def sequence_to_td64ns(data,
copy=False,
unit=None,
errors="raise") -> Tuple[np.ndarray, Optional[Tick]]:
"""
Parameters
----------
data : list-like
copy : bool, default False
unit : str, optional
The timedelta unit to treat integers as multiples of. For numeric
data this defaults to ``'ns'``.
Must be un-specified if the data contains a str and ``errors=="raise"``.
errors : {"raise", "coerce", "ignore"}, default "raise"
How to handle elements that cannot be converted to timedelta64[ns].
See ``pandas.to_timedelta`` for details.
Returns
-------
converted : numpy.ndarray
The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
The inferred frequency of the sequence.
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.
"""
inferred_freq = None
if unit is not None:
unit = parse_timedelta_unit(unit)
# Unwrap whatever we have into a np.ndarray
if not hasattr(data, "dtype"):
# e.g. list, tuple
if np.ndim(data) == 0:
# i.e. generator
data = list(data)
data = np.array(data, copy=False)
elif isinstance(data, ABCSeries):
data = data._values
elif isinstance(data, ABCTimedeltaIndex):
inferred_freq = data.freq
data = data._data._ndarray
elif isinstance(data, TimedeltaArray):
inferred_freq = data.freq
data = data._ndarray
elif isinstance(data, IntegerArray):
data = data.to_numpy("int64", na_value=tslibs.iNaT)
elif is_categorical_dtype(data.dtype):
data = data.categories.take(data.codes, fill_value=NaT)._values
copy = False
# Convert whatever we have into timedelta64[ns] dtype
if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
# no need to make a copy, need to convert if string-dtyped
data = objects_to_td64ns(data, unit=unit, errors=errors)
copy = False
elif is_integer_dtype(data.dtype):
# treat as multiples of the given unit
data, copy_made = ints_to_td64ns(data, unit=unit)
copy = copy and not copy_made
elif is_float_dtype(data.dtype):
# cast the unit, multiply base/frac separately
# to avoid precision issues from float -> int
mask = np.isnan(data)
m, p = precision_from_unit(unit or "ns")
base = data.astype(np.int64)
frac = data - base
if p:
frac = np.round(frac, p)
data = (base * m + (frac * m).astype(np.int64)).view("timedelta64[ns]")
data[mask] = iNaT
copy = False
elif is_timedelta64_dtype(data.dtype):
if data.dtype != TD64NS_DTYPE:
# non-nano unit
data = ensure_timedelta64ns(data)
copy = False
else:
# This includes datetime64-dtype, see GH#23539, GH#29794
raise TypeError(
f"dtype {data.dtype} cannot be converted to timedelta64[ns]")
data = np.array(data, copy=copy)
assert data.dtype == "m8[ns]", data
return data, inferred_freq
def sequence_to_td64ns(data, copy=False, unit="ns", errors="raise"):
"""
Parameters
----------
array : list-like
copy : bool, default False
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
-------
converted : numpy.ndarray
The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
The inferred frequency of the sequence.
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.
"""
inferred_freq = None
unit = parse_timedelta_unit(unit)
# Unwrap whatever we have into a np.ndarray
if not hasattr(data, "dtype"):
# e.g. list, tuple
if np.ndim(data) == 0:
# i.e. generator
data = list(data)
data = np.array(data, copy=False)
elif isinstance(data, ABCSeries):
data = data._values
elif isinstance(data, (ABCTimedeltaIndex, TimedeltaArray)):
inferred_freq = data.freq
data = data._data
# Convert whatever we have into timedelta64[ns] dtype
if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
# no need to make a copy, need to convert if string-dtyped
data = objects_to_td64ns(data, unit=unit, errors=errors)
copy = False
elif is_integer_dtype(data.dtype):
# treat as multiples of the given unit
data, copy_made = ints_to_td64ns(data, unit=unit)
copy = copy and not copy_made
elif is_float_dtype(data.dtype):
# cast the unit, multiply base/frace separately
# to avoid precision issues from float -> int
mask = np.isnan(data)
m, p = precision_from_unit(unit)
base = data.astype(np.int64)
frac = data - base
if p:
frac = np.round(frac, p)
data = (base * m + (frac * m).astype(np.int64)).view("timedelta64[ns]")
data[mask] = iNaT
copy = False
elif is_timedelta64_dtype(data.dtype):
if data.dtype != _TD_DTYPE:
# non-nano unit
# TODO: watch out for overflows
data = data.astype(_TD_DTYPE)
copy = False
else:
# This includes datetime64-dtype, see GH#23539, GH#29794
raise TypeError(
f"dtype {data.dtype} cannot be converted to timedelta64[ns]")
data = np.array(data, copy=copy)
assert data.dtype == "m8[ns]", data
return data, inferred_freq
def to_timedelta(arg, unit=None, errors="raise"):
"""
Convert argument to timedelta.
