def equals(self, other):
"""
Determines if two Index objects contain the same elements.
"""
if self.is_(other):
return True
if not isinstance(other, ABCIndexClass):
return False
elif not isinstance(other, type(self)):
try:
other = type(self)(other)
except Exception:
return False
if not is_dtype_equal(self.dtype, other.dtype):
# have different timezone
return False
elif is_period_dtype(self):
if not is_period_dtype(other):
return False
if self.freq != other.freq:
return False
return np.array_equal(self.asi8, other.asi8)
def test_is_period_dtype():
assert not com.is_period_dtype(object)
assert not com.is_period_dtype([1, 2, 3])
assert not com.is_period_dtype(pd.Period("2017-01-01"))
assert com.is_period_dtype(PeriodDtype(freq="D"))
assert com.is_period_dtype(pd.PeriodIndex([], freq="A"))
def sort_values(self, return_indexer=False, ascending=True):
"""
Return sorted copy of Index.
"""
if return_indexer:
_as = self.argsort()
if not ascending:
_as = _as[::-1]
sorted_index = self.take(_as)
return sorted_index, _as
else:
sorted_values = np.sort(self._ndarray_values)
attribs = self._get_attributes_dict()
freq = attribs['freq']
if freq is not None and not is_period_dtype(self):
if freq.n > 0 and not ascending:
freq = freq * -1
elif freq.n < 0 and ascending:
freq = freq * -1
attribs['freq'] = freq
if not ascending:
sorted_values = sorted_values[::-1]
return self._simple_new(sorted_values, **attribs)
def validate_dtype_freq(dtype, freq):
"""
If both a dtype and a freq are available, ensure they match. If only
dtype is available, extract the implied freq.
Parameters
----------
dtype : dtype
freq : DateOffset or None
Returns
-------
freq : DateOffset
Raises
------
ValueError : non-period dtype
IncompatibleFrequency : mismatch between dtype and freq
"""
if freq is not None:
freq = frequencies.to_offset(freq)
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:
raise IncompatibleFrequency('specified freq and dtype '
'are different')
return freq
def convert_pandas_type_to_json_field(arr, dtype=None):
dtype = dtype or arr.dtype
if arr.name is None:
name = 'values'
else:
name = arr.name
field = {'name': name,
'type': as_json_table_type(dtype)}
if is_categorical_dtype(arr):
if hasattr(arr, 'categories'):
cats = arr.categories
ordered = arr.ordered
else:
cats = arr.cat.categories
ordered = arr.cat.ordered
field['constraints'] = {"enum": list(cats)}
field['ordered'] = ordered
elif is_period_dtype(arr):
field['freq'] = arr.freqstr
elif is_datetime64tz_dtype(arr):
if hasattr(arr, 'dt'):
field['tz'] = arr.dt.tz.zone
else:
field['tz'] = arr.tz.zone
return field
def _addsub_offset_array(self, other, op):
"""
Add or subtract array-like of DateOffset objects
Parameters
----------
other : Index, np.ndarray
object-dtype containing pd.DateOffset objects
op : {operator.add, operator.sub}
Returns
-------
result : same class as self
"""
assert op in [operator.add, operator.sub]
if len(other) == 1:
return op(self, other[0])
warnings.warn("Adding/subtracting array of DateOffsets to "
"{cls} not vectorized"
.format(cls=type(self).__name__), PerformanceWarning)
# For EA self.astype('O') returns a numpy array, not an Index
left = lib.values_from_object(self.astype('O'))
res_values = op(left, np.array(other))
if not is_period_dtype(self):
return type(self)(res_values, freq='infer')
return self._from_sequence(res_values)
def _addsub_int_array(self, other, op):
"""
Add or subtract array-like of integers equivalent to applying
`_time_shift` pointwise.
Parameters
----------
other : Index, ExtensionArray, np.ndarray
integer-dtype
op : {operator.add, operator.sub}
Returns
-------
result : same class as self
"""
# _addsub_int_array is overriden by PeriodArray
assert not is_period_dtype(self)
assert op in [operator.add, operator.sub]
if self.freq is None:
# GH#19123
raise NullFrequencyError("Cannot shift with no freq")
elif isinstance(self.freq, Tick):
# easy case where we can convert to timedelta64 operation
td = Timedelta(self.freq)
return op(self, td * other)
# We should only get here with DatetimeIndex; dispatch
# to _addsub_offset_array
assert not is_timedelta64_dtype(self)
return op(self, np.array(other) * self.freq)
def _addsub_offset_array(self, other, op):
"""
Add or subtract array-like of DateOffset objects
Parameters
----------
other : Index, np.ndarray
object-dtype containing pd.DateOffset objects
op : {operator.add, operator.sub}
Returns
-------
result : same class as self
"""
assert op in [operator.add, operator.sub]
if len(other) == 1:
return op(self, other[0])
warnings.warn("Adding/subtracting array of DateOffsets to "
"{cls} not vectorized"
.format(cls=type(self).__name__), PerformanceWarning)
res_values = op(self.astype('O').values, np.array(other))
kwargs = {}
if not is_period_dtype(self):
kwargs['freq'] = 'infer'
return type(self)(res_values, **kwargs)
def _validate_frequency(cls, index, freq, **kwargs):
"""
Validate that a frequency is compatible with the values of a given
Datetime Array/Index or Timedelta Array/Index
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
The index on which to determine if the given frequency is valid
freq : DateOffset
The frequency to validate
"""
if is_period_dtype(cls):
# Frequency validation is not meaningful for Period Array/Index
return None
inferred = index.inferred_freq
if index.size == 0 or inferred == freq.freqstr:
return None
on_freq = cls._generate_range(start=index[0], end=None,
periods=len(index), freq=freq, **kwargs)
if not np.array_equal(index.asi8, on_freq.asi8):
raise ValueError('Inferred frequency {infer} from passed values '
'does not conform to passed frequency {passed}'
.format(infer=inferred, passed=freq.freqstr))
def __sub__(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._sub_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(-other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datetimelike_scalar(other)
elif lib.is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
maybe_integer_op_deprecated(self)
result = self._time_shift(-other)
elif isinstance(other, Period):
result = self._sub_period(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.sub)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
result = self._sub_datetime_arraylike(other)
elif is_period_dtype(other):
# PeriodIndex
result = self._sub_period_array(other)
elif is_integer_dtype(other):
maybe_integer_op_deprecated(self)
result = self._addsub_int_array(other, operator.sub)
elif isinstance(other, ABCIndexClass):
raise TypeError("cannot subtract {cls} and {typ}"
.format(cls=type(self).__name__,
typ=type(other).__name__))
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot subtract {dtype}-dtype from {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_extension_array_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if is_timedelta64_dtype(result) and isinstance(result, np.ndarray):
