def _evaluate_numeric_binop(self, other):
other = self._validate_for_numeric_binop(other, op, opstr)
attrs = self._get_attributes_dict()
attrs = self._maybe_update_attributes(attrs)
if reversed:
self, other = other, self
try:
# alppy if we have an override
if step:
with np.errstate(all='ignore'):
rstep = step(self._step, other)
# we don't have a representable op
# so return a base index
if not is_integer(rstep) or not rstep:
raise ValueError
else:
rstep = self._step
with np.errstate(all='ignore'):
rstart = op(self._start, other)
rstop = op(self._stop, other)
result = RangeIndex(rstart,
rstop,
rstep,
**attrs)
# for compat with numpy / Int64Index
# even if we can represent as a RangeIndex, return
# as a Float64Index if we have float-like descriptors
if not all([is_integer(x) for x in
[rstart, rstop, rstep]]):
result = result.astype('float64')
return result
except (ValueError, TypeError, AttributeError):
pass
# convert to Int64Index ops
if isinstance(self, RangeIndex):
self = self.values
if isinstance(other, RangeIndex):
other = other.values
with np.errstate(all='ignore'):
results = op(self, other)
return Index(results, **attrs)
def get_freq_code(freqstr):
"""
Return freq str or tuple to freq code and stride (mult)
Parameters
----------
freqstr : str or tuple
Returns
-------
return : tuple of base frequency code and stride (mult)
Example
-------
>>> get_freq_code('3D')
(6000, 3)
>>> get_freq_code('D')
(6000, 1)
>>> get_freq_code(('D', 3))
(6000, 3)
"""
if isinstance(freqstr, DateOffset):
freqstr = (freqstr.rule_code, freqstr.n)
if isinstance(freqstr, tuple):
if (is_integer(freqstr[0]) and
is_integer(freqstr[1])):
# e.g., freqstr = (2000, 1)
return freqstr
else:
# e.g., freqstr = ('T', 5)
try:
code = _period_str_to_code(freqstr[0])
stride = freqstr[1]
except:
if is_integer(freqstr[1]):
raise
code = _period_str_to_code(freqstr[1])
stride = freqstr[0]
return code, stride
if is_integer(freqstr):
return (freqstr, 1)
base, stride = _base_and_stride(freqstr)
code = _period_str_to_code(base)
return code, stride
def test_quantile_interpolation_dtype(self):
# GH #10174
if _np_version_under1p9:
pytest.skip("Numpy version is under 1.9")
from numpy import percentile
# interpolation = linear (default case)
q = pd.Series([1, 3, 4]).quantile(0.5, interpolation='lower')
self.assertEqual(q, percentile(np.array([1, 3, 4]), 50))
self.assertTrue(is_integer(q))
q = pd.Series([1, 3, 4]).quantile(0.5, interpolation='higher')
self.assertEqual(q, percentile(np.array([1, 3, 4]), 50))
self.assertTrue(is_integer(q))
def _random_state(state=None):
"""
Helper function for processing random_state arguments.
Parameters
----------
state : int, np.random.RandomState, None.
If receives an int, passes to np.random.RandomState() as seed.
If receives an np.random.RandomState object, just returns object.
If receives `None`, returns np.random.
If receives anything else, raises an informative ValueError.
Default None.
Returns
-------
np.random.RandomState
"""
if is_integer(state):
return np.random.RandomState(state)
elif isinstance(state, np.random.RandomState):
return state
elif state is None:
return np.random
else:
raise ValueError("random_state must be an integer, a numpy "
"RandomState, or None")
def _maybe_convert_timedelta(self, other):
if isinstance(other, (timedelta, np.timedelta64, offsets.Tick)):
offset = frequencies.to_offset(self.freq.rule_code)
if isinstance(offset, offsets.Tick):
nanos = tslib._delta_to_nanoseconds(other)
offset_nanos = tslib._delta_to_nanoseconds(offset)
if nanos % offset_nanos == 0:
return nanos // offset_nanos
elif isinstance(other, offsets.DateOffset):
freqstr = other.rule_code
base = frequencies.get_base_alias(freqstr)
if base == self.freq.rule_code:
return other.n
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
elif isinstance(other, np.ndarray):
if is_integer_dtype(other):
return other
elif is_timedelta64_dtype(other):
offset = frequencies.to_offset(self.freq)
if isinstance(offset, offsets.Tick):
nanos = tslib._delta_to_nanoseconds(other)
offset_nanos = tslib._delta_to_nanoseconds(offset)
if (nanos % offset_nanos).all() == 0:
return nanos // offset_nanos
elif is_integer(other):
# integer is passed to .shift via
# _add_datetimelike_methods basically
# but ufunc may pass integer to _add_delta
return other
# raise when input doesn't have freq
msg = "Input has different freq from PeriodIndex(freq={0})"
raise IncompatibleFrequency(msg.format(self.freqstr))
def _maybe_cast_slice_bound(self, label, side, kind):
"""
If label is a string, cast it to timedelta according to resolution.
Parameters
----------
label : object
side : {'left', 'right'}
kind : {'ix', 'loc', 'getitem'}
Returns
-------
label : object
"""
assert kind in ['ix', 'loc', 'getitem', None]
if isinstance(label, compat.string_types):
parsed = _coerce_scalar_to_timedelta_type(label, box=True)
lbound = parsed.round(parsed.resolution)
if side == 'left':
return lbound
else:
return (lbound + to_offset(parsed.resolution) -
Timedelta(1, 'ns'))
elif is_integer(label) or is_float(label):
self._invalid_indexer('slice', label)
return label
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 delete(self, loc):
"""
Make a new DatetimeIndex with passed location(s) deleted.
