Changelog is kept with respect to version 0.11 of Entropies.jl.
The API for Entropies.jl has been completely overhauled. Major changes are:
- Common generic interfaces
entropy
,entropy_normalized
andmaximum
(maximum entropy) that dispatches on different types of entropies (e.gRenyi()
Shannon()
,Tsallis()
). - Convenience functions for common entropies, such as permutation entropy and dispersion entropy.
- No more deprecation warnings for using the old keyword
α
for Renyi entropy. - An entirely new section of entropy-like complexity measures, such as the reverse dispersion entropy.
- Many new estimators, such as
SpatialPermutation
andPowerSpectrum
. - Check the online documentation for a comprehensive overview of the changes.
- New probability estimator
SpatialSymbolicPermutation
suitable for computing spatial permutation entropies - Introduce Tsallis entropy.
- Added dispersion entropy.
- Introduce convenience function
permentropy
. - Several type instabilities fixed.
No actual changes, just first major version release.
- Nearest neighbor searches now use Neighborhood.jl and the Theiler window properly.
probabilities(data, n::Int)
now uses a rectangular binning ofn
bins for each dimension. Before, while not documented as possible in the public API, using integern
would take it as the bin size.