def __rfloordiv__(self, other):
if isinstance(other, (ABCSeries, ABCDataFrame, ABCIndexClass)):
return NotImplemented
other = lib.item_from_zerodim(other)
if is_scalar(other):
if isinstance(other, (timedelta, np.timedelta64, Tick)):
other = Timedelta(other)
if other is NaT:
# treat this specifically as timedelta-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# dispatch to Timedelta implementation
result = other.__floordiv__(self._data)
return result
raise TypeError("Cannot divide {typ} by {cls}"
.format(typ=type(other).__name__,
cls=type(self).__name__))
if not hasattr(other, "dtype"):
# list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide with unequal lengths")
elif is_timedelta64_dtype(other):
other = type(self)(other)
# numpy timedelta64 does not natively support floordiv, so operate
# on the i8 values
result = other.asi8 // self.asi8
mask = self._isnan | other._isnan
if mask.any():
result = result.astype(np.int64)
result[mask] = np.nan
return result
elif is_object_dtype(other):
result = [other[n] // self[n] for n in range(len(self))]
result = np.array(result)
return result
else:
dtype = getattr(other, "dtype", type(other).__name__)
raise TypeError("Cannot divide {typ} by {cls}"
.format(typ=dtype, cls=type(self).__name__))
def wrapper(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCDataFrame, ABCSeries, ABCIndexClass)):
return NotImplemented
if _is_convertible_to_td(other) or other is NaT:
try:
other = Timedelta(other)
except ValueError:
# failed to parse as timedelta
return ops.invalid_comparison(self, other, op)
result = op(self.view('i8'), other.value)
if isna(other):
result.fill(nat_result)
elif not is_list_like(other):
return ops.invalid_comparison(self, other, op)
elif len(other) != len(self):
raise ValueError("Lengths must match")
else:
try:
other = type(self)._from_sequence(other)._data
except (ValueError, TypeError):
return ops.invalid_comparison(self, other, op)
result = op(self.view('i8'), other.view('i8'))
result = com.values_from_object(result)
o_mask = np.array(isna(other))
if o_mask.any():
result[o_mask] = nat_result
if self._hasnans:
result[self._isnan] = nat_result
return result
def _box_func(self, x) -> Union[Timedelta, NaTType]:
return Timedelta(x, unit="ns")
def __floordiv__(self, other):
if isinstance(other, (ABCSeries, ABCDataFrame, ABCIndexClass)):
return NotImplemented
other = lib.item_from_zerodim(other)
if is_scalar(other):
if isinstance(other, (timedelta, np.timedelta64, Tick)):
other = Timedelta(other)
if other is NaT:
# treat this specifically as timedelta-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# dispatch to Timedelta implementation
result = other.__rfloordiv__(self._data)
return result
# at this point we should only have numeric scalars; anything
# else will raise
result = self.asi8 // other
result[self._isnan] = iNaT
freq = None
if self.freq is not None:
# Note: freq gets division, not floor-division
freq = self.freq / other
return type(self)(result.view('m8[ns]'), freq=freq)
if not hasattr(other, "dtype"):
# list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide with unequal lengths")
elif is_timedelta64_dtype(other):
other = type(self)(other)
# numpy timedelta64 does not natively support floordiv, so operate
# on the i8 values
result = self.asi8 // other.asi8
mask = self._isnan | other._isnan
if mask.any():
result = result.astype(np.int64)
result[mask] = np.nan
return result
elif is_object_dtype(other):
result = [self[n] // other[n] for n in range(len(self))]
result = np.array(result)
if lib.infer_dtype(result, skipna=False) == 'timedelta':
result, _ = sequence_to_td64ns(result)
return type(self)(result)
return result
elif is_integer_dtype(other) or is_float_dtype(other):
result = self._data // other
return type(self)(result)
else:
dtype = getattr(other, "dtype", type(other).__name__)
raise TypeError("Cannot divide {typ} by {cls}"
.format(typ=dtype, cls=type(self).__name__))
def __floordiv__(self, other):
if is_scalar(other):
if isinstance(other, (timedelta, np.timedelta64, Tick)):
other = Timedelta(other)
if other is NaT:
# treat this specifically as timedelta-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# dispatch to Timedelta implementation
result = other.__rfloordiv__(self._data)
return result
# at this point we should only have numeric scalars; anything
# else will raise
result = self.asi8 // other
result[self._isnan] = iNaT
freq = None
if self.freq is not None:
# Note: freq gets division, not floor-division
freq = self.freq / other
if freq.nanos == 0 and self.freq.nanos != 0:
# e.g. if self.freq is Nano(1) then dividing by 2
# rounds down to zero
freq = None
