Create a usl object from a dataframe or matrix object

Description

Extends the native nls object to specialize it calculating Gunther's nls models for Universal Scaling Law. Allows multiple models to be stored in one workspace.

Usage

1
  usl(x, start = c(alpha = 0.1, beta = 0.01), ...)

Arguments

x

a data.frame or matrix object containing data for model. A data.frame should the data in columns named N,for "scaled objects" (e.g. users, cpus), and X_N, for measured throughput. The default for a matrix object is to put scaled objects in the matrix's column 1 (i.e. x[,1]) and throughput in column 2 x[,2]

start

a named list with initial guess two usl parameters

...

additional arguments to pass to function

Value

sfit object

Examples

1
2
3
4
5
data(USLcalc)
USL1<-usl(USLcalc)

data(SSUSLcalc)
USL2<-usl(SSUSLcalc,data.cols=c("V1","V2"),start=c(alpha=.1,beta=.001))

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.