from pandas.core.arrays import TimedeltaArrayMixin
# TODO: infer freq?
return TimedeltaArrayMixin(result)
return result
def _sub_period_array(self, other):
"""
Subtract one PeriodIndex from another. This is only valid if they
have the same frequency.
Parameters
----------
other : PeriodIndex
Returns
-------
result : np.ndarray[object]
Array of DateOffset objects; nulls represented by NaT
"""
if not is_period_dtype(self):
raise TypeError("cannot subtract {dtype}-dtype to {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
if not len(self) == len(other):
raise ValueError("cannot subtract indices of unequal length")
if self.freq != other.freq:
msg = _DIFFERENT_FREQ_INDEX.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
new_values = checked_add_with_arr(self.asi8, -other.asi8,
arr_mask=self._isnan,
b_mask=other._isnan)
new_values = np.array([self.freq * x for x in new_values])
if self.hasnans or other.hasnans:
mask = (self._isnan) | (other._isnan)
new_values[mask] = NaT
return new_values
def astype(self, dtype, copy=True):
# We handle Period[T] -> Period[U]
# Our parent handles everything else.
dtype = pandas_dtype(dtype)
if is_period_dtype(dtype):
return self.asfreq(dtype.freq)
return super(PeriodArray, self).astype(dtype, copy=copy)
def __new__(cls, values, freq=None, **kwargs):
if is_period_dtype(values):
# PeriodArray, PeriodIndex
if freq is not None and values.freq != freq:
raise IncompatibleFrequency(freq, values.freq)
freq = values.freq
values = values.asi8
return cls._simple_new(values, freq, **kwargs)
def __add__(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._add_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._add_datetimelike_scalar(other)
elif lib.is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
maybe_integer_op_deprecated(self)
result = self._time_shift(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.add)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
return self._add_datetime_arraylike(other)
elif is_integer_dtype(other):
maybe_integer_op_deprecated(self)
result = self._addsub_int_array(other, operator.add)
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot add {dtype}-dtype to {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_period_dtype(other):
# if self is a TimedeltaArray and other is a PeriodArray with
# a timedelta-like (i.e. Tick) freq, this operation is valid.
# Defer to the PeriodArray implementation.
# In remaining cases, this will end up raising TypeError.
return NotImplemented
elif is_extension_array_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if is_timedelta64_dtype(result) and isinstance(result, np.ndarray):
from pandas.core.arrays import TimedeltaArrayMixin
# TODO: infer freq?
return TimedeltaArrayMixin(result)
return result
def _add_nat(self):
"""Add pd.NaT to self"""
if is_period_dtype(self):
raise TypeError('Cannot add {cls} and {typ}'
.format(cls=type(self).__name__,
typ=type(NaT).__name__))
# GH#19124 pd.NaT is treated like a timedelta for both timedelta
# and datetime dtypes
return self._nat_new(box=True)
def test_construction(self):
with tm.assertRaises(ValueError):
PeriodDtype('xx')
for s in ['period[D]', 'Period[D]', 'D']:
dt = PeriodDtype(s)
self.assertEqual(dt.freq, pd.tseries.offsets.Day())
self.assertTrue(is_period_dtype(dt))
for s in ['period[3D]', 'Period[3D]', '3D']:
dt = PeriodDtype(s)
self.assertEqual(dt.freq, pd.tseries.offsets.Day(3))
self.assertTrue(is_period_dtype(dt))
for s in ['period[26H]', 'Period[26H]', '26H',
'period[1D2H]', 'Period[1D2H]', '1D2H']:
dt = PeriodDtype(s)
self.assertEqual(dt.freq, pd.tseries.offsets.Hour(26))
self.assertTrue(is_period_dtype(dt))
def astype(self, dtype, copy=True, how='start'):
dtype = pandas_dtype(dtype)
if is_integer_dtype(dtype):
return self._int64index.copy() if copy else self._int64index
elif is_datetime64_any_dtype(dtype):
tz = getattr(dtype, 'tz', None)
return self.to_timestamp(how=how).tz_localize(tz)
elif is_period_dtype(dtype):
return self.asfreq(freq=dtype.freq)
return super(PeriodIndex, self).astype(dtype, copy=copy)
def test_construction(self):
with pytest.raises(ValueError):
PeriodDtype('xx')
for s in ['period[D]', 'Period[D]', 'D']:
dt = PeriodDtype(s)
assert dt.freq == pd.tseries.offsets.Day()
assert is_period_dtype(dt)
for s in ['period[3D]', 'Period[3D]', '3D']:
dt = PeriodDtype(s)
assert dt.freq == pd.tseries.offsets.Day(3)
assert is_period_dtype(dt)
for s in ['period[26H]', 'Period[26H]', '26H',
'period[1D2H]', 'Period[1D2H]', '1D2H']:
dt = PeriodDtype(s)
assert dt.freq == pd.tseries.offsets.Hour(26)
assert is_period_dtype(dt)
def repeat(self, repeats, *args, **kwargs):
"""
Analogous to ndarray.repeat.
