[epclust.git] / epclust / R / algorithms.R

#NOTE: always keep ID in first column
curvesToCoeffs = function(series, wf)
{
	library(wavelets)
	L = length(series[1,])
	D = ceiling( log(L-1) )
	nb_sample_points = 2^D
	#TODO: parallel::parApply() ?!
	res = apply(series, 1, function(x) {
		interpolated_curve = spline(1:(L-1), x[2:L], n=nb_sample_points)$y
		W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
		nrj_coeffs = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
		return ( c(x[1], nrj_coeffs) )
	})
	return (as.data.frame(res))
}

getClusters = function(data, K)
{
	library(cluster)
	pam_output = cluster::pam(data, K)
	return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids,
		ranks=pam_output$id.med ) )
}
Commit	Line	Data
3465b246 BA	1	#NOTE: always keep ID in first column
3465b246 BA	2	curvesToCoeffs = function(series, wf)
b9f1c0c7	3	{
3465b246 BA	4	library(wavelets)
	5	L = length(series[1,])
	6	D = ceiling( log(L-1) )
	7	nb_sample_points = 2^D
	8	#TODO: parallel::parApply() ?!
	9	res = apply(series, 1, function(x) {
	10	interpolated_curve = spline(1:(L-1), x[2:L], n=nb_sample_points)$y
	11	W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
	12	nrj_coeffs = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
	13	return ( c(x[1], nrj_coeffs) )
	14	})
	15	return (as.data.frame(res))
b9f1c0c7 BA	16	}
	17
	18	getClusters = function(data, K)
	19	{
3465b246 BA	20	library(cluster)
3465b246 BA	21	pam_output = cluster::pam(data, K)
cea14f3a BA	22	return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids,
cea14f3a BA	23	ranks=pam_output$id.med ) )
b9f1c0c7	24	}