

Surrogate methods

Random amplitude Fourier surrogates

# TimeseriesSurrogates.randomamplitudes — Function.

randomamplitudes(a::AbstractArray{Number, 2}; cols = 1:size(d, 2))

Column-wise random amplitude Fourier surrogate of an array, where each column is a scalar-valued time series. cols controls which variables of the embedding are shuffled.

source

randomamplitudes(E::Embeddings.AbstractEmbedding;
                    cols = 1:size(E.points, 1))

Column-wise random amplitude Fourier surrogate of an embedding. cols controls which variables of the embedding are shuffled.

source

randomamplitudes(d::DynamicalSystemsBase.Dataset; cols = 1:size(d, 2))

Column-wise random amplitude Fourier surrogate of a Dataset. cols controls which variables of the embedding are shuffled.

source

Example

# Generate a dynamical system, create an orbit and extract a time series from
# the first component.
s = CausalityTools.Systems.logistic3()
orbit = trajectory(s, 150)
x = orbit[:, 1]

# Compare original time series and random amplitude surrogate
p1 = plot(x, label = "x", lc = :black)
p2 = plot(randomamplitudes(x), label = "randomamplitudes(x)",
            xlabel = "Time step")
plot(p1, p2, layout = (2, 1))
ylabel!("Value")