"""
nv.validate_repeat(args, kwargs)
if is_period_dtype(self):
freq = self.freq
else:
freq = None
return self._shallow_copy(self.asi8.repeat(repeats),
freq=freq)
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 = lib.is_integer(key)
if lib.is_scalar(key) and not is_int:
raise IndexError("only integers, slices (`:`), ellipsis (`...`), "
"numpy.newaxis (`None`) and integer or boolean "
"arrays are valid indices")
getitem = self._data.__getitem__
if is_int:
val = getitem(key)
return self._box_func(val)
if com.is_bool_indexer(key):
key = np.asarray(key, dtype=bool)
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 = is_period_dtype(self)
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
elif key is Ellipsis:
# GH#21282 indexing with Ellipsis is similar to a full slice,
# should preserve `freq` attribute
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 __new__(cls, values, freq=None, **kwargs):
if is_period_dtype(values):
# PeriodArray, PeriodIndex
if freq is not None and values.freq != freq:
raise IncompatibleFrequency(freq, values.freq)
freq = values.freq
values = values.asi8
elif is_datetime64_dtype(values):
# TODO: what if it has tz?
values = dt64arr_to_periodarr(values, freq)
return cls._simple_new(values, freq=freq, **kwargs)
def __add__(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._add_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._add_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.add)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
return self._add_datelike(other)
elif is_integer_dtype(other):
result = self._addsub_int_array(other, operator.add)
elif is_float_dtype(other) or is_period_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot add {dtype}-dtype to {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_categorical_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
def _add_nat(self):
"""
Add pd.NaT to self
"""
if is_period_dtype(self):
raise TypeError('Cannot add {cls} and {typ}'
.format(cls=type(self).__name__,
typ=type(NaT).__name__))
# GH#19124 pd.NaT is treated like a timedelta for both timedelta
# and datetime dtypes
result = np.zeros(len(self), dtype=np.int64)
result.fill(iNaT)
return type(self)(result, dtype=self.dtype, freq=None)
def __init__(self, obj, orient, date_format, double_precision,
ensure_ascii, date_unit, index, default_handler=None):
"""
Adds a `schema` attribute with the Table Schema, resets
the index (can't do in caller, because the schema inference needs
to know what the index is, forces orient to records, and forces
date_format to 'iso'.
"""
super(JSONTableWriter, self).__init__(
obj, orient, date_format, double_precision, ensure_ascii,
date_unit, index, default_handler=default_handler)
if date_format != 'iso':
msg = ("Trying to write with `orient='table'` and "
"`date_format='{fmt}'`. Table Schema requires dates "
"to be formatted with `date_format='iso'`"
.format(fmt=date_format))
raise ValueError(msg)
self.schema = build_table_schema(obj, index=self.index)
# NotImplementd on a column MultiIndex
if obj.ndim == 2 and isinstance(obj.columns, MultiIndex):
raise NotImplementedError(
"orient='table' is not supported for MultiIndex")
# TODO: Do this timedelta properly in objToJSON.c See GH #15137
if ((obj.ndim == 1) and (obj.name in set(obj.index.names)) or
len(obj.columns & obj.index.names)):
msg = "Overlapping names between the index and columns"
raise ValueError(msg)
obj = obj.copy()
timedeltas = obj.select_dtypes(include=['timedelta']).columns
if len(timedeltas):
obj[timedeltas] = obj[timedeltas].applymap(
lambda x: x.isoformat())
# Convert PeriodIndex to datetimes before serialzing
if is_period_dtype(obj.index):
obj.index = obj.index.to_timestamp()
# exclude index from obj if index=False
if not self.index:
self.obj = obj.reset_index(drop=True)
else:
self.obj = obj.reset_index(drop=False)
self.date_format = 'iso'
self.orient = 'records'
self.index = index
def _concat_same_dtype(self, to_concat, name):
"""
Concatenate to_concat which has the same class
"""
attribs = self._get_attributes_dict()
attribs['name'] = name
if not is_period_dtype(self):
# reset freq
attribs['freq'] = None
if getattr(self, 'tz', None) is not None:
return _concat._concat_datetimetz(to_concat, name)
else:
new_data = np.concatenate([c.asi8 for c in to_concat])
return self._simple_new(new_data, **attribs)
def _concat_same_dtype(self, to_concat, name):
"""
Concatenate to_concat which has the same class.
"""
attribs = self._get_attributes_dict()
attribs['name'] = name
# do not pass tz to set because tzlocal cannot be hashed
if len({str(x.dtype) for x in to_concat}) != 1:
raise ValueError('to_concat must have the same tz')
if not is_period_dtype(self):
# reset freq
attribs['freq'] = None
new_data = type(self._values)._concat_same_type(to_concat).asi8
return self._simple_new(new_data, **attribs)
def astype(self, dtype, copy=True, how='start'):
dtype = pandas_dtype(dtype)
if is_object_dtype(dtype):
return self.asobject
elif is_integer_dtype(dtype):
if copy:
return self._int64index.copy()
else:
return self._int64index
elif is_datetime64_dtype(dtype):
return self.to_timestamp(how=how)
elif is_datetime64tz_dtype(dtype):
return self.to_timestamp(how=how).tz_localize(dtype.tz)
elif is_period_dtype(dtype):
return self.asfreq(freq=dtype.freq)
raise ValueError('Cannot cast PeriodIndex to dtype %s' % dtype)
def as_json_table_type(x):
"""
Convert a NumPy / pandas type to its corresponding json_table.
