getResults: Compiles performance and selected features for a trained...
In BaderLab/netDx: Network-based patient classifier

Description Usage Arguments Details Value Examples

Compiles performance and selected features for a trained model.

1	getResults(res, status, featureSelCutoff = 1L, featureSelPct = 0)

`res`	(list) output of buildPredictor() function
`status`	(character) unique patient labels used by the classifier, found in colData()$STATUS
`featureSelCutoff`	(integer) cutoff score for feature selection. A feature must have minimum of this score for specified fraction of splits (see featureSelPct) to pass.
`featureSelPct`	(numeric between 0 and 1) cutoff percent for feature selection. A feature must have minimum score of featureSelCutoff for featureSelPct of train/test splits to pass.

This function is run after training a model using buildPredictor(). It takes patient input data, model output, and returns performance and selected features.

list of results. - selectedFeatures (list of character vectors): list, one per class - performance (list of mixed datatypes) including mean accuracy (meanAccuracy), split-level accuracy (splitAccuracy), split-level AUROC (auroc), split-level AUPR (splitAUR) Side effect of plotting ROC curve if binary classifier

1
2
3

data(toymodel) # load example results from binary breast classification
patlabels <- names(toymodel$Split1$featureSelected)
getResults(toymodel,patlabels,2,0.5)