Skip to content

BUG/Compat: dt64/td64 cummin, cummax on np 1.18 #30460

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.

Sign up for GitHub

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 1 commit into from
Dec 25, 2019
Merged

BUG/Compat: dt64/td64 cummin, cummax on np 1.18 #30460

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
34 changes: 28 additions & 6 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11131,11 +11131,35 @@ def cum_func(self, axis=None, skipna=True, *args, **kwargs):
axis = self._get_axis_number(axis)

y = com.values_from_object(self).copy()
d = self._construct_axes_dict()
Copy link
Contributor

Choose a reason for hiding this comment

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

ok, in the future let's refactor if possible.

d["copy"] = False

if issubclass(y.dtype.type, (np.datetime64, np.timedelta64)):
# numpy 1.18 started sorting NaTs at the end instead of beginning,
Copy link
Contributor

Choose a reason for hiding this comment

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

also add issue numbers here for future reference (follown)

# so we need to work around to maintain backwards-consistency.
orig_dtype = y.dtype
if accum_func == np.minimum.accumulate:
# Note: the accum_func comparison fails as an "is" comparison
# Note that "y" is always a copy, so we can safely modify it
mask = isna(self)
y = y.view("i8")
y[mask] = np.iinfo(np.int64).max

result = accum_func(y.view("i8"), axis).view(orig_dtype)
if skipna:
mask = isna(self)
np.putmask(result, mask, iNaT)
elif accum_func == np.minimum.accumulate:
# Restore NaTs that we masked previously
nz = (~np.asarray(mask)).nonzero()[0]
if len(nz):
# everything up to the first non-na entry stays NaT
result[: nz[0]] = iNaT

if self.ndim == 1:
# restore dt64tz dtype
d["dtype"] = self.dtype

if skipna and issubclass(y.dtype.type, (np.datetime64, np.timedelta64)):
result = accum_func(y, axis)
mask = isna(self)
np.putmask(result, mask, iNaT)
elif skipna and not issubclass(y.dtype.type, (np.integer, np.bool_)):
mask = isna(self)
np.putmask(y, mask, mask_a)
Expand All @@ -11144,8 +11168,6 @@ def cum_func(self, axis=None, skipna=True, *args, **kwargs):
else:
result = accum_func(y, axis)

d = self._construct_axes_dict()
d["copy"] = False
return self._constructor(result, **d).__finalize__(self)

return set_function_name(cum_func, name, cls)
Expand Down
40 changes: 18 additions & 22 deletions pandas/tests/series/test_cumulative.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,6 @@
import numpy as np
import pytest

from pandas.compat.numpy import _np_version_under1p18

import pandas as pd
import pandas.util.testing as tm

Expand Down Expand Up @@ -63,53 +61,54 @@ def test_cummax(self, datetime_series):

tm.assert_series_equal(result, expected)

@pytest.mark.xfail(
not _np_version_under1p18, reason="numpy 1.18 changed min/max behavior for NaT"
)
def test_cummin_datetime64(self):
@pytest.mark.parametrize("tz", [None, "US/Pacific"])
def test_cummin_datetime64(self, tz):
s = pd.Series(
pd.to_datetime(["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-3"])
pd.to_datetime(
["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-3"]
).tz_localize(tz)
)

expected = pd.Series(
pd.to_datetime(["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-1"])
pd.to_datetime(
["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-1"]
).tz_localize(tz)
)
result = s.cummin(skipna=True)
tm.assert_series_equal(expected, result)

expected = pd.Series(
pd.to_datetime(
["NaT", "2000-1-2", "2000-1-2", "2000-1-1", "2000-1-1", "2000-1-1"]
)
).tz_localize(tz)
)
result = s.cummin(skipna=False)
tm.assert_series_equal(expected, result)

@pytest.mark.xfail(
not _np_version_under1p18, reason="numpy 1.18 changed min/max behavior for NaT"
)
def test_cummax_datetime64(self):
@pytest.mark.parametrize("tz", [None, "US/Pacific"])
def test_cummax_datetime64(self, tz):
s = pd.Series(
pd.to_datetime(["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-3"])
pd.to_datetime(
["NaT", "2000-1-2", "NaT", "2000-1-1", "NaT", "2000-1-3"]
).tz_localize(tz)
)

expected = pd.Series(
pd.to_datetime(["NaT", "2000-1-2", "NaT", "2000-1-2", "NaT", "2000-1-3"])
pd.to_datetime(
["NaT", "2000-1-2", "NaT", "2000-1-2", "NaT", "2000-1-3"]
).tz_localize(tz)
)
result = s.cummax(skipna=True)
tm.assert_series_equal(expected, result)

expected = pd.Series(
pd.to_datetime(
["NaT", "2000-1-2", "2000-1-2", "2000-1-2", "2000-1-2", "2000-1-3"]
)
).tz_localize(tz)
)
result = s.cummax(skipna=False)
tm.assert_series_equal(expected, result)

@pytest.mark.xfail(
not _np_version_under1p18, reason="numpy 1.18 changed min/max behavior for NaT"
)
def test_cummin_timedelta64(self):
s = pd.Series(pd.to_timedelta(["NaT", "2 min", "NaT", "1 min", "NaT", "3 min"]))

Expand All @@ -125,9 +124,6 @@ def test_cummin_timedelta64(self):
result = s.cummin(skipna=False)
tm.assert_series_equal(expected, result)

@pytest.mark.xfail(
not _np_version_under1p18, reason="numpy 1.18 changed min/max behavior for NaT"
)
def test_cummax_timedelta64(self):
s = pd.Series(pd.to_timedelta(["NaT", "2 min", "NaT", "1 min", "NaT", "3 min"]))

Expand Down