def _get_time_delta_bins(self, ax):
if not isinstance(ax, TimedeltaIndex):
raise TypeError('axis must be a TimedeltaIndex, but got '
'an instance of %r' % type(ax).__name__)
if not len(ax):
binner = labels = TimedeltaIndex(data=[],
freq=self.freq,
name=ax.name)
return binner, [], labels
start = ax[0]
end = ax[-1]
labels = binner = TimedeltaIndex(start=start,
end=end,
freq=self.freq,
name=ax.name)
end_stamps = labels + 1
bins = ax.searchsorted(end_stamps, side='left')
# Addresses GH #10530
if self.base > 0:
labels += type(self.freq)(self.base)
return binner, bins, labels
def test_astype_object(self):
tdi = TimedeltaIndex(["1 Day", "3 Hours"])
arr = TimedeltaArray(tdi)
asobj = arr.astype("O")
assert isinstance(asobj, np.ndarray)
assert asobj.dtype == "O"
assert list(asobj) == list(tdi)
def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike
(e.g. datetime64[ns],timedelta64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
from pandas import Series
if not isinstance(data, Series):
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
index = data.index
name = data.name
orig = data if is_categorical_dtype(data) else None
if orig is not None:
data = orig.values.categories
if is_datetime64_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data, copy=copy),
index,
name=name,
orig=orig)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data, copy=copy),
index,
data.name,
orig=orig)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaProperties(TimedeltaIndex(data, copy=copy),
index,
name=name,
orig=orig)
else:
if is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy),
index,
name=name,
orig=orig)
if is_datetime_arraylike(data):
return DatetimeProperties(DatetimeIndex(data, copy=copy),
index,
name=name,
orig=orig)
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
def test_from_tdi(self):
tdi = TimedeltaIndex(["1 Day", "3 Hours"])
arr = TimedeltaArray(tdi)
assert list(arr) == list(tdi)
# Check that Index.__new__ knows what to do with TimedeltaArray
tdi2 = pd.Index(arr)
assert isinstance(tdi2, TimedeltaIndex)
assert list(tdi2) == list(arr)
def timedelta_index():
"""
A fixture to provide TimedeltaIndex objects with different frequencies.
Most TimedeltaArray behavior is already tested in TimedeltaIndex tests,
so here we just test that the TimedeltaArray behavior matches
the TimedeltaIndex behavior.
"""
# TODO: flesh this out
return TimedeltaIndex(["1 Day", "3 Hours", "NaT"])
def _get_values(self):
data = self._parent
if is_datetime64_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaIndex(data, copy=False, name=self.name)
elif is_period_dtype(data.dtype):
return PeriodArray(data, copy=False)
raise TypeError(
f"cannot convert an object of type {type(data)} to a datetimelike index"
)
def _get_values(self):
data = self.values
if is_datetime64_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaIndex(data, copy=False, name=self.name)
else:
if is_period_arraylike(data):
return PeriodIndex(data, copy=False, name=self.name)
if is_datetime_arraylike(data):
return DatetimeIndex(data, copy=False, name=self.name)
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
def test_diff(self):
# Just run the function
self.ts.diff()
# int dtype
a = 10000000000000000
b = a + 1
s = Series([a, b])
rs = s.diff()
assert rs[1] == 1
# neg n
rs = self.ts.diff(-1)
xp = self.ts - self.ts.shift(-1)
assert_series_equal(rs, xp)
# 0
rs = self.ts.diff(0)
xp = self.ts - self.ts
assert_series_equal(rs, xp)
# datetime diff (GH3100)
s = Series(date_range('20130102', periods=5))
rs = s - s.shift(1)
xp = s.diff()
assert_series_equal(rs, xp)
# timedelta diff
nrs = rs - rs.shift(1)
nxp = xp.diff()
assert_series_equal(nrs, nxp)
# with tz
s = Series(date_range('2000-01-01 09:00:00',
periods=5,
tz='US/Eastern'),
name='foo')
result = s.diff()
assert_series_equal(
result, Series(TimedeltaIndex(['NaT'] + ['1 days'] * 4),
name='foo'))
def _sub_datelike(self, other):
if other is tslib.NaT:
new_data = np.empty(len(self), dtype=np.int64)
new_data.fill(tslib.iNaT)
return TimedeltaIndex(new_data, name=self.name)
return NotImplemented
def test_shift(self):
shifted = self.ts.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, self.ts.index)
tm.assert_index_equal(unshifted.index, self.ts.index)
tm.assert_numpy_array_equal(unshifted.valid().values,
self.ts.values[:-1])
offset = BDay()
shifted = self.ts.shift(1, freq=offset)
unshifted = shifted.shift(-1, freq=offset)
assert_series_equal(unshifted, self.ts)