Timedeltas are absolute differences in times, expressed in difference
units (e.g. days, hours, minutes, seconds). This method converts
an argument from a recognized timedelta format / value into
a Timedelta type.
Parameters
----------
arg : str, timedelta, list-like or Series
The data to be converted to timedelta.
.. deprecated:: 1.2
Strings with units 'M', 'Y' and 'y' do not represent
unambiguous timedelta values and will be removed in a future version
unit : str, optional
Denotes the unit of the arg for numeric `arg`. Defaults to ``"ns"``.
Possible values:
* 'W'
* 'D' / 'days' / 'day'
* 'hours' / 'hour' / 'hr' / 'h'
* 'm' / 'minute' / 'min' / 'minutes' / 'T'
* 'S' / 'seconds' / 'sec' / 'second'
* 'ms' / 'milliseconds' / 'millisecond' / 'milli' / 'millis' / 'L'
* 'us' / 'microseconds' / 'microsecond' / 'micro' / 'micros' / 'U'
* 'ns' / 'nanoseconds' / 'nano' / 'nanos' / 'nanosecond' / 'N'
.. versionchanged:: 1.1.0
Must not be specified when `arg` context strings and
``errors="raise"``.
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.
Returns
-------
timedelta64 or numpy.array of timedelta64
Output type returned if parsing succeeded.
See Also
--------
DataFrame.astype : Cast argument to a specified dtype.
to_datetime : Convert argument to datetime.
convert_dtypes : Convert dtypes.
Notes
-----
If the precision is higher than nanoseconds, the precision of the duration is
truncated to nanoseconds for string inputs.
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015500')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015500', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['0 days 00:00:00', '0 days 00:00:01', '0 days 00:00:02',
'0 days 00:00:03', '0 days 00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
"""
if unit is not None:
unit = parse_timedelta_unit(unit)
if errors not in ("ignore", "raise", "coerce"):
raise ValueError(
"errors must be one of 'ignore', 'raise', or 'coerce'.")
if unit in {"Y", "y", "M"}:
raise ValueError(
"Units 'M', 'Y', and 'y' are no longer supported, as they do not "
"represent unambiguous timedelta values durations.")
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
values = _convert_listlike(arg._values, unit=unit, errors=errors)
return arg._constructor(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndex):
return _convert_listlike(arg, unit=unit, errors=errors, name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = lib.item_from_zerodim(arg)
elif is_list_like(arg) and getattr(arg, "ndim", 1) == 1:
return _convert_listlike(arg, unit=unit, errors=errors)
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, timedelta, list, tuple, 1-d array, or Series"
)
if isinstance(arg, str) and unit is not None:
raise ValueError(
"unit must not be specified if the input is/contains a str")
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg, unit=unit, errors=errors)
def sequence_to_td64ns(data, copy=False, unit="ns", errors="raise"):
"""
Parameters
----------
array : list-like
copy : bool, default False
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
-------
converted : numpy.ndarray
The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
The inferred frequency of the sequence.
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.
"""
inferred_freq = None
unit = parse_timedelta_unit(unit)
# Unwrap whatever we have into a np.ndarray
if not hasattr(data, 'dtype'):
# e.g. list, tuple
if np.ndim(data) == 0:
# i.e. generator
data = list(data)
data = np.array(data, copy=False)
elif isinstance(data, ABCSeries):
data = data._values
elif isinstance(data, (ABCTimedeltaIndex, TimedeltaArray)):
inferred_freq = data.freq
data = data._data
# Convert whatever we have into timedelta64[ns] dtype
if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
# no need to make a copy, need to convert if string-dtyped
data = objects_to_td64ns(data, unit=unit, errors=errors)
copy = False
elif is_integer_dtype(data.dtype):
# treat as multiples of the given unit
data, copy_made = ints_to_td64ns(data, unit=unit)
copy = copy and not copy_made
elif is_float_dtype(data.dtype):
# cast the unit, multiply base/frace separately
# to avoid precision issues from float -> int
mask = np.isnan(data)
m, p = precision_from_unit(unit)
base = data.astype(np.int64)
frac = data - base
if p:
frac = np.round(frac, p)
data = (base * m + (frac * m).astype(np.int64)).view('timedelta64[ns]')
data[mask] = iNaT
copy = False
elif is_timedelta64_dtype(data.dtype):
if data.dtype != _TD_DTYPE:
# non-nano unit
# TODO: watch out for overflows
data = data.astype(_TD_DTYPE)
copy = False
elif is_datetime64_dtype(data):
# GH#23539
warnings.warn("Passing datetime64-dtype data to TimedeltaIndex is "
"deprecated, will raise a TypeError in a future "
"version",
FutureWarning, stacklevel=4)
data = ensure_int64(data).view(_TD_DTYPE)
else:
raise TypeError("dtype {dtype} cannot be converted to timedelta64[ns]"
.format(dtype=data.dtype))
data = np.array(data, copy=copy)
if data.ndim != 1:
raise ValueError("Only 1-dimensional input arrays are supported.")
