unimib-thesis-mad
/
PyCTBN
Archived
1
0
Fork 0
Code Releases Activity
Old engine for Continuous Time Bayesian Networks. Superseded by reCTBN. 🐍 https://github.com/madlabunimib/PyCTBN
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This repo is archived. You can view files and clone it, but cannot push or open issues/pull-requests.
72 Commits
3 Branches
0 Tags
106 MiB
Tag: Branch: Tree: 8a13c33b93
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '8a13c33b93'
${ noResults }
PyCTBN/venv/lib/python3.9/site-packages/pandas/tests/arithmetic/test_datetime64.py

2477 lines
88 KiB
Raw Normal View History Unescape

Refactor on docs; Add performance comparison
4 years ago
# Arithmetic tests for DataFrame/Series/Index/Array classes that should
# behave identically.
# Specifically for datetime64 and datetime64tz dtypes
from datetime import datetime, time, timedelta
from itertools import product, starmap
import operator
import warnings
import numpy as np
import pytest
import pytz
from pandas._libs.tslibs.conversion import localize_pydatetime
from pandas._libs.tslibs.offsets import shift_months
from pandas.compat.numpy import np_datetime64_compat
from pandas.errors import PerformanceWarning
import pandas as pd
from pandas import (
DatetimeIndex,
NaT,
Period,
Series,
Timedelta,
TimedeltaIndex,
Timestamp,
date_range,
)
import pandas._testing as tm
from pandas.core.arrays import DatetimeArray, TimedeltaArray
from pandas.core.ops import roperator
from pandas.tests.arithmetic.common import (
assert_invalid_addsub_type,
assert_invalid_comparison,
get_upcast_box,
)
# ------------------------------------------------------------------
# Comparisons
class TestDatetime64ArrayLikeComparisons:
# Comparison tests for datetime64 vectors fully parametrized over
# DataFrame/Series/DatetimeIndex/DatetimeArray. Ideally all comparison
# tests will eventually end up here.
def test_compare_zerodim(self, tz_naive_fixture, box_with_array):
# Test comparison with zero-dimensional array is unboxed
tz = tz_naive_fixture
box = box_with_array
xbox = box_with_array if box_with_array is not pd.Index else np.ndarray
dti = date_range("20130101", periods=3, tz=tz)
other = np.array(dti.to_numpy()[0])
dtarr = tm.box_expected(dti, box)
result = dtarr <= other
expected = np.array([True, False, False])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(result, expected)
@pytest.mark.parametrize(
"other",
[
"foo",
-1,
99,
4.0,
object(),
timedelta(days=2),
# GH#19800, GH#19301 datetime.date comparison raises to
# match DatetimeIndex/Timestamp. This also matches the behavior
# of stdlib datetime.datetime
datetime(2001, 1, 1).date(),
# GH#19301 None and NaN are *not* cast to NaT for comparisons
None,
np.nan,
],
)
def test_dt64arr_cmp_scalar_invalid(self, other, tz_naive_fixture, box_with_array):
# GH#22074, GH#15966
tz = tz_naive_fixture
rng = date_range("1/1/2000", periods=10, tz=tz)
dtarr = tm.box_expected(rng, box_with_array)
assert_invalid_comparison(dtarr, other, box_with_array)
@pytest.mark.parametrize(
"other",
[
list(range(10)),
np.arange(10),
np.arange(10).astype(np.float32),
np.arange(10).astype(object),
pd.timedelta_range("1ns", periods=10).array,
np.array(pd.timedelta_range("1ns", periods=10)),
list(pd.timedelta_range("1ns", periods=10)),
pd.timedelta_range("1 Day", periods=10).astype(object),
pd.period_range("1971-01-01", freq="D", periods=10).array,
pd.period_range("1971-01-01", freq="D", periods=10).astype(object),
],
)
def test_dt64arr_cmp_arraylike_invalid(self, other, tz_naive_fixture):
# We don't parametrize this over box_with_array because listlike
# other plays poorly with assert_invalid_comparison reversed checks
tz = tz_naive_fixture
dta = date_range("1970-01-01", freq="ns", periods=10, tz=tz)._data
assert_invalid_comparison(dta, other, tm.to_array)
def test_dt64arr_cmp_mixed_invalid(self, tz_naive_fixture):
tz = tz_naive_fixture
dta = date_range("1970-01-01", freq="h", periods=5, tz=tz)._data
other = np.array([0, 1, 2, dta[3], pd.Timedelta(days=1)])
result = dta == other
expected = np.array([False, False, False, True, False])
tm.assert_numpy_array_equal(result, expected)
result = dta != other
tm.assert_numpy_array_equal(result, ~expected)
msg = "Invalid comparison between|Cannot compare type|not supported between"
with pytest.raises(TypeError, match=msg):
dta < other
with pytest.raises(TypeError, match=msg):
dta > other
with pytest.raises(TypeError, match=msg):
dta <= other
with pytest.raises(TypeError, match=msg):
dta >= other
def test_dt64arr_nat_comparison(self, tz_naive_fixture, box_with_array):
# GH#22242, GH#22163 DataFrame considered NaT == ts incorrectly
tz = tz_naive_fixture
box = box_with_array
xbox = box if box is not pd.Index else np.ndarray
ts = pd.Timestamp.now(tz)
ser = pd.Series([ts, pd.NaT])
obj = tm.box_expected(ser, box)
expected = pd.Series([True, False], dtype=np.bool_)
expected = tm.box_expected(expected, xbox)
result = obj == ts
tm.assert_equal(result, expected)
class TestDatetime64SeriesComparison:
# TODO: moved from tests.series.test_operators; needs cleanup
@pytest.mark.parametrize(
"pair",
[
(
[pd.Timestamp("2011-01-01"), NaT, pd.Timestamp("2011-01-03")],
[NaT, NaT, pd.Timestamp("2011-01-03")],
),
(
[pd.Timedelta("1 days"), NaT, pd.Timedelta("3 days")],
[NaT, NaT, pd.Timedelta("3 days")],
),
(
[pd.Period("2011-01", freq="M"), NaT, pd.Period("2011-03", freq="M")],
[NaT, NaT, pd.Period("2011-03", freq="M")],
),
],
)
@pytest.mark.parametrize("reverse", [True, False])
@pytest.mark.parametrize("dtype", [None, object])
def test_nat_comparisons(self, dtype, index_or_series, reverse, pair):
box = index_or_series
l, r = pair
if reverse:
# add lhs / rhs switched data
l, r = r, l
left = Series(l, dtype=dtype)
right = box(r, dtype=dtype)
# Series, Index
expected = Series([False, False, True])
tm.assert_series_equal(left == right, expected)
expected = Series([True, True, False])
tm.assert_series_equal(left != right, expected)
expected = Series([False, False, False])
tm.assert_series_equal(left < right, expected)
expected = Series([False, False, False])
tm.assert_series_equal(left > right, expected)
expected = Series([False, False, True])
tm.assert_series_equal(left >= right, expected)
expected = Series([False, False, True])
tm.assert_series_equal(left <= right, expected)
def test_comparison_invalid(self, tz_naive_fixture, box_with_array):
# GH#4968
# invalid date/int comparisons
tz = tz_naive_fixture
ser = Series(range(5))
ser2 = Series(pd.date_range("20010101", periods=5, tz=tz))
ser = tm.box_expected(ser, box_with_array)
ser2 = tm.box_expected(ser2, box_with_array)
assert_invalid_comparison(ser, ser2, box_with_array)
@pytest.mark.parametrize(
"data",
[
[Timestamp("2011-01-01"), NaT, Timestamp("2011-01-03")],
[Timedelta("1 days"), NaT, Timedelta("3 days")],
[Period("2011-01", freq="M"), NaT, Period("2011-03", freq="M")],
],
)
@pytest.mark.parametrize("dtype", [None, object])
def test_nat_comparisons_scalar(self, dtype, data, box_with_array):
if box_with_array is tm.to_array and dtype is object:
# dont bother testing ndarray comparison methods as this fails
# on older numpys (since they check object identity)
return
xbox = box_with_array if box_with_array is not pd.Index else np.ndarray
left = Series(data, dtype=dtype)
left = tm.box_expected(left, box_with_array)
expected = [False, False, False]
expected = tm.box_expected(expected, xbox)
tm.assert_equal(left == NaT, expected)
tm.assert_equal(NaT == left, expected)
expected = [True, True, True]
expected = tm.box_expected(expected, xbox)
tm.assert_equal(left != NaT, expected)
tm.assert_equal(NaT != left, expected)
expected = [False, False, False]
expected = tm.box_expected(expected, xbox)
tm.assert_equal(left < NaT, expected)
tm.assert_equal(NaT > left, expected)
tm.assert_equal(left <= NaT, expected)
tm.assert_equal(NaT >= left, expected)
tm.assert_equal(left > NaT, expected)
tm.assert_equal(NaT < left, expected)
tm.assert_equal(left >= NaT, expected)
tm.assert_equal(NaT <= left, expected)
@pytest.mark.parametrize("val", [datetime(2000, 1, 4), datetime(2000, 1, 5)])
def test_series_comparison_scalars(self, val):
series = Series(date_range("1/1/2000", periods=10))
result = series > val
expected = Series([x > val for x in series])
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"left,right", [("lt", "gt"), ("le", "ge"), ("eq", "eq"), ("ne", "ne")]
)
def test_timestamp_compare_series(self, left, right):