return type(self)(result.view("m8[ns]"), freq=freq)
if not hasattr(other, "dtype"):
# list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide with unequal lengths")
elif is_timedelta64_dtype(other.dtype):
other = type(self)(other)
# numpy timedelta64 does not natively support floordiv, so operate
# on the i8 values
result = self.asi8 // other.asi8
mask = self._isnan | other._isnan
if mask.any():
result = result.astype(np.int64)
result[mask] = np.nan
return result
elif is_object_dtype(other.dtype):
result = [self[n] // other[n] for n in range(len(self))]
result = np.array(result)
if lib.infer_dtype(result, skipna=False) == "timedelta":
result, _ = sequence_to_td64ns(result)
return type(self)(result)
return result
elif is_integer_dtype(other.dtype) or is_float_dtype(other.dtype):
result = self._data // other
return type(self)(result)
else:
dtype = getattr(other, "dtype", type(other).__name__)
raise TypeError(f"Cannot divide {dtype} by {type(self).__name__}")
def _box_func(self):
return lambda x: Timedelta(x, unit="ns")
def __floordiv__(self, other):
if isinstance(other, (ABCSeries, ABCDataFrame, ABCIndexClass)):
return NotImplemented
other = lib.item_from_zerodim(other)
if is_scalar(other):
if isinstance(other, (timedelta, np.timedelta64, Tick)):
other = Timedelta(other)
if other is NaT:
# treat this specifically as timedelta-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# dispatch to Timedelta implementation
result = other.__rfloordiv__(self._data)
return result
# at this point we should only have numeric scalars; anything
# else will raise
result = self.asi8 // other
result[self._isnan] = iNaT
freq = None
if self.freq is not None:
# Note: freq gets division, not floor-division
freq = self.freq / other
return type(self)(result.view('m8[ns]'), freq=freq)
if not hasattr(other, "dtype"):
# list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide with unequal lengths")
elif is_timedelta64_dtype(other):
other = type(self)(other)
# numpy timedelta64 does not natively support floordiv, so operate
# on the i8 values
result = self.asi8 // other.asi8
mask = self._isnan | other._isnan
if mask.any():
result = result.astype(np.int64)
result[mask] = np.nan
return result
elif is_object_dtype(other):
result = [self[n] // other[n] for n in range(len(self))]
result = np.array(result)
if lib.infer_dtype(result) == 'timedelta':
result, _ = sequence_to_td64ns(result)
return type(self)(result)
return result
elif is_integer_dtype(other) or is_float_dtype(other):
result = self._data // other
return type(self)(result)
else:
dtype = getattr(other, "dtype", type(other).__name__)
raise TypeError("Cannot divide {typ} by {cls}".format(
typ=dtype, cls=type(self).__name__))
def _scalar_from_string(self, value) -> Timedelta | NaTType:
return Timedelta(value)
def _adjust_to_origin(arg, origin, unit):
"""
Helper function for to_datetime.
Adjust input argument to the specified origin
Parameters
----------
arg : list, tuple, ndarray, Series, Index
date to be adjusted
origin : 'julian' or Timestamp
origin offset for the arg
unit : str
passed unit from to_datetime, must be 'D'
Returns
-------
ndarray or scalar of adjusted date(s)
"""
if origin == "julian":
original = arg
j0 = Timestamp(0).to_julian_date()
if unit != "D":
raise ValueError("unit must be 'D' for origin='julian'")
try:
arg = arg - j0
except TypeError as err:
raise ValueError(
"incompatible 'arg' type for given 'origin'='julian'") from err
# preemptively check this for a nice range
j_max = Timestamp.max.to_julian_date() - j0
j_min = Timestamp.min.to_julian_date() - j0
if np.any(arg > j_max) or np.any(arg < j_min):
raise OutOfBoundsDatetime(
f"{original} is Out of Bounds for origin='julian'")
else:
# arg must be numeric
if not ((is_scalar(arg) and (is_integer(arg) or is_float(arg)))
or is_numeric_dtype(np.asarray(arg))):
raise ValueError(
f"'{arg}' is not compatible with origin='{origin}'; "
"it must be numeric with a unit specified")
# we are going to offset back to unix / epoch time
try:
offset = Timestamp(origin)
except OutOfBoundsDatetime as err:
raise OutOfBoundsDatetime(
f"origin {origin} is Out of Bounds") from err
except ValueError as err:
raise ValueError(
f"origin {origin} cannot be converted to a Timestamp") from err
if offset.tz is not None:
raise ValueError(f"origin offset {offset} must be tz-naive")
td_offset = offset - Timestamp(0)
# convert the offset to the unit of the arg
# this should be lossless in terms of precision
ioffset = td_offset // Timedelta(1, unit=unit)
# scalars & ndarray-like can handle the addition
if is_list_like(arg) and not isinstance(
