Skip to content

BUG: partial-timestamp slicing near the end of year/quarter/month #31064

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
merged 2 commits into from
Jan 18, 2020
Merged
Show file tree
Hide file tree
Changes from all 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
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v1.1.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ Interval

Indexing
^^^^^^^^

- Bug in slicing on a :class:`DatetimeIndex` with a partial-timestamp dropping high-resolution indices near the end of a year, quarter, or month (:issue:`31064`)
-
-

Expand Down
27 changes: 17 additions & 10 deletions pandas/core/indexes/datetimes.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,14 @@

import numpy as np

from pandas._libs import NaT, Timestamp, index as libindex, lib, tslib as libts
from pandas._libs import (
NaT,
Timedelta,
Timestamp,
index as libindex,
lib,
tslib as libts,
)
from pandas._libs.tslibs import ccalendar, fields, parsing, timezones
from pandas.util._decorators import Appender, Substitution, cache_readonly

Expand All @@ -31,7 +38,7 @@
import pandas.core.tools.datetimes as tools

from pandas.tseries.frequencies import Resolution, to_offset
from pandas.tseries.offsets import Nano, prefix_mapping
from pandas.tseries.offsets import prefix_mapping


def _new_DatetimeIndex(cls, d):
Expand Down Expand Up @@ -519,27 +526,27 @@ def _parsed_string_to_bounds(self, reso, parsed):
raise KeyError
if reso == "year":
start = Timestamp(parsed.year, 1, 1)
end = Timestamp(parsed.year, 12, 31, 23, 59, 59, 999999)
end = Timestamp(parsed.year + 1, 1, 1) - Timedelta(nanoseconds=1)
elif reso == "month":
d = ccalendar.get_days_in_month(parsed.year, parsed.month)
start = Timestamp(parsed.year, parsed.month, 1)
end = Timestamp(parsed.year, parsed.month, d, 23, 59, 59, 999999)
end = start + Timedelta(days=d, nanoseconds=-1)
elif reso == "quarter":
qe = (((parsed.month - 1) + 2) % 12) + 1 # two months ahead
d = ccalendar.get_days_in_month(parsed.year, qe) # at end of month
start = Timestamp(parsed.year, parsed.month, 1)
end = Timestamp(parsed.year, qe, d, 23, 59, 59, 999999)
end = Timestamp(parsed.year, qe, 1) + Timedelta(days=d, nanoseconds=-1)
elif reso == "day":
start = Timestamp(parsed.year, parsed.month, parsed.day)
end = start + timedelta(days=1) - Nano(1)
end = start + Timedelta(days=1, nanoseconds=-1)
elif reso == "hour":
start = Timestamp(parsed.year, parsed.month, parsed.day, parsed.hour)
end = start + timedelta(hours=1) - Nano(1)
end = start + Timedelta(hours=1, nanoseconds=-1)
elif reso == "minute":
start = Timestamp(
parsed.year, parsed.month, parsed.day, parsed.hour, parsed.minute
)
end = start + timedelta(minutes=1) - Nano(1)
end = start + Timedelta(minutes=1, nanoseconds=-1)
elif reso == "second":
start = Timestamp(
parsed.year,
Expand All @@ -549,7 +556,7 @@ def _parsed_string_to_bounds(self, reso, parsed):
parsed.minute,
parsed.second,
)
end = start + timedelta(seconds=1) - Nano(1)
end = start + Timedelta(seconds=1, nanoseconds=-1)
elif reso == "microsecond":
start = Timestamp(
parsed.year,
Expand All @@ -560,7 +567,7 @@ def _parsed_string_to_bounds(self, reso, parsed):
parsed.second,
parsed.microsecond,
)
end = start + timedelta(microseconds=1) - Nano(1)
end = start + Timedelta(microseconds=1, nanoseconds=-1)
# GH 24076
# If an incoming date string contained a UTC offset, need to localize
# the parsed date to this offset first before aligning with the index's
Expand Down
20 changes: 20 additions & 0 deletions pandas/tests/indexes/datetimes/test_partial_slicing.py
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,26 @@ def test_slice_year(self):
expected = slice(3288, 3653)
assert result == expected

@pytest.mark.parametrize(
"partial_dtime",
[
"2019",
"2019Q4",
"Dec 2019",
"2019-12-31",
"2019-12-31 23",
"2019-12-31 23:59",
],
)
def test_slice_end_of_period_resolution(self, partial_dtime):
# GH#31064
dti = date_range("2019-12-31 23:59:55.999999999", periods=10, freq="s")

ser = pd.Series(range(10), index=dti)
result = ser[partial_dtime]
expected = ser.iloc[:5]
tm.assert_series_equal(result, expected)

def test_slice_quarter(self):
dti = date_range(freq="D", start=datetime(2000, 6, 1), periods=500)

Expand Down