def test_array_of_dt64_nat_raises(self):
# GH#39462
nat = np.datetime64("NaT", "ns")
arr = np.array([nat], dtype=object)
# TODO: should be TypeError?
msg = "Invalid type for timedelta scalar"
with pytest.raises(ValueError, match=msg):
TimedeltaIndex(arr)
with pytest.raises(ValueError, match=msg):
TimedeltaArray._from_sequence(arr)
with pytest.raises(ValueError, match=msg):
sequence_to_td64ns(arr)
def __new__(cls, data=None, unit=None, freq=None, start=None, end=None,
periods=None, closed=None, dtype=_TD_DTYPE, copy=False,
name=None, verify_integrity=None):
if verify_integrity is not None:
warnings.warn("The 'verify_integrity' argument is deprecated, "
"will be removed in a future version.",
FutureWarning, stacklevel=2)
else:
verify_integrity = True
if data is None:
freq, freq_infer = dtl.maybe_infer_freq(freq)
warnings.warn("Creating a TimedeltaIndex by passing range "
"endpoints is deprecated. Use "
"`pandas.timedelta_range` instead.",
FutureWarning, stacklevel=2)
result = TimedeltaArray._generate_range(start, end, periods, freq,
closed=closed)
return cls._simple_new(result._data, freq=freq, name=name)
if is_scalar(data):
raise TypeError('{cls}() must be called with a '
'collection of some kind, {data} was passed'
.format(cls=cls.__name__, data=repr(data)))
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 isinstance(data, TimedeltaArray):
if copy:
data = data.copy()
return cls._simple_new(data, name=name, freq=freq)
if (isinstance(data, TimedeltaIndex) and
freq is None and name is None):
if copy:
return data.copy()
else:
return data._shallow_copy()
# - Cases checked above all return/raise before reaching here - #
tdarr = TimedeltaArray._from_sequence(data, freq=freq, unit=unit,
dtype=dtype, copy=copy)
return cls._simple_new(tdarr._data, freq=tdarr.freq, name=name)
def __new__(cls, data=None, unit=None, freq=None, start=None, end=None,
periods=None, closed=None, dtype=_TD_DTYPE, copy=False,
name=None, verify_integrity=None):
if verify_integrity is not None:
warnings.warn("The 'verify_integrity' argument is deprecated, "
"will be removed in a future version.",
FutureWarning, stacklevel=2)
else:
verify_integrity = True
if data is None:
freq, freq_infer = dtl.maybe_infer_freq(freq)
warnings.warn("Creating a TimedeltaIndex by passing range "
"endpoints is deprecated. Use "
"`pandas.timedelta_range` instead.",
FutureWarning, stacklevel=2)
result = TimedeltaArray._generate_range(start, end, periods, freq,
closed=closed)
return cls._simple_new(result._data, freq=freq, name=name)
if is_scalar(data):
raise TypeError('{cls}() must be called with a '
'collection of some kind, {data} was passed'
.format(cls=cls.__name__, data=repr(data)))
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 isinstance(data, TimedeltaArray):
if copy:
data = data.copy()
return cls._simple_new(data, name=name, freq=freq)
if (isinstance(data, TimedeltaIndex) and
freq is None and name is None):
if copy:
return data.copy()
else:
return data._shallow_copy()
# - Cases checked above all return/raise before reaching here - #
tdarr = TimedeltaArray._from_sequence(data, freq=freq, unit=unit,
dtype=dtype, copy=copy)
return cls._simple_new(tdarr._data, freq=tdarr.freq, name=name)
def _simple_new(cls, values, name=None, freq=None, dtype=_TD_DTYPE):
# `dtype` is passed by _shallow_copy in corner cases, should always
# be timedelta64[ns] if present
if not isinstance(values, TimedeltaArray):
values = TimedeltaArray._simple_new(values, dtype=dtype, freq=freq)
assert isinstance(values, TimedeltaArray), type(values)
assert dtype == _TD_DTYPE, dtype
assert values.dtype == 'm8[ns]', values.dtype
freq = to_offset(freq)
tdarr = TimedeltaArray._simple_new(values, freq=freq)
result = object.__new__(cls)
result._data = tdarr
result.name = name
# For groupby perf. See note in indexes/base about _index_data
result._index_data = tdarr._data
result._reset_identity()
return result
def test_infer_from_tdi_mismatch(self):
# GH#23539
# fast-path for invalidating a frequency if the passed data already
# has one and it does not match the `freq` input
tdi = timedelta_range("1 second", periods=100, freq="1s")
