def test_resample_as_freq_with_subperiod():
# GH 13022
index = timedelta_range('00:00:00', '00:10:00', freq='5T')
df = DataFrame(data={'value': [1, 5, 10]}, index=index)
result = df.resample('2T').asfreq()
expected_data = {'value': [1, np.nan, np.nan, np.nan, np.nan, 10]}
expected = DataFrame(data=expected_data,
index=timedelta_range('00:00:00',
'00:10:00', freq='2T'))
tm.assert_frame_equal(result, expected)
def test_resample_base_with_timedeltaindex():
# GH 10530
rng = timedelta_range(start='0s', periods=25, freq='s')
ts = Series(np.random.randn(len(rng)), index=rng)
with_base = ts.resample('2s', base=5).mean()
without_base = ts.resample('2s').mean()
exp_without_base = timedelta_range(start='0s', end='25s', freq='2s')
exp_with_base = timedelta_range(start='5s', end='29s', freq='2s')
tm.assert_index_equal(without_base.index, exp_without_base)
tm.assert_index_equal(with_base.index, exp_with_base)
def test_timedelta_plot(self):
# test issue #8711
s = Series(range(5), timedelta_range('1day', periods=5))
_check_plot_works(s.plot)
# test long period
index = timedelta_range('1 day 2 hr 30 min 10 s',
periods=10, freq='1 d')
s = Series(np.random.randn(len(index)), index)
_check_plot_works(s.plot)
# test short period
index = timedelta_range('1 day 2 hr 30 min 10 s',
periods=10, freq='1 ns')
s = Series(np.random.randn(len(index)), index)
_check_plot_works(s.plot)
def test_resample_timedelta_values():
# GH 13119
# check that timedelta dtype is preserved when NaT values are
# introduced by the resampling
times = timedelta_range('1 day', '4 day', freq='4D')
df = DataFrame({'time': times}, index=times)
times2 = timedelta_range('1 day', '4 day', freq='2D')
exp = Series(times2, index=times2, name='time')
exp.iloc[1] = pd.NaT
res = df.resample('2D').first()['time']
tm.assert_series_equal(res, exp)
res = df['time'].resample('2D').first()
tm.assert_series_equal(res, exp)
def test_format_timedelta_ticks_wide(self):
if is_platform_mac():
pytest.skip("skip on mac for precision display issue on older mpl")
expected_labels = [
'00:00:00',
'1 days 03:46:40',
'2 days 07:33:20',
'3 days 11:20:00',
'4 days 15:06:40',
'5 days 18:53:20',
'6 days 22:40:00',
'8 days 02:26:40',
''
]
rng = timedelta_range('0', periods=10, freq='1 d')
df = DataFrame(np.random.randn(len(rng), 3), rng)
fig, ax = self.plt.subplots()
ax = df.plot(fontsize=2, ax=ax)
fig.canvas.draw()
labels = ax.get_xticklabels()
assert len(labels) == len(expected_labels)
for l, l_expected in zip(labels, expected_labels):
assert l.get_text() == l_expected
def test_timedelta_plot(self):
# test issue #8711
s = Series(range(5), timedelta_range('1day', periods=5))
_check_plot_works(s.plot)
# test long period
index = timedelta_range('1 day 2 hr 30 min 10 s',
periods=10,
freq='1 d')
s = Series(np.random.randn(len(index)), index)
_check_plot_works(s.plot)
# test short period
index = timedelta_range('1 day 2 hr 30 min 10 s',
periods=10,
freq='1 ns')
s = Series(np.random.randn(len(index)), index)
_check_plot_works(s.plot)
def test_resample_with_nat():
# GH 13223
index = pd.to_timedelta(['0s', pd.NaT, '2s'])
result = DataFrame({'value': [2, 3, 5]}, index).resample('1s').mean()
expected = DataFrame({'value': [2.5, np.nan, 5.0]},
index=timedelta_range('0 day',
periods=3,
freq='1S'))
assert_frame_equal(result, expected)
def test_asfreq_bug():
df = DataFrame(data=[1, 3],
index=[timedelta(), timedelta(minutes=3)])
result = df.resample('1T').asfreq()
expected = DataFrame(data=[1, np.nan, np.nan, 3],
index=timedelta_range('0 day',
periods=4,
freq='1T'))
assert_frame_equal(result, expected)
def test_resample_with_nat():
# GH 13223
index = pd.to_timedelta(["0s", pd.NaT, "2s"])
result = DataFrame({"value": [2, 3, 5]}, index).resample("1s").mean()