# see gh-4982
# Make sure we can compare Timestamps on the right AND left hand side.
ser = pd.Series(pd.date_range("20010101", periods=10), name="dates")
s_nat = ser.copy(deep=True)
ser[0] = pd.Timestamp("nat")
ser[3] = pd.Timestamp("nat")
left_f = getattr(operator, left)
right_f = getattr(operator, right)
# No NaT
expected = left_f(ser, pd.Timestamp("20010109"))
result = right_f(pd.Timestamp("20010109"), ser)
tm.assert_series_equal(result, expected)
# NaT
expected = left_f(ser, pd.Timestamp("nat"))
result = right_f(pd.Timestamp("nat"), ser)
tm.assert_series_equal(result, expected)
# Compare to Timestamp with series containing NaT
expected = left_f(s_nat, pd.Timestamp("20010109"))
result = right_f(pd.Timestamp("20010109"), s_nat)
tm.assert_series_equal(result, expected)
# Compare to NaT with series containing NaT
expected = left_f(s_nat, pd.Timestamp("nat"))
result = right_f(pd.Timestamp("nat"), s_nat)
tm.assert_series_equal(result, expected)
def test_dt64arr_timestamp_equality(self, box_with_array):
# GH#11034
xbox = box_with_array if box_with_array is not pd.Index else np.ndarray
ser = pd.Series([pd.Timestamp("2000-01-29 01:59:00"), "NaT"])
ser = tm.box_expected(ser, box_with_array)
result = ser != ser
expected = tm.box_expected([False, True], xbox)
tm.assert_equal(result, expected)
result = ser != ser[0]
expected = tm.box_expected([False, True], xbox)
tm.assert_equal(result, expected)
result = ser != ser[1]
expected = tm.box_expected([True, True], xbox)
tm.assert_equal(result, expected)
result = ser == ser
expected = tm.box_expected([True, False], xbox)
tm.assert_equal(result, expected)
result = ser == ser[0]
expected = tm.box_expected([True, False], xbox)
tm.assert_equal(result, expected)
result = ser == ser[1]
expected = tm.box_expected([False, False], xbox)
tm.assert_equal(result, expected)
class TestDatetimeIndexComparisons:
# TODO: moved from tests.indexes.test_base; parametrize and de-duplicate
@pytest.mark.parametrize(
"op",
[operator.eq, operator.ne, operator.gt, operator.lt, operator.ge, operator.le],
)
def test_comparators(self, op):
index = tm.makeDateIndex(100)
element = index[len(index) // 2]
element = Timestamp(element).to_datetime64()
arr = np.array(index)
arr_result = op(arr, element)
index_result = op(index, element)
assert isinstance(index_result, np.ndarray)
tm.assert_numpy_array_equal(arr_result, index_result)
@pytest.mark.parametrize(
"other",
[datetime(2016, 1, 1), Timestamp("2016-01-01"), np.datetime64("2016-01-01")],
)
def test_dti_cmp_datetimelike(self, other, tz_naive_fixture):
tz = tz_naive_fixture
dti = pd.date_range("2016-01-01", periods=2, tz=tz)
if tz is not None:
if isinstance(other, np.datetime64):
# no tzaware version available
return
other = localize_pydatetime(other, dti.tzinfo)
result = dti == other
expected = np.array([True, False])
tm.assert_numpy_array_equal(result, expected)
result = dti > other
expected = np.array([False, True])
tm.assert_numpy_array_equal(result, expected)
result = dti >= other
expected = np.array([True, True])
tm.assert_numpy_array_equal(result, expected)
result = dti < other
expected = np.array([False, False])
tm.assert_numpy_array_equal(result, expected)
result = dti <= other
expected = np.array([True, False])
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("dtype", [None, object])
def test_dti_cmp_nat(self, dtype, box_with_array):
if box_with_array is tm.to_array and dtype is object:
# dont bother testing ndarray comparison methods as this fails
# on older numpys (since they check object identity)
return
xbox = box_with_array if box_with_array is not pd.Index else np.ndarray
left = pd.DatetimeIndex(
[pd.Timestamp("2011-01-01"), pd.NaT, pd.Timestamp("2011-01-03")]
)
right = pd.DatetimeIndex([pd.NaT, pd.NaT, pd.Timestamp("2011-01-03")])
left = tm.box_expected(left, box_with_array)
right = tm.box_expected(right, box_with_array)
lhs, rhs = left, right
if dtype is object:
lhs, rhs = left.astype(object), right.astype(object)
result = rhs == lhs
expected = np.array([False, False, True])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(result, expected)
result = lhs != rhs
expected = np.array([True, True, False])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(result, expected)
expected = np.array([False, False, False])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(lhs == pd.NaT, expected)
tm.assert_equal(pd.NaT == rhs, expected)
expected = np.array([True, True, True])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(lhs != pd.NaT, expected)
tm.assert_equal(pd.NaT != lhs, expected)
expected = np.array([False, False, False])
expected = tm.box_expected(expected, xbox)
tm.assert_equal(lhs < pd.NaT, expected)
tm.assert_equal(pd.NaT > lhs, expected)
def test_dti_cmp_nat_behaves_like_float_cmp_nan(self):
fidx1 = pd.Index([1.0, np.nan, 3.0, np.nan, 5.0, 7.0])
fidx2 = pd.Index([2.0, 3.0, np.nan, np.nan, 6.0, 7.0])
didx1 = pd.DatetimeIndex(
["2014-01-01", pd.NaT, "2014-03-01", pd.NaT, "2014-05-01", "2014-07-01"]
)
didx2 = pd.DatetimeIndex(
["2014-02-01", "2014-03-01", pd.NaT, pd.NaT, "2014-06-01", "2014-07-01"]
)
darr = np.array(
[
np_datetime64_compat("2014-02-01 00:00Z"),
np_datetime64_compat("2014-03-01 00:00Z"),
np_datetime64_compat("nat"),
np.datetime64("nat"),
np_datetime64_compat("2014-06-01 00:00Z"),
np_datetime64_compat("2014-07-01 00:00Z"),
]
)
cases = [(fidx1, fidx2), (didx1, didx2), (didx1, darr)]
# Check pd.NaT is handles as the same as np.nan
with tm.assert_produces_warning(None):
for idx1, idx2 in cases:
result = idx1 < idx2
expected = np.array([True, False, False, False, True, False])
tm.assert_numpy_array_equal(result, expected)
result = idx2 > idx1
expected = np.array([True, False, False, False, True, False])
tm.assert_numpy_array_equal(result, expected)
result = idx1 <= idx2
expected = np.array([True, False, False, False, True, True])
tm.assert_numpy_array_equal(result, expected)
result = idx2 >= idx1
expected = np.array([True, False, False, False, True, True])
tm.assert_numpy_array_equal(result, expected)
result = idx1 == idx2
expected = np.array([False, False, False, False, False, True])
tm.assert_numpy_array_equal(result, expected)
result = idx1 != idx2
expected = np.array([True, True, True, True, True, False])
tm.assert_numpy_array_equal(result, expected)
with tm.assert_produces_warning(None):
for idx1, val in [(fidx1, np.nan), (didx1, pd.NaT)]:
result = idx1 < val
expected = np.array([False, False, False, False, False, False])
tm.assert_numpy_array_equal(result, expected)
result = idx1 > val
tm.assert_numpy_array_equal(result, expected)
result = idx1 <= val
tm.assert_numpy_array_equal(result, expected)
result = idx1 >= val
tm.assert_numpy_array_equal(result, expected)
result = idx1 == val
tm.assert_numpy_array_equal(result, expected)
result = idx1 != val
expected = np.array([True, True, True, True, True, True])
tm.assert_numpy_array_equal(result, expected)
# Check pd.NaT is handles as the same as np.nan
with tm.assert_produces_warning(None):
for idx1, val in [(fidx1, 3), (didx1, datetime(2014, 3, 1))]:
result = idx1 < val
expected = np.array([True, False, False, False, False, False])
tm.assert_numpy_array_equal(result, expected)
result = idx1 > val
expected = np.array([False, False, False, False, True, True])
tm.assert_numpy_array_equal(result, expected)
result = idx1 <= val
expected = np.array([True, False, True, False, False, False])
tm.assert_numpy_array_equal(result, expected)
result = idx1 >= val
expected = np.array([False, False, True, False, True, True])
tm.assert_numpy_array_equal(result, expected)
result = idx1 == val
expected = np.array([False, False, True, False, False, False])
tm.assert_numpy_array_equal(result, expected)
result = idx1 != val
expected = np.array([True, True, False, True, True, True])
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"op",
[operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
)
def test_comparison_tzawareness_compat(self, op, box_with_array):
# GH#18162
box = box_with_array
dr = pd.date_range("2016-01-01", periods=6)
dz = dr.tz_localize("US/Pacific")
dr = tm.box_expected(dr, box)
dz = tm.box_expected(dz, box)
msg = "Cannot compare tz-naive and tz-aware"
with pytest.raises(TypeError, match=msg):
op(dr, dz)
if box is pd.DataFrame:
tolist = lambda x: x.astype(object).values.tolist()[0]
else:
tolist = list
with pytest.raises(TypeError, match=msg):
op(dr, tolist(dz))
with pytest.raises(TypeError, match=msg):
op(dr, np.array(tolist(dz), dtype=object))
with pytest.raises(TypeError, match=msg):
op(dz, dr)
with pytest.raises(TypeError, match=msg):
op(dz, tolist(dr))
with pytest.raises(TypeError, match=msg):
op(dz, np.array(tolist(dr), dtype=object))
# The aware==aware and naive==naive comparisons should *not* raise
assert np.all(dr == dr)
assert np.all(dr == tolist(dr))
assert np.all(tolist(dr) == dr)
assert np.all(np.array(tolist(dr), dtype=object) == dr)
assert np.all(dr == np.array(tolist(dr), dtype=object))
assert np.all(dz == dz)
assert np.all(dz == tolist(dz))
assert np.all(tolist(dz) == dz)
assert np.all(np.array(tolist(dz), dtype=object) == dz)
assert np.all(dz == np.array(tolist(dz), dtype=object))
@pytest.mark.parametrize(
"op",
[operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
)
def test_comparison_tzawareness_compat_scalars(self, op, box_with_array):
# GH#18162
dr = pd.date_range("2016-01-01", periods=6)
dz = dr.tz_localize("US/Pacific")
dr = tm.box_expected(dr, box_with_array)
dz = tm.box_expected(dz, box_with_array)
# Check comparisons against scalar Timestamps
ts = pd.Timestamp("2000-03-14 01:59")
ts_tz = pd.Timestamp("2000-03-14 01:59", tz="Europe/Amsterdam")
assert np.all(dr > ts)
msg = "Cannot compare tz-naive and tz-aware"
with pytest.raises(TypeError, match=msg):
op(dr, ts_tz)
assert np.all(dz > ts_tz)
with pytest.raises(TypeError, match=msg):
op(dz, ts)
# GH#12601: Check comparison against Timestamps and DatetimeIndex
with pytest.raises(TypeError, match=msg):
op(ts, dz)
@pytest.mark.parametrize(
"op",
[operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
)
@pytest.mark.parametrize(
"other",
[datetime(2016, 1, 1), Timestamp("2016-01-01"), np.datetime64("2016-01-01")],
)
