def _assert_can_do_setop(self, other):
super(PeriodIndex, self)._assert_can_do_setop(other)
if not isinstance(other, PeriodIndex):
raise ValueError('can only call with other PeriodIndex-ed objects')
if self.freq != other.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
def searchsorted(self, key, side='left', sorter=None):
if isinstance(key, Period):
if key.freq != self.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, key.freqstr)
raise IncompatibleFrequency(msg)
key = key.ordinal
elif isinstance(key, compat.string_types):
key = Period(key, freq=self.freq).ordinal
return self._values.searchsorted(key, side=side, sorter=sorter)
def _sub_period(self, other):
if self.freq != other.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
asi8 = self.asi8
new_data = asi8 - other.ordinal
if self.hasnans:
new_data = new_data.astype(np.float64)
new_data[self._isnan] = np.nan
# result must be Int64Index or Float64Index
return Index(new_data, name=self.name)
def get_indexer(self, target, method=None, limit=None, tolerance=None):
target = _ensure_index(target)
if hasattr(target, 'freq') and target.freq != self.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, target.freqstr)
raise IncompatibleFrequency(msg)
if isinstance(target, PeriodIndex):
target = target.asi8
if tolerance is not None:
tolerance = self._convert_tolerance(tolerance)
return Index.get_indexer(self._int64index, target, method, limit,
tolerance)
def _sub_period(self, other):
if self.freq != other.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
if other.ordinal == tslib.iNaT:
new_data = np.empty(len(self))
new_data.fill(np.nan)
else:
asi8 = self.asi8
new_data = asi8 - other.ordinal
if self.hasnans:
mask = asi8 == tslib.iNaT
new_data = new_data.astype(np.float64)
new_data[mask] = np.nan
# result must be Int64Index or Float64Index
return Index(new_data, name=self.name)
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)
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)
else:
ordinal, freq = cls._from_arraylike(data, freq, tz)
data = np.array(ordinal, dtype=np.int64, copy=copy)
return cls._simple_new(data, name=name, freq=freq)
def _downsample(self, how, **kwargs):
"""
Downsample the cython defined function
Parameters
----------
how : string / cython mapped function
**kwargs : kw args passed to how function
"""
# we may need to actually resample as if we are timestamps
if self.kind == 'timestamp':
return super(PeriodIndexResampler, self)._downsample(how, **kwargs)
how = self._is_cython_func(how) or how
ax = self.ax
new_index = self._get_new_index()
# Start vs. end of period
memb = ax.asfreq(self.freq, how=self.convention)
if is_subperiod(ax.freq, self.freq):
# Downsampling
if len(new_index) == 0:
bins = []
else:
i8 = memb.asi8
rng = np.arange(i8[0], i8[-1] + 1)
bins = memb.searchsorted(rng, side='right')
grouper = BinGrouper(bins, new_index)
return self._groupby_and_aggregate(how, grouper=grouper)
elif is_superperiod(ax.freq, self.freq):
return self.asfreq()
elif ax.freq == self.freq:
return self.asfreq()
raise IncompatibleFrequency(
'Frequency {} cannot be resampled to {}, as they are not '
'sub or super periods'.format(ax.freq, self.freq))
def get_indexer(self, target, method=None, limit=None, tolerance=None):
if hasattr(target, 'freq') and target.freq != self.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, target.freqstr)
raise IncompatibleFrequency(msg)
return Index.get_indexer(self, target, method, limit, tolerance)
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)
