def _from_arraylike(cls, data, freq, tz):
if freq is not None:
freq = Period._maybe_convert_freq(freq)
if not isinstance(data, (np.ndarray, PeriodIndex,
DatetimeIndex, Int64Index)):
if is_scalar(data) or isinstance(data, Period):
raise ValueError('PeriodIndex() must be called with a '
'collection of some kind, %s was passed'
% repr(data))
# other iterable of some kind
if not isinstance(data, (list, tuple)):
data = list(data)
try:
data = _ensure_int64(data)
if freq is None:
raise ValueError('freq not specified')
data = np.array([Period(x, freq=freq) for x in data],
dtype=np.int64)
except (TypeError, ValueError):
data = _ensure_object(data)
if freq is None:
freq = period.extract_freq(data)
data = period.extract_ordinals(data, freq)
else:
if isinstance(data, PeriodIndex):
if freq is None or freq == data.freq:
freq = data.freq
data = data._values
else:
base1, _ = _gfc(data.freq)
base2, _ = _gfc(freq)
data = period.period_asfreq_arr(data._values,
base1, base2, 1)
else:
if is_object_dtype(data):
inferred = infer_dtype(data)
if inferred == 'integer':
data = data.astype(np.int64)
if freq is None and is_object_dtype(data):
# must contain Period instance and thus extract ordinals
freq = period.extract_freq(data)
data = period.extract_ordinals(data, freq)
if freq is None:
msg = 'freq not specified and cannot be inferred'
raise ValueError(msg)
if data.dtype != np.int64:
if np.issubdtype(data.dtype, np.datetime64):
data = dt64arr_to_periodarr(data, freq, tz)
else:
data = _ensure_object(data)
data = period.extract_ordinals(data, freq)
return data, freq
def to_timestamp(self, freq=None, how='start'):
"""
Cast to DatetimeIndex
Parameters
----------
freq : string or DateOffset, default 'D' for week or longer, 'S'
otherwise
Target frequency
how : {'s', 'e', 'start', 'end'}
Returns
-------
DatetimeIndex
"""
how = _validate_end_alias(how)
if freq is None:
base, mult = _gfc(self.freq)
freq = frequencies.get_to_timestamp_base(base)
else:
freq = Period._maybe_convert_freq(freq)
base, mult = _gfc(freq)
new_data = self.asfreq(freq, how)
new_data = period.periodarr_to_dt64arr(new_data.values, base)
return DatetimeIndex(new_data, freq='infer', name=self.name)
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
self.freq = Period._maybe_convert_freq(own_state[1])
else: # pragma: no cover
data = np.empty(state)
np.ndarray.__setstate__(self, state)
self._data = data
else:
raise Exception("invalid pickle state")
def to_timestamp(self, freq=None, how='start'):
"""
Cast to DatetimeIndex
Parameters
----------
freq : string or DateOffset, default 'D' for week or longer, 'S'
otherwise
Target frequency
how : {'s', 'e', 'start', 'end'}
Returns
-------
DatetimeIndex
"""
how = _validate_end_alias(how)
if freq is None:
base, mult = _gfc(self.freq)
freq = frequencies.get_to_timestamp_base(base)
else:
freq = Period._maybe_convert_freq(freq)
base, mult = _gfc(freq)
new_data = self.asfreq(freq, how)
new_data = period.periodarr_to_dt64arr(new_data._values, base)
return DatetimeIndex(new_data, freq='infer', name=self.name)
def dt64arr_to_periodarr(data, freq, tz):
if data.dtype != np.dtype('M8[ns]'):
raise ValueError('Wrong dtype: %s' % data.dtype)
freq = Period._maybe_convert_freq(freq)
base, mult = _gfc(freq)
return period.dt64arr_to_periodarr(data.view('i8'), base, tz)
def asfreq(self, freq=None, how='E'):
"""
Convert the PeriodIndex to the specified frequency `freq`.
Parameters
----------
freq : str
a frequency
how : str {'E', 'S'}
'E', 'END', or 'FINISH' for end,
'S', 'START', or 'BEGIN' for start.
Whether the elements should be aligned to the end
or start within pa period. January 31st ('END') vs.
Janury 1st ('START') for example.