# Bug in NumPy? https://github.com/numpy/numpy/issues/13841
# Raising in __eq__ will fallback to NumPy, which warns, fails,
# then re-raises the original exception. So we just need to ignore.
@pytest.mark.filterwarnings("ignore:elementwise comp:DeprecationWarning")
@pytest.mark.filterwarnings("ignore:Converting timezone-aware:FutureWarning")
def test_scalar_comparison_tzawareness(
self, op, other, tz_aware_fixture, box_with_array
):
tz = tz_aware_fixture
dti = pd.date_range("2016-01-01", periods=2, tz=tz)
dtarr = tm.box_expected(dti, box_with_array)
msg = "Cannot compare tz-naive and tz-aware"
with pytest.raises(TypeError, match=msg):
op(dtarr, other)
with pytest.raises(TypeError, match=msg):
op(other, dtarr)
@pytest.mark.parametrize(
"op",
[operator.eq, operator.ne, operator.gt, operator.ge, operator.lt, operator.le],
)
def test_nat_comparison_tzawareness(self, op):
# GH#19276
# tzaware DatetimeIndex should not raise when compared to NaT
dti = pd.DatetimeIndex(
["2014-01-01", pd.NaT, "2014-03-01", pd.NaT, "2014-05-01", "2014-07-01"]
)
expected = np.array([op == operator.ne] * len(dti))
result = op(dti, pd.NaT)
tm.assert_numpy_array_equal(result, expected)
result = op(dti.tz_localize("US/Pacific"), pd.NaT)
tm.assert_numpy_array_equal(result, expected)
def test_dti_cmp_str(self, tz_naive_fixture):
# GH#22074
# regardless of tz, we expect these comparisons are valid
tz = tz_naive_fixture
rng = date_range("1/1/2000", periods=10, tz=tz)
other = "1/1/2000"
result = rng == other
expected = np.array([True] + [False] * 9)
tm.assert_numpy_array_equal(result, expected)
result = rng != other
expected = np.array([False] + [True] * 9)
tm.assert_numpy_array_equal(result, expected)
result = rng < other
expected = np.array([False] * 10)
tm.assert_numpy_array_equal(result, expected)
result = rng <= other
expected = np.array([True] + [False] * 9)
tm.assert_numpy_array_equal(result, expected)
result = rng > other
expected = np.array([False] + [True] * 9)
tm.assert_numpy_array_equal(result, expected)
result = rng >= other
expected = np.array([True] * 10)
tm.assert_numpy_array_equal(result, expected)
def test_dti_cmp_list(self):
rng = date_range("1/1/2000", periods=10)
result = rng == list(rng)
expected = rng == rng
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"other",
[
pd.timedelta_range("1D", periods=10),
pd.timedelta_range("1D", periods=10).to_series(),
pd.timedelta_range("1D", periods=10).asi8.view("m8[ns]"),
],
ids=lambda x: type(x).__name__,
)
def test_dti_cmp_tdi_tzawareness(self, other):
# GH#22074
# reversion test that we _don't_ call _assert_tzawareness_compat
# when comparing against TimedeltaIndex
dti = date_range("2000-01-01", periods=10, tz="Asia/Tokyo")
result = dti == other
expected = np.array([False] * 10)
tm.assert_numpy_array_equal(result, expected)
result = dti != other
expected = np.array([True] * 10)
tm.assert_numpy_array_equal(result, expected)
msg = "Invalid comparison between"
with pytest.raises(TypeError, match=msg):
dti < other
with pytest.raises(TypeError, match=msg):
dti <= other
with pytest.raises(TypeError, match=msg):
dti > other
with pytest.raises(TypeError, match=msg):
dti >= other
def test_dti_cmp_object_dtype(self):
# GH#22074
dti = date_range("2000-01-01", periods=10, tz="Asia/Tokyo")
other = dti.astype("O")
result = dti == other
expected = np.array([True] * 10)
tm.assert_numpy_array_equal(result, expected)
other = dti.tz_localize(None)
msg = "Cannot compare tz-naive and tz-aware"
with pytest.raises(TypeError, match=msg):
# tzawareness failure
dti != other
other = np.array(list(dti[:5]) + [Timedelta(days=1)] * 5)
result = dti == other
expected = np.array([True] * 5 + [False] * 5)
tm.assert_numpy_array_equal(result, expected)
msg = ">=' not supported between instances of 'Timestamp' and 'Timedelta'"
with pytest.raises(TypeError, match=msg):
dti >= other
# ------------------------------------------------------------------
# Arithmetic
class TestDatetime64Arithmetic:
# This class is intended for "finished" tests that are fully parametrized
# over DataFrame/Series/Index/DatetimeArray
# -------------------------------------------------------------
# Addition/Subtraction of timedelta-like
def test_dt64arr_add_timedeltalike_scalar(
self, tz_naive_fixture, two_hours, box_with_array
):
# GH#22005, GH#22163 check DataFrame doesn't raise TypeError
tz = tz_naive_fixture
rng = pd.date_range("2000-01-01", "2000-02-01", tz=tz)
expected = pd.date_range("2000-01-01 02:00", "2000-02-01 02:00", tz=tz)
rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = rng + two_hours
tm.assert_equal(result, expected)
def test_dt64arr_iadd_timedeltalike_scalar(
self, tz_naive_fixture, two_hours, box_with_array
):
tz = tz_naive_fixture
rng = pd.date_range("2000-01-01", "2000-02-01", tz=tz)
expected = pd.date_range("2000-01-01 02:00", "2000-02-01 02:00", tz=tz)
rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)
rng += two_hours
tm.assert_equal(rng, expected)
def test_dt64arr_sub_timedeltalike_scalar(
self, tz_naive_fixture, two_hours, box_with_array
):
tz = tz_naive_fixture
rng = pd.date_range("2000-01-01", "2000-02-01", tz=tz)
expected = pd.date_range("1999-12-31 22:00", "2000-01-31 22:00", tz=tz)
rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = rng - two_hours
tm.assert_equal(result, expected)
def test_dt64arr_isub_timedeltalike_scalar(
self, tz_naive_fixture, two_hours, box_with_array
):
tz = tz_naive_fixture
rng = pd.date_range("2000-01-01", "2000-02-01", tz=tz)
expected = pd.date_range("1999-12-31 22:00", "2000-01-31 22:00", tz=tz)
rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)
rng -= two_hours
tm.assert_equal(rng, expected)
# TODO: redundant with test_dt64arr_add_timedeltalike_scalar
def test_dt64arr_add_td64_scalar(self, box_with_array):
# scalar timedeltas/np.timedelta64 objects
# operate with np.timedelta64 correctly
ser = Series([Timestamp("20130101 9:01"), Timestamp("20130101 9:02")])
expected = Series(
[Timestamp("20130101 9:01:01"), Timestamp("20130101 9:02:01")]
)
dtarr = tm.box_expected(ser, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = dtarr + np.timedelta64(1, "s")
tm.assert_equal(result, expected)
result = np.timedelta64(1, "s") + dtarr
tm.assert_equal(result, expected)
expected = Series(
[Timestamp("20130101 9:01:00.005"), Timestamp("20130101 9:02:00.005")]
)
expected = tm.box_expected(expected, box_with_array)
result = dtarr + np.timedelta64(5, "ms")
tm.assert_equal(result, expected)
result = np.timedelta64(5, "ms") + dtarr
tm.assert_equal(result, expected)
def test_dt64arr_add_sub_td64_nat(self, box_with_array, tz_naive_fixture):
# GH#23320 special handling for timedelta64("NaT")
tz = tz_naive_fixture
dti = pd.date_range("1994-04-01", periods=9, tz=tz, freq="QS")
other = np.timedelta64("NaT")
expected = pd.DatetimeIndex(["NaT"] * 9, tz=tz)
obj = tm.box_expected(dti, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = obj + other
tm.assert_equal(result, expected)
result = other + obj
tm.assert_equal(result, expected)
result = obj - other
tm.assert_equal(result, expected)
msg = "cannot subtract"
with pytest.raises(TypeError, match=msg):
other - obj
def test_dt64arr_add_sub_td64ndarray(self, tz_naive_fixture, box_with_array):
tz = tz_naive_fixture
dti = pd.date_range("2016-01-01", periods=3, tz=tz)
tdi = pd.TimedeltaIndex(["-1 Day", "-1 Day", "-1 Day"])
tdarr = tdi.values
expected = pd.date_range("2015-12-31", "2016-01-02", periods=3, tz=tz)
dtarr = tm.box_expected(dti, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = dtarr + tdarr
tm.assert_equal(result, expected)
result = tdarr + dtarr
tm.assert_equal(result, expected)
expected = pd.date_range("2016-01-02", "2016-01-04", periods=3, tz=tz)
expected = tm.box_expected(expected, box_with_array)
result = dtarr - tdarr
tm.assert_equal(result, expected)
msg = "cannot subtract|(bad|unsupported) operand type for unary"
with pytest.raises(TypeError, match=msg):
tdarr - dtarr
# -----------------------------------------------------------------
# Subtraction of datetime-like scalars
@pytest.mark.parametrize(
"ts",
[
pd.Timestamp("2013-01-01"),
pd.Timestamp("2013-01-01").to_pydatetime(),
pd.Timestamp("2013-01-01").to_datetime64(),
],
)
def test_dt64arr_sub_dtscalar(self, box_with_array, ts):
# GH#8554, GH#22163 DataFrame op should _not_ return dt64 dtype
idx = pd.date_range("2013-01-01", periods=3)._with_freq(None)
idx = tm.box_expected(idx, box_with_array)
expected = pd.TimedeltaIndex(["0 Days", "1 Day", "2 Days"])
expected = tm.box_expected(expected, box_with_array)
result = idx - ts
tm.assert_equal(result, expected)
def test_dt64arr_sub_datetime64_not_ns(self, box_with_array):
# GH#7996, GH#22163 ensure non-nano datetime64 is converted to nano
# for DataFrame operation
dt64 = np.datetime64("2013-01-01")