Parameters
----------
x : array or dtype
Returns
-------
t : str
the Table Schema data types
Notes
-----
This table shows the relationship between NumPy / pandas dtypes,
and Table Schema dtypes.
============== =================
Pandas type Table Schema type
============== =================
int64 integer
float64 number
bool boolean
datetime64[ns] datetime
timedelta64[ns] duration
object str
categorical any
=============== =================
"""
if is_integer_dtype(x):
return 'integer'
elif is_bool_dtype(x):
return 'boolean'
elif is_numeric_dtype(x):
return 'number'
elif (is_datetime64_dtype(x) or is_datetime64tz_dtype(x) or
is_period_dtype(x)):
return 'datetime'
elif is_timedelta64_dtype(x):
return 'duration'
elif is_categorical_dtype(x):
return 'any'
elif is_string_dtype(x):
return 'string'
else:
return 'any'
def take(self, indices, axis=0, allow_fill=True,
fill_value=None, **kwargs):
nv.validate_take(tuple(), kwargs)
indices = ensure_int64(indices)
maybe_slice = lib.maybe_indices_to_slice(indices, len(self))
if isinstance(maybe_slice, slice):
return self[maybe_slice]
taken = self._assert_take_fillable(self.asi8, indices,
allow_fill=allow_fill,
fill_value=fill_value,
na_value=iNaT)
# keep freq in PeriodArray/Index, reset otherwise
freq = self.freq if is_period_dtype(self) else None
return self._shallow_copy(taken, freq=freq)
def _simple_new(cls, values, freq=None, **kwargs):
"""
Values can be any type that can be coerced to Periods.
Ordinals in an ndarray are fastpath-ed to `_from_ordinals`
"""
if is_period_dtype(values):
freq = dtl.validate_dtype_freq(values.dtype, freq)
values = values.asi8
if not is_integer_dtype(values):
values = np.array(values, copy=False)
if len(values) > 0 and is_float_dtype(values):
raise TypeError("{cls} can't take floats"
.format(cls=cls.__name__))
return cls(values, freq=freq, **kwargs)
return cls._from_ordinals(values, freq=freq, **kwargs)
def __rsub__(self, other):
if is_datetime64_dtype(other) and is_timedelta64_dtype(self):
# ndarray[datetime64] cannot be subtracted from self, so
# we need to wrap in DatetimeArray/Index and flip the operation
if not isinstance(other, DatetimeLikeArrayMixin):
# Avoid down-casting DatetimeIndex
from pandas.core.arrays import DatetimeArrayMixin
other = DatetimeArrayMixin(other)
return other - self
elif (is_datetime64_any_dtype(self) and hasattr(other, 'dtype')
and not is_datetime64_any_dtype(other)):
# GH#19959 datetime - datetime is well-defined as timedelta,
# but any other type - datetime is not well-defined.
raise TypeError("cannot subtract {cls} from {typ}".format(
cls=type(self).__name__, typ=type(other).__name__))
elif is_period_dtype(self) and is_timedelta64_dtype(other):
# TODO: Can we simplify/generalize these cases at all?
raise TypeError("cannot subtract {cls} from {dtype}".format(
cls=type(self).__name__, dtype=other.dtype))
return -(self - other)
def _nat_new(self, box=True):
"""
Return Array/Index or ndarray filled with NaT which has the same
length as the caller.
Parameters
----------
box : boolean, default True
- If True returns a Array/Index as the same as caller.
- If False returns ndarray of np.int64.
"""
result = np.zeros(len(self), dtype=np.int64)
result.fill(iNaT)
if not box:
return result
attribs = self._get_attributes_dict()
if not is_period_dtype(self):
attribs['freq'] = None
return self._simple_new(result, **attribs)
def _get_delete_freq(self, loc: int):
"""
Find the `freq` for self.delete(loc).
"""
freq = None
if is_period_dtype(self.dtype):
freq = self.freq
elif self.freq is not None:
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(
np.asarray(loc, dtype=np.intp), 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 freq
def _concat_same_dtype(self, to_concat, name):
"""
Concatenate to_concat which has the same class.