assert data.dtype == 'm8[ns]', data
return data, inferred_freq
def to_timedelta(arg, unit="ns", errors="raise"):
"""
Convert argument to timedelta.
Timedeltas are absolute differences in times, expressed in difference
units (e.g. days, hours, minutes, seconds). This method converts
an argument from a recognized timedelta format / value into
a Timedelta type.
Parameters
----------
arg : str, timedelta, list-like or Series
The data to be converted to timedelta.
unit : str, default 'ns'
Denotes the unit of the arg. Possible values:
('Y', 'M', 'W', 'D', 'days', 'day', 'hours', hour', 'hr',
'h', 'm', 'minute', 'min', 'minutes', 'T', 'S', 'seconds',
'sec', 'second', 'ms', 'milliseconds', 'millisecond',
'milli', 'millis', 'L', 'us', 'microseconds', 'microsecond',
'micro', 'micros', 'U', 'ns', 'nanoseconds', 'nano', 'nanos',
'nanosecond', 'N').
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.
Returns
-------
timedelta64 or numpy.array of timedelta64
Output type returned if parsing succeeded.
See Also
--------
DataFrame.astype : Cast argument to a specified dtype.
to_datetime : Convert argument to datetime.
convert_dtypes : Convert dtypes.
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['00:00:00', '00:00:01', '00:00:02',
'00:00:03', '00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
"""
unit = parse_timedelta_unit(unit)
if errors not in ("ignore", "raise", "coerce"):
raise ValueError(
"errors must be one of 'ignore', 'raise', or 'coerce'}")
if unit in {"Y", "y", "M"}:
raise ValueError(
"Units 'M' and 'Y' are no longer supported, as they do not "
"represent unambiguous timedelta values durations.")
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
values = _convert_listlike(arg._values, unit=unit, errors=errors)
return arg._constructor(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndexClass):
return _convert_listlike(arg, unit=unit, errors=errors, name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = arg.item()
elif is_list_like(arg) and getattr(arg, "ndim", 1) == 1:
return _convert_listlike(arg, unit=unit, errors=errors)
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, timedelta, list, tuple, 1-d array, or Series"
)
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg, unit=unit, errors=errors)
def sequence_to_td64ns(data, copy=False, unit="ns", errors="raise"):
"""
Parameters
----------
array : list-like
copy : bool, default False
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
-------
converted : numpy.ndarray
The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
The inferred frequency of the sequence.
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.
"""
inferred_freq = None
unit = parse_timedelta_unit(unit)
# Unwrap whatever we have into a np.ndarray
if not hasattr(data, 'dtype'):
# e.g. list, tuple
if np.ndim(data) == 0:
# i.e. generator
data = list(data)
data = np.array(data, copy=False)
elif isinstance(data, ABCSeries):
data = data._values
elif isinstance(data, (ABCTimedeltaIndex, TimedeltaArray)):
inferred_freq = data.freq
data = data._data
# Convert whatever we have into timedelta64[ns] dtype
if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
# no need to make a copy, need to convert if string-dtyped
data = objects_to_td64ns(data, unit=unit, errors=errors)
copy = False
elif is_integer_dtype(data.dtype):
# treat as multiples of the given unit
data, copy_made = ints_to_td64ns(data, unit=unit)
copy = copy and not copy_made
elif is_float_dtype(data.dtype):
# treat as multiples of the given unit. If after converting to nanos,
# there are fractional components left, these are truncated
# (i.e. NOT rounded)
mask = np.isnan(data)
coeff = np.timedelta64(1, unit) / np.timedelta64(1, 'ns')
data = (coeff * data).astype(np.int64).view('timedelta64[ns]')
data[mask] = iNaT
copy = False
elif is_timedelta64_dtype(data.dtype):
if data.dtype != _TD_DTYPE:
# non-nano unit
# TODO: watch out for overflows
data = data.astype(_TD_DTYPE)
copy = False
elif is_datetime64_dtype(data):
# GH#23539
warnings.warn(
"Passing datetime64-dtype data to TimedeltaIndex is "
"deprecated, will raise a TypeError in a future "
"version",
FutureWarning,
stacklevel=4)
data = ensure_int64(data).view(_TD_DTYPE)
else:
raise TypeError(
"dtype {dtype} cannot be converted to timedelta64[ns]".format(
dtype=data.dtype))
data = np.array(data, copy=copy)
assert data.dtype == 'm8[ns]', data
return data, inferred_freq
def to_timedelta(arg, unit="ns", box=True, errors="raise"):
"""
Convert argument to timedelta.