assert dt64.dtype == "datetime64[D]"
dti = pd.date_range("20130101", periods=3)._with_freq(None)
dtarr = tm.box_expected(dti, box_with_array)
expected = pd.TimedeltaIndex(["0 Days", "1 Day", "2 Days"])
expected = tm.box_expected(expected, box_with_array)
result = dtarr - dt64
tm.assert_equal(result, expected)
result = dt64 - dtarr
tm.assert_equal(result, -expected)
def test_dt64arr_sub_timestamp(self, box_with_array):
ser = pd.date_range("2014-03-17", periods=2, freq="D", tz="US/Eastern")
ser = ser._with_freq(None)
ts = ser[0]
ser = tm.box_expected(ser, box_with_array)
delta_series = pd.Series([np.timedelta64(0, "D"), np.timedelta64(1, "D")])
expected = tm.box_expected(delta_series, box_with_array)
tm.assert_equal(ser - ts, expected)
tm.assert_equal(ts - ser, -expected)
def test_dt64arr_sub_NaT(self, box_with_array):
# GH#18808
dti = pd.DatetimeIndex([pd.NaT, pd.Timestamp("19900315")])
ser = tm.box_expected(dti, box_with_array)
result = ser - pd.NaT
expected = pd.Series([pd.NaT, pd.NaT], dtype="timedelta64[ns]")
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(result, expected)
dti_tz = dti.tz_localize("Asia/Tokyo")
ser_tz = tm.box_expected(dti_tz, box_with_array)
result = ser_tz - pd.NaT
expected = pd.Series([pd.NaT, pd.NaT], dtype="timedelta64[ns]")
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(result, expected)
# -------------------------------------------------------------
# Subtraction of datetime-like array-like
def test_dt64arr_sub_dt64object_array(self, box_with_array, tz_naive_fixture):
dti = pd.date_range("2016-01-01", periods=3, tz=tz_naive_fixture)
expected = dti - dti
obj = tm.box_expected(dti, box_with_array)
expected = tm.box_expected(expected, box_with_array)
warn = None
if box_with_array is not pd.DataFrame or tz_naive_fixture is None:
warn = PerformanceWarning
with tm.assert_produces_warning(warn):
result = obj - obj.astype(object)
tm.assert_equal(result, expected)
def test_dt64arr_naive_sub_dt64ndarray(self, box_with_array):
dti = pd.date_range("2016-01-01", periods=3, tz=None)
dt64vals = dti.values
dtarr = tm.box_expected(dti, box_with_array)
expected = dtarr - dtarr
result = dtarr - dt64vals
tm.assert_equal(result, expected)
result = dt64vals - dtarr
tm.assert_equal(result, expected)
def test_dt64arr_aware_sub_dt64ndarray_raises(
self, tz_aware_fixture, box_with_array
):
tz = tz_aware_fixture
dti = pd.date_range("2016-01-01", periods=3, tz=tz)
dt64vals = dti.values
dtarr = tm.box_expected(dti, box_with_array)
msg = "subtraction must have the same timezones or"
with pytest.raises(TypeError, match=msg):
dtarr - dt64vals
with pytest.raises(TypeError, match=msg):
dt64vals - dtarr
# -------------------------------------------------------------
# Addition of datetime-like others (invalid)
def test_dt64arr_add_dt64ndarray_raises(self, tz_naive_fixture, box_with_array):
tz = tz_naive_fixture
dti = pd.date_range("2016-01-01", periods=3, tz=tz)
dt64vals = dti.values
dtarr = tm.box_expected(dti, box_with_array)
msg = "cannot add"
with pytest.raises(TypeError, match=msg):
dtarr + dt64vals
with pytest.raises(TypeError, match=msg):
dt64vals + dtarr
def test_dt64arr_add_timestamp_raises(self, box_with_array):
# GH#22163 ensure DataFrame doesn't cast Timestamp to i8
idx = DatetimeIndex(["2011-01-01", "2011-01-02"])
idx = tm.box_expected(idx, box_with_array)
msg = "cannot add"
with pytest.raises(TypeError, match=msg):
idx + Timestamp("2011-01-01")
with pytest.raises(TypeError, match=msg):
Timestamp("2011-01-01") + idx
# -------------------------------------------------------------
# Other Invalid Addition/Subtraction
@pytest.mark.parametrize(
"other",
[
3.14,
np.array([2.0, 3.0]),
# GH#13078 datetime +/- Period is invalid
pd.Period("2011-01-01", freq="D"),
# https://github.com/pandas-dev/pandas/issues/10329
time(1, 2, 3),
],
)
@pytest.mark.parametrize("dti_freq", [None, "D"])
def test_dt64arr_add_sub_invalid(self, dti_freq, other, box_with_array):
dti = DatetimeIndex(["2011-01-01", "2011-01-02"], freq=dti_freq)
dtarr = tm.box_expected(dti, box_with_array)
msg = "|".join(
[
"unsupported operand type",
"cannot (add|subtract)",
"cannot use operands with types",
"ufunc '?(add|subtract)'? cannot use operands with types",
"Concatenation operation is not implemented for NumPy arrays",
]
)
assert_invalid_addsub_type(dtarr, other, msg)
@pytest.mark.parametrize("pi_freq", ["D", "W", "Q", "H"])
@pytest.mark.parametrize("dti_freq", [None, "D"])
def test_dt64arr_add_sub_parr(
self, dti_freq, pi_freq, box_with_array, box_with_array2
):
# GH#20049 subtracting PeriodIndex should raise TypeError
dti = pd.DatetimeIndex(["2011-01-01", "2011-01-02"], freq=dti_freq)
pi = dti.to_period(pi_freq)
dtarr = tm.box_expected(dti, box_with_array)
parr = tm.box_expected(pi, box_with_array2)
msg = "|".join(
[
"cannot (add|subtract)",
"unsupported operand",
"descriptor.*requires",
"ufunc.*cannot use operands",
]
)
assert_invalid_addsub_type(dtarr, parr, msg)
def test_dt64arr_addsub_time_objects_raises(self, box_with_array, tz_naive_fixture):
# https://github.com/pandas-dev/pandas/issues/10329
tz = tz_naive_fixture
obj1 = pd.date_range("2012-01-01", periods=3, tz=tz)
obj2 = [time(i, i, i) for i in range(3)]
obj1 = tm.box_expected(obj1, box_with_array)
obj2 = tm.box_expected(obj2, box_with_array)
with warnings.catch_warnings(record=True):
# pandas.errors.PerformanceWarning: Non-vectorized DateOffset being
# applied to Series or DatetimeIndex
# we aren't testing that here, so ignore.
warnings.simplefilter("ignore", PerformanceWarning)
# If `x + y` raises, then `y + x` should raise here as well
msg = (
r"unsupported operand type\(s\) for -: "
"'(Timestamp|DatetimeArray)' and 'datetime.time'"
)
with pytest.raises(TypeError, match=msg):
obj1 - obj2
msg = "|".join(
[
"cannot subtract DatetimeArray from ndarray",
"ufunc (subtract|'subtract') cannot use operands with types "
r"dtype\('O'\) and dtype\('<M8\[ns\]'\)",
]
)
with pytest.raises(TypeError, match=msg):
obj2 - obj1
msg = (
r"unsupported operand type\(s\) for \+: "
"'(Timestamp|DatetimeArray)' and 'datetime.time'"
)
with pytest.raises(TypeError, match=msg):
obj1 + obj2
msg = "|".join(
[
r"unsupported operand type\(s\) for \+: "
"'(Timestamp|DatetimeArray)' and 'datetime.time'",
"ufunc (add|'add') cannot use operands with types "
r"dtype\('O'\) and dtype\('<M8\[ns\]'\)",
]
)
with pytest.raises(TypeError, match=msg):
obj2 + obj1
class TestDatetime64DateOffsetArithmetic:
# -------------------------------------------------------------
# Tick DateOffsets
# TODO: parametrize over timezone?
def test_dt64arr_series_add_tick_DateOffset(self, box_with_array):
# GH#4532
# operate with pd.offsets
ser = Series([Timestamp("20130101 9:01"), Timestamp("20130101 9:02")])
expected = Series(
[Timestamp("20130101 9:01:05"), Timestamp("20130101 9:02:05")]
)
ser = tm.box_expected(ser, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = ser + pd.offsets.Second(5)
tm.assert_equal(result, expected)
result2 = pd.offsets.Second(5) + ser
tm.assert_equal(result2, expected)
def test_dt64arr_series_sub_tick_DateOffset(self, box_with_array):
# GH#4532
# operate with pd.offsets
ser = Series([Timestamp("20130101 9:01"), Timestamp("20130101 9:02")])
expected = Series(
[Timestamp("20130101 9:00:55"), Timestamp("20130101 9:01:55")]
)
ser = tm.box_expected(ser, box_with_array)
expected = tm.box_expected(expected, box_with_array)
result = ser - pd.offsets.Second(5)
tm.assert_equal(result, expected)
result2 = -pd.offsets.Second(5) + ser
tm.assert_equal(result2, expected)
msg = "(bad|unsupported) operand type for unary"
with pytest.raises(TypeError, match=msg):
pd.offsets.Second(5) - ser
@pytest.mark.parametrize(
"cls_name", ["Day", "Hour", "Minute", "Second", "Milli", "Micro", "Nano"]
)
def test_dt64arr_add_sub_tick_DateOffset_smoke(self, cls_name, box_with_array):
# GH#4532
# smoke tests for valid DateOffsets
ser = Series([Timestamp("20130101 9:01"), Timestamp("20130101 9:02")])
ser = tm.box_expected(ser, box_with_array)
offset_cls = getattr(pd.offsets, cls_name)
ser + offset_cls(5)
offset_cls(5) + ser
ser - offset_cls(5)
def test_dti_add_tick_tzaware(self, tz_aware_fixture, box_with_array):
# GH#21610, GH#22163 ensure DataFrame doesn't return object-dtype
tz = tz_aware_fixture
if tz == "US/Pacific":
dates = date_range("2012-11-01", periods=3, tz=tz)
offset = dates + pd.offsets.Hour(5)
assert dates[0] + pd.offsets.Hour(5) == offset[0]
dates = date_range("2010-11-01 00:00", periods=3, tz=tz, freq="H")
expected = DatetimeIndex(
["2010-11-01 05:00", "2010-11-01 06:00", "2010-11-01 07:00"],
freq="H",
tz=tz,
)
dates = tm.box_expected(dates, box_with_array)
expected = tm.box_expected(expected, box_with_array)