"""
attribs = self._get_attributes_dict()
attribs["name"] = name
# do not pass tz to set because tzlocal cannot be hashed
if len({str(x.dtype) for x in to_concat}) != 1:
raise ValueError("to_concat must have the same tz")
new_data = type(self._values)._concat_same_type(to_concat).asi8
# GH 3232: If the concat result is evenly spaced, we can retain the
# original frequency
is_diff_evenly_spaced = len(unique_deltas(new_data)) == 1
if not is_period_dtype(self) and not is_diff_evenly_spaced:
# reset freq
attribs["freq"] = None
return self._simple_new(new_data, **attribs)
def delete(self, loc):
new_i8s = np.delete(self.asi8, loc)
freq = None
if is_period_dtype(self.dtype):
freq = self.freq
elif 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(
np.asarray(loc, dtype=np.intp), 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
arr = type(self._data)._simple_new(new_i8s, dtype=self.dtype, freq=freq)
return type(self)._simple_new(arr, name=self.name)
def take(self,
indices,
axis=0,
allow_fill=True,
fill_value=None,
**kwargs):
nv.validate_take(tuple(), kwargs)
indices = ensure_int64(indices)
maybe_slice = lib.maybe_indices_to_slice(indices, len(self))
if isinstance(maybe_slice, slice):
return self[maybe_slice]
taken = ExtensionIndex.take(self, indices, axis, allow_fill,
fill_value, **kwargs)
# keep freq in PeriodArray/Index, reset otherwise
freq = self.freq if is_period_dtype(self) else None
assert taken.freq == freq, (taken.freq, freq, taken)
return self._shallow_copy(taken, freq=freq)
def get_dtype_kinds(l):
"""
Parameters
----------
l : list of arrays
Returns
-------
a set of kinds that exist in this list of arrays
"""
typs = set()
for arr in l:
dtype = arr.dtype
if is_categorical_dtype(dtype):
typ = 'category'
elif is_sparse(arr):
typ = 'sparse'
elif isinstance(arr, ABCRangeIndex):
typ = 'range'
elif is_datetimetz(arr):
# if to_concat contains different tz,
# the result must be object dtype
typ = str(arr.dtype)
elif is_datetime64_dtype(dtype):
typ = 'datetime'
elif is_timedelta64_dtype(dtype):
typ = 'timedelta'
elif is_object_dtype(dtype):
typ = 'object'
elif is_bool_dtype(dtype):
typ = 'bool'
elif is_period_dtype(dtype):
typ = str(arr.dtype)
elif is_interval_dtype(dtype):
typ = str(arr.dtype)
else:
typ = dtype.kind
typs.add(typ)
return typs
def astype(self, dtype, copy=True, how='start'):
dtype = pandas_dtype(dtype)
if is_object_dtype(dtype):
return self._box_values_as_index()
elif is_integer_dtype(dtype):
if copy:
return self._int64index.copy()
else:
return self._int64index
elif is_datetime64_dtype(dtype):
return self.to_timestamp(how=how)
elif is_datetime64tz_dtype(dtype):
return self.to_timestamp(how=how).tz_localize(dtype.tz)
elif is_period_dtype(dtype):
return self.asfreq(freq=dtype.freq)
elif is_categorical_dtype(dtype):
return CategoricalIndex(self.values,
name=self.name,
dtype=dtype,
copy=copy)
raise TypeError('Cannot cast PeriodIndex to dtype %s' % dtype)
def test_basic(self):
assert is_period_dtype(self.dtype)
pidx = pd.period_range('2013-01-01 09:00', periods=5, freq='H')
assert is_period_dtype(pidx.dtype)
assert is_period_dtype(pidx)
assert is_period(pidx)
s = Series(pidx, name='A')
assert is_period_dtype(s.dtype)
assert is_period_dtype(s)
assert is_period(s)
assert not is_period_dtype(np.dtype('float64'))
assert not is_period_dtype(1.0)
assert not is_period(np.dtype('float64'))
assert not is_period(1.0)
def test_unstack(self, data, index, obj):
data = data[:len(index)]
if obj == "series":
ser = pd.Series(data, index=index)
else:
ser = pd.DataFrame({"A": data, "B": data}, index=index)
n = index.nlevels
levels = list(range(n))
# [0, 1, 2]
# [(0,), (1,), (2,), (0, 1), (0, 2), (1, 0), (1, 2), (2, 0), (2, 1)]
combinations = itertools.chain.from_iterable(
itertools.permutations(levels, i) for i in range(1, n))
for level in combinations:
result = ser.unstack(level=level)
assert all(
isinstance(result[col].array, type(data))
for col in result.columns)
if obj == "series":
# We should get the same result with to_frame+unstack+droplevel
df = ser.to_frame()
alt = df.unstack(level=level).droplevel(0, axis=1)
self.assert_frame_equal(result, alt)
expected = ser.astype(object).unstack(
level=level, fill_value=data.dtype.na_value)
if obj == "series":
# TODO: special cases belong in dtype-specific tests
if is_period_dtype(data.dtype):
assert expected.dtypes.apply(is_period_dtype).all()
expected = expected.astype(object)
if is_interval_dtype(data.dtype):
assert expected.dtypes.apply(is_interval_dtype).all()
expected = expected.astype(object)
result = result.astype(object)
self.assert_frame_equal(result, expected)
def _addsub_int_array(self, other, op):
"""
Add or subtract array-like of integers equivalent to applying
`shift` pointwise.
Parameters
----------
other : Index, ExtensionArray, np.ndarray
integer-dtype
op : {operator.add, operator.sub}
Returns
-------
result : same class as self
"""
assert op in [operator.add, operator.sub]
if is_period_dtype(self):
# easy case for PeriodIndex
if op is operator.sub:
other = -other
res_values = checked_add_with_arr(self.asi8,
other,
arr_mask=self._isnan)
res_values = res_values.view('i8')
res_values[self._isnan] = iNaT
return self._from_ordinals(res_values, freq=self.freq)
elif self.freq is None:
# GH#19123
raise NullFrequencyError("Cannot shift with no freq")
elif isinstance(self.freq, Tick):
# easy case where we can convert to timedelta64 operation
td = Timedelta(self.freq)
return op(self, td * other)
# We should only get here with DatetimeIndex; dispatch
# to _addsub_offset_array
assert not is_timedelta64_dtype(self)
return op(self, np.array(other) * self.freq)
def convert_pandas_type_to_json_field(arr):
dtype = arr.dtype
if arr.name is None:
name = "values"
else:
name = arr.name
field: dict[str, JSONSerializable] = {
"name": name,
"type": as_json_table_type(dtype),
}
if is_categorical_dtype(dtype):
cats = dtype.categories
ordered = dtype.ordered
field["constraints"] = {"enum": list(cats)}
field["ordered"] = ordered
elif is_period_dtype(dtype):
field["freq"] = dtype.freq.freqstr
elif is_datetime64tz_dtype(dtype):
field["tz"] = dtype.tz.zone
return field
def make_field(arr, dtype=None):
dtype = dtype or arr.dtype
field = {'name': arr.name or 'values',
'type': as_json_table_type(dtype)}
if is_categorical_dtype(arr):
if hasattr(arr, 'categories'):
cats = arr.categories
ordered = arr.ordered
else:
cats = arr.cat.categories
ordered = arr.cat.ordered
field['constraints'] = {"enum": list(cats)}
field['ordered'] = ordered
elif is_period_dtype(arr):
field['freq'] = arr.freqstr
elif is_datetime64tz_dtype(arr):
if hasattr(arr, 'dt'):
field['tz'] = arr.dt.tz.zone
else:
field['tz'] = arr.tz.zone
return field
def _ea_wrap_cython_operation(
self,
kind: str,
values,
how: str,
axis: int,
min_count: int = -1,
**kwargs) -> Tuple[np.ndarray, Optional[List[str]]]:
"""
If we have an ExtensionArray, unwrap, call _cython_operation, and
re-wrap if appropriate.
