EntroPy is a Python 3 package providing several time-efficient algorithms for computing the complexity of one-dimensional time-series. It can be used for example to extract features from EEG signals.

EntroPy cannot be installed using pip or conda. There is already a package called entropy on the pip repository, which should not be mistaken with the current package.

Uses the mathematical analysis modules that you'd expect.

Can calculate permutation, spectral, singular value decomposition, appromate, sample, and Lempel-Ziv entropy. Can calculate Petrosian, Katz, Higuchi, and detrended fluctuation fractal dimensionality.

— Permalink]]>

David MacKay has put the textbook he wrote online for everyone to download in a variety of formats. If you find it useful, consider buying a copy.

— Permalink]]>