def __new__(cls, data, closed=None,
name=None, copy=False, dtype=None,
fastpath=False, verify_integrity=True):
if fastpath:
return cls._simple_new(data.left, data.right, closed, name,
copy=copy, verify_integrity=False)
if name is None and hasattr(data, 'name'):
name = data.name
if isinstance(data, IntervalIndex):
left = data.left
right = data.right
closed = data.closed
else:
# don't allow scalars
if is_scalar(data):
cls._scalar_data_error(data)
data = maybe_convert_platform(data)
left, right, infer_closed = intervals_to_interval_bounds(data)
if _all_not_none(closed, infer_closed) and closed != infer_closed:
# GH 18421
msg = ("conflicting values for closed: constructor got "
"'{closed}', inferred from data '{infer_closed}'"
.format(closed=closed, infer_closed=infer_closed))
raise ValueError(msg)
closed = closed or infer_closed
return cls._simple_new(left, right, closed, name,
copy=copy, verify_integrity=verify_integrity)
def __new__(cls, data, closed=None,
name=None, copy=False, dtype=None,
fastpath=False, verify_integrity=True):
if fastpath:
return cls._simple_new(data.left, data.right, closed, name,
copy=copy, verify_integrity=False)
if name is None and hasattr(data, 'name'):
name = data.name
if isinstance(data, IntervalIndex):
left = data.left
right = data.right
closed = data.closed
else:
# don't allow scalars
if is_scalar(data):
cls._scalar_data_error(data)
data = maybe_convert_platform(data)
left, right, infer_closed = intervals_to_interval_bounds(data)
if _all_not_none(closed, infer_closed) and closed != infer_closed:
# GH 18421
msg = ("conflicting values for closed: constructor got "
"'{closed}', inferred from data '{infer_closed}'"
.format(closed=closed, infer_closed=infer_closed))
raise ValueError(msg)
closed = closed or infer_closed
return cls._simple_new(left, right, closed, name,
copy=copy, verify_integrity=verify_integrity)
def set_default_names(data):
"""Sets index names to 'index' for regular, or 'level_x' for Multi"""
if _all_not_none(*data.index.names):
return data
data = data.copy()
if data.index.nlevels > 1:
names = [name if name is not None else 'level_{}'.format(i)
for i, name in enumerate(data.index.names)]
data.index.names = names
else:
data.index.name = data.index.name or 'index'
return data
def set_default_names(data):
"""Sets index names to 'index' for regular, or 'level_x' for Multi"""
if _all_not_none(*data.index.names):
return data
data = data.copy()
if data.index.nlevels > 1:
names = [
name if name is not None else 'level_{}'.format(i)
for i, name in enumerate(data.index.names)
]
data.index.names = names
else:
data.index.name = data.index.name or 'index'
return data
def set_default_names(data):
"""Sets index names to 'index' for regular, or 'level_x' for Multi"""
if com._all_not_none(*data.index.names):
nms = data.index.names
if len(nms) == 1 and data.index.name == 'index':
warnings.warn("Index name of 'index' is not round-trippable")
elif len(nms) > 1 and any(x.startswith('level_') for x in nms):
warnings.warn("Index names beginning with 'level_' are not "
"round-trippable")
return data
data = data.copy()
if data.index.nlevels > 1:
names = [name if name is not None else 'level_{}'.format(i)
for i, name in enumerate(data.index.names)]
data.index.names = names
else:
data.index.name = data.index.name or 'index'
return data
def set_default_names(data):
"""Sets index names to 'index' for regular, or 'level_x' for Multi"""
if com._all_not_none(*data.index.names):
nms = data.index.names
if len(nms) == 1 and data.index.name == 'index':
warnings.warn("Index name of 'index' is not round-trippable")
elif len(nms) > 1 and any(x.startswith('level_') for x in nms):
warnings.warn("Index names beginning with 'level_' are not "
"round-trippable")
return data
data = data.copy()
if data.index.nlevels > 1:
names = [name if name is not None else 'level_{}'.format(i)
for i, name in enumerate(data.index.names)]
data.index.names = names
else:
data.index.name = data.index.name or 'index'
return data
def test_all_not_none():
assert(com._all_not_none(1, 2, 3, 4))
assert(not com._all_not_none(1, 2, 3, None))
assert(not com._all_not_none(None, None, None, None))
def test_all_not_none():
assert (com._all_not_none(1, 2, 3, 4))
assert (not com._all_not_none(1, 2, 3, None))
assert (not com._all_not_none(None, None, None, None))
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' for datetime-like.
name : string, 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.
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
<http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases>`__.
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]]')
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]')
See Also
--------
IntervalIndex : an Index of intervals that are all closed on the same side.
"""
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):
msg = 'start must be numeric or datetime-like, got {start}'
raise ValueError(msg.format(start=start))
elif 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))
if freq is not None and 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")
# +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):
range_func = date_range
else:
range_func = timedelta_range
breaks = range_func(start=start, end=end, periods=periods, freq=freq)
return IntervalIndex.from_breaks(breaks, name=name, closed=closed)
def test_all_not_none():
assert com._all_not_none(1, 2, 3, 4)
assert not com._all_not_none(1, 2, 3, None)
assert not com._all_not_none(None, None, None, None)
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' for datetime-like.
name : string, 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
-------
rng : 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
<http://pandas.pydata.org/pandas-docs/stable/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):
msg = 'start must be numeric or datetime-like, got {start}'
raise ValueError(msg.format(start=start))
elif 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))
if freq is not None and 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")
# +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):
range_func = date_range
else:
range_func = timedelta_range
breaks = range_func(start=start, end=end, periods=periods, freq=freq)
return IntervalIndex.from_breaks(breaks, name=name, closed=closed)
def test_all_not_none():
assert com._all_not_none(1, 2, 3, 4)
assert not com._all_not_none(1, 2, 3, None)
assert not com._all_not_none(None, None, None, None)