# TODO: parametrize over the scalar being added? radd? sub?
offset = dates + pd.offsets.Hour(5)
tm.assert_equal(offset, expected)
offset = dates + np.timedelta64(5, "h")
tm.assert_equal(offset, expected)
offset = dates + timedelta(hours=5)
tm.assert_equal(offset, expected)
# -------------------------------------------------------------
# RelativeDelta DateOffsets
def test_dt64arr_add_sub_relativedelta_offsets(self, box_with_array):
# GH#10699
vec = DatetimeIndex(
[
Timestamp("2000-01-05 00:15:00"),
Timestamp("2000-01-31 00:23:00"),
Timestamp("2000-01-01"),
Timestamp("2000-03-31"),
Timestamp("2000-02-29"),
Timestamp("2000-12-31"),
Timestamp("2000-05-15"),
Timestamp("2001-06-15"),
]
)
vec = tm.box_expected(vec, box_with_array)
vec_items = vec.squeeze() if box_with_array is pd.DataFrame else vec
# DateOffset relativedelta fastpath
relative_kwargs = [
("years", 2),
("months", 5),
("days", 3),
("hours", 5),
("minutes", 10),
("seconds", 2),
("microseconds", 5),
]
for i, kwd in enumerate(relative_kwargs):
off = pd.DateOffset(**dict([kwd]))
expected = DatetimeIndex([x + off for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec + off)
expected = DatetimeIndex([x - off for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec - off)
off = pd.DateOffset(**dict(relative_kwargs[: i + 1]))
expected = DatetimeIndex([x + off for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec + off)
expected = DatetimeIndex([x - off for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec - off)
msg = "(bad|unsupported) operand type for unary"
with pytest.raises(TypeError, match=msg):
off - vec
# -------------------------------------------------------------
# Non-Tick, Non-RelativeDelta DateOffsets
# TODO: redundant with test_dt64arr_add_sub_DateOffset? that includes
# tz-aware cases which this does not
@pytest.mark.parametrize(
"cls_and_kwargs",
[
"YearBegin",
("YearBegin", {"month": 5}),
"YearEnd",
("YearEnd", {"month": 5}),
"MonthBegin",
"MonthEnd",
"SemiMonthEnd",
"SemiMonthBegin",
"Week",
("Week", {"weekday": 3}),
"Week",
("Week", {"weekday": 6}),
"BusinessDay",
"BDay",
"QuarterEnd",
"QuarterBegin",
"CustomBusinessDay",
"CDay",
"CBMonthEnd",
"CBMonthBegin",
"BMonthBegin",
"BMonthEnd",
"BusinessHour",
"BYearBegin",
"BYearEnd",
"BQuarterBegin",
("LastWeekOfMonth", {"weekday": 2}),
(
"FY5253Quarter",
{
"qtr_with_extra_week": 1,
"startingMonth": 1,
"weekday": 2,
"variation": "nearest",
},
),
("FY5253", {"weekday": 0, "startingMonth": 2, "variation": "nearest"}),
("WeekOfMonth", {"weekday": 2, "week": 2}),
"Easter",
("DateOffset", {"day": 4}),
("DateOffset", {"month": 5}),
],
)
@pytest.mark.parametrize("normalize", [True, False])
@pytest.mark.parametrize("n", [0, 5])
def test_dt64arr_add_sub_DateOffsets(
self, box_with_array, n, normalize, cls_and_kwargs
):
# GH#10699
# assert vectorized operation matches pointwise operations
if isinstance(cls_and_kwargs, tuple):
# If cls_name param is a tuple, then 2nd entry is kwargs for
# the offset constructor
cls_name, kwargs = cls_and_kwargs
else:
cls_name = cls_and_kwargs
kwargs = {}
if n == 0 and cls_name in [
"WeekOfMonth",
"LastWeekOfMonth",
"FY5253Quarter",
"FY5253",
]:
# passing n = 0 is invalid for these offset classes
return
vec = DatetimeIndex(
[
Timestamp("2000-01-05 00:15:00"),
Timestamp("2000-01-31 00:23:00"),
Timestamp("2000-01-01"),
Timestamp("2000-03-31"),
Timestamp("2000-02-29"),
Timestamp("2000-12-31"),
Timestamp("2000-05-15"),
Timestamp("2001-06-15"),
]
)
vec = tm.box_expected(vec, box_with_array)
vec_items = vec.squeeze() if box_with_array is pd.DataFrame else vec
offset_cls = getattr(pd.offsets, cls_name)
with warnings.catch_warnings(record=True):
# pandas.errors.PerformanceWarning: Non-vectorized DateOffset being
# applied to Series or DatetimeIndex
# we aren't testing that here, so ignore.
warnings.simplefilter("ignore", PerformanceWarning)
offset = offset_cls(n, normalize=normalize, **kwargs)
expected = DatetimeIndex([x + offset for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec + offset)
expected = DatetimeIndex([x - offset for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, vec - offset)
expected = DatetimeIndex([offset + x for x in vec_items])
expected = tm.box_expected(expected, box_with_array)
tm.assert_equal(expected, offset + vec)
msg = "(bad|unsupported) operand type for unary"
with pytest.raises(TypeError, match=msg):
offset - vec
def test_dt64arr_add_sub_DateOffset(self, box_with_array):
# GH#10699
s = date_range("2000-01-01", "2000-01-31", name="a")
s = tm.box_expected(s, box_with_array)
result = s + pd.DateOffset(years=1)
result2 = pd.DateOffset(years=1) + s
exp = date_range("2001-01-01", "2001-01-31", name="a")._with_freq(None)
exp = tm.box_expected(exp, box_with_array)
tm.assert_equal(result, exp)
tm.assert_equal(result2, exp)
result = s - pd.DateOffset(years=1)
exp = date_range("1999-01-01", "1999-01-31", name="a")._with_freq(None)
exp = tm.box_expected(exp, box_with_array)
tm.assert_equal(result, exp)
s = DatetimeIndex(
[
Timestamp("2000-01-15 00:15:00", tz="US/Central"),
Timestamp("2000-02-15", tz="US/Central"),
],
name="a",
)
s = tm.box_expected(s, box_with_array)
result = s + pd.offsets.Day()
result2 = pd.offsets.Day() + s
exp = DatetimeIndex(
[
Timestamp("2000-01-16 00:15:00", tz="US/Central"),
Timestamp("2000-02-16", tz="US/Central"),
],
name="a",
)
exp = tm.box_expected(exp, box_with_array)
tm.assert_equal(result, exp)
tm.assert_equal(result2, exp)
s = DatetimeIndex(
[
Timestamp("2000-01-15 00:15:00", tz="US/Central"),
Timestamp("2000-02-15", tz="US/Central"),
],
name="a",
)
s = tm.box_expected(s, box_with_array)
result = s + pd.offsets.MonthEnd()
result2 = pd.offsets.MonthEnd() + s
exp = DatetimeIndex(
[
Timestamp("2000-01-31 00:15:00", tz="US/Central"),
Timestamp("2000-02-29", tz="US/Central"),
],
name="a",
)
exp = tm.box_expected(exp, box_with_array)
tm.assert_equal(result, exp)
tm.assert_equal(result2, exp)
@pytest.mark.parametrize(
"other",
[
np.array([pd.offsets.MonthEnd(), pd.offsets.Day(n=2)]),
np.array([pd.offsets.DateOffset(years=1), pd.offsets.MonthEnd()]),
np.array( # matching offsets
[pd.offsets.DateOffset(years=1), pd.offsets.DateOffset(years=1)]
),
],
)
@pytest.mark.parametrize("op", [operator.add, roperator.radd, operator.sub])
@pytest.mark.parametrize("box_other", [True, False])
def test_dt64arr_add_sub_offset_array(
self, tz_naive_fixture, box_with_array, box_other, op, other
):
# GH#18849
# GH#10699 array of offsets
tz = tz_naive_fixture
dti = pd.date_range("2017-01-01", periods=2, tz=tz)
dtarr = tm.box_expected(dti, box_with_array)
other = np.array([pd.offsets.MonthEnd(), pd.offsets.Day(n=2)])
expected = DatetimeIndex([op(dti[n], other[n]) for n in range(len(dti))])
expected = tm.box_expected(expected, box_with_array)
if box_other:
other = tm.box_expected(other, box_with_array)
warn = PerformanceWarning
if box_with_array is pd.DataFrame and tz is not None:
warn = None
with tm.assert_produces_warning(warn):
res = op(dtarr, other)
tm.assert_equal(res, expected)
@pytest.mark.parametrize(
"op, offset, exp, exp_freq",
[
(
"__add__",
pd.DateOffset(months=3, days=10),
[
Timestamp("2014-04-11"),
Timestamp("2015-04-11"),
Timestamp("2016-04-11"),
Timestamp("2017-04-11"),
],
None,
),
(
"__add__",
pd.DateOffset(months=3),
[
Timestamp("2014-04-01"),
Timestamp("2015-04-01"),
Timestamp("2016-04-01"),
Timestamp("2017-04-01"),
],
"AS-APR",
),
(
"__sub__",
pd.DateOffset(months=3, days=10),
[
Timestamp("2013-09-21"),
Timestamp("2014-09-21"),
Timestamp("2015-09-21"),
Timestamp("2016-09-21"),
],
None,
),
(
"__sub__",
pd.DateOffset(months=3),
[
Timestamp("2013-10-01"),
Timestamp("2014-10-01"),
Timestamp("2015-10-01"),
Timestamp("2016-10-01"),
],
"AS-OCT",
),
],
)
def test_dti_add_sub_nonzero_mth_offset(
self, op, offset, exp, exp_freq, tz_aware_fixture, box_with_array
):
# GH 26258
tz = tz_aware_fixture
date = date_range(start="01 Jan 2014", end="01 Jan 2017", freq="AS", tz=tz)
date = tm.box_expected(date, box_with_array, False)
mth = getattr(date, op)
result = mth(offset)
expected = pd.DatetimeIndex(exp, tz=tz)
expected = tm.box_expected(expected, box_with_array, False)
tm.assert_equal(result, expected)
class TestDatetime64OverflowHandling:
# TODO: box + de-duplicate
def test_dt64_overflow_masking(self, box_with_array):
# GH#25317
left = Series([Timestamp("1969-12-31")])