Timedeltas are absolute differences in times, expressed in difference
units (e.g. days, hours, minutes, seconds). This method converts
an argument from a recognized timedelta format / value into
a Timedelta type.
Parameters
----------
arg : str, timedelta, list-like or Series
The data to be converted to timedelta.
unit : str, default 'ns'
Denotes the unit of the arg. Possible values:
('Y', 'M', 'W', 'D', 'days', 'day', 'hours', hour', 'hr',
'h', 'm', 'minute', 'min', 'minutes', 'T', 'S', 'seconds',
'sec', 'second', 'ms', 'milliseconds', 'millisecond',
'milli', 'millis', 'L', 'us', 'microseconds', 'microsecond',
'micro', 'micros', 'U', 'ns', 'nanoseconds', 'nano', 'nanos',
'nanosecond', 'N').
box : bool, default True
- If True returns a Timedelta/TimedeltaIndex of the results.
- If False returns a numpy.timedelta64 or numpy.darray of
values of dtype timedelta64[ns].
.. deprecated:: 0.25.0
Use :meth:`Series.to_numpy` or :meth:`Timedelta.to_timedelta64`
instead to get an ndarray of values or numpy.timedelta64,
respectively.
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.
Returns
-------
timedelta64 or numpy.array of timedelta64
Output type returned if parsing succeeded.
See Also
--------
DataFrame.astype : Cast argument to a specified dtype.
to_datetime : Convert argument to datetime.
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['00:00:00', '00:00:01', '00:00:02',
'00:00:03', '00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
Returning an ndarray by using the 'box' keyword argument:
>>> pd.to_timedelta(np.arange(5), box=False)
array([0, 1, 2, 3, 4], dtype='timedelta64[ns]')
"""
unit = parse_timedelta_unit(unit)
if errors not in ("ignore", "raise", "coerce"):
raise ValueError(
"errors must be one of 'ignore', 'raise', or 'coerce'}")
if unit in {"Y", "y", "M"}:
warnings.warn(
"M and Y units are deprecated and will be removed in a future version.",
FutureWarning,
stacklevel=2,
)
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
values = _convert_listlike(arg._values,
unit=unit,
box=False,
errors=errors)
return arg._constructor(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndexClass):
return _convert_listlike(arg,
unit=unit,
box=box,
errors=errors,
name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = arg.item()
elif is_list_like(arg) and getattr(arg, "ndim", 1) == 1:
return _convert_listlike(arg, unit=unit, box=box, errors=errors)
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, timedelta, list, tuple, 1-d array, or Series"
)
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg,
unit=unit,
box=box,
errors=errors)
def to_timedelta(arg, unit='ns', box=True, errors='raise'):
"""
Convert argument to timedelta.
Timedeltas are absolute differences in times, expressed in difference
units (e.g. days, hours, minutes, seconds). This method converts
an argument from a recognized timedelta format / value into
a Timedelta type.
Parameters
----------
arg : str, timedelta, list-like or Series
The data to be converted to timedelta.
unit : str, default 'ns'
Denotes the unit of the arg. Possible values:
('Y', 'M', 'W', 'D', 'days', 'day', 'hours', hour', 'hr',
'h', 'm', 'minute', 'min', 'minutes', 'T', 'S', 'seconds',
'sec', 'second', 'ms', 'milliseconds', 'millisecond',
'milli', 'millis', 'L', 'us', 'microseconds', 'microsecond',
'micro', 'micros', 'U', 'ns', 'nanoseconds', 'nano', 'nanos',
'nanosecond', 'N').
box : bool, default True
- If True returns a Timedelta/TimedeltaIndex of the results.
