dataclean {SuRF.vs}

dataclean

Description

This function is to 1)Scale the count data (count data only) to proportion 2)create a data frame consisting of proportion data, and 3) Keep an variable name list (original variable names and names in terms of X's, e.g.X1,X2,..,etc. ) #environmental data (host genome and other information about observations)

Usage

dataclean(X.c, X.o, y)

Arguments

X.c

data frame that has count data from all levels (only count data will be row scaled)

X.o

data frame that has other environmental variables (no scaling will be done, those variables will scaled together with proportion data in LASSO step)

y

a vector representing the outcome (0 or 1 for binomial model)

Value

data.Xy: a dataframe containing all variables named as X1,X2,...,Xp and the binary outcome (called status)in the last column; this data frame will be used in the other functions for data analysis