right = Series([NaT])
left = tm.box_expected(left, box_with_array)
right = tm.box_expected(right, box_with_array)
expected = TimedeltaIndex([NaT])
expected = tm.box_expected(expected, box_with_array)
result = left - right
tm.assert_equal(result, expected)
def test_dt64_series_arith_overflow(self):
# GH#12534, fixed by GH#19024
dt = pd.Timestamp("1700-01-31")
td = pd.Timedelta("20000 Days")
dti = pd.date_range("1949-09-30", freq="100Y", periods=4)
ser = pd.Series(dti)
msg = "Overflow in int64 addition"
with pytest.raises(OverflowError, match=msg):
ser - dt
with pytest.raises(OverflowError, match=msg):
dt - ser
with pytest.raises(OverflowError, match=msg):
ser + td
with pytest.raises(OverflowError, match=msg):
td + ser
ser.iloc[-1] = pd.NaT
expected = pd.Series(
["2004-10-03", "2104-10-04", "2204-10-04", "NaT"], dtype="datetime64[ns]"
)
res = ser + td
tm.assert_series_equal(res, expected)
res = td + ser
tm.assert_series_equal(res, expected)
ser.iloc[1:] = pd.NaT
expected = pd.Series(
["91279 Days", "NaT", "NaT", "NaT"], dtype="timedelta64[ns]"
)
res = ser - dt
tm.assert_series_equal(res, expected)
res = dt - ser
tm.assert_series_equal(res, -expected)
def test_datetimeindex_sub_timestamp_overflow(self):
dtimax = pd.to_datetime(["now", pd.Timestamp.max])
dtimin = pd.to_datetime(["now", pd.Timestamp.min])
tsneg = Timestamp("1950-01-01")
ts_neg_variants = [
tsneg,
tsneg.to_pydatetime(),
tsneg.to_datetime64().astype("datetime64[ns]"),
tsneg.to_datetime64().astype("datetime64[D]"),
]
tspos = Timestamp("1980-01-01")
ts_pos_variants = [
tspos,
tspos.to_pydatetime(),
tspos.to_datetime64().astype("datetime64[ns]"),
tspos.to_datetime64().astype("datetime64[D]"),
]
msg = "Overflow in int64 addition"
for variant in ts_neg_variants:
with pytest.raises(OverflowError, match=msg):
dtimax - variant
expected = pd.Timestamp.max.value - tspos.value
for variant in ts_pos_variants:
res = dtimax - variant
assert res[1].value == expected
expected = pd.Timestamp.min.value - tsneg.value
for variant in ts_neg_variants:
res = dtimin - variant
assert res[1].value == expected
for variant in ts_pos_variants:
with pytest.raises(OverflowError, match=msg):
dtimin - variant
def test_datetimeindex_sub_datetimeindex_overflow(self):
# GH#22492, GH#22508
dtimax = pd.to_datetime(["now", pd.Timestamp.max])
dtimin = pd.to_datetime(["now", pd.Timestamp.min])
ts_neg = pd.to_datetime(["1950-01-01", "1950-01-01"])
ts_pos = pd.to_datetime(["1980-01-01", "1980-01-01"])
# General tests
expected = pd.Timestamp.max.value - ts_pos[1].value
result = dtimax - ts_pos
assert result[1].value == expected
expected = pd.Timestamp.min.value - ts_neg[1].value
result = dtimin - ts_neg
assert result[1].value == expected
msg = "Overflow in int64 addition"
with pytest.raises(OverflowError, match=msg):
dtimax - ts_neg
with pytest.raises(OverflowError, match=msg):
dtimin - ts_pos
# Edge cases
tmin = pd.to_datetime([pd.Timestamp.min])
t1 = tmin + pd.Timedelta.max + pd.Timedelta("1us")
with pytest.raises(OverflowError, match=msg):
t1 - tmin
tmax = pd.to_datetime([pd.Timestamp.max])
t2 = tmax + pd.Timedelta.min - pd.Timedelta("1us")
with pytest.raises(OverflowError, match=msg):
tmax - t2
class TestTimestampSeriesArithmetic:
def test_empty_series_add_sub(self):
# GH#13844
a = Series(dtype="M8[ns]")
b = Series(dtype="m8[ns]")
tm.assert_series_equal(a, a + b)
tm.assert_series_equal(a, a - b)
tm.assert_series_equal(a, b + a)
msg = "cannot subtract"
with pytest.raises(TypeError, match=msg):
b - a
def test_operators_datetimelike(self):
# ## timedelta64 ###
td1 = Series([timedelta(minutes=5, seconds=3)] * 3)
td1.iloc[2] = np.nan
# ## datetime64 ###
dt1 = Series(
[
pd.Timestamp("20111230"),
pd.Timestamp("20120101"),
pd.Timestamp("20120103"),
]
)
dt1.iloc[2] = np.nan
dt2 = Series(
[
pd.Timestamp("20111231"),
pd.Timestamp("20120102"),
pd.Timestamp("20120104"),
]
)
dt1 - dt2
dt2 - dt1
# datetime64 with timetimedelta
dt1 + td1
td1 + dt1
dt1 - td1
# timetimedelta with datetime64
td1 + dt1
dt1 + td1
def test_dt64ser_sub_datetime_dtype(self):
ts = Timestamp(datetime(1993, 1, 7, 13, 30, 00))
dt = datetime(1993, 6, 22, 13, 30)
ser = Series([ts])
result = pd.to_timedelta(np.abs(ser - dt))
assert result.dtype == "timedelta64[ns]"
# -------------------------------------------------------------
# TODO: This next block of tests came from tests.series.test_operators,
# needs to be de-duplicated and parametrized over `box` classes
def test_operators_datetimelike_invalid(self, all_arithmetic_operators):
# these are all TypeEror ops
op_str = all_arithmetic_operators
def check(get_ser, test_ser):
# check that we are getting a TypeError
# with 'operate' (from core/ops.py) for the ops that are not
# defined
op = getattr(get_ser, op_str, None)
# Previously, _validate_for_numeric_binop in core/indexes/base.py
# did this for us.
with pytest.raises(
TypeError, match="operate|[cC]annot|unsupported operand"
):
op(test_ser)
# ## timedelta64 ###
td1 = Series([timedelta(minutes=5, seconds=3)] * 3)
td1.iloc[2] = np.nan
# ## datetime64 ###
dt1 = Series(
[Timestamp("20111230"), Timestamp("20120101"), Timestamp("20120103")]
)
dt1.iloc[2] = np.nan
dt2 = Series(
[Timestamp("20111231"), Timestamp("20120102"), Timestamp("20120104")]
)
if op_str not in ["__sub__", "__rsub__"]:
check(dt1, dt2)
# ## datetime64 with timetimedelta ###
# TODO(jreback) __rsub__ should raise?
if op_str not in ["__add__", "__radd__", "__sub__"]:
check(dt1, td1)
# 8260, 10763
# datetime64 with tz
tz = "US/Eastern"
dt1 = Series(date_range("2000-01-01 09:00:00", periods=5, tz=tz), name="foo")
dt2 = dt1.copy()
dt2.iloc[2] = np.nan
td1 = Series(pd.timedelta_range("1 days 1 min", periods=5, freq="H"))
td2 = td1.copy()
td2.iloc[1] = np.nan
if op_str not in ["__add__", "__radd__", "__sub__", "__rsub__"]:
check(dt2, td2)
def test_sub_single_tz(self):
# GH#12290
s1 = Series([pd.Timestamp("2016-02-10", tz="America/Sao_Paulo")])
s2 = Series([pd.Timestamp("2016-02-08", tz="America/Sao_Paulo")])
result = s1 - s2
expected = Series([Timedelta("2days")])
tm.assert_series_equal(result, expected)
result = s2 - s1
expected = Series([Timedelta("-2days")])
tm.assert_series_equal(result, expected)
def test_dt64tz_series_sub_dtitz(self):
# GH#19071 subtracting tzaware DatetimeIndex from tzaware Series
# (with same tz) raises, fixed by #19024
dti = pd.date_range("1999-09-30", periods=10, tz="US/Pacific")
ser = pd.Series(dti)
expected = pd.Series(pd.TimedeltaIndex(["0days"] * 10))
res = dti - ser
tm.assert_series_equal(res, expected)
res = ser - dti
tm.assert_series_equal(res, expected)
def test_sub_datetime_compat(self):
# see GH#14088
s = Series([datetime(2016, 8, 23, 12, tzinfo=pytz.utc), pd.NaT])
dt = datetime(2016, 8, 22, 12, tzinfo=pytz.utc)
exp = Series([Timedelta("1 days"), pd.NaT])
tm.assert_series_equal(s - dt, exp)
tm.assert_series_equal(s - Timestamp(dt), exp)
def test_dt64_series_add_mixed_tick_DateOffset(self):
# GH#4532
# operate with pd.offsets
s = Series([Timestamp("20130101 9:01"), Timestamp("20130101 9:02")])
result = s + pd.offsets.Milli(5)
result2 = pd.offsets.Milli(5) + s
expected = Series(
[Timestamp("20130101 9:01:00.005"), Timestamp("20130101 9:02:00.005")]
)
tm.assert_series_equal(result, expected)
tm.assert_series_equal(result2, expected)
result = s + pd.offsets.Minute(5) + pd.offsets.Milli(5)
expected = Series(
[Timestamp("20130101 9:06:00.005"), Timestamp("20130101 9:07:00.005")]
)
tm.assert_series_equal(result, expected)
def test_datetime64_ops_nat(self):
# GH#11349
datetime_series = Series([NaT, Timestamp("19900315")])
nat_series_dtype_timestamp = Series([NaT, NaT], dtype="datetime64[ns]")
single_nat_dtype_datetime = Series([NaT], dtype="datetime64[ns]")
# subtraction
tm.assert_series_equal(-NaT + datetime_series, nat_series_dtype_timestamp)
msg = "Unary negative expects"
with pytest.raises(TypeError, match=msg):
-single_nat_dtype_datetime + datetime_series
tm.assert_series_equal(
-NaT + nat_series_dtype_timestamp, nat_series_dtype_timestamp
)
with pytest.raises(TypeError, match=msg):
-single_nat_dtype_datetime + nat_series_dtype_timestamp
# addition
tm.assert_series_equal(
nat_series_dtype_timestamp + NaT, nat_series_dtype_timestamp
)
tm.assert_series_equal(
NaT + nat_series_dtype_timestamp, nat_series_dtype_timestamp
)
tm.assert_series_equal(