unshifted = self.ts.shift(0, freq=offset)
assert_series_equal(unshifted, self.ts)
shifted = self.ts.shift(1, freq='B')
unshifted = shifted.shift(-1, freq='B')
assert_series_equal(unshifted, self.ts)
# corner case
unshifted = self.ts.shift(0)
assert_series_equal(unshifted, self.ts)
# Shifting with PeriodIndex
ps = tm.makePeriodSeries()
shifted = ps.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, ps.index)
tm.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.valid().values, ps.values[:-1])
shifted2 = ps.shift(1, 'B')
shifted3 = ps.shift(1, BDay())
assert_series_equal(shifted2, shifted3)
assert_series_equal(ps, shifted2.shift(-1, 'B'))
pytest.raises(ValueError, ps.shift, freq='D')
# legacy support
shifted4 = ps.shift(1, freq='B')
assert_series_equal(shifted2, shifted4)
shifted5 = ps.shift(1, freq=BDay())
assert_series_equal(shifted5, shifted4)
# 32-bit taking
# GH 8129
index = date_range('2000-01-01', periods=5)
for dtype in ['int32', 'int64']:
s1 = Series(np.arange(5, dtype=dtype), index=index)
p = s1.iloc[1]
result = s1.shift(periods=p)
expected = Series([np.nan, 0, 1, 2, 3], index=index)
assert_series_equal(result, expected)
# xref 8260
# with tz
s = Series(date_range('2000-01-01 09:00:00',
periods=5,
tz='US/Eastern'),
name='foo')
result = s - s.shift()
exp = Series(TimedeltaIndex(['NaT'] + ['1 days'] * 4), name='foo')
assert_series_equal(result, exp)
# incompat tz
s2 = Series(date_range('2000-01-01 09:00:00', periods=5, tz='CET'),
name='foo')
pytest.raises(ValueError, lambda: s - s2)
def test_shift(self, datetime_series):
shifted = datetime_series.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, datetime_series.index)
tm.assert_index_equal(unshifted.index, datetime_series.index)
tm.assert_numpy_array_equal(unshifted.dropna().values,
datetime_series.values[:-1])
offset = BDay()
shifted = datetime_series.shift(1, freq=offset)
unshifted = shifted.shift(-1, freq=offset)
tm.assert_series_equal(unshifted, datetime_series)
unshifted = datetime_series.shift(0, freq=offset)
tm.assert_series_equal(unshifted, datetime_series)
shifted = datetime_series.shift(1, freq="B")
unshifted = shifted.shift(-1, freq="B")
tm.assert_series_equal(unshifted, datetime_series)
# corner case
unshifted = datetime_series.shift(0)
tm.assert_series_equal(unshifted, datetime_series)
# Shifting with PeriodIndex
ps = tm.makePeriodSeries()
shifted = ps.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, ps.index)
tm.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.dropna().values, ps.values[:-1])
shifted2 = ps.shift(1, "B")
shifted3 = ps.shift(1, BDay())
tm.assert_series_equal(shifted2, shifted3)
tm.assert_series_equal(ps, shifted2.shift(-1, "B"))
msg = "Given freq D does not match PeriodIndex freq B"
with pytest.raises(ValueError, match=msg):
ps.shift(freq="D")
# legacy support
shifted4 = ps.shift(1, freq="B")
tm.assert_series_equal(shifted2, shifted4)
shifted5 = ps.shift(1, freq=BDay())
tm.assert_series_equal(shifted5, shifted4)
# 32-bit taking
# GH 8129
index = date_range("2000-01-01", periods=5)
for dtype in ["int32", "int64"]:
s1 = Series(np.arange(5, dtype=dtype), index=index)
p = s1.iloc[1]
result = s1.shift(periods=p)
expected = Series([np.nan, 0, 1, 2, 3], index=index)
tm.assert_series_equal(result, expected)
# xref 8260
# with tz
s = Series(date_range("2000-01-01 09:00:00",
periods=5,
tz="US/Eastern"),
name="foo")
result = s - s.shift()
exp = Series(TimedeltaIndex(["NaT"] + ["1 days"] * 4), name="foo")
tm.assert_series_equal(result, exp)
# incompat tz
s2 = Series(date_range("2000-01-01 09:00:00", periods=5, tz="CET"),
name="foo")
msg = "DatetimeArray subtraction must have the same timezones or no timezones"
with pytest.raises(TypeError, match=msg):
s - s2
def test_strftime_nat(self):
# GH 29578
arr = PeriodArray(
PeriodIndex(["2019-01-01", pd.NaT], dtype="period[D]"))
result = arr.strftime("%Y-%m-%d")
expected = np.array(["2019-01-01", np.nan], dtype=object)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"array,casting_nats",
[
(
TimedeltaIndex(["1 Day", "3 Hours", "NaT"])._data,
(pd.NaT, np.timedelta64("NaT", "ns")),
),
(
pd.date_range("2000-01-01", periods=3, freq="D")._data,
(pd.NaT, np.datetime64("NaT", "ns")),
),
(pd.period_range("2000-01-01", periods=3, freq="D")._data, (pd.NaT, )),
],
ids=lambda x: type(x).__name__,
)
def test_casting_nat_setitem_array(array, casting_nats):
expected = type(array)._from_sequence([pd.NaT, array[1], array[2]])
for nat in casting_nats:
arr = array.copy()
