def interval_range(start=None,
end=None,
periods=None,
freq=None,
name=None,
closed="right"):
"""
Return a fixed frequency IntervalIndex.
Parameters
----------
start : numeric or datetime-like, default None
Left bound for generating intervals.
end : numeric or datetime-like, default None
Right bound for generating intervals.
periods : int, default None
Number of periods to generate.
freq : numeric, str, or DateOffset, default None
The length of each interval. Must be consistent with the type of start
and end, e.g. 2 for numeric, or '5H' for datetime-like. Default is 1
for numeric and 'D' for datetime-like.
name : str, default None
Name of the resulting IntervalIndex.
closed : {'left', 'right', 'both', 'neither'}, default 'right'
Whether the intervals are closed on the left-side, right-side, both
or neither.
Returns
-------
IntervalIndex
See Also
--------
IntervalIndex : An Index of intervals that are all closed on the same side.
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``IntervalIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end``, inclusively.
To learn more about datetime-like frequency strings, please see `this link
<https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
Examples
--------
Numeric ``start`` and ``end`` is supported.
>>> pd.interval_range(start=0, end=5)
IntervalIndex([(0, 1], (1, 2], (2, 3], (3, 4], (4, 5]],
closed='right', dtype='interval[int64]')
Additionally, datetime-like input is also supported.
>>> pd.interval_range(start=pd.Timestamp('2017-01-01'),
... end=pd.Timestamp('2017-01-04'))
IntervalIndex([(2017-01-01, 2017-01-02], (2017-01-02, 2017-01-03],
(2017-01-03, 2017-01-04]],
closed='right', dtype='interval[datetime64[ns]]')
The ``freq`` parameter specifies the frequency between the left and right.
endpoints of the individual intervals within the ``IntervalIndex``. For
numeric ``start`` and ``end``, the frequency must also be numeric.
>>> pd.interval_range(start=0, periods=4, freq=1.5)
IntervalIndex([(0.0, 1.5], (1.5, 3.0], (3.0, 4.5], (4.5, 6.0]],
closed='right', dtype='interval[float64]')
Similarly, for datetime-like ``start`` and ``end``, the frequency must be
convertible to a DateOffset.
>>> pd.interval_range(start=pd.Timestamp('2017-01-01'),
... periods=3, freq='MS')
IntervalIndex([(2017-01-01, 2017-02-01], (2017-02-01, 2017-03-01],
(2017-03-01, 2017-04-01]],
closed='right', dtype='interval[datetime64[ns]]')
Specify ``start``, ``end``, and ``periods``; the frequency is generated
automatically (linearly spaced).
>>> pd.interval_range(start=0, end=6, periods=4)
IntervalIndex([(0.0, 1.5], (1.5, 3.0], (3.0, 4.5], (4.5, 6.0]],
closed='right',
dtype='interval[float64]')
The ``closed`` parameter specifies which endpoints of the individual
intervals within the ``IntervalIndex`` are closed.
