Mercurial > repos > deepakjadmin > feature_selection_test1
changeset 1:69b8598d9338 draft
Uploaded
| author | deepakjadmin |
|---|---|
| date | Wed, 23 Mar 2016 04:53:29 -0400 |
| parents | 16c9aaf658e6 |
| children | 31cd51e67666 |
| files | feature_selection.R featureselect.zip tool_dependencies.xml toolrfe.xml |
| diffstat | 4 files changed, 223 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/feature_selection.R Wed Mar 23 04:53:29 2016 -0400 @@ -0,0 +1,123 @@ +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$outcome <- dataY +rawData <- dataX +predictorNames <- names(rawData) + +isNum <- apply(rawData[,predictorNames, drop = FALSE], 2, is.numeric) +if(any(!isNum)) stop("all predictors in rawData should be numeric") + +colRate <- apply(rawData[, predictorNames, drop = FALSE], + 2, function(x) mean(is.na(x))) +colExclude <- colRate > 0.01 + if(any(colExclude)){ + predictorNames <- predictorNames[-which(colExclude)] + rawData <- RAWDATA[, c(predictorNames,"outcome")] + } else { + rawData <- RAWDATA + } + rowRate <- apply(rawData[, predictorNames, drop = FALSE], + 1, function(x) mean(is.na(x))) + +rowno <- dim(rawData)[1] +if (rowno <= 1000){ +cutoff <- rowno / (rowno * 100) +} else if (rowno > 1000 & rowno <= 5000) { +cutoff <- rowno / (rowno * 100 * 0.5 ) +} else { +cutoff <- rowno / (rowno * 100 * 0.5 * 0.5) +} +rowExclude <- rowRate > cutoff + if(any(rowExclude)){ + rawData <- rawData[!rowExclude, ] + ##hasMissing <- apply(rawData[, predictorNames, drop = FALSE], + ##1, function(x) mean(is.na(x))) + +############################################################################ + + +############################################################################### + } else { + rawData <- rawData[complete.cases(rawData),] + + } + +set.seed(2) + +#print(dim(dataX)) +#print(dim(rawData)) +#print(length(dataY)) + +nzv <- nearZeroVar(rawData[,1:(length(rawData) - 1)]) + if(length(nzv) > 0) { + #nzvVars <- names(rawData)[nzv] + rawData <- rawData[,-nzv] + #rawData$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$outcome + +save(dataX,dataY,file=arg3) +rm(dataX) +rm(dataY) +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Wed Mar 23 04:53:29 2016 -0400 @@ -0,0 +1,13 @@ +<?xml version="1.0"?> +<tool_dependency> + +<set_environment version="1.0"> + <environment_variable name="FEATURE_SELECTION_R" action="set_to">$REPOSITORY_INSTALL_DIR</environment_variable> + </set_environment> + <package name="R" version="3.2.0"> + <repository changeset_revision="7833b0ebf8d6" name="package_r_3_2_0" owner="iuc" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + <package name="caret-tools" version="1.0.0"> + <repository changeset_revision="e5faefaf1037" name="caret_tool_test1" owner="deepakjadmin" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/toolrfe.xml Wed Mar 23 04:53:29 2016 -0400 @@ -0,0 +1,87 @@ +<tool id="featureSelectR" name="Feature Selection" > +<description> + This tool used for extract best feature subsets cantaining input data for model building. +</description> +<!--command interpreter="bash">step3run.sh $file1 $model $output1 2>/dev/null </command--> +<requirements> + <requirement type="set_environment">FEATURE_SELECTION_R</requirement> + <requirement type="set_environment">R_ROOT_DIR</requirement> + <requirement type="package" version="3.2.0">R</requirement> + <requirement type="package" version="1.0.0">caret-tools</requirement> +</requirements> +<command interpreter="Rscript">feature_selection.R $input $profile $finalset $function1 $resampling $repeat $number $corcutoff > /dev/null 2>&1 </command> + +<inputs> +<param name="input" format="RData" type="data" label="Select input data file" help="input .RData file" /> +<param name="function1" type="select" display="radio" label="Select appropriate function for algorithm" > + <option value="rfFuncs" selected="true">random forest based function </option> + <option value="lmFuncs">linear model based function</option> + <option value="treebagFuncs">treebag(CART) based function</option> + <option value="nbFuncs">neive bayes based function</option> +</param> + +<param name="corcutoff" type="float" value= "0.8" min="0.0" max = "1.0" label="Select correlation cutoff" help="values bewteen 0-1. fileds above cufoff value removed from data " /> +<param name="resampling" type="select" label="Select appropriate resampling method" > + <option value="repeatedcv" selected="true">repeatedcv </option> + <option value="boot">boot</option> + <option value="cv">cv</option> + <option value="boot632">boot632</option> +</param> + <param name="repeat" type="select" label="Set Number of times to repeat" help="default is 3 "> + <option value="3" selected="true">3</option> + <option value="1">1</option> + <option value="5">5</option> + <option value="10">10</option> + </param> +<param name="number" type="select" label="Set Number of times Resample" help="default is 10"> + <option value="10" selected="true">10</option> + <option value="5">5</option> + <option value="15">15</option> + <option value="20">20</option> + <option value="25">25</option> + </param> + +</inputs> +<outputs> +<data format="RData" name="profile" label="$function1-profile" /> +<data format="RData" name="finalset" label="Selected_feature.RData "/> +</outputs> +<help> +.. 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. + + + +</help> + + +<tests> +<test> + <param name="input" value="testinput.RData"/> + <param name="function1" value="rfFuncs" /> + <param name="corcutoff" value="0.6" /> + <param name="resampling" value="repeatedcv" /> + <param name="repeat" value="1" /> + <param name="number" value="5" /> + + + <output name="profile" file="rfprofile.RData" compare="sim_size" delta="2000000" /> + <output name="finalset" file="selected_fet.RData" compare="sim_size" delta="2000000"/> + </test> +</tests> + + +</tool>