Parameters
----------
loc: int, slice or array of ints
Indicate which sub-arrays to remove.
Returns
-------
new_index : TimedeltaIndex
"""
new_tds = np.delete(self.asi8, loc)
freq = 'infer'
if is_integer(loc):
if loc in (0, -len(self), -1, len(self) - 1):
freq = self.freq
else:
if is_list_like(loc):
loc = lib.maybe_indices_to_slice(
_ensure_int64(np.array(loc)), len(self))
if isinstance(loc, slice) and loc.step in (1, None):
if (loc.start in (0, None) or loc.stop in (len(self), None)):
freq = self.freq
return TimedeltaIndex(new_tds, name=self.name, freq=freq)
def __add__(self, other):
from pandas.core.index import Index
from pandas.tseries.tdi import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
if isinstance(other, TimedeltaIndex):
return self._add_delta(other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if hasattr(other, '_add_delta'):
return other._add_delta(self)
raise TypeError("cannot add TimedeltaIndex and {typ}"
.format(typ=type(other)))
elif isinstance(other, Index):
warnings.warn("using '+' to provide set union with "
"datetimelike Indexes is deprecated, "
"use .union()", FutureWarning, stacklevel=2)
return self.union(other)
elif isinstance(other, (DateOffset, timedelta, np.timedelta64,
tslib.Timedelta)):
return self._add_delta(other)
elif is_integer(other):
return self.shift(other)
elif isinstance(other, (tslib.Timestamp, datetime)):
return self._add_datelike(other)
else: # pragma: no cover
return NotImplemented
def _convert_scalar_indexer(self, key, kind=None):
"""
we don't allow integer or float indexing on datetime-like when using
loc
Parameters
----------
key : label of the slice bound
kind : {'ix', 'loc', 'getitem', 'iloc'} or None
"""
assert kind in ['ix', 'loc', 'getitem', 'iloc', None]
# we don't allow integer/float indexing for loc
# we don't allow float indexing for ix/getitem
if is_scalar(key):
is_int = is_integer(key)
is_flt = is_float(key)
if kind in ['loc'] and (is_int or is_flt):
self._invalid_indexer('index', key)
elif kind in ['ix', 'getitem'] and is_flt:
self._invalid_indexer('index', key)
return (super(DatetimeIndexOpsMixin, self)
._convert_scalar_indexer(key, kind=kind))
def __sub__(self, other):
from pandas.core.index import Index
from pandas.tseries.tdi import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
if isinstance(other, TimedeltaIndex):
return self._add_delta(-other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if not isinstance(other, TimedeltaIndex):
raise TypeError("cannot subtract TimedeltaIndex and {typ}"
.format(typ=type(other)))
return self._add_delta(-other)
elif isinstance(other, Index):
warnings.warn("using '-' to provide set differences with "
"datetimelike Indexes is deprecated, "
"use .difference()", FutureWarning, stacklevel=2)
return self.difference(other)
elif isinstance(other, (DateOffset, timedelta, np.timedelta64,
tslib.Timedelta)):
return self._add_delta(-other)
elif is_integer(other):
return self.shift(-other)
elif isinstance(other, (tslib.Timestamp, datetime)):
return self._sub_datelike(other)
elif isinstance(other, prlib.Period):
return self._sub_period(other)
else: # pragma: no cover
return NotImplemented
def get_loc(self, key, method=None, tolerance=None):
"""
Get integer location for requested label
Returns
-------
loc : int
"""
try:
return self._engine.get_loc(key)
except KeyError:
if is_integer(key):
raise
try:
asdt, parsed, reso = parse_time_string(key, self.freq)
key = asdt
except TypeError:
pass
try:
key = Period(key, freq=self.freq)
except ValueError:
# we cannot construct the Period
# as we have an invalid type
raise KeyError(key)
try:
ordinal = tslib.iNaT if key is tslib.NaT else key.ordinal
return Index.get_loc(self, ordinal, method, tolerance)
except KeyError:
raise KeyError(key)
def _maybe_cast_slice_bound(self, label, side, kind):
"""
If label is a string or a datetime, cast it to Period.ordinal according
to resolution.
Parameters
----------
label : object
side : {'left', 'right'}
kind : {'ix', 'loc', 'getitem'}
Returns
-------
bound : Period or object
Notes
-----
Value of `side` parameter should be validated in caller.
"""
assert kind in ['ix', 'loc', 'getitem']
if isinstance(label, datetime):
return Period(label, freq=self.freq)
elif isinstance(label, compat.string_types):
try:
_, parsed, reso = parse_time_string(label, self.freq)
bounds = self._parsed_string_to_bounds(reso, parsed)
return bounds[0 if side == 'left' else 1]
except Exception:
raise KeyError(label)
elif is_integer(label) or is_float(label):
self._invalid_indexer('slice', label)
return label
def _simple_new(cls, start, stop=None, step=None, name=None,
dtype=None, **kwargs):
result = object.__new__(cls)
# handle passed None, non-integers
if start is None and stop is None:
# empty
start, stop, step = 0, 0, 1
if start is None or not is_integer(start):
try:
return RangeIndex(start, stop, step, name=name, **kwargs)
except TypeError:
return Index(start, stop, step, name=name, **kwargs)
result._start = start
result._stop = stop or 0
result._step = step or 1
result.name = name
for k, v in compat.iteritems(kwargs):
setattr(result, k, v)
result._reset_identity()
return result
def __sub__(self, other):
from pandas.core.index import Index
from pandas.tseries.index import DatetimeIndex
from pandas.tseries.tdi import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
if isinstance(other, TimedeltaIndex):
return self._add_delta(-other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if not isinstance(other, TimedeltaIndex):
raise TypeError("cannot subtract TimedeltaIndex and {typ}"
.format(typ=type(other).__name__))
return self._add_delta(-other)
elif isinstance(other, DatetimeIndex):
return self._sub_datelike(other)
elif isinstance(other, Index):
raise TypeError("cannot subtract {typ1} and {typ2}"
.format(typ1=type(self).__name__,
typ2=type(other).__name__))
elif isinstance(other, (DateOffset, timedelta, np.timedelta64,
tslib.Timedelta)):
return self._add_delta(-other)
elif is_integer(other):
return self.shift(-other)
elif isinstance(other, (tslib.Timestamp, datetime)):
return self._sub_datelike(other)
elif isinstance(other, prlib.Period):
return self._sub_period(other)
else: # pragma: no cover
return NotImplemented
def qcut(x, q, labels=None, retbins=False, precision=3):
"""
Quantile-based discretization function. Discretize variable into
equal-sized buckets based on rank or based on sample quantiles. For example
1000 values for 10 quantiles would produce a Categorical object indicating
quantile membership for each data point.