"""
# TODO: general case implementation overrideable by EAs.
orig_values = values
if is_datetime64tz_dtype(values.dtype) or is_period_dtype(
values.dtype):
# All of the functions implemented here are ordinal, so we can
# operate on the tz-naive equivalents
values = values.view("M8[ns]")
res_values, names = self._cython_operation(kind, values, how, axis,
min_count, **kwargs)
res_values = res_values.astype("i8", copy=False)
# FIXME: this is wrong for rank, but not tested.
result = type(orig_values)._simple_new(res_values,
dtype=orig_values.dtype)
return result, names
elif is_integer_dtype(values.dtype) or is_bool_dtype(values.dtype):
# IntegerArray or BooleanArray
values = ensure_int_or_float(values)
res_values, names = self._cython_operation(kind, values, how, axis,
min_count, **kwargs)
result = maybe_cast_result(result=res_values,
obj=orig_values,
how=how)
return result, names
raise NotImplementedError(values.dtype)
def _concat_same_dtype(self, to_concat, name):
"""
Concatenate to_concat which has the same class.
"""
attribs = self._get_attributes_dict()
attribs['name'] = name
# do not pass tz to set because tzlocal cannot be hashed
if len({str(x.dtype) for x in to_concat}) != 1:
raise ValueError('to_concat must have the same tz')
if not is_period_dtype(self):
# reset freq
attribs['freq'] = None
# TODO(DatetimeArray)
# - remove the .asi8 here
# - remove the _maybe_box_as_values
# - combine with the `else` block
new_data = self._concat_same_type(to_concat).asi8
else:
new_data = type(self._values)._concat_same_type(to_concat)
return self._simple_new(new_data, **attribs)
def _get_delete_freq(self, loc: int | slice | Sequence[int]):
"""
Find the `freq` for self.delete(loc).
"""
freq = None
if is_period_dtype(self.dtype):
freq = self.freq
elif self.freq is not None:
if is_integer(loc):
if loc in (0, -len(self), -1, len(self) - 1):
freq = self.freq
else:
if is_list_like(loc):
# error: Incompatible types in assignment (expression has
# type "Union[slice, ndarray]", variable has type
# "Union[int, slice, Sequence[int]]")
loc = lib.maybe_indices_to_slice( # type: ignore[assignment]
np.asarray(loc, dtype=np.intp), 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 freq
def _validate_frequency(cls, index, freq, **kwargs):
"""
Validate that a frequency is compatible with the values of a given
Datetime Array/Index or Timedelta Array/Index
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
The index on which to determine if the given frequency is valid
freq : DateOffset
The frequency to validate
"""
if is_period_dtype(cls):
# Frequency validation is not meaningful for Period Array/Index
return None
inferred = index.inferred_freq
if index.size == 0 or inferred == freq.freqstr:
return None
try:
on_freq = cls._generate_range(start=index[0], end=None,
periods=len(index), freq=freq,
**kwargs)
if not np.array_equal(index.asi8, on_freq.asi8):
raise ValueError
except ValueError as e:
if "non-fixed" in str(e):
# non-fixed frequencies are not meaningful for timedelta64;
# we retain that error message
raise e
# GH#11587 the main way this is reached is if the `np.array_equal`
# check above is False. This can also be reached if index[0]
# is `NaT`, in which case the call to `cls._generate_range` will
# raise a ValueError, which we re-raise with a more targeted
# message.
raise ValueError('Inferred frequency {infer} from passed values '
'does not conform to passed frequency {passed}'
.format(infer=inferred, passed=freq.freqstr))
def _sub_period_array(self, other):
"""
Subtract a Period Array/Index from self. This is only valid if self
is itself a Period Array/Index, raises otherwise. Both objects must
have the same frequency.
Parameters
----------
other : PeriodIndex or PeriodArray
Returns
-------
result : np.ndarray[object]
Array of DateOffset objects; nulls represented by NaT
"""
if not is_period_dtype(self):
raise TypeError("cannot subtract {dtype}-dtype from {cls}".format(
dtype=other.dtype, cls=type(self).__name__))
if len(self) != len(other):
raise ValueError("cannot subtract arrays/indices of "
"unequal length")
if self.freq != other.freq:
msg = DIFFERENT_FREQ.format(cls=type(self).__name__,
own_freq=self.freqstr,
other_freq=other.freqstr)
raise IncompatibleFrequency(msg)
new_values = checked_add_with_arr(self.asi8,
-other.asi8,
arr_mask=self._isnan,
b_mask=other._isnan)
new_values = np.array([self.freq.base * x for x in new_values])
if self._hasnans or other._hasnans:
mask = (self._isnan) | (other._isnan)
new_values[mask] = NaT
return new_values
def validate_dtype_freq(
dtype, freq: BaseOffsetT | timedelta | str | None) -> BaseOffsetT:
"""
If both a dtype and a freq are available, ensure they match. If only
dtype is available, extract the implied freq.
