FRESA.CAD (version 3.3.0)

FilterUnivariate: Univariate Filters

Description

Returns the top set of features that are statistically associated with the outcome.

Usage

univariate_Logit(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH", 
                 uniTest=c("zIDI","zNRI"),limit=0,...,n=0)
univariate_residual(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH",
                    uniTest=c("Ftest","Binomial","Wilcox","tStudent"),
                    type=c("LM","LOGIT"),limit=0,...,n=0)
univariate_tstudent(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH",
                    limit=0,...,n=0)
univariate_Wilcoxon(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH",
                     limit=0,...,n=0)
univariate_correlation(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH",
                       method = "kendall",limit=0,...,n=0)
univariate_cox(data=NULL, Outcome=NULL, pvalue=0.2, adjustMethod="BH",
                     limit=0,...)
correlated_Remove(data=NULL,fnames=NULL,thr=0.999)

Arguments

data

The data frame

Outcome

The outcome feature

pvalue

The threshold pvalue used after the p.adjust method

adjustMethod

The method used by the p.adjust method

uniTest

The unitTest to be performed by the linear fitting model

type

The type of linear model: LM or LOGIT

method

The correlation method: pearson,spearman or kendall.

limit

The samples-wise fraction of features to return.

fnames

The list of features to test inside the correlated_Remove function

thr

The maximum correlation to allow between features

...

Parameters to be passed to the correlated_Remove function

n

the number of original features passed to p.adjust

Value

Named vector with the adjusted p-values or the list of no-correlated features for the correlated_Remove

Examples

# NOT RUN {
    
# }
# NOT RUN {
        library("FRESA.CAD")

        ### Univariate Filter Examples ####

        # Get the stage C prostate cancer data from the rpart package
        data(stagec,package = "rpart")

        # Prepare the data. Create a model matrix without the event time and interactions
        stagec$pgtime <- NULL
        stagec$eet <- as.factor(stagec$eet)
        options(na.action = 'na.pass')
        stagec_mat <- cbind(pgstat = stagec$pgstat,
                            as.data.frame(model.matrix(pgstat ~ .*.,stagec))[-1])
        fnames <- colnames(stagec_mat)
        fnames <- str_replace_all(fnames,":","__")
        colnames(stagec_mat) <- fnames

        # Impute the missing data
        dataCancerImputed <- nearestNeighborImpute(stagec_mat)
        dataCancerImputed[,1:ncol(dataCancerImputed)] <- sapply(dataCancerImputed,as.numeric)

        # Get the top Features associated to pgstat

        q_values <- univariate_Logit(data=dataCancerImputed, 
                                    Outcome="pgstat",
                                    pvalue = 0.05)

        qValueMatrix <- q_values
        idiqValueMatrix <- q_values
        barplot(-log(q_values),las=2,cex.names=0.4,ylab="-log(Q)",
        main="Association with PGStat: IDI Test")

        q_values <- univariate_Logit(data=dataCancerImputed, 
                                    Outcome="pgstat", 
                                    uniTest="zNRI",pvalue = 0.05)
        qValueMatrix <- cbind(idiqValueMatrix,q_values[names(idiqValueMatrix)])

        q_values <- univariate_residual(data=dataCancerImputed, 
                                    Outcome="pgstat", 
                                    pvalue = 0.05,type="LOGIT")
        qValueMatrix <- cbind(qValueMatrix,q_values[names(idiqValueMatrix)])

        q_values <- univariate_tstudent(data=dataCancerImputed, 
                                       Outcome="pgstat", 
                                       pvalue = 0.05)
        qValueMatrix <- cbind(qValueMatrix,q_values[names(idiqValueMatrix)])

        q_values <- univariate_Wilcoxon(data=dataCancerImputed, 
                                       Outcome="pgstat", 
                                       pvalue = 0.05)
        qValueMatrix <- cbind(qValueMatrix,q_values[names(idiqValueMatrix)])

        q_values <- univariate_correlation(data=dataCancerImputed, 
                                       Outcome="pgstat", 
                                       pvalue = 0.05)
        qValueMatrix <- cbind(qValueMatrix,q_values[names(idiqValueMatrix)])

        q_values <- univariate_correlation(data=dataCancerImputed, 
                                          Outcome="pgstat", 
                                          pvalue = 0.05,
                                          method = "pearson")

        #The qValueMatrix has the qValues of all filter methods.  
        qValueMatrix <- cbind(qValueMatrix,q_values[names(idiqValueMatrix)])
        colnames(qValueMatrix) <- c("IDI","NRI","F","t","W","K","P")
        #Do the log transform to display the heatmap
        qValueMatrix <- -log10(qValueMatrix)
        #the Heatmap of the q-values
        gplots::heatmap.2(qValueMatrix,Rowv = FALSE,dendrogram = "col",
        main = "Method q.values",cexRow = 0.4)

    
# }