- If False returns a numpy.timedelta64 or numpy.darray of
values of dtype timedelta64[ns].
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.
Returns
-------
timedelta64 or numpy.array of timedelta64
Output type returned if parsing succeeded.
See Also
--------
DataFrame.astype : Cast argument to a specified dtype.
to_datetime : Convert argument to datetime.
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['00:00:00', '00:00:01', '00:00:02',
'00:00:03', '00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
Returning an ndarray by using the 'box' keyword argument:
>>> pd.to_timedelta(np.arange(5), box=False)
array([0, 1, 2, 3, 4], dtype='timedelta64[ns]')
"""
unit = parse_timedelta_unit(unit)
if errors not in ('ignore', 'raise', 'coerce'):
raise ValueError("errors must be one of 'ignore', "
"'raise', or 'coerce'}")
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
from pandas import Series
values = _convert_listlike(arg._values, unit=unit,
box=False, errors=errors)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndexClass):
return _convert_listlike(arg, unit=unit, box=box,
errors=errors, name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = arg.item()
elif is_list_like(arg) and getattr(arg, 'ndim', 1) == 1:
return _convert_listlike(arg, unit=unit, box=box, errors=errors)
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, timedelta, list, tuple, '
'1-d array, or Series')
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg, unit=unit,
box=box, errors=errors)
def to_timedelta(arg, unit='ns', box=True, errors='raise'):
"""
Convert argument to timedelta
Parameters
----------
arg : string, timedelta, list, tuple, 1-d array, or Series
unit : string, {'Y', 'M', 'W', 'D', 'days', 'day',
'hours', hour', 'hr', 'h', 'm', 'minute', 'min', 'minutes',
'T', 'S', 'seconds', 'sec', 'second', 'ms',
'milliseconds', 'millisecond', 'milli', 'millis', 'L',
'us', 'microseconds', 'microsecond', 'micro', 'micros',
'U', 'ns', 'nanoseconds', 'nano', 'nanos', 'nanosecond'
'N'}, optional
Denote the unit of the input, if input is an integer. Default 'ns'.
box : boolean, default True
- If True returns a Timedelta/TimedeltaIndex of the results
- if False returns a np.timedelta64 or ndarray of values of dtype
timedelta64[ns]
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
Returns
-------
ret : timedelta64/arrays of timedelta64 if parsing succeeded
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['00:00:00', '00:00:01', '00:00:02',
'00:00:03', '00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
See also
--------
pandas.DataFrame.astype : Cast argument to a specified dtype.
pandas.to_datetime : Convert argument to datetime.
"""
unit = parse_timedelta_unit(unit)
if errors not in ('ignore', 'raise', 'coerce'):
raise ValueError("errors must be one of 'ignore', "
"'raise', or 'coerce'}")
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
from pandas import Series
values = _convert_listlike(arg._values, unit=unit,
box=False, errors=errors)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndexClass):
return _convert_listlike(arg, unit=unit, box=box,
errors=errors, name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = arg.item()
elif is_list_like(arg) and getattr(arg, 'ndim', 1) == 1:
return _convert_listlike(arg, unit=unit, box=box, errors=errors)
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, timedelta, list, tuple, '
'1-d array, or Series')
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg, unit=unit,
box=box, errors=errors)
def to_timedelta(arg, unit='ns', box=True, errors='raise'):
"""
Convert argument to timedelta
Parameters
----------
arg : string, timedelta, list, tuple, 1-d array, or Series
unit : str, optional
Denote the unit of the input, if input is an integer. Default 'ns'.