>>> pd.interval_range(end=5, periods=4, closed='both')
IntervalIndex([[1, 2], [2, 3], [3, 4], [4, 5]],
closed='both', dtype='interval[int64]')
"""
start = maybe_box_datetimelike(start)
end = maybe_box_datetimelike(end)
endpoint = start if start is not None else end
if freq is None and com.any_none(periods, start, end):
freq = 1 if is_number(endpoint) else "D"
if com.count_not_none(start, end, periods, freq) != 3:
raise ValueError("Of the four parameters: start, end, periods, and "
"freq, exactly three must be specified")
if not _is_valid_endpoint(start):
raise ValueError(
f"start must be numeric or datetime-like, got {start}")
elif not _is_valid_endpoint(end):
raise ValueError(f"end must be numeric or datetime-like, got {end}")
if is_float(periods):
periods = int(periods)
elif not is_integer(periods) and periods is not None:
raise TypeError(f"periods must be a number, got {periods}")
if freq is not None and not is_number(freq):
try:
freq = to_offset(freq)
except ValueError as err:
raise ValueError(
f"freq must be numeric or convertible to DateOffset, got {freq}"
) from err
# verify type compatibility
if not all([
_is_type_compatible(start, end),
_is_type_compatible(start, freq),
_is_type_compatible(end, freq),
]):
raise TypeError("start, end, freq need to be type compatible")
# +1 to convert interval count to breaks count (n breaks = n-1 intervals)
if periods is not None:
periods += 1
if is_number(endpoint):
# force consistency between start/end/freq (lower end if freq skips it)
if com.all_not_none(start, end, freq):
end -= (end - start) % freq
# compute the period/start/end if unspecified (at most one)
if periods is None:
periods = int((end - start) // freq) + 1
elif start is None:
start = end - (periods - 1) * freq
elif end is None:
end = start + (periods - 1) * freq
breaks = np.linspace(start, end, periods)
if all(is_integer(x) for x in com.not_none(start, end, freq)):
# np.linspace always produces float output
breaks = maybe_downcast_to_dtype(breaks, "int64")
else:
# delegate to the appropriate range function
if isinstance(endpoint, Timestamp):
breaks = date_range(start=start,
end=end,
periods=periods,
freq=freq)
else:
breaks = timedelta_range(start=start,
end=end,
periods=periods,
freq=freq)
return IntervalIndex.from_breaks(breaks, name=name, closed=closed)
def timedelta_range(
start=None, end=None, periods=None, freq=None, name=None, closed=None
) -> TimedeltaIndex:
"""
Return a fixed frequency TimedeltaIndex, with day as the default
frequency.
Parameters
----------
start : str or timedelta-like, default None
Left bound for generating timedeltas.
end : str or timedelta-like, default None
Right bound for generating timedeltas.
periods : int, default None
Number of periods to generate.
freq : str or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'.
name : str, default None
Name of the resulting TimedeltaIndex.
closed : str, default None
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None).
Returns
-------
rng : TimedeltaIndex
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``TimedeltaIndex`` 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
--------
>>> pd.timedelta_range(start='1 day', periods=4)
TimedeltaIndex(['1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``closed`` parameter specifies which endpoint is included. The default
behavior is to include both endpoints.
>>> pd.timedelta_range(start='1 day', periods=4, closed='right')
TimedeltaIndex(['2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``freq`` parameter specifies the frequency of the TimedeltaIndex.
Only fixed frequencies can be passed, non-fixed frequencies such as
'M' (month end) will raise.
>>> pd.timedelta_range(start='1 day', end='2 days', freq='6H')
TimedeltaIndex(['1 days 00:00:00', '1 days 06:00:00', '1 days 12:00:00',
'1 days 18:00:00', '2 days 00:00:00'],
dtype='timedelta64[ns]', freq='6H')
Specify ``start``, ``end``, and ``periods``; the frequency is generated
automatically (linearly spaced).
>>> pd.timedelta_range(start='1 day', end='5 days', periods=4)
TimedeltaIndex(['1 days 00:00:00', '2 days 08:00:00', '3 days 16:00:00',
'5 days 00:00:00'],
dtype='timedelta64[ns]', freq=None)
"""
if freq is None and com.any_none(periods, start, end):
freq = "D"
freq, _ = dtl.maybe_infer_freq(freq)
tdarr = TimedeltaArray._generate_range(start, end, periods, freq, closed=closed)
return TimedeltaIndex._simple_new(tdarr, name=name)
def date_range(
start=None,
end=None,
periods=None,
freq=None,
tz=None,
normalize: bool = False,
name: Hashable = None,
closed: Literal["left", "right"] | None | lib.NoDefault = lib.no_default,
inclusive: IntervalClosedType | 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')
`inclusive` controls whether to include `start` and `end` that are on the
boundary. The default, "both", includes boundary points on either end.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', inclusive="both")
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04'],
dtype='datetime64[ns]', freq='D')
Use ``inclusive='left'`` to exclude `end` if it falls on the boundary.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', inclusive='left')
DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03'],
dtype='datetime64[ns]', freq='D')
Use ``inclusive='right'`` to exclude `start` if it falls on the boundary, and
similarly ``inclusive='neither'`` will exclude both `start` and `end`.
>>> pd.date_range(start='2017-01-01', end='2017-01-04', inclusive='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)
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 test_any_none():
assert com.any_none(1, 2, 3, None)
assert not com.any_none(1, 2, 3, 4)