nat_series_dtype_timestamp + NaT, nat_series_dtype_timestamp
)
tm.assert_series_equal(
NaT + nat_series_dtype_timestamp, nat_series_dtype_timestamp
)
# -------------------------------------------------------------
# Invalid Operations
# TODO: this block also needs to be de-duplicated and parametrized
@pytest.mark.parametrize(
"dt64_series",
[
Series([Timestamp("19900315"), Timestamp("19900315")]),
Series([pd.NaT, Timestamp("19900315")]),
Series([pd.NaT, pd.NaT], dtype="datetime64[ns]"),
],
)
@pytest.mark.parametrize("one", [1, 1.0, np.array(1)])
def test_dt64_mul_div_numeric_invalid(self, one, dt64_series):
# multiplication
msg = "cannot perform .* with this index type"
with pytest.raises(TypeError, match=msg):
dt64_series * one
with pytest.raises(TypeError, match=msg):
one * dt64_series
# division
with pytest.raises(TypeError, match=msg):
dt64_series / one
with pytest.raises(TypeError, match=msg):
one / dt64_series
# TODO: parametrize over box
@pytest.mark.parametrize("op", ["__add__", "__radd__", "__sub__", "__rsub__"])
def test_dt64_series_add_intlike(self, tz_naive_fixture, op):
# GH#19123
tz = tz_naive_fixture
dti = pd.DatetimeIndex(["2016-01-02", "2016-02-03", "NaT"], tz=tz)
ser = Series(dti)
other = Series([20, 30, 40], dtype="uint8")
method = getattr(ser, op)
msg = "|".join(
[
"Addition/subtraction of integers and integer-arrays",
"cannot subtract .* from ndarray",
]
)
with pytest.raises(TypeError, match=msg):
method(1)
with pytest.raises(TypeError, match=msg):
method(other)
with pytest.raises(TypeError, match=msg):
method(np.array(other))
with pytest.raises(TypeError, match=msg):
method(pd.Index(other))
# -------------------------------------------------------------
# Timezone-Centric Tests
def test_operators_datetimelike_with_timezones(self):
tz = "US/Eastern"
dt1 = Series(date_range("2000-01-01 09:00:00", periods=5, tz=tz), name="foo")
dt2 = dt1.copy()
dt2.iloc[2] = np.nan
td1 = Series(pd.timedelta_range("1 days 1 min", periods=5, freq="H"))
td2 = td1.copy()
td2.iloc[1] = np.nan
result = dt1 + td1[0]
exp = (dt1.dt.tz_localize(None) + td1[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = dt2 + td2[0]
exp = (dt2.dt.tz_localize(None) + td2[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
# odd numpy behavior with scalar timedeltas
result = td1[0] + dt1
exp = (dt1.dt.tz_localize(None) + td1[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = td2[0] + dt2
exp = (dt2.dt.tz_localize(None) + td2[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = dt1 - td1[0]
exp = (dt1.dt.tz_localize(None) - td1[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
msg = "(bad|unsupported) operand type for unary"
with pytest.raises(TypeError, match=msg):
td1[0] - dt1
result = dt2 - td2[0]
exp = (dt2.dt.tz_localize(None) - td2[0]).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
with pytest.raises(TypeError, match=msg):
td2[0] - dt2
result = dt1 + td1
exp = (dt1.dt.tz_localize(None) + td1).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = dt2 + td2
exp = (dt2.dt.tz_localize(None) + td2).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = dt1 - td1
exp = (dt1.dt.tz_localize(None) - td1).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
result = dt2 - td2
exp = (dt2.dt.tz_localize(None) - td2).dt.tz_localize(tz)
tm.assert_series_equal(result, exp)
msg = "cannot (add|subtract)"
with pytest.raises(TypeError, match=msg):
td1 - dt1
with pytest.raises(TypeError, match=msg):
td2 - dt2
class TestDatetimeIndexArithmetic:
# -------------------------------------------------------------
# Binary operations DatetimeIndex and int
def test_dti_addsub_int(self, tz_naive_fixture, one):
# Variants of `one` for #19012
tz = tz_naive_fixture
rng = pd.date_range("2000-01-01 09:00", freq="H", periods=10, tz=tz)
msg = "Addition/subtraction of integers"
with pytest.raises(TypeError, match=msg):
rng + one
with pytest.raises(TypeError, match=msg):
rng += one
with pytest.raises(TypeError, match=msg):
rng - one
with pytest.raises(TypeError, match=msg):
rng -= one
# -------------------------------------------------------------
# __add__/__sub__ with integer arrays
@pytest.mark.parametrize("freq", ["H", "D"])
@pytest.mark.parametrize("int_holder", [np.array, pd.Index])
def test_dti_add_intarray_tick(self, int_holder, freq):
# GH#19959
dti = pd.date_range("2016-01-01", periods=2, freq=freq)
other = int_holder([4, -1])
msg = "Addition/subtraction of integers|cannot subtract DatetimeArray from"
assert_invalid_addsub_type(dti, other, msg)
@pytest.mark.parametrize("freq", ["W", "M", "MS", "Q"])
@pytest.mark.parametrize("int_holder", [np.array, pd.Index])
def test_dti_add_intarray_non_tick(self, int_holder, freq):
# GH#19959
dti = pd.date_range("2016-01-01", periods=2, freq=freq)
other = int_holder([4, -1])
msg = "Addition/subtraction of integers|cannot subtract DatetimeArray from"
assert_invalid_addsub_type(dti, other, msg)
@pytest.mark.parametrize("int_holder", [np.array, pd.Index])
def test_dti_add_intarray_no_freq(self, int_holder):
# GH#19959
dti = pd.DatetimeIndex(["2016-01-01", "NaT", "2017-04-05 06:07:08"])
other = int_holder([9, 4, -1])
msg = "|".join(
["cannot subtract DatetimeArray from", "Addition/subtraction of integers"]
)
assert_invalid_addsub_type(dti, other, msg)
# -------------------------------------------------------------
# Binary operations DatetimeIndex and TimedeltaIndex/array
def test_dti_add_tdi(self, tz_naive_fixture):
# GH#17558
tz = tz_naive_fixture
dti = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
tdi = pd.timedelta_range("0 days", periods=10)
expected = pd.date_range("2017-01-01", periods=10, tz=tz)
expected = expected._with_freq(None)
# add with TimdeltaIndex
result = dti + tdi
tm.assert_index_equal(result, expected)
result = tdi + dti
tm.assert_index_equal(result, expected)
# add with timedelta64 array
result = dti + tdi.values
tm.assert_index_equal(result, expected)
result = tdi.values + dti
tm.assert_index_equal(result, expected)
def test_dti_iadd_tdi(self, tz_naive_fixture):
# GH#17558
tz = tz_naive_fixture
dti = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
tdi = pd.timedelta_range("0 days", periods=10)
expected = pd.date_range("2017-01-01", periods=10, tz=tz)
expected = expected._with_freq(None)
# iadd with TimdeltaIndex
result = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
result += tdi
tm.assert_index_equal(result, expected)
result = pd.timedelta_range("0 days", periods=10)
result += dti
tm.assert_index_equal(result, expected)
# iadd with timedelta64 array
result = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
result += tdi.values
tm.assert_index_equal(result, expected)
result = pd.timedelta_range("0 days", periods=10)
result += dti
tm.assert_index_equal(result, expected)
def test_dti_sub_tdi(self, tz_naive_fixture):
# GH#17558
tz = tz_naive_fixture
dti = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
tdi = pd.timedelta_range("0 days", periods=10)
expected = pd.date_range("2017-01-01", periods=10, tz=tz, freq="-1D")
expected = expected._with_freq(None)
# sub with TimedeltaIndex
result = dti - tdi
tm.assert_index_equal(result, expected)
msg = "cannot subtract .*TimedeltaArray"
with pytest.raises(TypeError, match=msg):
tdi - dti
# sub with timedelta64 array
result = dti - tdi.values
tm.assert_index_equal(result, expected)
msg = "cannot subtract DatetimeArray from"
with pytest.raises(TypeError, match=msg):
tdi.values - dti
def test_dti_isub_tdi(self, tz_naive_fixture):
# GH#17558
tz = tz_naive_fixture
dti = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
tdi = pd.timedelta_range("0 days", periods=10)
expected = pd.date_range("2017-01-01", periods=10, tz=tz, freq="-1D")
expected = expected._with_freq(None)
# isub with TimedeltaIndex
result = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
result -= tdi
tm.assert_index_equal(result, expected)
msg = "cannot subtract .* from a TimedeltaArray"
with pytest.raises(TypeError, match=msg):
tdi -= dti
# isub with timedelta64 array
result = DatetimeIndex([Timestamp("2017-01-01", tz=tz)] * 10)
result -= tdi.values
tm.assert_index_equal(result, expected)
msg = "|".join(
[
"cannot perform __neg__ with this index type:",
"ufunc subtract cannot use operands with types",
"cannot subtract DatetimeArray from",
]
)
with pytest.raises(TypeError, match=msg):