Parameters
----------
x : ndarray or Series
q : integer or array of quantiles
Number of quantiles. 10 for deciles, 4 for quartiles, etc. Alternately
array of quantiles, e.g. [0, .25, .5, .75, 1.] for quartiles
labels : array or boolean, default None
Used as labels for the resulting bins. Must be of the same length as
the resulting bins. If False, return only integer indicators of the
bins.
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
precision : int
The precision at which to store and display the bins labels
Returns
-------
out : Categorical or Series or array of integers if labels is False
The return type (Categorical or Series) depends on the input: a Series
of type category if input is a Series else Categorical. Bins are
represented as categories when categorical data is returned.
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
Out of bounds values will be NA in the resulting Categorical object
Examples
--------
>>> pd.qcut(range(5), 4)
[[0, 1], [0, 1], (1, 2], (2, 3], (3, 4]]
Categories (4, object): [[0, 1] < (1, 2] < (2, 3] < (3, 4]]
>>> pd.qcut(range(5), 3, labels=["good","medium","bad"])
[good, good, medium, bad, bad]
Categories (3, object): [good < medium < bad]
>>> pd.qcut(range(5), 4, labels=False)
array([0, 0, 1, 2, 3], dtype=int64)
"""
x_is_series, series_index, name, x = _preprocess_for_cut(x)
x, dtype = _coerce_to_type(x)
if is_integer(q):
quantiles = np.linspace(0, 1, q + 1)
else:
quantiles = q
bins = algos.quantile(x, quantiles)
fac, bins = _bins_to_cuts(x, bins, labels=labels, precision=precision, include_lowest=True, dtype=dtype)
return _postprocess_for_cut(fac, bins, retbins, x_is_series, series_index, name)
def _get_string_slice(self, key, use_lhs=True, use_rhs=True):
freq = getattr(self, 'freqstr',
getattr(self, 'inferred_freq', None))
if is_integer(key) or is_float(key) or key is tslib.NaT:
self._invalid_indexer('slice', key)
loc = self._partial_td_slice(key, freq, use_lhs=use_lhs,
use_rhs=use_rhs)
return loc
def convert(value, unit, axis):
valid_types = (str, pydt.time)
if (isinstance(value, valid_types) or is_integer(value) or
is_float(value)):
return time2num(value)
if isinstance(value, Index):
return value.map(time2num)
if isinstance(value, (list, tuple, np.ndarray, Index)):
return [time2num(x) for x in value]
return value
def __floordiv__(self, other):
if is_integer(other):
if len(self) == 0 or self._start % other == 0 and self._step % other == 0:
start = self._start // other
step = self._step // other
stop = start + len(self) * step
return RangeIndex(start, stop, step, name=self.name, fastpath=True)
if len(self) == 1:
start = self._start // other
return RangeIndex(start, start + 1, 1, name=self.name, fastpath=True)
return self._int64index // other
def get_datevalue(date, freq):
if isinstance(date, Period):
return date.asfreq(freq).ordinal
elif isinstance(date, (compat.string_types, datetime,
pydt.date, pydt.time)):
return Period(date, freq).ordinal
elif (is_integer(date) or is_float(date) or
(isinstance(date, (np.ndarray, Index)) and (date.size == 1))):
return date
elif date is None:
return None
raise ValueError("Unrecognizable date '%s'" % date)
def take(self, indices, axis=0, allow_fill=True,
fill_value=None, **kwargs):
"""
Sparse-compatible version of ndarray.take
Returns
-------
taken : ndarray
"""
nv.validate_take(tuple(), kwargs)
if axis:
raise ValueError("axis must be 0, input was {0}".format(axis))
if is_integer(indices):
# return scalar
return self[indices]
indices = _ensure_platform_int(indices)
n = len(self)
if allow_fill and fill_value is not None:
# allow -1 to indicate self.fill_value,
# self.fill_value may not be NaN
if (indices < -1).any():
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
raise ValueError(msg)
elif (n <= indices).any():
msg = 'index is out of bounds for size {0}'
raise IndexError(msg.format(n))
else:
if ((indices < -n) | (n <= indices)).any():
msg = 'index is out of bounds for size {0}'
raise IndexError(msg.format(n))
indices = indices.astype(np.int32)
if not (allow_fill and fill_value is not None):
indices = indices.copy()
indices[indices < 0] += n
locs = self.sp_index.lookup_array(indices)
indexer = np.arange(len(locs), dtype=np.int32)
mask = locs != -1
if mask.any():
indexer = indexer[mask]
new_values = self.sp_values.take(locs[mask])
else:
indexer = np.empty(shape=(0, ), dtype=np.int32)
new_values = np.empty(shape=(0, ), dtype=self.sp_values.dtype)
sp_index = _make_index(len(indices), indexer, kind=self.sp_index)
return self._simple_new(new_values, sp_index, self.fill_value)
def validate_argsort_with_ascending(ascending, args, kwargs):
"""
If 'Categorical.argsort' is called via the 'numpy' library, the
first parameter in its signature is 'axis', which takes either
an integer or 'None', so check if the 'ascending' parameter has