arg, (ABCSeries, Index, np.ndarray)):
arg = np.asarray(arg)
arg = arg + ioffset
return arg
def to_offset(freq):
"""
Return DateOffset object from string or tuple representation
or datetime.timedelta object
Parameters
----------
freq : str, tuple, datetime.timedelta, DateOffset or None
Returns
-------
delta : DateOffset
None if freq is None
Raises
------
ValueError
If freq is an invalid frequency
See Also
--------
pandas.DateOffset
Examples
--------
>>> to_offset('5min')
<5 * Minutes>
>>> to_offset('1D1H')
<25 * Hours>
>>> to_offset(('W', 2))
<2 * Weeks: weekday=6>
>>> to_offset((2, 'B'))
<2 * BusinessDays>
>>> to_offset(datetime.timedelta(days=1))
<Day>
>>> to_offset(Hour())
<Hour>
"""
if freq is None:
return None
if isinstance(freq, DateOffset):
return freq
if isinstance(freq, tuple):
name = freq[0]
stride = freq[1]
if isinstance(stride, compat.string_types):
name, stride = stride, name
name, _ = libfreqs._base_and_stride(name)
delta = get_offset(name) * stride
elif isinstance(freq, timedelta):
delta = None
freq = Timedelta(freq)
try:
for name in freq.components._fields:
offset = _name_to_offset_map[name]
stride = getattr(freq.components, name)
if stride != 0:
offset = stride * offset
if delta is None:
delta = offset
else:
delta = delta + offset
except Exception:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
else:
delta = None
stride_sign = None
try:
splitted = re.split(libfreqs.opattern, freq)
if splitted[-1] != '' and not splitted[-1].isspace():
# the last element must be blank
raise ValueError('last element must be blank')
for sep, stride, name in zip(splitted[0::4], splitted[1::4],
splitted[2::4]):
if sep != '' and not sep.isspace():
raise ValueError('separator must be spaces')
prefix = libfreqs._lite_rule_alias.get(name) or name
if stride_sign is None:
stride_sign = -1 if stride.startswith('-') else 1
if not stride:
stride = 1
if prefix in Resolution._reso_str_bump_map.keys():
stride, name = Resolution.get_stride_from_decimal(
float(stride), prefix)
stride = int(stride)
offset = get_offset(name)
offset = offset * int(np.fabs(stride) * stride_sign)
if delta is None:
delta = offset
else:
delta = delta + offset
except Exception:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
if delta is None:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
return delta
def _scalar_from_string(self, value) -> Union[Timedelta, NaTType]:
return Timedelta(value)
def __init__(
self,
obj: FrameOrSeries,
com: Optional[float] = None,
span: Optional[float] = None,
halflife: Optional[Union[float, TimedeltaConvertibleTypes]] = None,
alpha: Optional[float] = None,
min_periods: int = 0,
adjust: bool = True,
ignore_na: bool = False,
axis: Axis = 0,
times: Optional[Union[str, np.ndarray, FrameOrSeries]] = None,
):
super().__init__(
obj=obj,
min_periods=max(int(min_periods), 1),
on=None,
center=False,
closed=None,
method="single",
axis=axis,
)
self.com = com
self.span = span
self.halflife = halflife
self.alpha = alpha
self.adjust = adjust
self.ignore_na = ignore_na
self.times = times
if self.times is not None:
if not self.adjust:
raise NotImplementedError(
"times is not supported with adjust=False.")
if isinstance(self.times, str):
self.times = self._selected_obj[self.times]
if not is_datetime64_ns_dtype(self.times):
raise ValueError("times must be datetime64[ns] dtype.")
# error: Argument 1 to "len" has incompatible type "Union[str, ndarray,
# FrameOrSeries, None]"; expected "Sized"
if len(self.times) != len(obj): # type: ignore[arg-type]
raise ValueError(
"times must be the same length as the object.")
if not isinstance(self.halflife, (str, datetime.timedelta)):
raise ValueError(
"halflife must be a string or datetime.timedelta object")
if isna(self.times).any():
raise ValueError("Cannot convert NaT values to integer")
# error: Item "str" of "Union[str, ndarray, FrameOrSeries, None]" has no
# attribute "view"
# error: Item "None" of "Union[str, ndarray, FrameOrSeries, None]" has no
# attribute "view"
_times = np.asarray(
self.times.view(np.int64),
dtype=np.float64 # type: ignore[union-attr]
)
_halflife = float(Timedelta(self.halflife).value)
self._deltas = np.diff(_times) / _halflife
# Halflife is no longer applicable when calculating COM
# But allow COM to still be calculated if the user passes other decay args
if common.count_not_none(self.com, self.span, self.alpha) > 0:
self._com = get_center_of_mass(self.com, self.span, None,
self.alpha)
else:
self._com = 1.0
else:
if self.halflife is not None and isinstance(
self.halflife, (str, datetime.timedelta)):
raise ValueError(
"halflife can only be a timedelta convertible argument if "
"times is not None.")
