def __setstate__(self, state):
"""Necessary for making this object picklable"""
if isinstance(state, dict):
super(PeriodIndex, self).__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)
# backcompat
freq = Period._maybe_convert_freq(own_state[1])
else: # pragma: no cover
data = np.empty(state)
np.ndarray.__setstate__(self, state)
freq = None # ?
data = PeriodArray(data, freq=freq)
self._data = data
else:
raise Exception("invalid pickle state")
def _shallow_copy(self, values=None, **kwargs):
# TODO: simplify, figure out type of values
if values is None:
values = self._data
if isinstance(values, type(self)):
values = values._values
if not isinstance(values, PeriodArray):
if (isinstance(values, np.ndarray) and
is_integer_dtype(values.dtype)):
values = PeriodArray(values, freq=self.freq)
else:
# in particular, I would like to avoid period_array here.
# Some people seem to be calling use with unexpected types
# Index.difference -> ndarray[Period]
# DatetimelikeIndexOpsMixin.repeat -> ndarray[ordinal]
# I think that once all of Datetime* are EAs, we can simplify
# this quite a bit.
values = period_array(values, freq=self.freq)
# I don't like overloading shallow_copy with freq changes.
# See if it's used anywhere outside of test_resample_empty_dataframe
attributes = self._get_attributes_dict()
freq = kwargs.pop("freq", None)
if freq:
values = values.asfreq(freq)
attributes.pop("freq", None)
attributes.update(kwargs)
if not len(values) and 'dtype' not in kwargs:
attributes['dtype'] = self.dtype
return self._simple_new(values, **attributes)
def _simple_new(cls, values, name=None, freq=None, **kwargs):
"""
Create a new PeriodIndex.
Parameters
----------
values : PeriodArray, PeriodIndex, Index[int64], ndarray[int64]
Values that can be converted to a PeriodArray without inference
or coercion.
"""
# TODO: raising on floats is tested, but maybe not useful.
# Should the callers know not to pass floats?
# At the very least, I think we can ensure that lists aren't passed.
if isinstance(values, list):
values = np.asarray(values)
if is_float_dtype(values):
raise TypeError("PeriodIndex._simple_new does not accept floats.")
values = PeriodArray(values, freq=freq)
if not isinstance(values, PeriodArray):
raise TypeError("PeriodIndex._simple_new only accepts PeriodArray")
result = object.__new__(cls)
result._data = values
result.name = name
result._reset_identity()
return result
def _shallow_copy(self, values=None, **kwargs):
# TODO: simplify, figure out type of values
if values is None:
values = self._data
if isinstance(values, type(self)):
values = values._values
if not isinstance(values, PeriodArray):
if isinstance(values, np.ndarray) and is_integer_dtype(values.dtype):
values = PeriodArray(values, freq=self.freq)
else:
# in particular, I would like to avoid period_array here.
# Some people seem to be calling use with unexpected types
# Index.difference -> ndarray[Period]
# DatetimelikeIndexOpsMixin.repeat -> ndarray[ordinal]
# I think that once all of Datetime* are EAs, we can simplify
# this quite a bit.
values = period_array(values, freq=self.freq)
# We don't allow changing `freq` in _shallow_copy.
validate_dtype_freq(self.dtype, kwargs.get("freq"))
attributes = self._get_attributes_dict()
attributes.update(kwargs)
if not len(values) and "dtype" not in kwargs:
attributes["dtype"] = self.dtype
return self._simple_new(values, **attributes)
def _new_PeriodIndex(cls, **d):
# GH13277 for unpickling
values = d.pop('data')
if values.dtype == 'int64':
freq = d.pop('freq', None)
values = PeriodArray(values, freq=freq)
return cls._simple_new(values, **d)
else:
return cls(values, **d)
def _new_PeriodIndex(cls, **d):
# GH13277 for unpickling
values = d.pop("area_data")
if values.dtype == "int64":
freq = d.pop("freq", None)
values = PeriodArray(values, freq=freq)
return cls._simple_new(values, **d)
else:
return cls(values, **d)
def _add_period(self, other: Period):
"""
Add a Period object.
