RecurrenceAnalysis.jl
RecurrenceAnalysis.jl copied to clipboard
JuliaDynamics
Recurrence Quantification Analysis in Julia
Currently work in progress, ported over from https://github.com/JuliaDynamics/DynamicalSystems.jl/pull/172 , see JuliaDynamics/RecurrenceAnalysis.jl#130 Needs to be updated accordingly! Help appreciated!!! The docs can be viewed here: https://juliadynamics.github.io/RecurrenceAnalysis.jl/previews/PR145
The 'recurrence flow' and 'recurrence lacunarity' measures proposed in https://doi.org/10.1140/epjs/s11734-022-00687-3 https://doi.org/10.1007/s11071-021-06457-5 could be added to RecurrenceAnalysis.jl. Python implementations for both already exist and could be helpful: https://github.com/ToBraun/RECFLOW https://github.com/ToBraun/RECLAC
see also https://github.com/JuliaDynamics/DynamicalSystems.jl/issues/210 Would be nice to allow a 4th argument `εy` for the recurrences of `y`. Only question is: what would be the recurrence type stored and displayed by...
After the test overhauling of v2 that demands analytic tests to be trustworthy, the plotting functions `recurrenceplot, grayscale, coordinates` are not tested; Would be nice to test them for completeness.
Alright, we stand to gain MASSIVE, 2x, performance benefit here for all `RecurrenceType`s except `RecurrenceThreshold`. Take a look at our source code that computes the recurrence threshold for a given...
Have a look at our analytic tests: https://github.com/JuliaDynamics/RecurrenceAnalysis.jl/blob/main/test/rmatrix_analytic.jl#L97-L116 The local recurrence rate results are wrong. They do not give what is expected analytically and due to the symmetries of the...
Have a look at our new tests; https://github.com/JuliaDynamics/RecurrenceAnalysis.jl/blob/main/test/rmatrix_analytic.jl#L71-L95 There I have noted that `GlobalRecurrenceRate` does not give **exactly** the results expected analytically. Only approximately. Why isn't this exact? What can...
In a [very recent paper](https://aip.scitation.org/doi/pdf/10.1063/5.0114797) it is suggested to obtain an adaptive recurrence threshold based on local maximum attractor densities/distances. Basically, the distance matrix gets scanned using a sliding window...
At the moment the source code of `recurrence_matrix`, which is where the central computations of a recurrence matrix take place, is full of duplication. There version complexity scales as 2...
I did some comparison of the calculation speed for RPs and simple RQA. More details at . The Julia implementation (RecurrenceAnalysis.jl) is (surprising to me) not the fastest one. 