Returns
-------
new : PeriodIndex with the new frequency
Examples
--------
>>> pidx = pd.period_range('2010-01-01', '2015-01-01', freq='A')
>>> pidx
<class 'pandas.tseries.period.PeriodIndex'>
[2010, ..., 2015]
Length: 6, Freq: A-DEC
>>> pidx.asfreq('M')
<class 'pandas.tseries.period.PeriodIndex'>
[2010-12, ..., 2015-12]
Length: 6, Freq: M
>>> pidx.asfreq('M', how='S')
<class 'pandas.tseries.period.PeriodIndex'>
[2010-01, ..., 2015-01]
Length: 6, Freq: M
"""
how = _validate_end_alias(how)
freq = Period._maybe_convert_freq(freq)
base1, mult1 = _gfc(self.freq)
base2, mult2 = _gfc(freq)
asi8 = self.asi8
# mult1 can't be negative or 0
end = how == 'E'
if end:
ordinal = asi8 + mult1 - 1
else:
ordinal = asi8
new_data = period.period_asfreq_arr(ordinal, base1, base2, end)
if self.hasnans:
new_data[self._isnan] = tslib.iNaT
return self._simple_new(new_data, self.name, freq=freq)
def _from_arraylike(cls, data, freq, tz):
if freq is not None:
freq = Period._maybe_convert_freq(freq)
if not isinstance(
data, (np.ndarray, PeriodIndex, DatetimeIndex, Int64Index)):
if is_scalar(data) or isinstance(data, Period):
raise ValueError('PeriodIndex() must be called with a '
'collection of some kind, %s was passed' %
repr(data))
# other iterable of some kind
if not isinstance(data, (list, tuple)):
data = list(data)
try:
data = _ensure_int64(data)
if freq is None:
raise ValueError('freq not specified')
data = np.array([Period(x, freq=freq) for x in data],
dtype=np.int64)
except (TypeError, ValueError):
data = _ensure_object(data)
if freq is None:
freq = period.extract_freq(data)
data = period.extract_ordinals(data, freq)
else:
if isinstance(data, PeriodIndex):
if freq is None or freq == data.freq:
freq = data.freq
data = data._values
else:
base1, _ = _gfc(data.freq)
base2, _ = _gfc(freq)
data = period.period_asfreq_arr(data._values, base1, base2,
1)
else:
if is_object_dtype(data):
inferred = infer_dtype(data)
if inferred == 'integer':
data = data.astype(np.int64)
if freq is None and is_object_dtype(data):
# must contain Period instance and thus extract ordinals
freq = period.extract_freq(data)
data = period.extract_ordinals(data, freq)
if freq is None:
msg = 'freq not specified and cannot be inferred'
raise ValueError(msg)
if data.dtype != np.int64:
if np.issubdtype(data.dtype, np.datetime64):
data = dt64arr_to_periodarr(data, freq, tz)
else:
data = _ensure_object(data)
data = period.extract_ordinals(data, freq)
return data, freq
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
self.freq = Period._maybe_convert_freq(own_state[1])
else: # pragma: no cover
data = np.empty(state)
np.ndarray.__setstate__(self, state)
self._data = data
else:
raise Exception("invalid pickle state")
def dt64arr_to_periodarr(data, freq, tz):
if data.dtype != np.dtype('M8[ns]'):
raise ValueError('Wrong dtype: %s' % data.dtype)
freq = Period._maybe_convert_freq(freq)
base, mult = _gfc(freq)
return period.dt64arr_to_periodarr(data.view('i8'), base, tz)
def asfreq(self, freq=None, how='E'):
"""
Convert the PeriodIndex to the specified frequency `freq`.
Parameters
----------
freq : str
a frequency
how : str {'E', 'S'}
'E', 'END', or 'FINISH' for end,
'S', 'START', or 'BEGIN' for start.
Whether the elements should be aligned to the end
or start within pa period. January 31st ('END') vs.
Janury 1st ('START') for example.
Returns
-------
new : PeriodIndex with the new frequency
Examples
--------
>>> pidx = pd.period_range('2010-01-01', '2015-01-01', freq='A')
>>> pidx
<class 'pandas.tseries.period.PeriodIndex'>
[2010, ..., 2015]
Length: 6, Freq: A-DEC
>>> pidx.asfreq('M')
<class 'pandas.tseries.period.PeriodIndex'>
[2010-12, ..., 2015-12]
Length: 6, Freq: M
>>> pidx.asfreq('M', how='S')
<class 'pandas.tseries.period.PeriodIndex'>
[2010-01, ..., 2015-01]
Length: 6, Freq: M
"""
how = _validate_end_alias(how)
freq = Period._maybe_convert_freq(freq)
base1, mult1 = _gfc(self.freq)
base2, mult2 = _gfc(freq)
asi8 = self.asi8
# mult1 can't be negative or 0
end = how == 'E'
if end:
ordinal = asi8 + mult1 - 1
else:
ordinal = asi8
new_data = period.period_asfreq_arr(ordinal, base1, base2, end)
if self.hasnans:
new_data[self._isnan] = tslib.iNaT
return self._simple_new(new_data, self.name, freq=freq)
def _simple_new(cls, values, name=None, freq=None, **kwargs):
if not getattr(values, 'dtype', None):
values = np.array(values, copy=False)
if is_object_dtype(values):
return PeriodIndex(values, name=name, freq=freq, **kwargs)
result = object.__new__(cls)
result._data = values
result.name = name
if freq is None:
raise ValueError('freq is not specified')
result.freq = Period._maybe_convert_freq(freq)
result._reset_identity()
return result
def _simple_new(cls, values, name=None, freq=None, **kwargs):
if not getattr(values, 'dtype', None):
values = np.array(values, copy=False)
if is_object_dtype(values):
return PeriodIndex(values, name=name, freq=freq, **kwargs)
result = object.__new__(cls)
result._data = values
