COMTE

`COMTECF(model, data, backend, mode, method='opt', number_distractors=2, max_attempts=1000, max_iter=1000, silent=False)`

Bases: CF

Calculates and Visualizes Counterfactuals for Multivariate Time Series in accordance to the paper [1].

References

[1] Ates, Emre, et al. "Counterfactual Explanations for Multivariate Time Series." 2021 International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 2021.

PARAMETER	DESCRIPTION
`model`	Model to be interpreted. TYPE: `[Module, Callable, model]`
`ref`	Reference Dataset as Tuple (x,y). TYPE: `Tuple`
`backend`	desired Model Backend ('PYT', 'TF', 'SK'). TYPE: `str`
`mode`	Name of second dimension: `time` -> `(-1, time, feature)` or `feat` -> `(-1, feature, time)` TYPE: `str`
`method`	'opt' if optimized calculation, 'brute' for Brute Force TYPE: `str` DEFAULT: `'opt'`
`number_distractors`	number of distractore to be used TYPE: `int` DEFAULT: `2`
`silent`	logging. TYPE: `bool` DEFAULT: `False`

`explain(x, orig_class=None, target=None)`

Calculates the Counterfactual according to Ates. Arguments: x (np.array): The instance to explain. Shape : mode = time -> (1,time, feat) or mode = time -> (1,feat, time) target int: target class. If no target class is given, the class with the secon heighest classification probability is selected.

RETURNS	DESCRIPTION
`([array], int)`	Tuple of Counterfactual and Label. Shape of CF : `mode = time` -> `(time, feat)` or `mode = time` -> `(feat, time)`