either integer type or is None, since 'ascending' itself should
be a boolean
"""
if is_integer(ascending) or ascending is None:
args = (ascending,) + args
ascending = True
validate_argsort(args, kwargs, max_fname_arg_count=1)
return ascending
def __getitem__(self, key):
"""
This getitem defers to the underlying array, which by-definition can
only handle list-likes, slices, and integer scalars
"""
is_int = is_integer(key)
if is_scalar(key) and not is_int:
raise ValueError
getitem = self._data.__getitem__
if is_int:
val = getitem(key)
return self._box_func(val)
else:
if com.is_bool_indexer(key):
key = np.asarray(key)
if key.all():
key = slice(0, None, None)
else:
key = lib.maybe_booleans_to_slice(key.view(np.uint8))
attribs = self._get_attributes_dict()
is_period = isinstance(self, ABCPeriodIndex)
if is_period:
freq = self.freq
else:
freq = None
if isinstance(key, slice):
if self.freq is not None and key.step is not None:
freq = key.step * self.freq
else:
freq = self.freq
attribs['freq'] = freq
result = getitem(key)
if result.ndim > 1:
# To support MPL which performs slicing with 2 dim
# even though it only has 1 dim by definition
if is_period:
return self._simple_new(result, **attribs)
return result
return self._simple_new(result, **attribs)
def convert(values, units, axis):
if not hasattr(axis, 'freq'):
raise TypeError('Axis must have `freq` set to convert to Periods')
valid_types = (compat.string_types, datetime,
Period, pydt.date, pydt.time)
if (isinstance(values, valid_types) or is_integer(values) or
is_float(values)):
return get_datevalue(values, axis.freq)
if isinstance(values, PeriodIndex):
return values.asfreq(axis.freq)._values
if isinstance(values, Index):
return values.map(lambda x: get_datevalue(x, axis.freq))
if is_period_arraylike(values):
return PeriodIndex(values, freq=axis.freq)._values
if isinstance(values, (list, tuple, np.ndarray, Index)):
return [get_datevalue(x, axis.freq) for x in values]
return values
def __getitem__(self, key):
"""
"""
if is_integer(key):
return self._get_val_at(key)
elif isinstance(key, tuple):
data_slice = self.values[key]
else:
if isinstance(key, SparseArray):
key = np.asarray(key)
if hasattr(key, "__len__") and len(self) != len(key):
return self.take(key)
else:
data_slice = self.values[key]
return self._constructor(data_slice)
def __floordiv__(self, other):
if is_integer(other):
if (len(self) == 0
or self._start % other == 0 and self._step % other == 0):
start = self._start // other
step = self._step // other
stop = start + len(self) * step
return RangeIndex(start,
stop,
step,
name=self.name,
fastpath=True)
if len(self) == 1:
start = self._start // other
return RangeIndex(start,
start + 1,
1,
name=self.name,
fastpath=True)
return self._int64index // other
def _ensure_numeric(x):
if isinstance(x, np.ndarray):
if is_integer_dtype(x) or is_bool_dtype(x):
x = x.astype(np.float64)
elif is_object_dtype(x):
try:
x = x.astype(np.complex128)
except:
x = x.astype(np.float64)
else:
if not np.any(x.imag):
x = x.real
elif not (is_float(x) or is_integer(x) or is_complex(x)):
try:
x = float(x)
except Exception:
try:
x = complex(x)
except Exception:
raise TypeError('Could not convert %s to numeric' % str(x))
return x
def _ensure_numeric(x):
if isinstance(x, np.ndarray):
if is_integer_dtype(x) or is_bool_dtype(x):
x = x.astype(np.float64)
elif is_object_dtype(x):
try:
x = x.astype(np.complex128)
except:
x = x.astype(np.float64)
else:
if not np.any(x.imag):
x = x.real
elif not (is_float(x) or is_integer(x) or is_complex(x)):
try:
x = float(x)
except Exception:
try:
x = complex(x)
except Exception:
raise TypeError('Could not convert %s to numeric' % str(x))
return x
def __getitem__(self, key):
"""
"""
if is_integer(key):
return self._get_val_at(key)
elif isinstance(key, tuple):
data_slice = self.values[key]
else:
if isinstance(key, SparseArray):
if is_bool_dtype(key):
key = key.to_dense()
else:
key = np.asarray(key)
if hasattr(key, '__len__') and len(self) != len(key):
return self.take(key)
else:
data_slice = self.values[key]
return self._constructor(data_slice)
def __add__(self, other):
from pandas.core.index import Index
from pandas.tseries.tdi import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
if isinstance(other, TimedeltaIndex):
return self._add_delta(other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if hasattr(other, '_add_delta'):
return other._add_delta(self)
raise TypeError("cannot add TimedeltaIndex and {typ}".format(
typ=type(other)))
elif isinstance(other, Index):
raise TypeError("cannot add {typ1} and {typ2}".format(
typ1=type(self).__name__, typ2=type(other).__name__))
elif isinstance(
other, (DateOffset, timedelta, np.timedelta64, Timedelta)):
return self._add_delta(other)
elif is_integer(other):
return self.shift(other)