"""
# We will wrap in a PeriodArray and defer to the reversed operation
from pandas.core.arrays.period import PeriodArray
i8vals = np.broadcast_to(other.ordinal, self.shape)
oth = PeriodArray(i8vals, freq=other.freq)
return oth + self
def _maybe_box_as_values(self, values, **attribs):
"""Box an array of ordinals to a PeriodArray
This is purely for compatibility between PeriodIndex
and Datetime/TimedeltaIndex. Once these are all backed by
an ExtensionArray, this can be removed
"""
# TODO(DatetimeArray): remove
freq = attribs['freq']
return PeriodArray(values, freq=freq)
def __new__(cls, data=None, ordinal=None, freq=None, start=None, end=None,
periods=None, tz=None, dtype=None, copy=False, name=None,
**fields):
valid_field_set = {'year', 'month', 'day', 'quarter',
'hour', 'minute', 'second'}
if not set(fields).issubset(valid_field_set):
raise TypeError('__new__() got an unexpected keyword argument {}'.
format(list(set(fields) - valid_field_set)[0]))
if name is None and hasattr(data, 'name'):
name = data.name
if data is None and ordinal is None:
# range-based.
data, freq = PeriodArray._generate_range(start, end, periods,
freq, fields)
data = PeriodArray(data, freq=freq)
else:
freq = dtl.validate_dtype_freq(dtype, freq)
# PeriodIndex allow PeriodIndex(period_index, freq=different)
# Let's not encourage that kind of behavior in PeriodArray.
if freq and isinstance(data, cls) and data.freq != freq:
# TODO: We can do some of these with no-copy / coercion?
# e.g. D -> 2D seems to be OK
data = data.asfreq(freq)
if data is None and ordinal is not None:
# we strangely ignore `ordinal` if data is passed.
ordinal = np.asarray(ordinal, dtype=np.int64)
data = PeriodArray(ordinal, freq)
else:
# don't pass copy here, since we copy later.
data = period_array(data=data, freq=freq)
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
def _shallow_copy(self, values=None, name: Label = no_default):
# TODO: simplify, figure out type of values
name = name if name is not no_default else self.name
if values is None:
values = self._data
if isinstance(values, type(self)):
values = values._data
if not isinstance(values, PeriodArray):
if isinstance(values, np.ndarray) and values.dtype == "i8":
values = PeriodArray(values, freq=self.freq)
else:
# GH#30713 this should never be reached
raise TypeError(type(values), getattr(values, "dtype", None))
return self._simple_new(values, name=name)
def _shallow_copy(self, values=None, **kwargs):
# TODO: simplify, figure out type of values
if values is None:
values = self._data
if isinstance(values, type(self)):
values = values._data
if not isinstance(values, PeriodArray):
if isinstance(values, np.ndarray) and values.dtype == "i8":
values = PeriodArray(values, freq=self.freq)
else:
# GH#30713 this should never be reached
raise TypeError(type(values), getattr(values, "dtype", None))
# We don't allow changing `freq` in _shallow_copy.
validate_dtype_freq(self.dtype, kwargs.get("freq"))
attributes = self._get_attributes_dict()
attributes.update(kwargs)
if not len(values) and "dtype" not in kwargs:
attributes["dtype"] = self.dtype
return self._simple_new(values, **attributes)
def period_range(
start=None, end=None, periods=None, freq=None, name=None
) -> PeriodIndex:
"""
Return a fixed frequency PeriodIndex.
The day (calendar) is the default frequency.
Parameters
----------
start : str or period-like, default None
Left bound for generating periods.
end : str or period-like, default None
Right bound for generating periods.
periods : int, default None
Number of periods to generate.
freq : str or DateOffset, optional
Frequency alias. By default the freq is taken from `start` or `end`
if those are Period objects. Otherwise, the default is ``"D"`` for
daily frequency.
name : str, default None
Name of the resulting PeriodIndex.
Returns
-------
PeriodIndex
Notes
-----
Of the three parameters: ``start``, ``end``, and ``periods``, exactly two
must be specified.
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.period_range(start='2017-01-01', end='2018-01-01', freq='M')
PeriodIndex(['2017-01', '2017-02', '2017-03', '2017-04', '2017-05', '2017-06',
'2017-07', '2017-08', '2017-09', '2017-10', '2017-11', '2017-12',
'2018-01'],
dtype='period[M]', freq='M')
If ``start`` or ``end`` are ``Period`` objects, they will be used as anchor
endpoints for a ``PeriodIndex`` with frequency matching that of the
``period_range`` constructor.
