Add an MI estimator in Julia about bmi HOT 2 CLOSED

using CSV
using DataFrames
# using YAML
using TransferEntropy

samples_filename = ARGS[1]
seed = parse(Int, ARGS[2])
dim_x = parse(Int, ARGS[3])
dim_y = parse(Int, ARGS[4])


# metadata = YAML.load_file(metadata_filename)
# show(metadata)
# dim_x = metadata["dim_x"]
# dim_y = metadata["dim_y"]

df = CSV.File(samples_filename) |> DataFrame

df = df[df.seed .== seed, :] 

x_samples = Dataset(Matrix(df[:, 2:1+dim_x]))
y_samples = Dataset(Matrix(df[:, 2+dim_x: 1+dim_x+dim_y]))

# show(x_samples)
# show(y_samples)


mi = mutualinfo(x_samples, y_samples, Kraskov())
println(mi)


mi = mutualinfo(x_samples, y_samples, Kraskov1())
println(mi)


mi = mutualinfo(x_samples, y_samples, Kraskov2())
println(mi)


mi = mutualinfo(x_samples, y_samples, KozachenkoLeonenko())
println(mi)


est = VisitationFrequency(RectangularBinning(0.1))
mi = mutualinfo(x_samples, y_samples, est)
println(mi)


est = VisitationFrequency(RectangularBinning(0.2))
mi = mutualinfo(x_samples, y_samples, est)
println(mi)


est = VisitationFrequency(RectangularBinning(0.5))
mi = mutualinfo(x_samples, y_samples, est)
println(mi)

est = VisitationFrequency(RectangularBinning(1))
mi = mutualinfo(x_samples, y_samples, est)
println(mi)

dim_x: 1
dim_y: 2
mi_true: 0.5108256237659909
n_samples: 5000
task_id: some-correlation

$ julia mi_estimator.jl testdir/samples.csv 1 1 2

-Inf
2.0348837647400924
2.405459973695475
-Inf
3.5470532390132483
1.7091615702982228
0.8061644481070918
0.0