def _check_cutoffs_against_train_windows(cutoffs, windows, y):
# Cutoffs should always be the last values of the train windows.
if array_is_int(cutoffs):
actual = np.array([window[-1] for window in windows[1:]])
elif array_is_datetime64(cutoffs):
actual = np.array(
[y.index[window[-1]].to_datetime64() for window in windows[1:]],
dtype="datetime64",
)
else:
raise ValueError(
f"Provided `cutoffs` type is not supported: {type(cutoffs[0])}")
np.testing.assert_array_equal(actual, cutoffs[1:])
# We treat the first window separately, since it may be empty when setting
# `start_with_window=False`.
if len(windows[0]) > 0:
if array_is_int(cutoffs):
np.testing.assert_array_equal(windows[0][-1], cutoffs[0])
elif array_is_datetime64(cutoffs):
np.testing.assert_array_equal(
y.index[windows[0][-1]].to_datetime64(), cutoffs[0])
else:
raise ValueError(
f"Provided `cutoffs` type is not supported: {type(cutoffs[0])}"
)
def _check_cutoffs_and_y(cutoffs: VALID_CUTOFF_TYPES,
y: ACCEPTED_Y_TYPES) -> None:
"""Check that combination of inputs is compatible.
Parameters
----------
cutoffs : np.array or pd.Index
cutoff points, positive and integer- or datetime-index like
y : pd.Series, pd.DataFrame, np.ndarray, or pd.Index
coerced and checked version of input y
Raises
------
ValueError
if max cutoff is above the last observation in `y`
TypeError
if `cutoffs` type is not supported
"""
max_cutoff = np.max(cutoffs)
msg = ("`cutoffs` are incompatible with given `y`. "
"Maximum cutoff is not smaller than the ")
if array_is_int(cutoffs):
if max_cutoff >= y.shape[0]:
raise ValueError(msg + "number of observations.")
elif array_is_datetime64(cutoffs):
if max_cutoff >= np.max(y):
raise ValueError(msg + "maximum index value of `y`.")
else:
raise TypeError("Unsupported type of `cutoffs`")
def _cutoffs_fh_window_length_types_are_supported(
cutoffs: VALID_CUTOFF_TYPES,
fh: FORECASTING_HORIZON_TYPES,
window_length: ACCEPTED_WINDOW_LENGTH_TYPES,
) -> bool:
"""Check that combination of inputs is supported.
Currently, only two cases are allowed:
either all inputs are integers, or they are all datetime or timedelta
Parameters
----------
cutoffs : np.array or pd.Index
cutoff points, positive and integer- or datetime-index like
fh : int, timedelta, list or np.array of ints or timedeltas
window_length : int or timedelta or pd.DateOffset
Returns
-------
True if all inputs are compatible, False otherwise
"""
all_int = array_is_int(cutoffs) and array_is_int(fh) and is_int(
window_length)
all_dates = (array_is_datetime64(cutoffs)
and array_is_timedelta_or_date_offset(fh)
and is_timedelta_or_date_offset(window_length))
if all_int or all_dates:
return True
else:
return False
def check_cutoffs(cutoffs: VALID_CUTOFF_TYPES) -> np.ndarray:
"""Validate the cutoff.
Parameters
----------
cutoffs : np.ndarray or pd.Index
Returns
-------
cutoffs (Sorted array)
Raises
------
ValueError
If cutoffs is not a instance of np.array or pd.Index
If cutoffs array is empty.
"""
if not isinstance(cutoffs, ACCEPTED_CUTOFF_TYPES):
raise ValueError(
f"`cutoffs` must be a np.array or pd.Index, but found: {type(cutoffs)}"
)
assert array_is_int(cutoffs) or array_is_datetime64(cutoffs)
if len(cutoffs) == 0:
raise ValueError("Found empty `cutoff` array")
return np.sort(cutoffs)
def _check_cutoffs(cutoffs):
assert isinstance(cutoffs, np.ndarray)
assert array_is_int(cutoffs) or array_is_datetime64(cutoffs)
assert cutoffs.ndim == 1
assert len(cutoffs) > 0