This function adds metadata to the feature matrix to be later used as predictors

add.meta.pred(siamcat, pred.names,
    std.meta = TRUE,
    feature.type='normalized',
    verbose = 1)

Arguments

siamcat

object of class siamcat-class

pred.names

vector of names of the variables within the metadata to be added to the feature matrix as predictors

std.meta

boolean, should added metadata features be standardized?, defaults to TRUE

feature.type

string, on which type of features should the function work? Can be either "original", "filtered", or "normalized". Please only change this paramter if you know what you are doing!

verbose

integer, control output: 0 for no output at all, 1 for only information about progress and success, 2 for normal level of information and 3 for full debug information, defaults to 1

Value

an object of class siamcat-class with metadata added to the features

Details

This functions adds one or several metadata variables to the set of features, so that they can be included for model training.

Usually, this function should be called before train.model.

Numerical meta-variables are added as z-scores to the feature matrix unless specified otherwise.

Please be aware, that non-numerical metadata variables will be converted to numerical values by using as.numeric() and could therefore lead to errors. Thus, it makes sense to encode non-numerical metadata variables to numerically before you start the SIAMCAT workflow.

Examples

data(siamcat_example) # Add the Age of the patients as potential predictor siamcat_age_added <- add.meta.pred(siamcat_example, pred.names=c('Age'))
#> Adding metadata as predictor finished
# Add Age and BMI as potential predictors # Additionally, prevent standardization of the added features siamcat_meta_added <- add.meta.pred(siamcat_example, pred.names=c('Age', 'BMI'), std.meta=FALSE)
#> Adding metadata as predictor finished