def objects_to_td64ns(data, unit="ns", errors="raise"):
"""
Convert a object-dtyped or string-dtyped array into an
timedelta64[ns]-dtyped array.
Parameters
----------
data : ndarray or Index
unit : str, default "ns"
The timedelta unit to treat integers as multiples of.
errors : {"raise", "coerce", "ignore"}, default "raise"
How to handle elements that cannot be converted to timedelta64[ns].
See ``pandas.to_timedelta`` for details.
Returns
-------
numpy.ndarray : timedelta64[ns] array converted from data
Raises
------
ValueError : Data cannot be converted to timedelta64[ns].
Notes
-----
Unlike `pandas.to_timedelta`, if setting `errors=ignore` will not cause
errors to be ignored; they are caught and subsequently ignored at a
higher level.
"""
# coerce Index to np.ndarray, converting string-dtype if necessary
values = np.array(data, dtype=np.object_, copy=False)
result = array_to_timedelta64(values,
unit=unit, errors=errors)
return result.view('timedelta64[ns]')
def _convert_listlike(arg, unit='ns', box=True, errors='raise', name=None):
"""Convert a list of objects to a timedelta index object."""
if isinstance(arg, (list, tuple)) or not hasattr(arg, 'dtype'):
arg = np.array(list(arg), dtype='O')
# these are shortcut-able
if is_timedelta64_dtype(arg):
value = arg.astype('timedelta64[ns]')
elif is_integer_dtype(arg):
value = arg.astype('timedelta64[{unit}]'.format(unit=unit)).astype(
'timedelta64[ns]', copy=False)
else:
try:
value = array_to_timedelta64(ensure_object(arg),
unit=unit, errors=errors)
value = value.astype('timedelta64[ns]', copy=False)
except ValueError:
if errors == 'ignore':
return arg
else:
# This else-block accounts for the cases when errors='raise'
# and errors='coerce'. If errors == 'raise', these errors
# should be raised. If errors == 'coerce', we shouldn't
# expect any errors to be raised, since all parsing errors
# cause coercion to pd.NaT. However, if an error / bug is
# introduced that causes an Exception to be raised, we would
# like to surface it.
raise
if box:
from pandas import TimedeltaIndex
value = TimedeltaIndex(value, unit='ns', name=name)
return value
def __new__(cls, data=None, unit=None, freq=None, start=None, end=None,
periods=None, closed=None, dtype=None, copy=False,
name=None, verify_integrity=True):
if isinstance(data, TimedeltaIndex) and freq is None and name is None:
if copy:
return data.copy()
else:
return data._shallow_copy()
freq, freq_infer = dtl.maybe_infer_freq(freq)
if data is None:
# TODO: Remove this block and associated kwargs; GH#20535
result = cls._generate_range(start, end, periods, freq,
closed=closed)
result.name = name
return result
if unit is not None:
data = to_timedelta(data, unit=unit, box=False)
if is_scalar(data):
raise ValueError('TimedeltaIndex() must be called with a '
'collection of some kind, {data} was passed'
.format(data=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)
data = np.array(data, copy=False)
if data.dtype == np.object_:
data = array_to_timedelta64(data)
if data.dtype != _TD_DTYPE:
if is_timedelta64_dtype(data):
# non-nano unit
# TODO: watch out for overflows
data = data.astype(_TD_DTYPE)
else:
data = ensure_int64(data).view(_TD_DTYPE)
assert data.dtype == 'm8[ns]', data.dtype
subarr = cls._simple_new(data, name=name, freq=freq)
# check that we are matching freqs
if verify_integrity and len(subarr) > 0:
if freq is not None and not freq_infer:
cls._validate_frequency(subarr, freq)
if freq_infer:
inferred = subarr.inferred_freq
if inferred:
subarr.freq = to_offset(inferred)
return subarr
def _simple_new(cls, values, name=None, freq=None, **kwargs):
values = np.array(values, copy=False)
if values.dtype == np.object_:
values = array_to_timedelta64(values)
if values.dtype != _TD_DTYPE:
values = _ensure_int64(values).view(_TD_DTYPE)
result = object.__new__(cls)
result._data = values
result.name = name
result.freq = freq
result._reset_identity()
return result
def __new__(cls, values, freq=None):
freq, freq_infer = dtl.maybe_infer_freq(freq)
values = np.array(values, copy=False)
if values.dtype == np.object_:
values = array_to_timedelta64(values)
result = cls._simple_new(values, freq=freq)
if freq_infer:
result.freq = to_offset(result.inferred_freq)
return result
def _simple_new(cls, values, freq=None, **kwargs):
values = np.array(values, copy=False)
if values.dtype == np.object_:
values = array_to_timedelta64(values)
if values.dtype != _TD_DTYPE:
if is_timedelta64_dtype(values):
# non-nano unit
values = values.astype(_TD_DTYPE)
else:
values = _ensure_int64(values).view(_TD_DTYPE)
result = object.__new__(cls)
result._data = values
result._freq = freq
return result
def __new__(cls, values, freq=None):
freq, freq_infer = dtl.maybe_infer_freq(freq)
values = np.array(values, copy=False)
if values.dtype == np.object_:
values = array_to_timedelta64(values)
result = cls._simple_new(values, freq=freq)
if freq_infer:
inferred = result.inferred_freq
if inferred:
result.freq = to_offset(inferred)
return result
def _simple_new(cls, values, freq=None, **kwargs):
values = np.array(values, copy=False)
if values.dtype == np.object_:
values = array_to_timedelta64(values)
if values.dtype != _TD_DTYPE:
if is_timedelta64_dtype(values):
# non-nano unit
values = values.astype(_TD_DTYPE)
else:
values = ensure_int64(values).view(_TD_DTYPE)
result = object.__new__(cls)
result._data = values
result._freq = freq
return result
def astype_nansafe(
arr: np.ndarray, dtype: DtypeObj, copy: bool = True, skipna: bool = False
) -> ArrayLike:
"""
Cast the elements of an array to a given dtype a nan-safe manner.