expected = DataFrame(
{"value": [2.5, np.nan, 5.0]},
index=timedelta_range("0 day", periods=3, freq="1S"),
)
tm.assert_frame_equal(result, expected)
def test_resample_with_nat(self):
# GH 13223
index = pd.to_timedelta(['0s', pd.NaT, '2s'])
result = DataFrame({'value': [2, 3, 5]}, index).resample('1s').mean()
expected = DataFrame({'value': [2.5, np.nan, 5.0]},
index=timedelta_range('0 day',
periods=3,
freq='1S'))
assert_frame_equal(result, expected)
def test_resample_with_timedelta_yields_no_empty_groups(duplicates):
# GH 10603
df = DataFrame(
np.random.normal(size=(10000, 4)),
index=timedelta_range(start="0s", periods=10000, freq="3906250n"),
)
if duplicates:
# case with non-unique columns
df.columns = ["A", "B", "A", "C"]
result = df.loc["1s":, :].resample("3s").apply(lambda x: len(x))
expected = DataFrame(
[[768] * 4] * 12 + [[528] * 4],
index=timedelta_range(start="1s", periods=13, freq="3s"),
)
expected.columns = df.columns
tm.assert_frame_equal(result, expected)
def test_asfreq_bug(self):
import datetime as dt
df = DataFrame(data=[1, 3],
index=[dt.timedelta(),
dt.timedelta(minutes=3)])
result = df.resample('1T').asfreq()
expected = DataFrame(data=[1, np.nan, np.nan, 3],
index=timedelta_range('0 day',
periods=4,
freq='1T'))
assert_frame_equal(result, expected)
def test_resample_with_timedeltas():
expected = DataFrame({"A": np.arange(1480)})
expected = expected.groupby(expected.index // 30).sum()
expected.index = timedelta_range("0 days", freq="30T", periods=50)
df = DataFrame({"A": np.arange(1480)},
index=pd.to_timedelta(np.arange(1480), unit="T"))
result = df.resample("30T").sum()
tm.assert_frame_equal(result, expected)
s = df["A"]
result = s.resample("30T").sum()
tm.assert_series_equal(result, expected["A"])
def test_format_timedelta_ticks_narrow(self):
if is_platform_mac():
pytest.skip("skip on mac for precision display issue on older mpl")
expected_labels = [
'00:00:00.00000000{:d}'.format(i)
for i in range(10)]
rng = timedelta_range('0', periods=10, freq='ns')
df = DataFrame(np.random.randn(len(rng), 3), rng)
fig, ax = self.plt.subplots()
df.plot(fontsize=2, ax=ax)
fig.canvas.draw()
labels = ax.get_xticklabels()
assert len(labels) == len(expected_labels)
for l, l_expected in zip(labels, expected_labels):
assert l.get_text() == l_expected
def test_format_timedelta_ticks_narrow(self):
if is_platform_mac():
pytest.skip("skip on mac for precision display issue on older mpl")
expected_labels = [
'00:00:00.00000000{:d}'.format(i) for i in range(10)
]
rng = timedelta_range('0', periods=10, freq='ns')
df = DataFrame(np.random.randn(len(rng), 3), rng)
ax = df.plot(fontsize=2)
fig = ax.get_figure()
fig.canvas.draw()
labels = ax.get_xticklabels()
self.assertEqual(len(labels), len(expected_labels))
for l, l_expected in zip(labels, expected_labels):
self.assertEqual(l.get_text(), l_expected)
def test_format_timedelta_ticks_wide(self):
if is_platform_mac():
pytest.skip("skip on mac for precision display issue on older mpl")
expected_labels = [
'00:00:00', '1 days 03:46:40', '2 days 07:33:20',
'3 days 11:20:00', '4 days 15:06:40', '5 days 18:53:20',
'6 days 22:40:00', '8 days 02:26:40', ''
]
rng = timedelta_range('0', periods=10, freq='1 d')
df = DataFrame(np.random.randn(len(rng), 3), rng)
ax = df.plot(fontsize=2)
fig = ax.get_figure()
fig.canvas.draw()
labels = ax.get_xticklabels()
self.assertEqual(len(labels), len(expected_labels))
for l, l_expected in zip(labels, expected_labels):
self.assertEqual(l.get_text(), l_expected)
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 : integer, default None
Number of periods to generate
freq : numeric, string, 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' (calendar daily) for datetime-like.
name : string, default None
Name of the resulting IntervalIndex
closed : string, default 'right'
options are: 'left', 'right', 'both', 'neither'
Notes
-----
Of the three parameters: ``start``, ``end``, and ``periods``, exactly two
must be specified.
Returns
-------
rng : IntervalIndex
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]]')
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]')
See Also
--------
IntervalIndex : an Index of intervals that are all closed on the same side.
"""
if _count_not_none(start, end, periods) != 2:
raise ValueError('Of the three parameters: start, end, and periods, '
'exactly two must be specified')
start = _maybe_box_datetimelike(start)
end = _maybe_box_datetimelike(end)
endpoint = next(_not_none(start, end))
if not _is_valid_endpoint(start):
msg = 'start must be numeric or datetime-like, got {start}'
raise ValueError(msg.format(start=start))
if not _is_valid_endpoint(end):
msg = 'end must be numeric or datetime-like, got {end}'
raise ValueError(msg.format(end=end))
if is_float(periods):
periods = int(periods)
elif not is_integer(periods) and periods is not None:
msg = 'periods must be a number, got {periods}'
raise TypeError(msg.format(periods=periods))
freq = freq or (1 if is_number(endpoint) else 'D')
if not is_number(freq):
try:
freq = to_offset(freq)
except ValueError:
raise ValueError('freq must be numeric or convertible to '
'DateOffset, got {freq}'.format(freq=freq))
# 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")
if is_number(endpoint):
if periods is None:
periods = int((end - start) // freq)
if start is None:
start = end - periods * freq
# force end to be consistent with freq (lower if freq skips over end)
end = start + periods * freq
# end + freq for inclusive endpoint
breaks = np.arange(start, end + freq, freq)
elif isinstance(endpoint, Timestamp):
# add one to account for interval endpoints (n breaks = n-1 intervals)
if periods is not None:
periods += 1
breaks = date_range(start=start, end=end, periods=periods, freq=freq)
else:
# add one to account for interval endpoints (n breaks = n-1 intervals)
if periods is not None:
periods += 1
breaks = timedelta_range(start=start, end=end, periods=periods,
freq=freq)
return IntervalIndex.from_breaks(breaks, name=name, closed=closed)
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 = com.maybe_box_datetimelike(start)
end = com.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 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 : integer, default None
Number of periods to generate
freq : numeric, string, 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' (calendar daily) for datetime-like.
name : string, default None
Name of the resulting IntervalIndex
closed : string, default 'right'
options are: 'left', 'right', 'both', 'neither'
Notes
-----
Of the three parameters: ``start``, ``end``, and ``periods``, exactly two
must be specified.
Returns
-------
rng : IntervalIndex
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]]')
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]')
See Also
--------
IntervalIndex : an Index of intervals that are all closed on the same side.