# Without times, points are equally spaced
self._deltas = np.ones(max(len(self.obj) - 1, 0), dtype=np.float64)
self._com = get_center_of_mass(
# error: Argument 3 to "get_center_of_mass" has incompatible type
# "Union[float, Any, None, timedelta64, signedinteger[_64Bit]]";
# expected "Optional[float]"
self.com,
self.span,
self.halflife, # type: ignore[arg-type]
self.alpha,
)
def test_to_offset_pd_timedelta(kwargs, expected):
# see gh-9064
td = Timedelta(**kwargs)
result = to_offset(td)
assert result == expected
def _box_func(self, x: np.timedelta64) -> Timedelta | NaTType:
y = x.view("i8")
if y == NaT.value:
return NaT
return Timedelta._from_value_and_reso(y, reso=self._reso)
def __truediv__(self, other):
# timedelta / X is well-defined for timedelta-like or numeric X
if isinstance(other, self._recognized_scalars):
other = Timedelta(other)
# mypy assumes that __new__ returns an instance of the class
# github.com/python/mypy/issues/1020
if cast("Timedelta | NaTType", other) is NaT:
# specifically timedelta64-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# otherwise, dispatch to Timedelta implementation
return self._ndarray / other
elif lib.is_scalar(other):
# assume it is numeric
result = self._ndarray / other
freq = None
if self.freq is not None:
# Tick division is not implemented, so operate on Timedelta
freq = self.freq.delta / other
freq = to_offset(freq)
return type(self)._simple_new(result, dtype=result.dtype, freq=freq)
if not hasattr(other, "dtype"):
# e.g. list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide vectors with unequal lengths")
elif is_timedelta64_dtype(other.dtype):
# let numpy handle it
return self._ndarray / other
elif is_object_dtype(other.dtype):
# We operate on raveled arrays to avoid problems in inference
# on NaT
# TODO: tests with non-nano
srav = self.ravel()
orav = other.ravel()
result_list = [srav[n] / orav[n] for n in range(len(srav))]
result = np.array(result_list).reshape(self.shape)
# We need to do dtype inference in order to keep DataFrame ops
# behavior consistent with Series behavior
inferred = lib.infer_dtype(result, skipna=False)
if inferred == "timedelta":
flat = result.ravel()
result = type(self)._from_sequence(flat).reshape(result.shape)
elif inferred == "floating":
result = result.astype(float)
elif inferred == "datetime":
# GH#39750 this occurs when result is all-NaT, in which case
# we want to interpret these NaTs as td64.
# We construct an all-td64NaT result.
# error: Incompatible types in assignment (expression has type
# "TimedeltaArray", variable has type "ndarray[Any,
# dtype[floating[_64Bit]]]")
result = self * np.nan # type: ignore[assignment]
return result
else:
result = self._ndarray / other
return type(self)._simple_new(result, dtype=result.dtype)
class TestTimestampArithmetic:
def test_overflow_offset(self):
# no overflow expected
stamp = Timestamp("2000/1/1")
offset_no_overflow = to_offset("D") * 100
expected = Timestamp("2000/04/10")
assert stamp + offset_no_overflow == expected
assert offset_no_overflow + stamp == expected
expected = Timestamp("1999/09/23")
assert stamp - offset_no_overflow == expected
def test_overflow_offset_raises(self):
# xref https://github.com/statsmodels/statsmodels/issues/3374
# ends up multiplying really large numbers which overflow
stamp = Timestamp("2017-01-13 00:00:00")
offset_overflow = 20169940 * offsets.Day(1)
msg = ("the add operation between "
r"\<-?\d+ \* Days\> and \d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2} "
"will overflow")
lmsg = "|".join([
"Python int too large to convert to C long",
"int too big to convert"
])
with pytest.raises(OverflowError, match=lmsg):
stamp + offset_overflow
with pytest.raises(OverflowError, match=msg):
offset_overflow + stamp
with pytest.raises(OverflowError, match=lmsg):
stamp - offset_overflow
# xref https://github.com/pandas-dev/pandas/issues/14080
# used to crash, so check for proper overflow exception
stamp = Timestamp("2000/1/1")
offset_overflow = to_offset("D") * 100**5
with pytest.raises(OverflowError, match=lmsg):
stamp + offset_overflow
with pytest.raises(OverflowError, match=msg):
offset_overflow + stamp
with pytest.raises(OverflowError, match=lmsg):
stamp - offset_overflow
def test_overflow_timestamp_raises(self):
# https://github.com/pandas-dev/pandas/issues/31774
msg = "Result is too large"
a = Timestamp("2101-01-01 00:00:00")
b = Timestamp("1688-01-01 00:00:00")
with pytest.raises(OutOfBoundsDatetime, match=msg):
a - b
# but we're OK for timestamp and datetime.datetime
assert (a - b.to_pydatetime()) == (a.to_pydatetime() - b)
def test_delta_preserve_nanos(self):
val = Timestamp(1337299200000000123)
result = val + timedelta(1)
