Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add complexity estimate feature calculators #325

Open
MaxBenChrist opened this issue Sep 26, 2017 · 4 comments
Open

Add complexity estimate feature calculators #325

MaxBenChrist opened this issue Sep 26, 2017 · 4 comments

Comments

@MaxBenChrist
Copy link
Collaborator

MaxBenChrist commented Sep 26, 2017

This paper defines a estimate of the complexity of a time series.

http://www.cs.ucr.edu/~eamonn/Complexity-Invariant%20Distance%20Measure.pdf

I would like to add that feature.

Edit: the respective journal paper discusses 8 different measure for the complexity of a time series, e.g.

  • Fractal dimension
  • Absolute difference
  • Compression
  • Pseudo-pairs
  • edges
  • zero-crossings
  • spektrum
  • fourier entropy
  • permutations entropy

I implemented the complexity estimate measure used in CID. I will leave this issue open as a starting point for new features

@MaxBenChrist MaxBenChrist changed the title Add complexity estimate Add complexity estimate feature calculators Sep 27, 2017
@MaxBenChrist
Copy link
Collaborator Author

pr #332 contains the cid complexity estiator

@nils-braun
Copy link
Collaborator

I implemented the fourier entropy in #688.

@nils-braun
Copy link
Collaborator

and the permutation entropy in #691

@nils-braun
Copy link
Collaborator

absolute differences and zero crossings are already implemented.
That leaves us with:

  • Fractal dimension
  • Compression -> might be very slow
  • Pseudo-pairs
  • edges
  • spektrum

I will keep this issue open but I do not plan to implement more of them in the near future

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants