MLRMPA (version 1.0)

VarCor: VarCor Selection and Dataset Partition

Description

Firstly, select the eligible variales according to the values of var.lower and var.upper. Secondly, divide activity as well as corresponding descriptor into training set and test set with personal setting.

Usage

VarCor(tst, activity, descriptor, deleted_descriptor, var.lower, var.upper, xy.cor)

Arguments

tst

a numeric vector of the serial number of test set

activity

a 1*n dataframe of activity (n is the number of samples)

descriptor

a n*P dataframe of corresponding descriptors (n is the number of samples, P is the number of descriptors)

deleted_descriptor

a 1*M dataframe of needed to delete descriptors which contains insignificant and noisy variables (M is the number of deleted descriptors)

var.lower

a numeric in the varance selection as the lower limit value

var.upper

a numeric in the varance selection as the upper limit value

xy.cor

a numeric in the correlation selection

Value

expr.tr

a dataframe with the experimental data of training set

expr.tst

a dataframe with the experimental data of test set

dscrp.all

a dataframe with the descriptors both of training set and test set

dscrp.tr

a dataframe with the descriptors of training set

dscrp.tst

a dataframe with the descriptors of test set

VarCordim

the dim of variance selection and correlation selection