# HG changeset patch # User deepakjadmin # Date 1483428377 18000 # Node ID 016c69bfb2a147e1f887c83ef3d8ea43f2cf3cae # Parent 5364cf43a8c15ba64554d28a22f1d4f4dd47f09b Uploaded diff -r 5364cf43a8c1 -r 016c69bfb2a1 feature_selection.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/feature_selection.R Tue Jan 03 02:26:17 2017 -0500 @@ -0,0 +1,147 @@ +args <- commandArgs(T) + +arg1 <- args[1] +arg2 <- args[2] +arg3 <- args[3] +arg4 <- args[4] +arg5 <- args[5] +arg6 <- args[6] +arg7 <- args[7] +arg8 <- args[8] +arg9 <- args[9] +library(caret) +load(arg1) + +#RAWDATA <- dataX +#RAWDATA$outcome <- dataY + + +########################### +Smpling <- arg9 + +if(Smpling=="downsampling") +{ +dwnsmpl <- downSample(dataX,dataY) +RAWDATA <- dwnsmpl[,1:length(dwnsmpl)-1] +RAWDATA$outcome <- dwnsmpl[,length(dwnsmpl)] +dataX <- RAWDATA[,1:length(dwnsmpl)-1] +dataY <- RAWDATA[,"outcome"] +remove("dwnsmpl") +}else if(Smpling=="upsampling"){ +upsmpl <- upSample(dataX,dataY) +RAWDATA <- upsmpl[,1:length(upsmpl)-1] +RAWDATA$outcome <- upsmpl[,length(upsmpl)] +dataX <- RAWDATA[,1:length(upsmpl)-1] +dataY <- RAWDATA[,"outcome"] +remove("upsmpl") +}else { +RAWDATA <- dataX +RAWDATA$outcome <- dataY +} + + + + +########################## + + +rawData <- dataX +predictorNames <- names(rawData) + +isNum <- apply(rawData[,predictorNames, drop = FALSE], 2, is.numeric) +if(any(!isNum)) stop("all predictors in rawData should be numeric") + +colRate <- apply(rawData[, predictorNames, drop = FALSE], + 2, function(x) mean(is.na(x))) +colExclude <- colRate > 0.1 + if(any(colExclude)){ + predictorNames <- predictorNames[-which(colExclude)] + rawData <- RAWDATA[, c(predictorNames,"outcome")] + } else { + rawData <- RAWDATA + } + rowRate <- apply(rawData[, predictorNames, drop = FALSE], + 1, function(x) mean(is.na(x))) + + +rowExclude <- rowRate > 0 + if(any(rowExclude)){ + rawData <- rawData[!rowExclude, ] + ##hasMissing <- apply(rawData[, predictorNames, drop = FALSE], + ##1, function(x) mean(is.na(x))) + +############################################################################ + + +############################################################################### + } else { + rawData <- rawData[complete.cases(rawData),] + + } + +set.seed(2) + +#print(dim(dataX)) +#print(dim(rawData)) +#print(length(dataY)) + +nzv <- nearZeroVar(rawData[,1:(length(rawData) - 1)]) + if(length(nzv) > 0) { + #nzvVars <- names(rawData)[nzv] + rawData <- rawData[,-nzv] + #rawData$outcome <- dataY + } + +predictorNames <- names(rawData)[names(rawData) != "outcome"] + +dx <- rawData[,1:length(rawData)-1] +dy <- rawData[,length(rawData)] +corrThresh <- as.numeric(arg8) +highCorr <- findCorrelation(cor(dx, use = "pairwise.complete.obs"),corrThresh) +dx <- dx[, -highCorr] +subsets <- seq(1,length(dx),by=5) +normalization <- preProcess(dx) +dx <- predict(normalization, dx) +dx <- as.data.frame(dx) + +if (arg4 == "lmFuncs"){ +ctrl1 <- rfeControl(functions = lmFuncs, + method = arg5 , + repeats = as.numeric(arg6), + number = as.numeric(arg7), + verbose = FALSE) +} else if(arg4 == "rfFuncs"){ +ctrl1 <- rfeControl(functions = rfFuncs, + method = arg5 , + repeats = as.numeric(arg6), + number = as.numeric(arg7), + verbose = FALSE) +}else if (arg4 == "treebagFuncs"){ +ctrl1 <- rfeControl(functions = treebagFuncs, + method = arg5 , + repeats = as.numeric(arg6), + number = as.numeric(arg7), + verbose = FALSE) +}else { + +ctrl1 <- rfeControl(functions = nbFuncs, + method = arg5 , + repeats = as.numeric(arg6), + number = as.numeric(arg7), + verbose = FALSE) +} + + + + +Profile <- rfe(dx, dy,sizes = subsets,rfeControl = ctrl1) + +pred11 <- predictors(Profile) +save(Profile,file=arg2) +dataX <- rawData[,pred11] +dataY <- rawData$outcome + +save(dataX,dataY,file=arg3) +rm(dataX) +rm(dataY) + diff -r 5364cf43a8c1 -r 016c69bfb2a1 featureselect/feature_selection.R --- a/featureselect/feature_selection.R Sun Oct 02 05:36:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,116 +0,0 @@ -args <- commandArgs(T) - -arg1 <- args[1] -arg2 <- args[2] -arg3 <- args[3] -arg4 <- args[4] -arg5 <- args[5] -arg6 <- args[6] -arg7 <- args[7] -arg8 <- args[8] - -library(caret) -load(arg1) - -RAWDATA <- dataX -RAWDATA$outcome <- dataY -rawData <- dataX -predictorNames <- names(rawData) - -isNum <- apply(rawData[,predictorNames, drop = FALSE], 2, is.numeric) -if(any(!isNum)) stop("all predictors in rawData should be numeric") - -colRate <- apply(rawData[, predictorNames, drop = FALSE], - 2, function(x) mean(is.na(x))) -colExclude <- colRate > 0.1 - if(any(colExclude)){ - predictorNames <- predictorNames[-which(colExclude)] - rawData <- RAWDATA[, c(predictorNames,"outcome")] - } else { - rawData <- RAWDATA - } - rowRate <- apply(rawData[, predictorNames, drop = FALSE], - 1, function(x) mean(is.na(x))) - - -rowExclude <- rowRate > 0 - if(any(rowExclude)){ - rawData <- rawData[!rowExclude, ] - ##hasMissing <- apply(rawData[, predictorNames, drop = FALSE], - ##1, function(x) mean(is.na(x))) - -############################################################################ - - -############################################################################### - } else { - rawData <- rawData[complete.cases(rawData),] - - } - -set.seed(2) - -#print(dim(dataX)) -#print(dim(rawData)) -#print(length(dataY)) - -nzv <- nearZeroVar(rawData[,1:(length(rawData) - 1)]) - if(length(nzv) > 0) { - #nzvVars <- names(rawData)[nzv] - rawData <- rawData[,-nzv] - #rawData$outcome <- dataY - } - -predictorNames <- names(rawData)[names(rawData) != "outcome"] - -dx <- rawData[,1:length(rawData)-1] -dy <- rawData[,length(rawData)] -corrThresh <- as.numeric(arg8) -highCorr <- findCorrelation(cor(dx, use = "pairwise.complete.obs"),corrThresh) -dx <- dx[, -highCorr] -subsets <- seq(1,length(dx),by=5) -normalization <- preProcess(dx) -dx <- predict(normalization, dx) -dx <- as.data.frame(dx) - -if (arg4 == "lmFuncs"){ -ctrl1 <- rfeControl(functions = lmFuncs, - method = arg5 , - repeats = as.numeric(arg6), - number = as.numeric(arg7), - verbose = FALSE) -} else if(arg4 == "rfFuncs"){ -ctrl1 <- rfeControl(functions = rfFuncs, - method = arg5 , - repeats = as.numeric(arg6), - number = as.numeric(arg7), - verbose = FALSE) -}else if (arg4 == "treebagFuncs"){ -ctrl1 <- rfeControl(functions = treebagFuncs, - method = arg5 , - repeats = as.numeric(arg6), - number = as.numeric(arg7), - verbose = FALSE) -}else { - -ctrl1 <- rfeControl(functions = nbFuncs, - method = arg5 , - repeats = as.numeric(arg6), - number = as.numeric(arg7), - verbose = FALSE) -} - - - - -Profile <- rfe(dx, dy,sizes = subsets,rfeControl = ctrl1) - -pred11 <- predictors(Profile) -save(Profile,file=arg2) -dataX <- rawData[,pred11] -dataY <- rawData$outcome - -save(dataX,dataY,file=arg3) -rm(dataX) -rm(dataY) - diff -r 5364cf43a8c1 -r 016c69bfb2a1 featureselect/tool_dependencies.xml --- a/featureselect/tool_dependencies.xml Sun Oct 02 05:36:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13 +0,0 @@ - - - - - $REPOSITORY_INSTALL_DIR - - - - - - - - diff -r 5364cf43a8c1 -r 016c69bfb2a1 featureselect/toolrfe.xml --- a/featureselect/toolrfe.xml Sun Oct 02 05:36:30 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,87 +0,0 @@ - - - This tool used for extract best feature subsets cantaining input data for model building. - - - - FEATURE_SELECTION_R - R_ROOT_DIR - R - caret-tools - -feature_selection.R $input $profile $finalset $function1 $resampling $repeat $number $corcutoff > /dev/null 2>&1 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -.. class:: infomark - -**RFE based feature selection for classification and regression** - -Input file must be RData file obtained by converting csv file in to RData. - -output "Selected_feature.RData" file used for model building purpose.While profile - -represents feature selection model. - -Correlation cutoff value is desired for choosing independent variables For example - -Cutoff value = 0.8 removes all descriptors sharing equal or highet correlation values. - -User may choose varous resampling methods in combination with repeats and times of resample. - - - - - - - - - - - - - - - - - - - - - - - diff -r 5364cf43a8c1 -r 016c69bfb2a1 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Jan 03 02:26:17 2017 -0500 @@ -0,0 +1,13 @@ + + + + + $REPOSITORY_INSTALL_DIR + + + + + + + + diff -r 5364cf43a8c1 -r 016c69bfb2a1 toolrfe.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/toolrfe.xml Tue Jan 03 02:26:17 2017 -0500 @@ -0,0 +1,92 @@ + + + This tool used for extract best feature subsets cantaining input data for model building. + + + + FEATURE_SELECTION_R + R_ROOT_DIR + R + caret-tools + +feature_selection.R $input $profile $finalset $function1 $resampling $repeat $number $corcutoff $SAMPLING> /dev/null 2>&1 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +.. class:: infomark + +**RFE based feature selection for classification and regression** + +Input file must be RData file obtained by converting csv file in to RData. + +output "Selected_feature.RData" file used for model building purpose.While profile + +represents feature selection model. + +Correlation cutoff value is desired for choosing independent variables For example + +Cutoff value = 0.8 removes all descriptors sharing equal or highet correlation values. + +User may choose varous resampling methods in combination with repeats and times of resample. + + + + + + + + + + + + + + + + + + + + + + +