"]):
if freq_name.lstrip("B")[0:2] in ["MS", "QS", "YS"]:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if freq_name.lstrip("B")[0:2] in ["MS", "QS", "YS"]:
if freq_name.lstrip("B")[0:2] in ["MS", "QS", "YS"]:

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

end_month = 12 if month_kw == 1 else month_kw - 1
start_month = month_kw
else:
Expand Down
6 changes: 3 additions & 3 deletions pandas/_libs/tslibs/timestamps.pyx
Original file line number Diff line number Diff line change
Expand Up @@ -579,15 +579,15 @@ cdef class _Timestamp(ABCTimestamp):
if freq:
kwds = freq.kwds
month_kw = kwds.get("startingMonth", kwds.get("month", 12))
freqstr = freq.freqstr
freq_name = freq.name
else:
month_kw = 12
freqstr = None
freq_name = None

val = self._maybe_convert_value_to_local()

out = get_start_end_field(np.array([val], dtype=np.int64),
field, freqstr, month_kw, self._creso)
field, freq_name, month_kw, self._creso)
return out[0]

@property
Expand Down
6 changes: 5 additions & 1 deletion pandas/core/arrays/datetimes.py
Original file line number Diff line number Diff line change
Expand Up @@ -145,8 +145,12 @@ def f(self):
kwds = freq.kwds
month_kw = kwds.get("startingMonth", kwds.get("month", 12))

if freq is not None:
freq_name = freq.name
else:
freq_name = None
result = fields.get_start_end_field(
values, field, self.freqstr, month_kw, reso=self._creso
values, field, freq_name, month_kw, reso=self._creso
)
else:
result = fields.get_date_field(values, field, reso=self._creso)
Expand Down
7 changes: 7 additions & 0 deletions pandas/tests/indexes/datetimes/test_scalar_compat.py
Original file line number Diff line number Diff line change
Expand Up @@ -328,3 +328,10 @@ def test_dti_is_month_start_custom(self):
msg = "Custom business days is not supported by is_month_start"
with pytest.raises(ValueError, match=msg):
dti.is_month_start

def test_dti_is_year_start_freq_custom_business_day_with_digit(self):
# GH#58664
dr = date_range("2020-01-01", periods=2, freq="2C")
msg = "Custom business days is not supported by is_year_start"
with pytest.raises(ValueError, match=msg):
dr.is_year_start
Loading