build_supervised_sample: Build_supervised_sample

In imbs-hl/MDRDist: This Package calculates something like a distance

Description

The function build_supervised_sample creates a dataset which combines real and artificial data, that could be passed to a classification algorithm. Some model assumptions are transmittet to function by the selection of "method", which is a function of class "comparison_distriobution" (see file comparison_distributions.R).

Usage

build_supervised_sample(data, fraction_of_real_data,
  fraction_of_artificial_data, do_bootstrapping, method)

Arguments

data	A data.frame with original data
fraction_of_real_data	number of real observations randomly drawn, where 1 equals nrow(data)
fraction_of_artificial_data	number of artificial observations, where 1 equals nrow(data)
do_bootstrapping	choosing real observations randomly with (-> bootstrapping) or without (-> subsampling) replacement
method	a function describing the distribution of artificial data

Value

A data.frame with a sample of original data (coded with status==1) and artificial data (coded with status==0).

imbs-hl/MDRDist documentation built on May 18, 2019, 4:45 a.m.