Parameters
----------
dtype : dtype
freq : DateOffset or None
Returns
-------
freq : DateOffset
Raises
------
ValueError : non-period dtype
IncompatibleFrequency : mismatch between dtype and freq
"""
if freq is not None:
# error: Incompatible types in assignment (expression has type
# "BaseOffset", variable has type "Union[BaseOffsetT, timedelta,
# str, None]")
freq = to_offset(freq) # type: ignore[assignment]
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:
raise IncompatibleFrequency(
"specified freq and dtype are different")
# error: Incompatible return value type (got "Union[BaseOffset, Any, None]",
# expected "BaseOffset")
return freq # type: ignore[return-value]
def test_basic(self):
assert is_period_dtype(self.dtype)
pidx = pd.period_range('2013-01-01 09:00', periods=5, freq='H')
assert is_period_dtype(pidx.dtype)
assert is_period_dtype(pidx)
assert is_period(pidx)
s = Series(pidx, name='A')
# dtypes
# series results in object dtype currently,
# is_period checks period_arraylike
assert not is_period_dtype(s.dtype)
assert not is_period_dtype(s)
assert is_period(s)
assert not is_period_dtype(np.dtype('float64'))
assert not is_period_dtype(1.0)
assert not is_period(np.dtype('float64'))
assert not is_period(1.0)
def astype(self, dtype, copy=True):
# TODO: Figure out something better here...
# We have DatetimeLikeArrayMixin ->
# super(...), which ends up being... DatetimeIndexOpsMixin?
# this is complicated.
# need a pandas_astype(arr, dtype).
from pandas import Categorical
dtype = pandas_dtype(dtype)
if is_object_dtype(dtype):
return np.asarray(self, dtype=object)
elif is_string_dtype(dtype) and not is_categorical_dtype(dtype):
return self._format_native_types()
elif is_integer_dtype(dtype):
values = self._data
if values.dtype != dtype:
# int32 vs. int64
values = values.astype(dtype)
elif copy:
values = values.copy()
return values
elif (is_datetime_or_timedelta_dtype(dtype) and
not is_dtype_equal(self.dtype, dtype)) or is_float_dtype(dtype):
# disallow conversion between datetime/timedelta,
# and conversions for any datetimelike to float
msg = 'Cannot cast {name} to dtype {dtype}'
raise TypeError(msg.format(name=type(self).__name__, dtype=dtype))
elif is_categorical_dtype(dtype):
return Categorical(self, dtype=dtype)
elif is_period_dtype(dtype):
return self.asfreq(dtype.freq)
else:
return np.asarray(self, dtype=dtype)
def as_json_table_type(x) -> str:
if is_integer_dtype(x):
return 'integer'
elif is_bool_dtype(x):
return 'boolean'
elif is_numeric_dtype(x):
return 'number'
elif (is_datetime64_dtype(x) or is_datetime64tz_dtype(x)
or is_period_dtype(x)):
# TODO: fix this
# return 'datetime'
return 'string'
elif is_timedelta64_dtype(x):
# TODO: fix this
# return 'duration'
return 'string'
elif is_categorical_dtype(x):
# TODO: fix this
# return 'any'
return 'string'
elif is_string_dtype(x):
return 'string'
else:
return 'any'
def _get_insert_freq(self, loc: int, item):
"""
Find the `freq` for self.insert(loc, item).
"""
value = self._data._validate_scalar(item)
item = self._data._box_func(value)
freq = None
if is_period_dtype(self.dtype):
freq = self.freq
elif self.freq is not None:
# freq can be preserved on edge cases
if self.size:
if item is NaT:
pass
elif (loc == 0 or loc == -len(self)) and item + self.freq == self[0]:
freq = self.freq
elif (loc == len(self)) and item - self.freq == self[-1]:
freq = self.freq
else:
# Adding a single item to an empty index may preserve freq
if self.freq.is_on_offset(item):
freq = self.freq
return freq
def test_basic(self):
assert is_period_dtype(self.dtype)
pidx = pd.period_range('2013-01-01 09:00', periods=5, freq='H')
assert is_period_dtype(pidx.dtype)
assert is_period_dtype(pidx)
with tm.assert_produces_warning(FutureWarning):
assert is_period(pidx)
s = Series(pidx, name='A')
assert is_period_dtype(s.dtype)
assert is_period_dtype(s)
with tm.assert_produces_warning(FutureWarning):
assert is_period(s)
assert not is_period_dtype(np.dtype('float64'))
assert not is_period_dtype(1.0)
with tm.assert_produces_warning(FutureWarning):
assert not is_period(np.dtype('float64'))
with tm.assert_produces_warning(FutureWarning):
assert not is_period(1.0)
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):
msg = 'periods must be a number, got {periods}'
raise TypeError(msg.format(periods=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 __sub__(self, other):
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._sub_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(-other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datetimelike_scalar(other)
elif lib.is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
if not is_period_dtype(self):
maybe_integer_op_deprecated(self)
result = self._time_shift(-other)
elif isinstance(other, Period):
result = self._sub_period(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.sub)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
result = self._sub_datetime_arraylike(other)
elif is_period_dtype(other):
# PeriodIndex
result = self._sub_period_array(other)
elif is_integer_dtype(other):
if not is_period_dtype(self):
maybe_integer_op_deprecated(self)
result = self._addsub_int_array(other, operator.sub)
elif isinstance(other, ABCIndexClass):
raise TypeError("cannot subtract {cls} and {typ}"
.format(cls=type(self).__name__,
typ=type(other).__name__))
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError("cannot subtract {dtype}-dtype from {cls}"
.format(dtype=other.dtype,
cls=type(self).__name__))
elif is_extension_array_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if is_timedelta64_dtype(result) and isinstance(result, np.ndarray):
from pandas.core.arrays import TimedeltaArrayMixin
# TODO: infer freq?
return TimedeltaArrayMixin(result)
return result
def __init__(
self,
obj,
orient: str | None,
date_format: str,
double_precision: int,
ensure_ascii: bool,
date_unit: str,
index: bool,
default_handler: Callable[[Any], JSONSerializable] | None = None,
indent: int = 0,
):
"""
Adds a `schema` attribute with the Table Schema, resets
the index (can't do in caller, because the schema inference needs
to know what the index is, forces orient to records, and forces
date_format to 'iso'.
