def _simple_new(cls, values, name=None, freq=None, tz=None, dtype=None):
"""
We require the we have a dtype compat for the values
if we are passed a non-dtype compat, then coerce using the constructor
"""
if isinstance(values, DatetimeArray):
if tz:
tz = validate_tz_from_dtype(dtype, tz)
dtype = DatetimeTZDtype(tz=tz)
elif dtype is None:
dtype = _NS_DTYPE
values = DatetimeArray(values, freq=freq, dtype=dtype)
tz = values.tz
freq = values.freq
values = values._data
# DatetimeArray._simple_new will accept either i8 or M8[ns] dtypes
if isinstance(values, DatetimeIndex):
values = values._data
dtype = tz_to_dtype(tz)
dtarr = DatetimeArray._simple_new(values, freq=freq, dtype=dtype)
assert isinstance(dtarr, DatetimeArray)
result = object.__new__(cls)
result._data = dtarr
result.name = name
result._no_setting_name = False
# For groupby perf. See note in indexes/base about _index_data
result._index_data = dtarr._data
result._reset_identity()
return result
def __setstate__(self, state):
"""
Necessary for making this object picklable.
"""
if isinstance(state, dict):
super().__setstate__(state)
elif isinstance(state, tuple):
# < 0.15 compat
if len(state) == 2:
nd_state, own_state = state
data = np.empty(nd_state[1], dtype=nd_state[2])
np.ndarray.__setstate__(data, nd_state)
freq = own_state[1]
tz = timezones.tz_standardize(own_state[2])
dtype = tz_to_dtype(tz)
dtarr = DatetimeArray._simple_new(data, freq=freq, dtype=dtype)
self.name = own_state[0]
else: # pragma: no cover
data = np.empty(state)
np.ndarray.__setstate__(data, state)
dtarr = DatetimeArray(data)
self._data = dtarr
self._reset_identity()
else:
raise Exception("invalid pickle state")
def snap(self, freq="S"):
"""
Snap time stamps to nearest occurring frequency.
Returns
-------
DatetimeIndex
"""
# Superdumb, punting on any optimizing
freq = to_offset(freq)
snapped = np.empty(len(self), dtype=_NS_DTYPE)
for i, v in enumerate(self):
s = v
if not freq.is_on_offset(s):
t0 = freq.rollback(s)
t1 = freq.rollforward(s)
if abs(s - t0) < abs(t1 - s):
s = t0
else:
s = t1
snapped[i] = s
dta = DatetimeArray(snapped, dtype=self.dtype)
return DatetimeIndex._simple_new(dta, name=self.name)
def _new_DatetimeIndex(cls, d):
"""
This is called upon unpickling, rather than the default which doesn't
have arguments and breaks __new__
"""
if "data" in d and not isinstance(d["data"], DatetimeIndex):
# Avoid need to verify integrity by calling simple_new directly
data = d.pop("data")
if not isinstance(data, DatetimeArray):
# For backward compat with older pickles, we may need to construct
# a DatetimeArray to adapt to the newer _simple_new signature
tz = d.pop("tz")
freq = d.pop("freq")
dta = DatetimeArray._simple_new(data, dtype=tz_to_dtype(tz), freq=freq)
else:
dta = data
for key in ["tz", "freq"]:
# These are already stored in our DatetimeArray; if they are
# also in the pickle and don't match, we have a problem.
if key in d:
assert d.pop(key) == getattr(dta, key)
result = cls._simple_new(dta, **d)
else:
with warnings.catch_warnings():
# TODO: If we knew what was going in to **d, we might be able to
# go through _simple_new instead
warnings.simplefilter("ignore")
result = cls.__new__(cls, **d)
return result
def __new__(
cls,
data=None,
freq=lib.no_default,
tz=None,
normalize: bool = False,
closed=None,
ambiguous="raise",
dayfirst: bool = False,
yearfirst: bool = False,
dtype: Dtype | None = None,
copy: bool = False,
name: Hashable = None,
) -> DatetimeIndex:
if is_scalar(data):
raise cls._scalar_data_error(data)
# - Cases checked above all return/raise before reaching here - #
name = maybe_extract_name(name, data, cls)
dtarr = DatetimeArray._from_sequence_not_strict(
data,
dtype=dtype,
copy=copy,
tz=tz,
freq=freq,
dayfirst=dayfirst,
yearfirst=yearfirst,
ambiguous=ambiguous,
)
subarr = cls._simple_new(dtarr, name=name)
return subarr
def _get_slice_index(self, start=None, end=None, periods=None, **kwargs):
"""
Time Array
"""
if not periods:
periods = None
if self.normalize:
start = rollback_minute(start)
end = rollforword_minute(end)
freq = round(self.window * (1 - self.overlap))
freq = str(freq) + 's'
# TODO: Here we use datetime array to get every
# start points and end points of windows during whole timeline
dtarr = DatetimeArray._generate_range(
start=start, end=end, periods=periods, freq=freq,
**kwargs) # generate datetime array
print(dtarr)
dtarr_start = dtarr[:-1]
dtarr_end = dtarr_start + Second(self.window)
if self.closed == 'right':
dtarr_start = dtarr_start - Second(1)
if self.closed == 'left':
dtarr_end = dtarr_end - Second(1)
_index = range(len(dtarr_start))
dt_index = list(map(lambda i: (dtarr_start[i], dtarr_end[i]), _index))
return dt_index
def __new__(
cls,
data=None,
freq: str | BaseOffset | lib.NoDefault = lib.no_default,
tz=None,
normalize: bool = False,
closed=None,
ambiguous="raise",
dayfirst: bool = False,
yearfirst: bool = False,
dtype: Dtype | None = None,
copy: bool = False,
name: Hashable = None,
) -> DatetimeIndex:
if is_scalar(data):
raise cls._scalar_data_error(data)
# - Cases checked above all return/raise before reaching here - #
name = maybe_extract_name(name, data, cls)
if (
isinstance(data, DatetimeArray)
and freq is lib.no_default
and tz is None
and dtype is None
):
# fastpath, similar logic in TimedeltaIndex.__new__;
# Note in this particular case we retain non-nano.
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
elif (
isinstance(data, DatetimeArray)
and freq is lib.no_default
and tz is None
and is_dtype_equal(data.dtype, dtype)
):
# Reached via Index.__new__ when we call .astype
# TODO(2.0): special casing can be removed once _from_sequence_not_strict
# no longer chokes on non-nano
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
dtarr = DatetimeArray._from_sequence_not_strict(
data,
dtype=dtype,
copy=copy,
tz=tz,
freq=freq,
dayfirst=dayfirst,
yearfirst=yearfirst,
ambiguous=ambiguous,
)
subarr = cls._simple_new(dtarr, name=name)
return subarr
def __new__(
cls,
data=None,
freq=None,
tz=None,
normalize=False,
closed=None,
ambiguous="raise",
dayfirst=False,
yearfirst=False,
dtype=None,
copy=False,
name=None,
):
if is_scalar(data):
raise TypeError(
f"{cls.__name__}() must be called with a "
f"collection of some kind, {repr(data)} was passed")
# - Cases checked above all return/raise before reaching here - #
name = maybe_extract_name(name, data, cls)
dtarr = DatetimeArray._from_sequence(
data,
dtype=dtype,
copy=copy,
tz=tz,
freq=freq,
dayfirst=dayfirst,
yearfirst=yearfirst,
ambiguous=ambiguous,
)
subarr = cls._simple_new(dtarr,
name=name,
freq=dtarr.freq,
tz=dtarr.tz)
return subarr
def date_range(
start=None,
end=None,
periods=None,
freq=None,
tz=None,
normalize=False,
name=None,
closed=None,
**kwargs,
) -> DatetimeIndex:
"""
Return a fixed frequency DatetimeIndex.