assert result.nanosecond == val.nanosecond
def test_rsub_dtscalars(self, tz_naive_fixture):
# In particular, check that datetime64 - Timestamp works GH#28286
td = Timedelta(1235345642000)
ts = Timestamp.now(tz_naive_fixture)
other = ts + td
assert other - ts == td
assert other.to_pydatetime() - ts == td
if tz_naive_fixture is None:
assert other.to_datetime64() - ts == td
else:
msg = "subtraction must have"
with pytest.raises(TypeError, match=msg):
other.to_datetime64() - ts
def test_timestamp_sub_datetime(self):
dt = datetime(2013, 10, 12)
ts = Timestamp(datetime(2013, 10, 13))
assert (ts - dt).days == 1
assert (dt - ts).days == -1
def test_addition_subtraction_types(self):
# Assert on the types resulting from Timestamp +/- various date/time
# objects
dt = datetime(2014, 3, 4)
td = timedelta(seconds=1)
# build a timestamp with a frequency, since then it supports
# addition/subtraction of integers
with tm.assert_produces_warning(FutureWarning,
match="The 'freq' argument"):
# freq deprecated
ts = Timestamp(dt, freq="D")
msg = "Addition/subtraction of integers"
with pytest.raises(TypeError, match=msg):
# GH#22535 add/sub with integers is deprecated
ts + 1
with pytest.raises(TypeError, match=msg):
ts - 1
# Timestamp + datetime not supported, though subtraction is supported
# and yields timedelta more tests in tseries/base/tests/test_base.py
assert type(ts - dt) == Timedelta
assert type(ts + td) == Timestamp
assert type(ts - td) == Timestamp
# Timestamp +/- datetime64 not supported, so not tested (could possibly
# assert error raised?)
td64 = np.timedelta64(1, "D")
assert type(ts + td64) == Timestamp
assert type(ts - td64) == Timestamp
@pytest.mark.parametrize(
"freq, td, td64",
[
("S", timedelta(seconds=1), np.timedelta64(1, "s")),
("min", timedelta(minutes=1), np.timedelta64(1, "m")),
("H", timedelta(hours=1), np.timedelta64(1, "h")),
("D", timedelta(days=1), np.timedelta64(1, "D")),
("W", timedelta(weeks=1), np.timedelta64(1, "W")),
("M", None, np.timedelta64(1, "M")),
],
)
@pytest.mark.filterwarnings(
"ignore:Timestamp.freq is deprecated:FutureWarning")
@pytest.mark.filterwarnings("ignore:The 'freq' argument:FutureWarning")
def test_addition_subtraction_preserve_frequency(self, freq, td, td64):
ts = Timestamp("2014-03-05 00:00:00", freq=freq)
original_freq = ts.freq
assert (ts + 1 * original_freq).freq == original_freq
assert (ts - 1 * original_freq).freq == original_freq
if td is not None:
# timedelta does not support months as unit
assert (ts + td).freq == original_freq
assert (ts - td).freq == original_freq
assert (ts + td64).freq == original_freq
assert (ts - td64).freq == original_freq
@pytest.mark.parametrize(
"td", [Timedelta(hours=3),
np.timedelta64(3, "h"),
timedelta(hours=3)])
def test_radd_tdscalar(self, td):
# GH#24775 timedelta64+Timestamp should not raise
ts = Timestamp.now()
assert td + ts == ts + td
@pytest.mark.parametrize(
"other,expected_difference",
[
(np.timedelta64(-123, "ns"), -123),
(np.timedelta64(1234567898, "ns"), 1234567898),
(np.timedelta64(-123, "us"), -123000),
(np.timedelta64(-123, "ms"), -123000000),
],
)
def test_timestamp_add_timedelta64_unit(self, other, expected_difference):
ts = Timestamp(datetime.utcnow())
result = ts + other
valdiff = result.value - ts.value
assert valdiff == expected_difference
@pytest.mark.parametrize(
"ts",
[
Timestamp("1776-07-04"),
Timestamp("1776-07-04", tz="UTC"),
],
)
@pytest.mark.parametrize(
"other",
[
1,
np.int64(1),
np.array([1, 2], dtype=np.int32),
np.array([3, 4], dtype=np.uint64),
],
)
def test_add_int_with_freq(self, ts, other):
msg = "Addition/subtraction of integers and integer-arrays"
with pytest.raises(TypeError, match=msg):
ts + other
with pytest.raises(TypeError, match=msg):
other + ts
with pytest.raises(TypeError, match=msg):
ts - other
msg = "unsupported operand type"
with pytest.raises(TypeError, match=msg):
other - ts
@pytest.mark.parametrize("shape", [(6, ), (2, 3)])
def test_addsub_m8ndarray(self, shape):
# GH#33296
ts = Timestamp("2020-04-04 15:45")
other = np.arange(6).astype("m8[h]").reshape(shape)
result = ts + other
ex_stamps = [ts + Timedelta(hours=n) for n in range(6)]
expected = np.array([x.asm8 for x in ex_stamps],
dtype="M8[ns]").reshape(shape)
tm.assert_numpy_array_equal(result, expected)
result = other + ts
tm.assert_numpy_array_equal(result, expected)
result = ts - other
ex_stamps = [ts - Timedelta(hours=n) for n in range(6)]
expected = np.array([x.asm8 for x in ex_stamps],
dtype="M8[ns]").reshape(shape)
tm.assert_numpy_array_equal(result, expected)
msg = r"unsupported operand type\(s\) for -: 'numpy.ndarray' and 'Timestamp'"
with pytest.raises(TypeError, match=msg):
other - ts
