Skip to content

COMPAT: numpy compat with NaT != NaT, #12049 #12058

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
Jan 16, 2016
+55 −24
Merged

COMPAT: numpy compat with NaT != NaT, #12049 #12058

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
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v0.18.0.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,7 +445,7 @@ Bug Fixes
- Accept unicode in ``Timedelta`` constructor (:issue:`11995`)
- Bug in value label reading for ``StataReader`` when reading incrementally (:issue:`12014`)
- Bug in vectorized ``DateOffset`` when ``n`` parameter is ``0`` (:issue:`11370`)

- Compat for numpy 1.11 w.r.t. ``NaT`` comparison changes (:issue:`12049`)



Expand Down
15 changes: 12 additions & 3 deletions pandas/core/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -379,12 +379,13 @@ def array_equivalent(left, right, strict_nan=False):
"""

left, right = np.asarray(left), np.asarray(right)

# shape compat
if left.shape != right.shape:
return False

# Object arrays can contain None, NaN and NaT.
if (issubclass(left.dtype.type, np.object_) or
issubclass(right.dtype.type, np.object_)):
if is_object_dtype(left) or is_object_dtype(right):

if not strict_nan:
# pd.isnull considers NaN and None to be equivalent.
Expand All @@ -405,13 +406,21 @@ def array_equivalent(left, right, strict_nan=False):
return True

# NaNs can occur in float and complex arrays.
if issubclass(left.dtype.type, (np.floating, np.complexfloating)):
if is_float_dtype(left) or is_complex_dtype(left):
return ((left == right) | (np.isnan(left) & np.isnan(right))).all()

# numpy will will not allow this type of datetimelike vs integer comparison
elif is_datetimelike_v_numeric(left, right):
return False

# M8/m8
elif needs_i8_conversion(left) and needs_i8_conversion(right):
if not is_dtype_equal(left.dtype, right.dtype):
return False

left = left.view('i8')
right = right.view('i8')

# NaNs cannot occur otherwise.
return np.array_equal(left, right)

Expand Down
44 changes: 33 additions & 11 deletions pandas/tests/test_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,9 @@
import numpy as np
import pandas as pd
from pandas.tslib import iNaT, NaT
from pandas import Series, DataFrame, date_range, DatetimeIndex, Timestamp, Float64Index
from pandas import (Series, DataFrame, date_range,
DatetimeIndex, TimedeltaIndex,
Timestamp, Float64Index)
from pandas import compat
from pandas.compat import range, long, lrange, lmap, u
from pandas.core.common import notnull, isnull, array_equivalent
Expand Down Expand Up @@ -322,20 +324,40 @@ def test_array_equivalent():
np.array([np.nan, 1, np.nan]))
assert array_equivalent(np.array([np.nan, None], dtype='object'),
Copy link
Member

Choose a reason for hiding this comment

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

glad to see some pep8 clean up :)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I have gotten religion err flake8

np.array([np.nan, None], dtype='object'))
assert array_equivalent(np.array([np.nan, 1+1j], dtype='complex'),
np.array([np.nan, 1+1j], dtype='complex'))
assert not array_equivalent(np.array([np.nan, 1+1j], dtype='complex'),
np.array([np.nan, 1+2j], dtype='complex'))
assert array_equivalent(np.array([np.nan, 1 + 1j], dtype='complex'),
np.array([np.nan, 1 + 1j], dtype='complex'))
assert not array_equivalent(np.array([np.nan, 1 + 1j], dtype='complex'),
np.array([np.nan, 1 + 2j], dtype='complex'))
assert not array_equivalent(np.array([np.nan, 1, np.nan]),
np.array([np.nan, 2, np.nan]))
assert not array_equivalent(np.array(['a', 'b', 'c', 'd']), np.array(['e', 'e']))
assert array_equivalent(Float64Index([0, np.nan]), Float64Index([0, np.nan]))
assert not array_equivalent(Float64Index([0, np.nan]), Float64Index([1, np.nan]))
assert array_equivalent(DatetimeIndex([0, np.nan]), DatetimeIndex([0, np.nan]))
assert not array_equivalent(DatetimeIndex([0, np.nan]), DatetimeIndex([1, np.nan]))
assert not array_equivalent(np.array(['a', 'b', 'c', 'd']),
np.array(['e', 'e']))
assert array_equivalent(Float64Index([0, np.nan]),
Float64Index([0, np.nan]))
assert not array_equivalent(Float64Index([0, np.nan]),
Float64Index([1, np.nan]))
assert array_equivalent(DatetimeIndex([0, np.nan]),
DatetimeIndex([0, np.nan]))
assert not array_equivalent(DatetimeIndex([0, np.nan]),
DatetimeIndex([1, np.nan]))
assert array_equivalent(TimedeltaIndex([0, np.nan]),
TimedeltaIndex([0, np.nan]))
assert not array_equivalent(TimedeltaIndex([0, np.nan]),
TimedeltaIndex([1, np.nan]))
assert array_equivalent(DatetimeIndex([0, np.nan], tz='US/Eastern'),
DatetimeIndex([0, np.nan], tz='US/Eastern'))
assert not array_equivalent(DatetimeIndex([0, np.nan], tz='US/Eastern'),
DatetimeIndex([1, np.nan], tz='US/Eastern'))
assert not array_equivalent(DatetimeIndex([0, np.nan]),
DatetimeIndex([0, np.nan], tz='US/Eastern'))
assert not array_equivalent(DatetimeIndex([0, np.nan], tz='CET'),
DatetimeIndex([0, np.nan], tz='US/Eastern'))
assert not array_equivalent(DatetimeIndex([0, np.nan]),
TimedeltaIndex([0, np.nan]))


def test_datetimeindex_from_empty_datetime64_array():
for unit in [ 'ms', 'us', 'ns' ]:
for unit in ['ms', 'us', 'ns']:
idx = DatetimeIndex(np.array([], dtype='datetime64[%s]' % unit))
assert(len(idx) == 0)

Expand Down
18 changes: 9 additions & 9 deletions pandas/tseries/tests/test_tslib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,8 +399,10 @@ def test_asm8(self):
1000,
]
for n in ns:
self.assertEqual(Timestamp(n).asm8, np.datetime64(n, 'ns'), n)
self.assertEqual(Timestamp('nat').asm8, np.datetime64('nat', 'ns'))
self.assertEqual(Timestamp(n).asm8.view('i8'),
np.datetime64(n, 'ns').view('i8'), n)
self.assertEqual(Timestamp('nat').asm8.view('i8'),
np.datetime64('nat', 'ns').view('i8'))

def test_fields(self):

Expand Down Expand Up @@ -752,13 +754,11 @@ def test_coercing_dates_outside_of_datetime64_ns_bounds(self):
np.array([invalid_date], dtype='object'),
errors='raise',
)
self.assertTrue(
np.array_equal(
tslib.array_to_datetime(
np.array([invalid_date], dtype='object'), errors='coerce',
),
np.array([tslib.iNaT], dtype='M8[ns]')
)
self.assert_numpy_array_equal(
tslib.array_to_datetime(
np.array([invalid_date], dtype='object'),
errors='coerce'),
np.array([tslib.iNaT], dtype='M8[ns]')
)

arr = np.array(['1/1/1000', '1/1/2000'], dtype=object)
Expand Down