Parameters
----------
start : str or datetime-like, optional
Left bound for generating dates.
end : str or datetime-like, optional
Right bound for generating dates.
periods : int, optional
Number of periods to generate.
freq : str or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'. See
:ref:`here <timeseries.offset_aliases>` for a list of
frequency aliases.
tz : str or tzinfo, optional
Time zone name for returning localized DatetimeIndex, for example
'Asia/Hong_Kong'. By default, the resulting DatetimeIndex is
timezone-naive.
normalize : bool, default False
Normalize start/end dates to midnight before generating date range.
name : str, default None
Name of the resulting DatetimeIndex.
closed : {None, 'left', 'right'}, optional
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None, the default).
**kwargs
For compatibility. Has no effect on the result.
Returns
-------
rng : DatetimeIndex
See Also
--------
DatetimeIndex : An immutable container for datetimes.
timedelta_range : Return a fixed frequency TimedeltaIndex.
period_range : Return a fixed frequency PeriodIndex.
interval_range : Return a fixed frequency IntervalIndex.
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``DatetimeIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end`` (closed on both sides).
To learn more about the frequency strings, please see `this link
<https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
Examples
--------
**Specifying the values**
The next four examples generate the same `DatetimeIndex`, but vary
the combination of `start`, `end` and `periods`.
Specify `start` and `end`, with the default daily frequency.
>>> pd.date_range(start='1/1/2018', end='1/08/2018')
DatetimeIndex(['2018-01-01', '2018-01-02', '2018-01-03', '2018-01-04',
'2018-01-05', '2018-01-06', '2018-01-07', '2018-01-08'],
dtype='datetime64[ns]', freq='D')
Specify `start` and `periods`, the number of periods (days).
>>> pd.date_range(start='1/1/2018', periods=8)
DatetimeIndex(['2018-01-01', '2018-01-02', '2018-01-03', '2018-01-04',
'2018-01-05', '2018-01-06', '2018-01-07', '2018-01-08'],
dtype='datetime64[ns]', freq='D')
Specify `end` and `periods`, the number of periods (days).
>>> pd.date_range(end='1/1/2018', periods=8)
DatetimeIndex(['2017-12-25', '2017-12-26', '2017-12-27', '2017-12-28',
'2017-12-29', '2017-12-30', '2017-12-31', '2018-01-01'],
dtype='datetime64[ns]', freq='D')
Specify `start`, `end`, and `periods`; the frequency is generated
automatically (linearly spaced).
>>> pd.date_range(start='2018-04-24', end='2018-04-27', periods=3)
DatetimeIndex(['2018-04-24 00:00:00', '2018-04-25 12:00:00',
'2018-04-27 00:00:00'],
dtype='datetime64[ns]', freq=None)
**Other Parameters**
Changed the `freq` (frequency) to ``'M'`` (month end frequency).
>>> pd.date_range(start='1/1/2018', periods=5, freq='M')
DatetimeIndex(['2018-01-31', '2018-02-28', '2018-03-31', '2018-04-30',
'2018-05-31'],
dtype='datetime64[ns]', freq='M')
Multiples are allowed
>>> pd.date_range(start='1/1/2018', periods=5, freq='3M')
DatetimeIndex(['2018-01-31', '2018-04-30', '2018-07-31', '2018-10-31',
'2019-01-31'],
dtype='datetime64[ns]', freq='3M')
`freq` can also be specified as an Offset object.
>>> pd.date_range(start='1/1/2018', periods=5, freq=pd.offsets.MonthEnd(3))
DatetimeIndex(['2018-01-31', '2018-04-30', '2018-07-31', '2018-10-31',
'2019-01-31'],
dtype='datetime64[ns]', freq='3M')
Specify `tz` to set the timezone.