elif isinstance(other, (Timestamp, datetime)):
return self._add_datelike(other)
else: # pragma: no cover
return NotImplemented
def __add__(self, other):
from pandas.core.index import Index
from pandas.tseries.tdi import TimedeltaIndex
from pandas.tseries.offsets import DateOffset
if isinstance(other, TimedeltaIndex):
return self._add_delta(other)
elif isinstance(self, TimedeltaIndex) and isinstance(other, Index):
if hasattr(other, "_add_delta"):
return other._add_delta(self)
raise TypeError("cannot add TimedeltaIndex and {typ}".format(typ=type(other)))
elif isinstance(other, Index):
raise TypeError(
"cannot add {typ1} and {typ2}".format(typ1=type(self).__name__, typ2=type(other).__name__)
)
elif isinstance(other, (DateOffset, timedelta, np.timedelta64, tslib.Timedelta)):
return self._add_delta(other)
elif is_integer(other):
return self.shift(other)
elif isinstance(other, (tslib.Timestamp, datetime)):
return self._add_datelike(other)
else: # pragma: no cover
return NotImplemented
def __getitem__(self, key):
"""
This getitem defers to the underlying array, which by-definition can
only handle list-likes, slices, and integer scalars
"""
is_int = is_integer(key)
if is_scalar(key) and not is_int:
raise ValueError
getitem = self._data.__getitem__
if is_int:
val = getitem(key)
return self._box_func(val)
else:
if com.is_bool_indexer(key):
key = np.asarray(key)
if key.all():
key = slice(0, None, None)
else:
key = lib.maybe_booleans_to_slice(key.view(np.uint8))
attribs = self._get_attributes_dict()
freq = None
if isinstance(key, slice):
if self.freq is not None and key.step is not None:
freq = key.step * self.freq
else:
freq = self.freq
attribs['freq'] = freq
result = getitem(key)
if result.ndim > 1:
return result
return self._simple_new(result, **attribs)
def convert(values, unit, axis):
def try_parse(values):
try:
return _dt_to_float_ordinal(tools.to_datetime(values))
except Exception:
return values
if isinstance(values, (datetime, pydt.date)):
return _dt_to_float_ordinal(values)
elif isinstance(values, np.datetime64):
return _dt_to_float_ordinal(lib.Timestamp(values))
elif isinstance(values, pydt.time):
return dates.date2num(values)
elif (is_integer(values) or is_float(values)):
return values
elif isinstance(values, compat.string_types):
return try_parse(values)
elif isinstance(values, (list, tuple, np.ndarray, Index)):
if isinstance(values, Index):
values = values.values
if not isinstance(values, np.ndarray):
values = com._asarray_tuplesafe(values)
if is_integer_dtype(values) or is_float_dtype(values):
return values
try:
values = tools.to_datetime(values)
if isinstance(values, Index):
values = values.map(_dt_to_float_ordinal)
else:
values = [_dt_to_float_ordinal(x) for x in values]
except Exception:
values = _dt_to_float_ordinal(values)
return values
def __new__(cls, data=None, ordinal=None, freq=None, start=None, end=None,
periods=None, copy=False, name=None, tz=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 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 __new__(cls, data=None, ordinal=None, freq=None, start=None, end=None,
periods=None, copy=False, name=None, tz=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 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 convert(values, unit, axis):
def try_parse(values):
try:
return _dt_to_float_ordinal(tools.to_datetime(values))
except Exception:
return values
if isinstance(values, (datetime, pydt.date)):
return _dt_to_float_ordinal(values)
elif isinstance(values, np.datetime64):
return _dt_to_float_ordinal(lib.Timestamp(values))
elif isinstance(values, pydt.time):
return dates.date2num(values)
elif (is_integer(values) or is_float(values)):
return values
elif isinstance(values, compat.string_types):
return try_parse(values)
elif isinstance(values, (list, tuple, np.ndarray, Index)):
if isinstance(values, Index):
values = values.values
if not isinstance(values, np.ndarray):
values = com._asarray_tuplesafe(values)
if is_integer_dtype(values) or is_float_dtype(values):
return values
try:
values = tools.to_datetime(values)
if isinstance(values, Index):
values = _dt_to_float_ordinal(values)
else:
values = [_dt_to_float_ordinal(x) for x in values]
except Exception:
values = _dt_to_float_ordinal(values)
return values
def __new__(cls, data=None, unit=None,
freq=None, start=None, end=None, periods=None,
copy=False, name=None,
closed=None, verify_integrity=True, **kwargs):
if isinstance(data, TimedeltaIndex) and freq is None and name is None:
if copy:
return data.copy()
else:
return data._shallow_copy()
freq_infer = False
if not isinstance(freq, DateOffset):
# if a passed freq is None, don't infer automatically
if freq != 'infer':
freq = to_offset(freq)
else:
freq_infer = True
freq = None
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 data is None and freq is None:
raise ValueError("Must provide freq argument if no data is "
"supplied")
if data is None:
return cls._generate(start, end, periods, name, freq,
closed=closed)
if unit is not None:
data = to_timedelta(data, unit=unit, box=False)
if not isinstance(data, (np.ndarray, Index, ABCSeries)):
if is_scalar(data):
raise ValueError('TimedeltaIndex() must be called with a '
'collection of some kind, %s was passed'
% repr(data))
# convert if not already
if getattr(data, 'dtype', None) != _TD_DTYPE:
data = to_timedelta(data, unit=unit, box=False)
elif copy:
data = np.array(data, copy=True)
# check that we are matching freqs
if verify_integrity and len(data) > 0:
if freq is not None and not freq_infer:
index = cls._simple_new(data, name=name)
inferred = index.inferred_freq
if inferred != freq.freqstr:
on_freq = cls._generate(
index[0], None, len(index), name, freq)
if not np.array_equal(index.asi8, on_freq.asi8):
raise ValueError('Inferred frequency {0} from passed '
'timedeltas does not conform to '
'passed frequency {1}'
.format(inferred, freq.freqstr))
index.freq = freq
return index
if freq_infer:
index = cls._simple_new(data, name=name)
inferred = index.inferred_freq
if inferred:
index.freq = to_offset(inferred)
return index
return cls._simple_new(data, name=name, freq=freq)
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)
def test_is_integer(self):
self.assertTrue(is_integer(1))
self.assertTrue(is_integer(np.int64(1)))
self.assertFalse(is_integer(True))
self.assertFalse(is_integer(1.1))
self.assertFalse(is_integer(1 + 3j))
self.assertFalse(is_integer(np.bool(False)))
self.assertFalse(is_integer(np.bool_(False)))
self.assertFalse(is_integer(np.float64(1.1)))
self.assertFalse(is_integer(np.complex128(1 + 3j)))
self.assertFalse(is_integer(np.nan))
self.assertFalse(is_integer(None))
self.assertFalse(is_integer('x'))
self.assertFalse(is_integer(datetime(2011, 1, 1)))
self.assertFalse(is_integer(np.datetime64('2011-01-01')))
self.assertFalse(is_integer(Timestamp('2011-01-01')))
self.assertFalse(is_integer(Timestamp('2011-01-01',
tz='US/Eastern')))
self.assertFalse(is_integer(timedelta(1000)))
self.assertFalse(is_integer(Timedelta('1 days')))
# questionable
self.assertTrue(is_integer(np.timedelta64(1, 'D')))
def test_is_integer(self):
self.assertTrue(is_integer(1))
self.assertTrue(is_integer(np.int64(1)))
self.assertFalse(is_integer(True))
self.assertFalse(is_integer(1.1))
self.assertFalse(is_integer(1 + 3j))
self.assertFalse(is_integer(np.bool(False)))
self.assertFalse(is_integer(np.bool_(False)))
self.assertFalse(is_integer(np.float64(1.1)))
self.assertFalse(is_integer(np.complex128(1 + 3j)))
self.assertFalse(is_integer(np.nan))
self.assertFalse(is_integer(None))
self.assertFalse(is_integer('x'))
self.assertFalse(is_integer(datetime(2011, 1, 1)))
self.assertFalse(is_integer(np.datetime64('2011-01-01')))
self.assertFalse(is_integer(Timestamp('2011-01-01')))
self.assertFalse(is_integer(Timestamp('2011-01-01', tz='US/Eastern')))
self.assertFalse(is_integer(timedelta(1000)))
self.assertFalse(is_integer(Timedelta('1 days')))
# questionable
self.assertTrue(is_integer(np.timedelta64(1, 'D')))
def interpolate_1d(xvalues,
yvalues,
method='linear',
limit=None,
limit_direction='forward',
fill_value=None,
bounds_error=False,
order=None,
**kwargs):
"""
Logic for the 1-d interpolation. The result should be 1-d, inputs
xvalues and yvalues will each be 1-d arrays of the same length.
Bounds_error is currently hardcoded to False since non-scipy ones don't
take it as an argumnet.
"""
# Treat the original, non-scipy methods first.
invalid = isnull(yvalues)
valid = ~invalid
if not valid.any():
# have to call np.asarray(xvalues) since xvalues could be an Index
# which cant be mutated
result = np.empty_like(np.asarray(xvalues), dtype=np.float64)
result.fill(np.nan)
return result
if valid.all():
return yvalues
if method == 'time':
if not getattr(xvalues, 'is_all_dates', None):
# if not issubclass(xvalues.dtype.type, np.datetime64):
raise ValueError('time-weighted interpolation only works '
'on Series or DataFrames with a '
'DatetimeIndex')
method = 'values'
def _interp_limit(invalid, fw_limit, bw_limit):
"Get idx of values that won't be filled b/c they exceed the limits."
for x in np.where(invalid)[0]:
if invalid[max(0, x - fw_limit):x + bw_limit + 1].all():
yield x
valid_limit_directions = ['forward', 'backward', 'both']
limit_direction = limit_direction.lower()
if limit_direction not in valid_limit_directions:
raise ValueError('Invalid limit_direction: expecting one of %r, got '
'%r.' % (valid_limit_directions, limit_direction))
from pandas import Series
ys = Series(yvalues)
start_nans = set(range(ys.first_valid_index()))
end_nans = set(range(1 + ys.last_valid_index(), len(valid)))