@pytest.mark.parametrize("shape", [(6, ), (2, 3)])
def test_addsub_m8ndarray_tzaware(self, shape):
# GH#33296
ts = Timestamp("2020-04-04 15:45", tz="US/Pacific")
other = np.arange(6).astype("m8[h]").reshape(shape)
result = ts + other
ex_stamps = [ts + Timedelta(hours=n) for n in range(6)]
expected = np.array(ex_stamps).reshape(shape)
tm.assert_numpy_array_equal(result, expected)
result = other + ts
tm.assert_numpy_array_equal(result, expected)
result = ts - other
ex_stamps = [ts - Timedelta(hours=n) for n in range(6)]
expected = np.array(ex_stamps).reshape(shape)
tm.assert_numpy_array_equal(result, expected)
msg = r"unsupported operand type\(s\) for -: 'numpy.ndarray' and 'Timestamp'"
with pytest.raises(TypeError, match=msg):
other - ts
def _box_func(self, x) -> Timedelta | NaTType:
return Timedelta(x, unit="ns")
def to_offset(freq) -> Optional[DateOffset]:
"""
Return DateOffset object from string or tuple representation
or datetime.timedelta object.
Parameters
----------
freq : str, tuple, datetime.timedelta, DateOffset or None
Returns
-------
DateOffset
None if freq is None.
Raises
------
ValueError
If freq is an invalid frequency
See Also
--------
DateOffset
Examples
--------
>>> to_offset("5min")
<5 * Minutes>
>>> to_offset("1D1H")
<25 * Hours>
>>> to_offset(("W", 2))
<2 * Weeks: weekday=6>
>>> to_offset((2, "B"))
<2 * BusinessDays>
>>> to_offset(pd.Timedelta(days=1))
<Day>
>>> to_offset(Hour())
<Hour>
"""
if freq is None:
return None
if isinstance(freq, DateOffset):
return freq
if isinstance(freq, tuple):
name = freq[0]
stride = freq[1]
if isinstance(stride, str):
name, stride = stride, name
name, _ = libfreqs._base_and_stride(name)
delta = _get_offset(name) * stride
elif isinstance(freq, timedelta):
delta = None
freq = Timedelta(freq)
try:
for name in freq.components._fields:
offset = _name_to_offset_map[name]
stride = getattr(freq.components, name)
if stride != 0:
offset = stride * offset
if delta is None:
delta = offset
else:
delta = delta + offset
except ValueError as err:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq)) from err
else:
delta = None
stride_sign = None
try:
split = re.split(libfreqs.opattern, freq)
if split[-1] != "" and not split[-1].isspace():
# the last element must be blank
raise ValueError("last element must be blank")
for sep, stride, name in zip(split[0::4], split[1::4], split[2::4]):
if sep != "" and not sep.isspace():
raise ValueError("separator must be spaces")
prefix = libfreqs._lite_rule_alias.get(name) or name
if stride_sign is None:
stride_sign = -1 if stride.startswith("-") else 1
if not stride:
stride = 1
if prefix in Resolution._reso_str_bump_map.keys():
stride, name = Resolution.get_stride_from_decimal(
float(stride), prefix
)
stride = int(stride)
offset = _get_offset(name)
offset = offset * int(np.fabs(stride) * stride_sign)
if delta is None:
delta = offset
else:
delta = delta + offset
except (ValueError, TypeError) as err:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq)) from err
if delta is None:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
return delta
def __rmod__(self, other):
# Note: This is a naive implementation, can likely be optimized
if isinstance(other, self._recognized_scalars):
other = Timedelta(other)
return other - (other // self) * self
def __truediv__(self, other):
# timedelta / X is well-defined for timedelta-like or numeric X
if isinstance(other, self._recognized_scalars):
other = Timedelta(other)
if other is NaT:
# specifically timedelta64-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# otherwise, dispatch to Timedelta implementation
return self._ndarray / other
elif lib.is_scalar(other):
# assume it is numeric
result = self._ndarray / other
freq = None
if self.freq is not None:
# Tick division is not implemented, so operate on Timedelta
freq = self.freq.delta / other
return type(self)(result, freq=freq)
if not hasattr(other, "dtype"):
# e.g. list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide vectors with unequal lengths")
elif is_timedelta64_dtype(other.dtype):
# let numpy handle it
return self._ndarray / other
elif is_object_dtype(other.dtype):
# We operate on raveled arrays to avoid problems in inference
# on NaT
srav = self.ravel()
orav = other.ravel()
result = [srav[n] / orav[n] for n in range(len(srav))]
result = np.array(result).reshape(self.shape)
# We need to do dtype inference in order to keep DataFrame ops
# behavior consistent with Series behavior
inferred = lib.infer_dtype(result, skipna=False)
if inferred == "timedelta":
flat = result.ravel()
result = type(self)._from_sequence(flat).reshape(result.shape)
elif inferred == "floating":
result = result.astype(float)
elif inferred == "datetime":