tdi.values -= dti
# -------------------------------------------------------------
# Binary Operations DatetimeIndex and datetime-like
# TODO: A couple other tests belong in this section. Move them in
# A PR where there isn't already a giant diff.
@pytest.mark.parametrize(
"addend",
[
datetime(2011, 1, 1),
DatetimeIndex(["2011-01-01", "2011-01-02"]),
DatetimeIndex(["2011-01-01", "2011-01-02"]).tz_localize("US/Eastern"),
np.datetime64("2011-01-01"),
Timestamp("2011-01-01"),
],
ids=lambda x: type(x).__name__,
)
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_add_datetimelike_and_dtarr(self, box_with_array, addend, tz):
# GH#9631
dti = DatetimeIndex(["2011-01-01", "2011-01-02"]).tz_localize(tz)
dtarr = tm.box_expected(dti, box_with_array)
msg = "cannot add DatetimeArray and"
with pytest.raises(TypeError, match=msg):
dtarr + addend
with pytest.raises(TypeError, match=msg):
addend + dtarr
# -------------------------------------------------------------
def test_dta_add_sub_index(self, tz_naive_fixture):
# Check that DatetimeArray defers to Index classes
dti = date_range("20130101", periods=3, tz=tz_naive_fixture)
dta = dti.array
result = dta - dti
expected = dti - dti
tm.assert_index_equal(result, expected)
tdi = result
result = dta + tdi
expected = dti + tdi
tm.assert_index_equal(result, expected)
result = dta - tdi
expected = dti - tdi
tm.assert_index_equal(result, expected)
def test_sub_dti_dti(self):
# previously performed setop (deprecated in 0.16.0), now changed to
# return subtraction -> TimeDeltaIndex (GH ...)
dti = date_range("20130101", periods=3)
dti_tz = date_range("20130101", periods=3).tz_localize("US/Eastern")
dti_tz2 = date_range("20130101", periods=3).tz_localize("UTC")
expected = TimedeltaIndex([0, 0, 0])
result = dti - dti
tm.assert_index_equal(result, expected)
result = dti_tz - dti_tz
tm.assert_index_equal(result, expected)
msg = "DatetimeArray subtraction must have the same timezones or"
with pytest.raises(TypeError, match=msg):
dti_tz - dti
with pytest.raises(TypeError, match=msg):
dti - dti_tz
with pytest.raises(TypeError, match=msg):
dti_tz - dti_tz2
# isub
dti -= dti
tm.assert_index_equal(dti, expected)
# different length raises ValueError
dti1 = date_range("20130101", periods=3)
dti2 = date_range("20130101", periods=4)
msg = "cannot add indices of unequal length"
with pytest.raises(ValueError, match=msg):
dti1 - dti2
# NaN propagation
dti1 = DatetimeIndex(["2012-01-01", np.nan, "2012-01-03"])
dti2 = DatetimeIndex(["2012-01-02", "2012-01-03", np.nan])
expected = TimedeltaIndex(["1 days", np.nan, np.nan])
result = dti2 - dti1
tm.assert_index_equal(result, expected)
# -------------------------------------------------------------------
# TODO: Most of this block is moved from series or frame tests, needs
# cleanup, box-parametrization, and de-duplication
@pytest.mark.parametrize("op", [operator.add, operator.sub])
def test_timedelta64_equal_timedelta_supported_ops(self, op):
ser = Series(
[
Timestamp("20130301"),
Timestamp("20130228 23:00:00"),
Timestamp("20130228 22:00:00"),
Timestamp("20130228 21:00:00"),
]
)
intervals = ["D", "h", "m", "s", "us"]
def timedelta64(*args):
# see casting notes in NumPy gh-12927
return np.sum(list(starmap(np.timedelta64, zip(args, intervals))))
for d, h, m, s, us in product(*([range(2)] * 5)):
nptd = timedelta64(d, h, m, s, us)
pytd = timedelta(days=d, hours=h, minutes=m, seconds=s, microseconds=us)
lhs = op(ser, nptd)
rhs = op(ser, pytd)
tm.assert_series_equal(lhs, rhs)
def test_ops_nat_mixed_datetime64_timedelta64(self):
# GH#11349
timedelta_series = Series([NaT, Timedelta("1s")])
datetime_series = Series([NaT, Timestamp("19900315")])
nat_series_dtype_timedelta = Series([NaT, NaT], dtype="timedelta64[ns]")
nat_series_dtype_timestamp = Series([NaT, NaT], dtype="datetime64[ns]")
single_nat_dtype_datetime = Series([NaT], dtype="datetime64[ns]")
single_nat_dtype_timedelta = Series([NaT], dtype="timedelta64[ns]")
# subtraction
tm.assert_series_equal(
datetime_series - single_nat_dtype_datetime, nat_series_dtype_timedelta
)
tm.assert_series_equal(
datetime_series - single_nat_dtype_timedelta, nat_series_dtype_timestamp
)
tm.assert_series_equal(
-single_nat_dtype_timedelta + datetime_series, nat_series_dtype_timestamp
)
# without a Series wrapping the NaT, it is ambiguous
# whether it is a datetime64 or timedelta64
# defaults to interpreting it as timedelta64
tm.assert_series_equal(
nat_series_dtype_timestamp - single_nat_dtype_datetime,
nat_series_dtype_timedelta,
)
tm.assert_series_equal(
nat_series_dtype_timestamp - single_nat_dtype_timedelta,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
-single_nat_dtype_timedelta + nat_series_dtype_timestamp,
nat_series_dtype_timestamp,
)
msg = "cannot subtract a datelike"
with pytest.raises(TypeError, match=msg):
timedelta_series - single_nat_dtype_datetime
# addition
tm.assert_series_equal(
nat_series_dtype_timestamp + single_nat_dtype_timedelta,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
single_nat_dtype_timedelta + nat_series_dtype_timestamp,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
nat_series_dtype_timestamp + single_nat_dtype_timedelta,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
single_nat_dtype_timedelta + nat_series_dtype_timestamp,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
nat_series_dtype_timedelta + single_nat_dtype_datetime,
nat_series_dtype_timestamp,
)
tm.assert_series_equal(
single_nat_dtype_datetime + nat_series_dtype_timedelta,
nat_series_dtype_timestamp,
)
def test_ufunc_coercions(self):
idx = date_range("2011-01-01", periods=3, freq="2D", name="x")
delta = np.timedelta64(1, "D")
exp = date_range("2011-01-02", periods=3, freq="2D", name="x")
for result in [idx + delta, np.add(idx, delta)]:
assert isinstance(result, DatetimeIndex)
tm.assert_index_equal(result, exp)
assert result.freq == "2D"
exp = date_range("2010-12-31", periods=3, freq="2D", name="x")
for result in [idx - delta, np.subtract(idx, delta)]:
assert isinstance(result, DatetimeIndex)
tm.assert_index_equal(result, exp)
assert result.freq == "2D"
# When adding/subtracting an ndarray (which has no .freq), the result
# does not infer freq
idx = idx._with_freq(None)
delta = np.array(
[np.timedelta64(1, "D"), np.timedelta64(2, "D"), np.timedelta64(3, "D")]
)
exp = DatetimeIndex(["2011-01-02", "2011-01-05", "2011-01-08"], name="x")
for result in [idx + delta, np.add(idx, delta)]:
tm.assert_index_equal(result, exp)
assert result.freq == exp.freq
exp = DatetimeIndex(["2010-12-31", "2011-01-01", "2011-01-02"], name="x")
for result in [idx - delta, np.subtract(idx, delta)]:
assert isinstance(result, DatetimeIndex)
tm.assert_index_equal(result, exp)
assert result.freq == exp.freq
def test_dti_add_series(self, tz_naive_fixture, names):
# GH#13905
tz = tz_naive_fixture
index = DatetimeIndex(
["2016-06-28 05:30", "2016-06-28 05:31"], tz=tz, name=names[0]
)
ser = Series([Timedelta(seconds=5)] * 2, index=index, name=names[1])
expected = Series(index + Timedelta(seconds=5), index=index, name=names[2])
# passing name arg isn't enough when names[2] is None
expected.name = names[2]
assert expected.dtype == index.dtype
result = ser + index
tm.assert_series_equal(result, expected)
result2 = index + ser
tm.assert_series_equal(result2, expected)
expected = index + Timedelta(seconds=5)
result3 = ser.values + index
tm.assert_index_equal(result3, expected)
result4 = index + ser.values
tm.assert_index_equal(result4, expected)
@pytest.mark.parametrize("op", [operator.add, roperator.radd, operator.sub])
def test_dti_addsub_offset_arraylike(
self, tz_naive_fixture, names, op, index_or_series
):
# GH#18849, GH#19744
box = pd.Index
other_box = index_or_series
tz = tz_naive_fixture
dti = pd.date_range("2017-01-01", periods=2, tz=tz, name=names[0])
other = other_box([pd.offsets.MonthEnd(), pd.offsets.Day(n=2)], name=names[1])
xbox = get_upcast_box(box, other)
with tm.assert_produces_warning(PerformanceWarning):
res = op(dti, other)
expected = DatetimeIndex(
[op(dti[n], other[n]) for n in range(len(dti))], name=names[2], freq="infer"
)
expected = tm.box_expected(expected, xbox)
tm.assert_equal(res, expected)
@pytest.mark.parametrize("other_box", [pd.Index, np.array])
def test_dti_addsub_object_arraylike(
self, tz_naive_fixture, box_with_array, other_box
):
tz = tz_naive_fixture
dti = pd.date_range("2017-01-01", periods=2, tz=tz)
dtarr = tm.box_expected(dti, box_with_array)
other = other_box([pd.offsets.MonthEnd(), pd.Timedelta(days=4)])
xbox = get_upcast_box(box_with_array, other)
expected = pd.DatetimeIndex(["2017-01-31", "2017-01-06"], tz=tz_naive_fixture)
expected = tm.box_expected(expected, xbox)
warn = PerformanceWarning
if box_with_array is pd.DataFrame and tz is not None:
warn = None
with tm.assert_produces_warning(warn):
result = dtarr + other
tm.assert_equal(result, expected)
expected = pd.DatetimeIndex(["2016-12-31", "2016-12-29"], tz=tz_naive_fixture)
expected = tm.box_expected(expected, xbox)
with tm.assert_produces_warning(warn):
result = dtarr - other
tm.assert_equal(result, expected)
@pytest.mark.parametrize("years", [-1, 0, 1])
@pytest.mark.parametrize("months", [-2, 0, 2])
def test_shift_months(years, months):
dti = DatetimeIndex(
[
Timestamp("2000-01-05 00:15:00"),
Timestamp("2000-01-31 00:23:00"),
Timestamp("2000-01-01"),
Timestamp("2000-02-29"),
Timestamp("2000-12-31"),
]
)
actual = DatetimeIndex(shift_months(dti.asi8, years * 12 + months))
raw = [x + pd.offsets.DateOffset(years=years, months=months) for x in dti]
expected = DatetimeIndex(raw)
tm.assert_index_equal(actual, expected)
def test_dt64arr_addsub_object_dtype_2d():
# block-wise DataFrame operations will require operating on 2D
# DatetimeArray/TimedeltaArray, so check that specifically.
dti = pd.date_range("1994-02-13", freq="2W", periods=4)
dta = dti._data.reshape((4, 1))
other = np.array([[pd.offsets.Day(n)] for n in range(4)])
assert other.shape == dta.shape
with tm.assert_produces_warning(PerformanceWarning):
result = dta + other
with tm.assert_produces_warning(PerformanceWarning):
expected = (dta[:, 0] + other[:, 0]).reshape(-1, 1)
assert isinstance(result, DatetimeArray)
assert result.freq is None
tm.assert_numpy_array_equal(result._data, expected._data)
with tm.assert_produces_warning(PerformanceWarning):
# Case where we expect to get a TimedeltaArray back
result2 = dta - dta.astype(object)
assert isinstance(result2, TimedeltaArray)
assert result2.shape == (4, 1)
assert result2.freq is None
assert (result2.asi8 == 0).all()