# This is a list of the indexes in the series whose yvalue is currently
# NaN, but whose interpolated yvalue will be overwritten with NaN after
# computing the interpolation. For each index in this list, one of these
# conditions is true of the corresponding NaN in the yvalues:
#
# a) It is one of a chain of NaNs at the beginning of the series, and
# either limit is not specified or limit_direction is 'forward'.
# b) It is one of a chain of NaNs at the end of the series, and limit is
# specified and limit_direction is 'backward' or 'both'.
# c) Limit is nonzero and it is further than limit from the nearest non-NaN
# value (with respect to the limit_direction setting).
#
# The default behavior is to fill forward with no limit, ignoring NaNs at
# the beginning (see issues #9218 and #10420)
violate_limit = sorted(start_nans)
if limit is not None:
if not is_integer(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
if limit_direction == 'forward':
violate_limit = sorted(start_nans
| set(_interp_limit(invalid, limit, 0)))
if limit_direction == 'backward':
violate_limit = sorted(end_nans
| set(_interp_limit(invalid, 0, limit)))
if limit_direction == 'both':
violate_limit = sorted(_interp_limit(invalid, limit, limit))
xvalues = getattr(xvalues, 'values', xvalues)
yvalues = getattr(yvalues, 'values', yvalues)
result = yvalues.copy()
if method in ['linear', 'time', 'index', 'values']:
if method in ('values', 'index'):
inds = np.asarray(xvalues)
# hack for DatetimeIndex, #1646
if needs_i8_conversion(inds.dtype.type):
inds = inds.view(np.int64)
if inds.dtype == np.object_:
inds = lib.maybe_convert_objects(inds)
else:
inds = xvalues
result[invalid] = np.interp(inds[invalid], inds[valid], yvalues[valid])
result[violate_limit] = np.nan
return result
sp_methods = [
'nearest', 'zero', 'slinear', 'quadratic', 'cubic', 'barycentric',
'krogh', 'spline', 'polynomial', 'from_derivatives',
'piecewise_polynomial', 'pchip', 'akima'
]
if method in sp_methods:
inds = np.asarray(xvalues)
# hack for DatetimeIndex, #1646
if issubclass(inds.dtype.type, np.datetime64):
inds = inds.view(np.int64)
result[invalid] = _interpolate_scipy_wrapper(inds[valid],
yvalues[valid],
inds[invalid],
method=method,
fill_value=fill_value,
bounds_error=bounds_error,
order=order,
**kwargs)
result[violate_limit] = np.nan
return result
def to_datetime(arg,
errors='raise',
dayfirst=False,
yearfirst=False,
utc=None,
box=True,
format=None,
exact=True,
unit=None,
infer_datetime_format=False,
origin='unix'):
"""
Convert argument to datetime.
Parameters
----------
arg : integer, float, string, datetime, list, tuple, 1-d array, Series
.. versionadded: 0.18.1
or DataFrame/dict-like
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaT
- If 'ignore', then invalid parsing will return the input
dayfirst : boolean, default False
Specify a date parse order if `arg` is str or its list-likes.
If True, parses dates with the day first, eg 10/11/12 is parsed as
2012-11-10.
Warning: dayfirst=True is not strict, but will prefer to parse
with day first (this is a known bug, based on dateutil behavior).
yearfirst : boolean, default False
Specify a date parse order if `arg` is str or its list-likes.
- If True parses dates with the year first, eg 10/11/12 is parsed as
2010-11-12.
- If both dayfirst and yearfirst are True, yearfirst is preceded (same
as dateutil).
Warning: yearfirst=True is not strict, but will prefer to parse
with year first (this is a known bug, based on dateutil beahavior).
.. versionadded: 0.16.1
utc : boolean, default None
Return UTC DatetimeIndex if True (converting any tz-aware
datetime.datetime objects as well).
box : boolean, default True
- If True returns a DatetimeIndex
- If False returns ndarray of values.
format : string, default None
strftime to parse time, eg "%d/%m/%Y", note that "%f" will parse
all the way up to nanoseconds.
exact : boolean, True by default
- If True, require an exact format match.
- If False, allow the format to match anywhere in the target string.
unit : string, default 'ns'
unit of the arg (D,s,ms,us,ns) denote the unit, which is an
integer or float number. This will be based off the origin.
Example, with unit='ms' and origin='unix' (the default), this
would calculate the number of milliseconds to the unix epoch start.
infer_datetime_format : boolean, default False
If True and no `format` is given, attempt to infer the format of the
datetime strings, and if it can be inferred, switch to a faster
method of parsing them. In some cases this can increase the parsing
speed by ~5-10x.
origin : scalar, default is 'unix'
Define the reference date. The numeric values would be parsed as number
of units (defined by `unit`) since this reference date.
- If 'unix' (or POSIX) time; origin is set to 1970-01-01.
- If 'julian', unit must be 'D', and origin is set to beginning of
Julian Calendar. Julian day number 0 is assigned to the day starting
at noon on January 1, 4713 BC.
- If Timestamp convertible, origin is set to Timestamp identified by
origin.
.. versionadded: 0.20.0
Returns
-------
ret : datetime if parsing succeeded.
Return type depends on input:
- list-like: DatetimeIndex
- Series: Series of datetime64 dtype
- scalar: Timestamp
In case when it is not possible to return designated types (e.g. when
any element of input is before Timestamp.min or after Timestamp.max)
return will have datetime.datetime type (or correspoding array/Series).
Examples
--------
Assembling a datetime from multiple columns of a DataFrame. The keys can be
common abbreviations like ['year', 'month', 'day', 'minute', 'second',
'ms', 'us', 'ns']) or plurals of the same
>>> df = pd.DataFrame({'year': [2015, 2016],
'month': [2, 3],
'day': [4, 5]})
>>> pd.to_datetime(df)
0 2015-02-04
1 2016-03-05
dtype: datetime64[ns]
If a date does not meet the `timestamp limitations
<http://pandas.pydata.org/pandas-docs/stable/timeseries.html
#timeseries-timestamp-limits>`_, passing errors='ignore'
will return the original input instead of raising any exception.
Passing errors='coerce' will force an out-of-bounds date to NaT,
in addition to forcing non-dates (or non-parseable dates) to NaT.
>>> pd.to_datetime('13000101', format='%Y%m%d', errors='ignore')
datetime.datetime(1300, 1, 1, 0, 0)
>>> pd.to_datetime('13000101', format='%Y%m%d', errors='coerce')
NaT
Passing infer_datetime_format=True can often-times speedup a parsing
if its not an ISO8601 format exactly, but in a regular format.