Possible values:
{'Y', 'M', 'W', 'D', 'days', 'day', 'hours', hour', 'hr', 'h',
'm', 'minute', 'min', 'minutes', 'T', 'S', 'seconds', 'sec', 'second',
'ms', 'milliseconds', 'millisecond', 'milli', 'millis', 'L',
'us', 'microseconds', 'microsecond', 'micro', 'micros', 'U',
'ns', 'nanoseconds', 'nano', 'nanos', 'nanosecond', 'N'}
box : boolean, default True
- If True returns a Timedelta/TimedeltaIndex of the results
- if False returns a np.timedelta64 or ndarray of values of dtype
timedelta64[ns]
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
Returns
-------
ret : timedelta64/arrays of timedelta64 if parsing succeeded
Examples
--------
Parsing a single string to a Timedelta:
>>> pd.to_timedelta('1 days 06:05:01.00003')
Timedelta('1 days 06:05:01.000030')
>>> pd.to_timedelta('15.5us')
Timedelta('0 days 00:00:00.000015')
Parsing a list or array of strings:
>>> pd.to_timedelta(['1 days 06:05:01.00003', '15.5us', 'nan'])
TimedeltaIndex(['1 days 06:05:01.000030', '0 days 00:00:00.000015', NaT],
dtype='timedelta64[ns]', freq=None)
Converting numbers by specifying the `unit` keyword argument:
>>> pd.to_timedelta(np.arange(5), unit='s')
TimedeltaIndex(['00:00:00', '00:00:01', '00:00:02',
'00:00:03', '00:00:04'],
dtype='timedelta64[ns]', freq=None)
>>> pd.to_timedelta(np.arange(5), unit='d')
TimedeltaIndex(['0 days', '1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq=None)
See Also
--------
pandas.DataFrame.astype : Cast argument to a specified dtype.
pandas.to_datetime : Convert argument to datetime.
"""
unit = parse_timedelta_unit(unit)
if errors not in ('ignore', 'raise', 'coerce'):
raise ValueError("errors must be one of 'ignore', "
"'raise', or 'coerce'}")
if arg is None:
return arg
elif isinstance(arg, ABCSeries):
from pandas import Series
values = _convert_listlike(arg._values,
unit=unit,
box=False,
errors=errors)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, ABCIndexClass):
return _convert_listlike(arg,
unit=unit,
box=box,
errors=errors,
name=arg.name)
elif isinstance(arg, np.ndarray) and arg.ndim == 0:
# extract array scalar and process below
arg = arg.item()
elif is_list_like(arg) and getattr(arg, 'ndim', 1) == 1:
return _convert_listlike(arg, unit=unit, box=box, errors=errors)
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, timedelta, list, tuple, '
'1-d array, or Series')
# ...so it must be a scalar value. Return scalar.
return _coerce_scalar_to_timedelta_type(arg,
unit=unit,
box=box,
errors=errors)
def sequence_to_td64ns(
data, copy: bool = False, unit=None, errors="raise"
) -> tuple[np.ndarray, Tick | None]:
"""
Parameters
----------
data : list-like
copy : bool, default False
unit : str, optional
The timedelta unit to treat integers as multiples of. For numeric
data this defaults to ``'ns'``.
Must be un-specified if the data contains a str and ``errors=="raise"``.
errors : {"raise", "coerce", "ignore"}, default "raise"
How to handle elements that cannot be converted to timedelta64[ns].
See ``pandas.to_timedelta`` for details.
Returns
-------
converted : numpy.ndarray
The sequence converted to a numpy array with dtype ``timedelta64[ns]``.
inferred_freq : Tick or None
The inferred frequency of the sequence.
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.
"""
assert unit not in ["Y", "y", "M"] # caller is responsible for checking
inferred_freq = None
if unit is not None:
unit = parse_timedelta_unit(unit)
data, copy = dtl.ensure_arraylike_for_datetimelike(
data, copy, cls_name="TimedeltaArray"
)
if isinstance(data, TimedeltaArray):
inferred_freq = data.freq
# Convert whatever we have into timedelta64[ns] dtype
if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
# no need to make a copy, need to convert if string-dtyped
data = _objects_to_td64ns(data, unit=unit, errors=errors)
copy = False
elif is_integer_dtype(data.dtype):
# treat as multiples of the given unit
data, copy_made = ints_to_td64ns(data, unit=unit)
copy = copy and not copy_made
elif is_float_dtype(data.dtype):
# cast the unit, multiply base/frac separately
# to avoid precision issues from float -> int
mask = np.isnan(data)
# The next few lines are effectively a vectorized 'cast_from_unit'
m, p = precision_from_unit(unit or "ns")
base = data.astype(np.int64)
frac = data - base
if p:
frac = np.round(frac, p)
data = (base * m + (frac * m).astype(np.int64)).view("timedelta64[ns]")
data[mask] = iNaT
copy = False
elif is_timedelta64_dtype(data.dtype):
if data.dtype != TD64NS_DTYPE:
# non-nano unit
data = astype_overflowsafe(data, dtype=TD64NS_DTYPE)
copy = False
else:
# This includes datetime64-dtype, see GH#23539, GH#29794
raise TypeError(f"dtype {data.dtype} cannot be converted to timedelta64[ns]")
data = np.array(data, copy=copy)
assert data.dtype == "m8[ns]", data
return data, inferred_freq