# GH#39750 this occurs when result is all-NaT, in which case
# we want to interpret these NaTs as td64.
# We construct an all-td64NaT result.
result = self * np.nan
return result
else:
result = self._ndarray / other
return type(self)(result)
def convert_value(self, v) -> "TermValue":
""" convert the expression that is in the term to something that is
accepted by pytables """
def stringify(value):
if self.encoding is not None:
encoder = partial(pprint_thing_encoded, encoding=self.encoding)
else:
encoder = pprint_thing
return encoder(value)
kind = _ensure_decoded(self.kind)
meta = _ensure_decoded(self.meta)
if kind == "datetime64" or kind == "datetime":
if isinstance(v, (int, float)):
v = stringify(v)
v = _ensure_decoded(v)
v = Timestamp(v)
if v.tz is not None:
v = v.tz_convert("UTC")
return TermValue(v, v.value, kind)
elif kind == "timedelta64" or kind == "timedelta":
v = Timedelta(v, unit="s").value
return TermValue(int(v), v, kind)
elif meta == "category":
metadata = com.values_from_object(self.metadata)
result = metadata.searchsorted(v, side="left")
# result returns 0 if v is first element or if v is not in metadata
# check that metadata contains v
if not result and v not in metadata:
result = -1
return TermValue(result, result, "integer")
elif kind == "integer":
v = int(float(v))
return TermValue(v, v, kind)
elif kind == "float":
v = float(v)
return TermValue(v, v, kind)
elif kind == "bool":
if isinstance(v, str):
v = not v.strip().lower() in [
"false",
"f",
"no",
"n",
"none",
"0",
"[]",
"{}",
"",
]
else:
v = bool(v)
return TermValue(v, v, kind)
elif isinstance(v, str):
# string quoting
return TermValue(v, stringify(v), "string")
else:
raise TypeError(
"Cannot compare {v} of type {typ} to {kind} column".format(
v=v, typ=type(v), kind=kind
)
)
def __floordiv__(self, other):
if is_scalar(other):
if isinstance(other, self._recognized_scalars):
other = Timedelta(other)
if other is NaT:
# treat this specifically as timedelta-NaT
result = np.empty(self.shape, dtype=np.float64)
result.fill(np.nan)
return result
# dispatch to Timedelta implementation
result = other.__rfloordiv__(self._ndarray)
return result
# at this point we should only have numeric scalars; anything
# else will raise
result = self._ndarray // other
freq = None
if self.freq is not None:
# Note: freq gets division, not floor-division
freq = self.freq / other
if freq.nanos == 0 and self.freq.nanos != 0:
# e.g. if self.freq is Nano(1) then dividing by 2
# rounds down to zero
freq = None
return type(self)(result, freq=freq)
if not hasattr(other, "dtype"):
# list, tuple
other = np.array(other)
if len(other) != len(self):
raise ValueError("Cannot divide with unequal lengths")
elif is_timedelta64_dtype(other.dtype):
other = type(self)(other)
# numpy timedelta64 does not natively support floordiv, so operate
# on the i8 values
result = self.asi8 // other.asi8
mask = self._isnan | other._isnan
if mask.any():
result = result.astype(np.float64)
np.putmask(result, mask, np.nan)
return result
elif is_object_dtype(other.dtype):
# error: Incompatible types in assignment (expression has type
# "List[Any]", variable has type "ndarray")
srav = self.ravel()
orav = other.ravel()
res_list = [srav[n] // orav[n] for n in range(len(srav))]
result_flat = np.asarray(res_list)
inferred = lib.infer_dtype(result_flat, skipna=False)
result = result_flat.reshape(self.shape)
if inferred == "timedelta":
result, _ = sequence_to_td64ns(result)
return type(self)(result)
if inferred == "datetime":
# GH#39750 occurs when result is all-NaT, which in this
# case should be interpreted as td64nat. This can only
# occur when self is all-td64nat
return self * np.nan
return result
elif is_integer_dtype(other.dtype) or is_float_dtype(other.dtype):
result = self._ndarray // other
return type(self)(result)
else:
dtype = getattr(other, "dtype", type(other).__name__)
raise TypeError(f"Cannot divide {dtype} by {type(self).__name__}")
def _scalar_from_string(self, value):
return Timedelta(value)
def convert_value(self, v) -> TermValue:
"""