>>> pd.date_range(start='1/1/2018', periods=5, tz='Asia/Tokyo')
DatetimeIndex(['2018-01-01 00:00:00+09:00', '2018-01-02 00:00:00+09:00',
'2018-01-03 00:00:00+09:00', '2018-01-04 00:00:00+09:00',
'2018-01-05 00:00:00+09:00'],
dtype='datetime64[ns, Asia/Tokyo]', freq='D')
`closed` controls whether to include `start` and `end` that are on the
boundary. The default includes boundary points on either end.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed=None)
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04'],
dtype='datetime64[ns]', freq='D')
Use ``closed='left'`` to exclude `end` if it falls on the boundary.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed='left')
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03'],
dtype='datetime64[ns]', freq='D')
Use ``closed='right'`` to exclude `start` if it falls on the boundary.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed='right')
DatetimeIndex(['2017-01-02', '2017-01-03', '2017-01-04'],
dtype='datetime64[ns]', freq='D')
"""
if freq is None and com.any_none(periods, start, end):
freq = "D"
dtarr = DatetimeArray._generate_range(
start=start,
end=end,
periods=periods,
freq=freq,
tz=tz,
normalize=normalize,
closed=closed,
**kwargs,
)
return DatetimeIndex._simple_new(dtarr, name=name)
def date_range(
start=None,
end=None,
periods=None,
freq=None,
tz=None,
normalize: bool = False,
name: Hashable = None,
closed: str | None | lib.NoDefault = lib.no_default,
inclusive: str | None = None,
**kwargs,
) -> DatetimeIndex:
"""
Return a fixed frequency DatetimeIndex.
Returns the range of equally spaced time points (where the difference between any
two adjacent points is specified by the given frequency) such that they all
satisfy `start <[=] x <[=] end`, where the first one and the last one are, resp.,
the first and last time points in that range that fall on the boundary of ``freq``
(if given as a frequency string) or that are valid for ``freq`` (if given as a
:class:`pandas.tseries.offsets.DateOffset`). (If exactly one of ``start``,
``end``, or ``freq`` is *not* specified, this missing parameter can be computed
given ``periods``, the number of timesteps in the range. See the note below.)
Parameters
----------
start : str or datetime-like, optional
Left bound for generating dates.
end : str or datetime-like, optional
Right bound for generating dates.
periods : int, optional
Number of periods to generate.
freq : str or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'. See
:ref:`here <timeseries.offset_aliases>` for a list of
frequency aliases.
tz : str or tzinfo, optional
Time zone name for returning localized DatetimeIndex, for example
'Asia/Hong_Kong'. By default, the resulting DatetimeIndex is
timezone-naive.
normalize : bool, default False
Normalize start/end dates to midnight before generating date range.
name : str, default None
Name of the resulting DatetimeIndex.
closed : {None, 'left', 'right'}, optional
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None, the default).
.. deprecated:: 1.4.0
Argument `closed` has been deprecated to standardize boundary inputs.
Use `inclusive` instead, to set each bound as closed or open.
inclusive : {"both", "neither", "left", "right"}, default "both"
Include boundaries; Whether to set each bound as closed or open.
.. versionadded:: 1.4.0
**kwargs
For compatibility. Has no effect on the result.
Returns
-------
rng : DatetimeIndex
See Also
--------
DatetimeIndex : An immutable container for datetimes.
timedelta_range : Return a fixed frequency TimedeltaIndex.
period_range : Return a fixed frequency PeriodIndex.
interval_range : Return a fixed frequency IntervalIndex.
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``DatetimeIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end`` (closed on both sides).
To learn more about the frequency strings, please see `this link
<https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
Examples
--------
**Specifying the values**
The next four examples generate the same `DatetimeIndex`, but vary
the combination of `start`, `end` and `periods`.
Specify `start` and `end`, with the default daily frequency.
>>> pd.date_range(start='1/1/2018', end='1/08/2018')
DatetimeIndex(['2018-01-01', '2018-01-02', '2018-01-03', '2018-01-04',
'2018-01-05', '2018-01-06', '2018-01-07', '2018-01-08'],
dtype='datetime64[ns]', freq='D')
Specify `start` and `periods`, the number of periods (days).