"""
if com._count_not_none(start, end, periods) != 2:
raise ValueError('Of the three parameters: start, end, and periods, '
'exactly two must be specified')
start = com._maybe_box_datetimelike(start)
end = com._maybe_box_datetimelike(end)
endpoint = next(com._not_none(start, end))
if not _is_valid_endpoint(start):
msg = 'start must be numeric or datetime-like, got {start}'
raise ValueError(msg.format(start=start))
if not _is_valid_endpoint(end):
msg = 'end must be numeric or datetime-like, got {end}'
raise ValueError(msg.format(end=end))
if is_float(periods):
periods = int(periods)
elif not is_integer(periods) and periods is not None:
msg = 'periods must be a number, got {periods}'
raise TypeError(msg.format(periods=periods))
freq = freq or (1 if is_number(endpoint) else 'D')
if not is_number(freq):
try:
freq = to_offset(freq)
except ValueError:
raise ValueError('freq must be numeric or convertible to '
'DateOffset, got {freq}'.format(freq=freq))
# 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")
if is_number(endpoint):
if periods is None:
periods = int((end - start) // freq)
if start is None:
start = end - periods * freq
# force end to be consistent with freq (lower if freq skips over end)
end = start + periods * freq
# end + freq for inclusive endpoint
breaks = np.arange(start, end + freq, freq)
elif isinstance(endpoint, Timestamp):
# add one to account for interval endpoints (n breaks = n-1 intervals)
if periods is not None:
periods += 1
breaks = date_range(start=start, end=end, periods=periods, freq=freq)
else:
# add one to account for interval endpoints (n breaks = n-1 intervals)
if periods is not None:
periods += 1
breaks = timedelta_range(start=start, end=end, periods=periods,
freq=freq)
return IntervalIndex.from_breaks(breaks, name=name, closed=closed)
def create_series(self):
i = timedelta_range('1 day',
'10 day', freq='D')
return Series(np.arange(len(i)), index=i, name='tdi')
def interval_range(
start=None,
end=None,
periods=None,
freq=None,
name: Hashable = None,
closed: lib.NoDefault = lib.no_default,
inclusive: IntervalClosedType | None = None,
) -> IntervalIndex:
"""
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.
.. deprecated:: 1.5.0
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:: 1.5.0
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, inclusive="right")
IntervalIndex([(0, 1], (1, 2], (2, 3], (3, 4], (4, 5]],
dtype='interval[int64, right]')
Additionally, datetime-like input is also supported.
>>> pd.interval_range(start=pd.Timestamp('2017-01-01'),
... end=pd.Timestamp('2017-01-04'), inclusive="right")
IntervalIndex([(2017-01-01, 2017-01-02], (2017-01-02, 2017-01-03],
(2017-01-03, 2017-01-04]],
dtype='interval[datetime64[ns], right]')
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, inclusive="right")
IntervalIndex([(0.0, 1.5], (1.5, 3.0], (3.0, 4.5], (4.5, 6.0]],
dtype='interval[float64, right]')
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', inclusive="right")
IntervalIndex([(2017-01-01, 2017-02-01], (2017-02-01, 2017-03-01],
(2017-03-01, 2017-04-01]],
dtype='interval[datetime64[ns], right]')
Specify ``start``, ``end``, and ``periods``; the frequency is generated
automatically (linearly spaced).
>>> pd.interval_range(start=0, end=6, periods=4, inclusive="right")
IntervalIndex([(0.0, 1.5], (1.5, 3.0], (3.0, 4.5], (4.5, 6.0]],
dtype='interval[float64, right]')
The ``inclusive`` parameter specifies which endpoints of the individual
intervals within the ``IntervalIndex`` are closed.
>>> pd.interval_range(end=5, periods=4, inclusive='both')
IntervalIndex([[1, 2], [2, 3], [3, 4], [4, 5]],
dtype='interval[int64, both]')
"""
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=2,
)
if closed is None:
inclusive = "both"
elif closed in ("both", "neither", "left", "right"):
inclusive = closed
else:
raise ValueError(
"Argument `closed` has to be either"
"'both', 'neither', 'left' or 'right'"
)
elif inclusive is None:
inclusive = "both"
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
breaks: np.ndarray | TimedeltaIndex | DatetimeIndex
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
# error: Incompatible types in assignment (expression has type
# "Union[ExtensionArray, ndarray]", variable has type "ndarray")
breaks = maybe_downcast_numeric( # type: ignore[assignment]
breaks, np.dtype("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=inclusive)
def test_resample_single_period_timedelta():
s = Series(list(range(5)), index=timedelta_range("1 day", freq="s", periods=5))
result = s.resample("2s").sum()
expected = Series([1, 5, 4], index=timedelta_range("1 day", freq="2s", periods=3))
tm.assert_series_equal(result, expected)
def create_series(self):
i = timedelta_range('1 day', '10 day', freq='D')
return Series(np.arange(len(i)), index=i, name='tdi')