tslearn.shapelets.grabocka_params_to_shapelet_size_dict

tslearn.shapelets.grabocka_params_to_shapelet_size_dict(n_ts, ts_sz, n_classes, l, r)[source]

Compute number and length of shapelets.

This function uses the heuristic from [1].
Parameters:
n_ts: int

Number of time series in the dataset

ts_sz: int

Length of time series in the dataset

n_classes: int

Number of classes in the dataset

l: float

Fraction of the length of time series to be used for base shapelet length

r: int

Number of different shapelet lengths to use

Returns:
dict

Dictionary giving, for each shapelet length, the number of such shapelets to be generated

References

[1]
  1. Grabocka et al. Learning Time-Series Shapelets. SIGKDD 2014.

Examples

>>> d = grabocka_params_to_shapelet_size_dict(
...         n_ts=100, ts_sz=100, n_classes=3, l=0.1, r=2)
>>> keys = sorted(d.keys())
>>> print(keys)
[10, 20]
>>> print([d[k] for k in keys])
[4, 4]

Examples using tslearn.shapelets.grabocka_params_to_shapelet_size_dict