"""
super().__init__(
obj,
orient,
date_format,
double_precision,
ensure_ascii,
date_unit,
index,
default_handler=default_handler,
indent=indent,
)
if date_format != "iso":
msg = (
"Trying to write with `orient='table'` and "
f"`date_format='{date_format}'`. Table Schema requires dates "
"to be formatted with `date_format='iso'`")
raise ValueError(msg)
self.schema = build_table_schema(obj, index=self.index)
# NotImplemented on a column MultiIndex
if obj.ndim == 2 and isinstance(obj.columns, MultiIndex):
raise NotImplementedError(
"orient='table' is not supported for MultiIndex columns")
# TODO: Do this timedelta properly in objToJSON.c See GH #15137
if ((obj.ndim == 1) and (obj.name in set(obj.index.names))
or len(obj.columns.intersection(obj.index.names))):
msg = "Overlapping names between the index and columns"
raise ValueError(msg)
obj = obj.copy()
timedeltas = obj.select_dtypes(include=["timedelta"]).columns
if len(timedeltas):
obj[timedeltas] = obj[timedeltas].applymap(lambda x: x.isoformat())
# Convert PeriodIndex to datetimes before serializing
if is_period_dtype(obj.index.dtype):
obj.index = obj.index.to_timestamp()
# exclude index from obj if index=False
if not self.index:
self.obj = obj.reset_index(drop=True)
else:
self.obj = obj.reset_index(drop=False)
self.date_format = "iso"
self.orient = "records"
self.index = index
def repeat(self, repeats, axis=None):
nv.validate_repeat(tuple(), dict(axis=axis))
freq = self.freq if is_period_dtype(self) else None
return self._shallow_copy(self.asi8.repeat(repeats), freq=freq)
def infer_freq(index, warn: bool = True) -> Optional[str]:
"""
Infer the most likely frequency given the input index. If the frequency is
uncertain, a warning will be printed.
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
If passed a Series will use the values of the series (NOT THE INDEX).
warn : bool, default True
Returns
-------
str or None
None if no discernible frequency.
Raises
------
TypeError
If the index is not datetime-like.
ValueError
If there are fewer than three values.
"""
import pandas as pd
if isinstance(index, ABCSeries):
values = index._values
if not (
is_datetime64_dtype(values)
or is_timedelta64_dtype(values)
or values.dtype == object
):
raise TypeError(
"cannot infer freq from a non-convertible dtype "
f"on a Series of {index.dtype}"
)
index = values
inferer: _FrequencyInferer
if not hasattr(index, "dtype"):
pass
elif is_period_dtype(index.dtype):
raise TypeError(
"PeriodIndex given. Check the `freq` attribute "
"instead of using infer_freq."
)
elif is_timedelta64_dtype(index.dtype):
# Allow TimedeltaIndex and TimedeltaArray
inferer = _TimedeltaFrequencyInferer(index, warn=warn)
return inferer.get_freq()
if isinstance(index, pd.Index) and not isinstance(index, pd.DatetimeIndex):
if isinstance(index, (pd.Int64Index, pd.Float64Index)):
raise TypeError(
f"cannot infer freq from a non-convertible index type {type(index)}"
)
index = index._values
if not isinstance(index, pd.DatetimeIndex):
index = pd.DatetimeIndex(index)
inferer = _FrequencyInferer(index, warn=warn)
return inferer.get_freq()
def __sub__(self, other):
from pandas import Index
other = lib.item_from_zerodim(other)
if isinstance(other, (ABCSeries, ABCDataFrame)):
return NotImplemented
# scalar others
elif other is NaT:
result = self._sub_nat()
elif isinstance(other, (Tick, timedelta, np.timedelta64)):
result = self._add_delta(-other)
elif isinstance(other, DateOffset):
# specifically _not_ a Tick
result = self._add_offset(-other)
elif isinstance(other, (datetime, np.datetime64)):
result = self._sub_datelike(other)
elif is_integer(other):
# This check must come after the check for np.timedelta64
# as is_integer returns True for these
result = self.shift(-other)
elif isinstance(other, Period):
result = self._sub_period(other)
# array-like others
elif is_timedelta64_dtype(other):
# TimedeltaIndex, ndarray[timedelta64]
result = self._add_delta(-other)
elif is_offsetlike(other):
# Array/Index of DateOffset objects
result = self._addsub_offset_array(other, operator.sub)
elif is_datetime64_dtype(other) or is_datetime64tz_dtype(other):
# DatetimeIndex, ndarray[datetime64]
result = self._sub_datelike(other)
elif is_period_dtype(other):
# PeriodIndex
result = self._sub_period_array(other)
elif is_integer_dtype(other):
result = self._addsub_int_array(other, operator.sub)
elif isinstance(other, Index):
raise TypeError("cannot subtract {cls} and {typ}".format(
cls=type(self).__name__, typ=type(other).__name__))
elif is_float_dtype(other):
# Explicitly catch invalid dtypes
raise TypeError(
"cannot subtract {dtype}-dtype from {cls}".format(
dtype=other.dtype, cls=type(self).__name__))
elif is_categorical_dtype(other):
# Categorical op will raise; defer explicitly
return NotImplemented
else: # pragma: no cover
return NotImplemented
if result is NotImplemented:
return NotImplemented
elif not isinstance(result, Index):
# Index.__new__ will choose appropriate subclass for dtype
result = Index(result)
res_name = ops.get_op_result_name(self, other)
result.name = res_name
return result
