Feature: bubble entropy (description is WIP) about complexitymeasures.jl HOT 4 CLOSED

Oooooooooooioh now I understand what you mean by "vector to be sorted". I thought you meant: sort the vectors wtihin the embedded set. You mean: sort the elements of each statespace point, i.e., the same as getting the sortperm for the patterns.

OKay, all good, I'll look at the PR now.

from complexitymeasures.jl.

encode(::BubbleSortCountEncoder, x::AbstractVector) converts x into an integer in the range 0:n(n−1)/2 (the number of swaps required to sort x).

I don't see how this is possible. encode should give the same encoding irrespectively of the order of the vectors in the state space set (embedded set). That's also why the encoding doesn't depend on the input data, but only one 1 element of the input data. For sorting this not the case. If the original dataset is already sorted, encode(e, x) would always return 0 irrespectively of x.

I think for this feature it makes sense to have the outcome space, but not the encoding. I find this more similar to the spectral entropy and the PowerSpectrum outcome space.

from complexitymeasures.jl.

encode(::BubbleSortCountEncoder, x::AbstractVector) converts x into an integer in the range 0:n(n−1)/2 (the number of swaps required to sort x).
don't see how this is possible. encode should give the same encoding irrespectively of the order of the vectors in the state space set (embedded set).

encode works strictly on single state vectors, not the entire embedding. Each vector has a certain amplitude distribution, which maps directly onto an integer in the range 0:n(n−1)/2, because 0 is the minimum number of swaps for the bubble sort algorithm to render the state vector sorted, and 0:n(n−1)/2 is the maximum number of swaps.

Many state vectors in the same embedding can map to the same integer, because the number of sorting operations required to sort them is the same, even though the vectors are different. The order of the embedding does matter here, because the input to encode is a state vector, not an embedding.

I've implemented my suggestion in #390. This should be clear from the source code there

from complexitymeasures.jl.

Closed by #390

from complexitymeasures.jl.