msg = ("Inferred frequency .* from passed values does "
"not conform to passed frequency")
with pytest.raises(ValueError, match=msg):
TimedeltaIndex(tdi, freq="D")
with pytest.raises(ValueError, match=msg):
# GH#23789
TimedeltaArray(tdi, freq="D")
with pytest.raises(ValueError, match=msg):
TimedeltaIndex(tdi._data, freq="D")
with pytest.raises(ValueError, match=msg):
TimedeltaArray(tdi._data, freq="D")
def _simple_new(cls, values, name=None, freq=None, dtype=_TD_DTYPE):
# `dtype` is passed by _shallow_copy in corner cases, should always
# be timedelta64[ns] if present
if not isinstance(values, TimedeltaArray):
values = TimedeltaArray._simple_new(values, dtype=dtype,
freq=freq)
else:
if freq is None:
freq = values.freq
assert isinstance(values, TimedeltaArray), type(values)
assert dtype == _TD_DTYPE, dtype
assert values.dtype == 'm8[ns]', values.dtype
tdarr = TimedeltaArray._simple_new(values._data, freq=freq)
result = object.__new__(cls)
result._data = tdarr
result.name = name
# For groupby perf. See note in indexes/base about _index_data
result._index_data = tdarr._data
result._reset_identity()
return result
def test_explicit_none_freq(self):
# Explicitly passing freq=None is respected
tdi = timedelta_range(1, periods=5)
assert tdi.freq is not None
result = TimedeltaIndex(tdi, freq=None)
assert result.freq is None
result = TimedeltaIndex(tdi._data, freq=None)
assert result.freq is None
tda = TimedeltaArray(tdi, freq=None)
assert tda.freq is None
def __new__(
cls,
data=None,
unit=None,
freq=lib.no_default,
closed=None,
dtype=TD64NS_DTYPE,
copy=False,
name=None,
):
name = maybe_extract_name(name, data, cls)
if is_scalar(data):
raise TypeError(
f"{cls.__name__}() must be called with a "
f"collection of some kind, {repr(data)} was passed")
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 isinstance(data, TimedeltaArray) and freq is lib.no_default:
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
if isinstance(
data,
TimedeltaIndex) and freq is lib.no_default and name is None:
if copy:
return data.copy()
else:
return data._shallow_copy()
# - Cases checked above all return/raise before reaching here - #
tdarr = TimedeltaArray._from_sequence_not_strict(data,
freq=freq,
unit=unit,
dtype=dtype,
copy=copy)
return cls._simple_new(tdarr, name=name)
def __new__(
cls,
data=None,
unit=None,
freq=None,
closed=None,
dtype=_TD_DTYPE,
copy=False,
name=None,
):
if is_scalar(data):
raise TypeError(
"{cls}() must be called with a "
"collection of some kind, {data} was passed".format(
cls=cls.__name__, data=repr(data)
)
)
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 isinstance(data, TimedeltaArray):
if copy:
data = data.copy()
return cls._simple_new(data, name=name, freq=freq)
if isinstance(data, TimedeltaIndex) and freq is None and name is None:
if copy:
return data.copy()
else:
return data._shallow_copy()
# - Cases checked above all return/raise before reaching here - #
tdarr = TimedeltaArray._from_sequence(
data, freq=freq, unit=unit, dtype=dtype, copy=copy
)
return cls._simple_new(tdarr._data, freq=tdarr.freq, name=name)
def __new__(
cls,
data=None,
unit=None,
freq=lib.no_default,
closed=None,
dtype=TD64NS_DTYPE,
copy=False,
name=None,
):
name = maybe_extract_name(name, data, cls)
if is_scalar(data):
raise cls._scalar_data_error(data)
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.")
# FIXME: need to check for dtype/data match
if isinstance(data, TimedeltaArray) and freq is lib.no_default:
if copy:
data = data.copy()
return cls._simple_new(data, name=name)
if isinstance(
data,
TimedeltaIndex) and freq is lib.no_default and name is None:
if copy:
return data.copy()
else:
return data._view()
# - Cases checked above all return/raise before reaching here - #
tdarr = TimedeltaArray._from_sequence_not_strict(data,
freq=freq,
unit=unit,
dtype=dtype,
copy=copy)
return cls._simple_new(tdarr, name=name)
def timedelta_range(start=None,
end=None,
periods=None,
freq=None,
name=None,
closed=None) -> TimedeltaIndex:
"""
Return a fixed frequency TimedeltaIndex, with day as the default
frequency.
Parameters
----------
start : str or timedelta-like, default None
Left bound for generating timedeltas.
end : str or timedelta-like, default None
Right bound for generating timedeltas.
periods : int, default None
Number of periods to generate.
freq : str or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'.
name : str, default None
Name of the resulting TimedeltaIndex.
closed : str, default None
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None).
Returns
-------
rng : TimedeltaIndex
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``TimedeltaIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end`` (closed on both sides).
To learn more about the frequency strings, please see `this link
<https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`__.
Examples
--------
>>> pd.timedelta_range(start='1 day', periods=4)
TimedeltaIndex(['1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``closed`` parameter specifies which endpoint is included. The default
behavior is to include both endpoints.
>>> pd.timedelta_range(start='1 day', periods=4, closed='right')
TimedeltaIndex(['2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``freq`` parameter specifies the frequency of the TimedeltaIndex.
Only fixed frequencies can be passed, non-fixed frequencies such as
'M' (month end) will raise.
>>> pd.timedelta_range(start='1 day', end='2 days', freq='6H')
TimedeltaIndex(['1 days 00:00:00', '1 days 06:00:00', '1 days 12:00:00',
'1 days 18:00:00', '2 days 00:00:00'],
dtype='timedelta64[ns]', freq='6H')
Specify ``start``, ``end``, and ``periods``; the frequency is generated
automatically (linearly spaced).
>>> pd.timedelta_range(start='1 day', end='5 days', periods=4)
TimedeltaIndex(['1 days 00:00:00', '2 days 08:00:00', '3 days 16:00:00',
'5 days 00:00:00'],
dtype='timedelta64[ns]', freq='32H')
"""
if freq is None and com.any_none(periods, start, end):
freq = "D"
freq, freq_infer = dtl.maybe_infer_freq(freq)
tdarr = TimedeltaArray._generate_range(start,
end,
periods,
freq,
closed=closed)
return TimedeltaIndex._simple_new(tdarr, name=name)
def timedelta_range(start=None, end=None, periods=None, freq=None,
name=None, closed=None):
"""
Return a fixed frequency TimedeltaIndex, with day as the default
frequency
Parameters
----------
start : string or timedelta-like, default None
Left bound for generating timedeltas
end : string or timedelta-like, default None
Right bound for generating timedeltas
periods : integer, default None
Number of periods to generate
freq : string or DateOffset, default 'D'
Frequency strings can have multiples, e.g. '5H'
name : string, default None
Name of the resulting TimedeltaIndex
closed : string, default None
Make the interval closed with respect to the given frequency to
the 'left', 'right', or both sides (None)
Returns
-------
rng : TimedeltaIndex
Notes
-----
Of the four parameters ``start``, ``end``, ``periods``, and ``freq``,
exactly three must be specified. If ``freq`` is omitted, the resulting
``TimedeltaIndex`` will have ``periods`` linearly spaced elements between
``start`` and ``end`` (closed on both sides).
To learn more about the frequency strings, please see `this link
<http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases>`__.
Examples
--------
>>> pd.timedelta_range(start='1 day', periods=4)
TimedeltaIndex(['1 days', '2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``closed`` parameter specifies which endpoint is included. The default
behavior is to include both endpoints.
>>> pd.timedelta_range(start='1 day', periods=4, closed='right')
TimedeltaIndex(['2 days', '3 days', '4 days'],
dtype='timedelta64[ns]', freq='D')
The ``freq`` parameter specifies the frequency of the TimedeltaIndex.
Only fixed frequencies can be passed, non-fixed frequencies such as
'M' (month end) will raise.
>>> pd.timedelta_range(start='1 day', end='2 days', freq='6H')
TimedeltaIndex(['1 days 00:00:00', '1 days 06:00:00', '1 days 12:00:00',
'1 days 18:00:00', '2 days 00:00:00'],
dtype='timedelta64[ns]', freq='6H')
Specify ``start``, ``end``, and ``periods``; the frequency is generated
automatically (linearly spaced).
>>> pd.timedelta_range(start='1 day', end='5 days', periods=4)
TimedeltaIndex(['1 days 00:00:00', '2 days 08:00:00', '3 days 16:00:00',
'5 days 00:00:00'],
dtype='timedelta64[ns]', freq=None)
"""
if freq is None and com._any_none(periods, start, end):
freq = 'D'
freq, freq_infer = dtl.maybe_infer_freq(freq)
tdarr = TimedeltaArray._generate_range(start, end, periods, freq,
closed=closed)
return TimedeltaIndex._simple_new(tdarr._data, freq=tdarr.freq, name=name)