>>> pd.date_range(start='1/1/2018', periods=8)
DatetimeIndex(['2018-01-01', '2018-01-02', '2018-01-03', '2018-01-04',
'2018-01-05', '2018-01-06', '2018-01-07', '2018-01-08'],
dtype='datetime64[ns]', freq='D')
Specify `end` and `periods`, the number of periods (days).
>>> pd.date_range(end='1/1/2018', periods=8)
DatetimeIndex(['2017-12-25', '2017-12-26', '2017-12-27', '2017-12-28',
'2017-12-29', '2017-12-30', '2017-12-31', '2018-01-01'],
dtype='datetime64[ns]', freq='D')
Specify `start`, `end`, and `periods`; the frequency is generated
automatically (linearly spaced).
>>> pd.date_range(start='2018-04-24', end='2018-04-27', periods=3)
DatetimeIndex(['2018-04-24 00:00:00', '2018-04-25 12:00:00',
'2018-04-27 00:00:00'],
dtype='datetime64[ns]', freq=None)
**Other Parameters**
Changed the `freq` (frequency) to ``'M'`` (month end frequency).
>>> pd.date_range(start='1/1/2018', periods=5, freq='M')
DatetimeIndex(['2018-01-31', '2018-02-28', '2018-03-31', '2018-04-30',
'2018-05-31'],
dtype='datetime64[ns]', freq='M')
Multiples are allowed
>>> pd.date_range(start='1/1/2018', periods=5, freq='3M')
DatetimeIndex(['2018-01-31', '2018-04-30', '2018-07-31', '2018-10-31',
'2019-01-31'],
dtype='datetime64[ns]', freq='3M')
`freq` can also be specified as an Offset object.
>>> pd.date_range(start='1/1/2018', periods=5, freq=pd.offsets.MonthEnd(3))
DatetimeIndex(['2018-01-31', '2018-04-30', '2018-07-31', '2018-10-31',
'2019-01-31'],
dtype='datetime64[ns]', freq='3M')
Specify `tz` to set the timezone.
>>> pd.date_range(start='1/1/2018', periods=5, tz='Asia/Tokyo')
DatetimeIndex(['2018-01-01 00:00:00+09:00', '2018-01-02 00:00:00+09:00',
'2018-01-03 00:00:00+09:00', '2018-01-04 00:00:00+09:00',
'2018-01-05 00:00:00+09:00'],
dtype='datetime64[ns, Asia/Tokyo]', freq='D')
`closed` controls whether to include `start` and `end` that are on the
boundary. The default includes boundary points on either end.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed=None)
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04'],
dtype='datetime64[ns]', freq='D')
Use ``closed='left'`` to exclude `end` if it falls on the boundary.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed='left')
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03'],
dtype='datetime64[ns]', freq='D')
Use ``closed='right'`` to exclude `start` if it falls on the boundary.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', closed='right')
DatetimeIndex(['2017-01-02', '2017-01-03', '2017-01-04'],
dtype='datetime64[ns]', freq='D')
"""
if inclusive is not None and not isinstance(closed, lib.NoDefault):
raise ValueError("Deprecated argument `closed` cannot be passed"
"if argument `inclusive` is not None")
elif not isinstance(closed, lib.NoDefault):
warnings.warn(
"Argument `closed` is deprecated in favor of `inclusive`.",
FutureWarning,
stacklevel=find_stack_level(),
)
if closed is None:
inclusive = "both"
elif closed in ("left", "right"):
inclusive = closed
else:
raise ValueError(
"Argument `closed` has to be either 'left', 'right' or None")
elif inclusive is None:
inclusive = "both"
if freq is None and com.any_none(periods, start, end):
freq = "D"
dtarr = DatetimeArray._generate_range(
start=start,
end=end,
periods=periods,
freq=freq,
tz=tz,
normalize=normalize,
inclusive=inclusive,
**kwargs,
)
return DatetimeIndex._simple_new(dtarr, name=name)