convert the expression that is in the term to something that is
accepted by pytables
"""
def stringify(value):
if self.encoding is not None:
return pprint_thing_encoded(value, encoding=self.encoding)
return pprint_thing(value)
kind = ensure_decoded(self.kind)
meta = ensure_decoded(self.meta)
if kind == "datetime64" or kind == "datetime":
if isinstance(v, (int, float)):
v = stringify(v)
v = ensure_decoded(v)
v = Timestamp(v)
if v.tz is not None:
v = v.tz_convert("UTC")
return TermValue(v, v.value, kind)
elif kind == "timedelta64" or kind == "timedelta":
if isinstance(v, str):
v = Timedelta(v).value
else:
v = Timedelta(v, unit="s").value
return TermValue(int(v), v, kind)
elif meta == "category":
metadata = extract_array(self.metadata, extract_numpy=True)
if v not in metadata:
result = -1
else:
# error: Incompatible types in assignment (expression has type
# "Union[Any, ndarray]", variable has type "int")
result = metadata.searchsorted( # type: ignore[assignment]
v, side="left")
return TermValue(result, result, "integer")
elif kind == "integer":
v = int(float(v))
return TermValue(v, v, kind)
elif kind == "float":
v = float(v)
return TermValue(v, v, kind)
elif kind == "bool":
if isinstance(v, str):
v = not v.strip().lower() in [
"false",
"f",
"no",
"n",
"none",
"0",
"[]",
"{}",
"",
]
else:
v = bool(v)
return TermValue(v, v, kind)
elif isinstance(v, str):
# string quoting
return TermValue(v, stringify(v), "string")
else:
raise TypeError(
f"Cannot compare {v} of type {type(v)} to {kind} column")
def __mod__(self, other):
# Note: This is a naive implementation, can likely be optimized
if isinstance(other, (timedelta, np.timedelta64, Tick)):
other = Timedelta(other)
return self - (self // other) * other
def _parse_with_reso(self, label: str):
# the "with_reso" is a no-op for TimedeltaIndex
parsed = Timedelta(label)
return parsed, None
def _parsed_string_to_bounds(self, reso, parsed: Timedelta):
# reso is unused, included to match signature of DTI/PI
lbound = parsed.round(parsed.resolution_string)
rbound = lbound + to_offset(parsed.resolution_string) - Timedelta(1, "ns")
return lbound, rbound
def __init__(
self,
obj,
com: Optional[float] = None,
span: Optional[float] = None,
halflife: Optional[Union[float, TimedeltaConvertibleTypes]] = None,
alpha: Optional[float] = None,
min_periods: int = 0,
adjust: bool = True,
ignore_na: bool = False,
axis: int = 0,
times: Optional[Union[str, np.ndarray, FrameOrSeries]] = None,
):
super().__init__(
obj=obj,
min_periods=max(int(min_periods), 1),
on=None,
center=False,
closed=None,
method="single",
axis=axis,
)
self.com = com
self.span = span
self.halflife = halflife
self.alpha = alpha
self.adjust = adjust
self.ignore_na = ignore_na
self.times = times
if self.times is not None:
if isinstance(self.times, str):
self.times = self._selected_obj[self.times]
if not is_datetime64_ns_dtype(self.times):
raise ValueError("times must be datetime64[ns] dtype.")
if len(self.times) != len(obj):
raise ValueError("times must be the same length as the object.")
if not isinstance(self.halflife, (str, datetime.timedelta)):
raise ValueError(
"halflife must be a string or datetime.timedelta object"
)
if isna(self.times).any():
raise ValueError("Cannot convert NaT values to integer")
_times = np.asarray(self.times.view(np.int64), dtype=np.float64)
_halflife = float(Timedelta(self.halflife).value)
self._deltas = np.diff(_times) / _halflife
# Halflife is no longer applicable when calculating COM
# But allow COM to still be calculated if the user passes other decay args
if common.count_not_none(self.com, self.span, self.alpha) > 0:
self._com = get_center_of_mass(self.com, self.span, None, self.alpha)
else:
self._com = 1.0
else:
if self.halflife is not None and isinstance(
self.halflife, (str, datetime.timedelta)
):
raise ValueError(
"halflife can only be a timedelta convertible argument if "
"times is not None."
)
# Without times, points are equally spaced
self._deltas = np.ones(max(len(self.obj) - 1, 0), dtype=np.float64)
self._com = get_center_of_mass(
self.com, self.span, self.halflife, self.alpha
)