>>> pd.period_range(start=pd.Period('2017Q1', freq='Q'),
... end=pd.Period('2017Q2', freq='Q'), freq='M')
PeriodIndex(['2017-03', '2017-04', '2017-05', '2017-06'],
dtype='period[M]', freq='M')
"""
if com.count_not_none(start, end, periods) != 2:
raise ValueError(
"Of the three parameters: start, end, and periods, "
"exactly two must be specified"
)
if freq is None and (not isinstance(start, Period) and not isinstance(end, Period)):
freq = "D"
data, freq = PeriodArray._generate_range(start, end, periods, freq, fields={})
data = PeriodArray(data, freq=freq)
return PeriodIndex(data, name=name)
def __new__(cls,
data=None,
ordinal=None,
freq=None,
start=None,
end=None,
periods=None,
tz=None,
dtype=None,
copy=False,
name=None,
**fields):
valid_field_set = {
"year",
"month",
"day",
"quarter",
"hour",
"minute",
"second",
}
if not set(fields).issubset(valid_field_set):
raise TypeError(
"__new__() got an unexpected keyword argument {}".format(
list(set(fields) - valid_field_set)[0]))
if name is None and hasattr(data, "name"):
name = data.name
if data is None and ordinal is None:
# range-based.
data, freq2 = PeriodArray._generate_range(start, end, periods,
freq, fields)
# PeriodArray._generate range does validate that fields is
# empty when really using the range-based constructor.
if not fields:
msg = ("Creating a PeriodIndex by passing range "
"endpoints is deprecated. Use "
"`pandas.period_range` instead.")
# period_range differs from PeriodIndex for cases like
# start="2000", periods=4
# PeriodIndex interprets that as A-DEC freq.
# period_range interprets it as 'D' freq.
cond = freq is None and (
(start and not isinstance(start, Period)) or
(end and not isinstance(end, Period)))
if cond:
msg += (" Note that the default `freq` may differ. Pass "
"'freq=\"{}\"' to ensure the same output.").format(
freq2.freqstr)
warnings.warn(msg, FutureWarning, stacklevel=2)
freq = freq2
data = PeriodArray(data, freq=freq)
else:
freq = validate_dtype_freq(dtype, freq)
# PeriodIndex allow PeriodIndex(period_index, freq=different)
# Let's not encourage that kind of behavior in PeriodArray.
if freq and isinstance(data, cls) and data.freq != freq:
# TODO: We can do some of these with no-copy / coercion?
# e.g. D -> 2D seems to be OK
data = data.asfreq(freq)
if data is None and ordinal is not None:
# we strangely ignore `ordinal` if data is passed.
ordinal = np.asarray(ordinal, dtype=np.int64)
data = PeriodArray(ordinal, freq)
else:
# don't pass copy here, since we copy later.
data = period_array(data=data, freq=freq)
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
def __new__(
cls,
data=None,
ordinal=None,
freq=None,
tz=None,
dtype=None,
copy=False,
name=None,
**fields,
):
valid_field_set = {
"year",
"month",
"day",
"quarter",
"hour",
"minute",
"second",
}
if not set(fields).issubset(valid_field_set):
argument = list(set(fields) - valid_field_set)[0]
raise TypeError(
f"__new__() got an unexpected keyword argument {argument}")
name = maybe_extract_name(name, data, cls)
if data is None and ordinal is None:
# range-based.
data, freq2 = PeriodArray._generate_range(None, None, None, freq,
fields)
# PeriodArray._generate range does validation that fields is
# empty when really using the range-based constructor.
freq = freq2
data = PeriodArray(data, freq=freq)
else:
freq = validate_dtype_freq(dtype, freq)
# PeriodIndex allow PeriodIndex(period_index, freq=different)
# Let's not encourage that kind of behavior in PeriodArray.
if freq and isinstance(data, cls) and data.freq != freq:
# TODO: We can do some of these with no-copy / coercion?
# e.g. D -> 2D seems to be OK
data = data.asfreq(freq)
if data is None and ordinal is not None:
# we strangely ignore `ordinal` if data is passed.
ordinal = np.asarray(ordinal, dtype=np.int64)
data = PeriodArray(ordinal, freq)
else:
# don't pass copy here, since we copy later.
data = period_array(data=data, freq=freq)
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
def _apply_meta(self, rawarr) -> "PeriodIndex":
if not isinstance(rawarr, PeriodIndex):
if not isinstance(rawarr, PeriodArray):
rawarr = PeriodArray(rawarr, freq=self.freq)
rawarr = PeriodIndex._simple_new(rawarr, name=self.name)
return rawarr