Parameters
----------
arr : ndarray
dtype : np.dtype or ExtensionDtype
copy : bool, default True
If False, a view will be attempted but may fail, if
e.g. the item sizes don't align.
skipna: bool, default False
Whether or not we should skip NaN when casting as a string-type.
Raises
------
ValueError
The dtype was a datetime64/timedelta64 dtype, but it had no unit.
"""
# We get here with 0-dim from sparse
arr = np.atleast_1d(arr)
# dispatch on extension dtype if needed
if isinstance(dtype, ExtensionDtype):
return dtype.construct_array_type()._from_sequence(arr, dtype=dtype, copy=copy)
elif not isinstance(dtype, np.dtype): # pragma: no cover
raise ValueError("dtype must be np.dtype or ExtensionDtype")
if arr.dtype.kind in ["m", "M"] and (
issubclass(dtype.type, str) or dtype == _dtype_obj
):
from pandas.core.construction import ensure_wrapped_if_datetimelike
arr = ensure_wrapped_if_datetimelike(arr)
return arr.astype(dtype, copy=copy)
if issubclass(dtype.type, str):
shape = arr.shape
if arr.ndim > 1:
arr = arr.ravel()
return lib.ensure_string_array(
arr, skipna=skipna, convert_na_value=False
).reshape(shape)
elif is_datetime64_dtype(arr.dtype):
if dtype == np.int64:
if isna(arr).any():
raise ValueError("Cannot convert NaT values to integer")
return arr.view(dtype)
# allow frequency conversions
if dtype.kind == "M":
return arr.astype(dtype)
raise TypeError(f"cannot astype a datetimelike from [{arr.dtype}] to [{dtype}]")
elif is_timedelta64_dtype(arr.dtype):
if dtype == np.int64:
if isna(arr).any():
raise ValueError("Cannot convert NaT values to integer")
return arr.view(dtype)
elif dtype.kind == "m":
return astype_td64_unit_conversion(arr, dtype, copy=copy)
raise TypeError(f"cannot astype a timedelta from [{arr.dtype}] to [{dtype}]")
elif np.issubdtype(arr.dtype, np.floating) and is_integer_dtype(dtype):
return _astype_float_to_int_nansafe(arr, dtype, copy)
elif is_object_dtype(arr.dtype):
# if we have a datetime/timedelta array of objects
# then coerce to a proper dtype and recall astype_nansafe
if is_datetime64_dtype(dtype):
from pandas import to_datetime
return astype_nansafe(
to_datetime(arr.ravel()).values.reshape(arr.shape),
dtype,
copy=copy,
)
elif is_timedelta64_dtype(dtype):
# bc we know arr.dtype == object, this is equivalent to
# `np.asarray(to_timedelta(arr))`, but using a lower-level API that
# does not require a circular import.
return array_to_timedelta64(arr).view("m8[ns]").astype(dtype, copy=False)
if dtype.name in ("datetime64", "timedelta64"):
msg = (
f"The '{dtype.name}' dtype has no unit. Please pass in "
f"'{dtype.name}[ns]' instead."
)
raise ValueError(msg)
if copy or is_object_dtype(arr.dtype) or is_object_dtype(dtype):
# Explicit copy, or required since NumPy can't view from / to object.
return arr.astype(dtype, copy=True)
return arr.astype(dtype, copy=copy)
def test_array_to_timedelta64_string_with_unit_2d_raises(self):
# check the 'unit is not None and errors != "coerce"' path
# in array_to_timedelta64 raises correctly with 2D values
values = np.array([["1", 2], [3, "4"]], dtype=object)
with pytest.raises(ValueError, match="unit must not be specified"):
array_to_timedelta64(values, unit="s")
def __new__(cls,
data=None,
unit=None,
freq=None,
start=None,
end=None,
periods=None,
closed=None,
dtype=None,
copy=False,
name=None,
verify_integrity=True):
if isinstance(data, TimedeltaIndex) and freq is None and name is None:
if copy:
return data.copy()
else:
return data._shallow_copy()
freq, freq_infer = dtl.maybe_infer_freq(freq)
if data is None:
# TODO: Remove this block and associated kwargs; GH#20535
result = cls._generate_range(start,
end,
periods,
freq,
closed=closed)
result.name = name
return result
if unit is not None:
data = to_timedelta(data, unit=unit, box=False)
if is_scalar(data):
raise ValueError(
'TimedeltaIndex() must be called with a '
'collection of some kind, {data} was passed'.format(
data=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)
data = np.array(data, copy=False)
if data.dtype == np.object_:
data = array_to_timedelta64(data)
if data.dtype != _TD_DTYPE:
if is_timedelta64_dtype(data):
# non-nano unit
# TODO: watch out for overflows
data = data.astype(_TD_DTYPE)
else:
data = ensure_int64(data).view(_TD_DTYPE)
assert data.dtype == 'm8[ns]', data.dtype
subarr = cls._simple_new(data, name=name, freq=freq)
# check that we are matching freqs
if verify_integrity and len(subarr) > 0:
if freq is not None and not freq_infer:
cls._validate_frequency(subarr, freq)
if freq_infer:
inferred = subarr.inferred_freq
if inferred:
subarr.freq = to_offset(inferred)
return subarr
