Transformer

ReverseAugmenter

Augmenter reversing the time series.

If transform is given a time series \(X={x_1, x_2,..., x_n}\), then returns \(X_t={x_n, x_{n-1},..., x_2, x_1}\). Time series augmentation by reversing has been discussed e.g. in [1].

Quickstart

python

from sktime.transformations.augmenter import ReverseAugmenter

estimator = ReverseAugmenter

Examples

>>> import pandas as pd
>>> from sktime.transformations.augmenter import ReverseAugmenter
>>> X = pd. Series ([1, 2, 3, 4, 5 ])
>>> augmenter = ReverseAugmenter ()
>>> Xt = augmenter. fit_transform (X)
>>> Xt 0 5 1 4 2 3 3 2 4 1 dtype: int64 References and Footnotes ¶ [1]: IWANA, Brian Kenji; UCHIDA, Seiichi. An empirical survey of data augmentation for time series classification with neural networks. Plos one, 2021, 16. Jg., Nr. 7, S. e0254841.