>>> s = pd.Series(['3/11/2000', '3/12/2000', '3/13/2000']*1000)
>>> s.head()
0 3/11/2000
1 3/12/2000
2 3/13/2000
3 3/11/2000
4 3/12/2000
dtype: object
>>> %timeit pd.to_datetime(s,infer_datetime_format=True)
100 loops, best of 3: 10.4 ms per loop
>>> %timeit pd.to_datetime(s,infer_datetime_format=False)
1 loop, best of 3: 471 ms per loop
Using a non-unix epoch origin
>>> pd.to_datetime([1, 2, 3], unit='D',
origin=pd.Timestamp('1960-01-01'))
0 1960-01-02
1 1960-01-03
2 1960-01-04
"""
from pandas.tseries.index import DatetimeIndex
tz = 'utc' if utc else None
def _convert_listlike(arg, box, format, name=None, tz=tz):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz=tz, name=name)
if utc:
arg = arg.tz_convert(None).tz_localize('UTC')
return arg
elif is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, 'values', arg)
result = tslib.array_with_unit_to_datetime(arg,
unit,
errors=errors)
if box:
if errors == 'ignore':
from pandas import Index
return Index(result)
return DatetimeIndex(result, tz=tz, name=name)
return result
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = _ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = _format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError("cannot convert the input to "
"'%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except tslib.OutOfBoundsDatetime:
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
require_iso8601=require_iso8601)
if is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz=tz, name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
if arg is None:
return None
# handle origin
if origin == 'julian':
original = arg
j0 = tslib.Timestamp(0).to_julian_date()
if unit != 'D':
raise ValueError("unit must be 'D' for origin='julian'")
try:
arg = arg - j0
except:
raise ValueError("incompatible 'arg' type for given "
"'origin'='julian'")
# premptively check this for a nice range
j_max = tslib.Timestamp.max.to_julian_date() - j0
j_min = tslib.Timestamp.min.to_julian_date() - j0
if np.any(arg > j_max) or np.any(arg < j_min):
raise tslib.OutOfBoundsDatetime(
"{original} is Out of Bounds for "
"origin='julian'".format(original=original))
elif origin not in ['unix', 'julian']:
# arg must be a numeric
original = arg
if not ((is_scalar(arg) and (is_integer(arg) or is_float(arg)))
or is_numeric_dtype(np.asarray(arg))):
raise ValueError(
"'{arg}' is not compatible with origin='{origin}'; "
"it must be numeric with a unit specified ".format(
arg=arg, origin=origin))
# we are going to offset back to unix / epoch time
try:
offset = tslib.Timestamp(origin) - tslib.Timestamp(0)
except tslib.OutOfBoundsDatetime:
raise tslib.OutOfBoundsDatetime(
"origin {} is Out of Bounds".format(origin))
except ValueError:
raise ValueError("origin {} cannot be converted "
"to a Timestamp".format(origin))
# convert the offset to the unit of the arg
# this should be lossless in terms of precision
offset = offset // tslib.Timedelta(1, unit=unit)
# scalars & ndarray-like can handle the addition
if is_list_like(arg) and not isinstance(
arg, (ABCSeries, ABCIndexClass, np.ndarray)):
arg = np.asarray(arg)
arg = arg + offset
if isinstance(arg, tslib.Timestamp):
result = arg
elif isinstance(arg, ABCSeries):
from pandas import Series
values = _convert_listlike(arg._values, False, format)
result = Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, (ABCDataFrame, MutableMapping)):
result = _assemble_from_unit_mappings(arg, errors=errors)
elif isinstance(arg, ABCIndexClass):
result = _convert_listlike(arg, box, format, name=arg.name)
elif is_list_like(arg):
result = _convert_listlike(arg, box, format)
else:
result = _convert_listlike(np.array([arg]), box, format)[0]
return result
def qcut(x, q, labels=None, retbins=False, precision=3, duplicates='raise'):
"""
Quantile-based discretization function. Discretize variable into
equal-sized buckets based on rank or based on sample quantiles. For example
1000 values for 10 quantiles would produce a Categorical object indicating
quantile membership for each data point.
Parameters
----------
x : ndarray or Series
q : integer or array of quantiles
Number of quantiles. 10 for deciles, 4 for quartiles, etc. Alternately
array of quantiles, e.g. [0, .25, .5, .75, 1.] for quartiles
labels : array or boolean, default None
Used as labels for the resulting bins. Must be of the same length as
the resulting bins. If False, return only integer indicators of the
bins.
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
precision : int
The precision at which to store and display the bins labels
duplicates : {default 'raise', 'drop'}, optional
If bin edges are not unique, raise ValueError or drop non-uniques.
.. versionadded:: 0.20.0
Returns
-------
out : Categorical or Series or array of integers if labels is False
The return type (Categorical or Series) depends on the input: a Series
of type category if input is a Series else Categorical. Bins are
represented as categories when categorical data is returned.
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
Out of bounds values will be NA in the resulting Categorical object
Examples
--------
>>> pd.qcut(range(5), 4)
[[0, 1], [0, 1], (1, 2], (2, 3], (3, 4]]
Categories (4, object): [[0, 1] < (1, 2] < (2, 3] < (3, 4]]
>>> pd.qcut(range(5), 3, labels=["good","medium","bad"])
[good, good, medium, bad, bad]
Categories (3, object): [good < medium < bad]
>>> pd.qcut(range(5), 4, labels=False)
array([0, 0, 1, 2, 3], dtype=int64)
"""
x_is_series, series_index, name, x = _preprocess_for_cut(x)
x, dtype = _coerce_to_type(x)
if is_integer(q):
quantiles = np.linspace(0, 1, q + 1)
else:
quantiles = q
bins = algos.quantile(x, quantiles)
fac, bins = _bins_to_cuts(x, bins, labels=labels,
precision=precision, include_lowest=True,
dtype=dtype, duplicates=duplicates)
return _postprocess_for_cut(fac, bins, retbins, x_is_series,
series_index, name)