result.name = name
if freq is None:
raise ValueError('freq is not specified')
result.freq = Period._maybe_convert_freq(freq)
result._reset_identity()
return result
def _from_ordinals(cls, values, name=None, freq=None, **kwargs):
"""
Values should be int ordinals
`__new__` & `_simple_new` cooerce to ordinals and call this method
"""
values = np.array(values, dtype='int64', copy=False)
result = object.__new__(cls)
result._data = values
result.name = name
if freq is None:
raise ValueError('freq is not specified and cannot be inferred')
result.freq = Period._maybe_convert_freq(freq)
result._reset_identity()
return result
def _generate_range(cls, start, end, periods, freq, fields):
if freq is not None:
freq = Period._maybe_convert_freq(freq)
field_count = len(fields)
if com._count_not_none(start, end) > 0:
if field_count > 0:
raise ValueError('Can either instantiate from fields '
'or endpoints, but not both')
subarr, freq = _get_ordinal_range(start, end, periods, freq)
elif field_count > 0:
subarr, freq = _range_from_fields(freq=freq, **fields)
else:
raise ValueError('Not enough parameters to construct '
'Period range')
return subarr, freq
def _generate_range(cls, start, end, periods, freq, fields):
if freq is not None:
freq = Period._maybe_convert_freq(freq)
field_count = len(fields)
if com._count_not_none(start, end) > 0:
if field_count > 0:
raise ValueError('Can either instantiate from fields '
'or endpoints, but not both')
subarr, freq = _get_ordinal_range(start, end, periods, freq)
elif field_count > 0:
subarr, freq = _range_from_fields(freq=freq, **fields)
else:
raise ValueError('Not enough parameters to construct '
'Period range')
return subarr, freq
def _simple_new(cls, values, name=None, freq=None, **kwargs):
if not is_integer_dtype(values):
values = np.array(values, copy=False)
if (len(values) > 0 and is_float_dtype(values)):
raise TypeError("PeriodIndex can't take floats")
else:
return PeriodIndex(values, name=name, freq=freq, **kwargs)
values = np.array(values, dtype='int64', copy=False)
result = object.__new__(cls)
result._data = values
result.name = name
if freq is None:
raise ValueError('freq is not specified')
result.freq = Period._maybe_convert_freq(freq)
result._reset_identity()
return result
def _simple_new(cls, values, name=None, freq=None, **kwargs):
if not is_integer_dtype(values):
values = np.array(values, copy=False)
if (len(values) > 0 and is_float_dtype(values)):
raise TypeError("PeriodIndex can't take floats")
else:
return PeriodIndex(values, name=name, freq=freq, **kwargs)
values = np.array(values, dtype='int64', copy=False)
result = object.__new__(cls)
result._data = values
result.name = name
if freq is None:
raise ValueError('freq is not specified')
result.freq = Period._maybe_convert_freq(freq)
result._reset_identity()
return result
def __new__(cls,
data=None,
ordinal=None,
freq=None,
start=None,
end=None,
periods=None,
copy=False,
name=None,
tz=None,
dtype=None,
**kwargs):
if periods is not None:
if is_float(periods):
periods = int(periods)
elif not is_integer(periods):
raise ValueError('Periods must be a number, got %s' %
str(periods))
if name is None and hasattr(data, 'name'):
name = data.name
if dtype is not None:
dtype = pandas_dtype(dtype)
if not is_period_dtype(dtype):
raise ValueError('dtype must be PeriodDtype')
if freq is None:
freq = dtype.freq
elif freq != dtype.freq:
msg = 'specified freq and dtype are different'
raise IncompatibleFrequency(msg)
# coerce freq to freq object, otherwise it can be coerced elementwise
# which is slow
if freq:
freq = Period._maybe_convert_freq(freq)
if data is None:
if ordinal is not None:
data = np.asarray(ordinal, dtype=np.int64)
else:
data, freq = cls._generate_range(start, end, periods, freq,
kwargs)
return cls._from_ordinals(data, name=name, freq=freq)
if isinstance(data, PeriodIndex):
if freq is None or freq == data.freq: # no freq change
freq = data.freq
data = data._values
else:
base1, _ = _gfc(data.freq)
base2, _ = _gfc(freq)
data = period.period_asfreq_arr(data._values, base1, base2, 1)
return cls._simple_new(data, name=name, freq=freq)
# not array / index
if not isinstance(
data, (np.ndarray, PeriodIndex, DatetimeIndex, Int64Index)):
if is_scalar(data) or isinstance(data, Period):
cls._scalar_data_error(data)
# other iterable of some kind
if not isinstance(data, (list, tuple)):
data = list(data)
data = np.asarray(data)
# datetime other than period
if is_datetime64_dtype(data.dtype):
data = dt64arr_to_periodarr(data, freq, tz)
return cls._from_ordinals(data, name=name, freq=freq)
# check not floats
if infer_dtype(data) == 'floating' and len(data) > 0:
raise TypeError("PeriodIndex does not allow "
"floating point in construction")
# anything else, likely an array of strings or periods
data = _ensure_object(data)
freq = freq or period.extract_freq(data)
data = period.extract_ordinals(data, freq)
return cls._from_ordinals(data, name=name, freq=freq)
