Mercurial > repos > anmoljh > feature_selection

changeset 0:b4d2524e79ab draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit a1f4dd8eb560c649391ada1a6bb9505893a35272
author anmoljh
date Fri, 01 Jun 2018 05:16:19 -0400
parents
children f3aeeb15d4cc
files feature_selection.R feature_selection.xml tool_dependencies.xml
diffstat 3 files changed, 269 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/feature_selection.R	Fri Jun 01 05:16:19 2018 -0400
@@ -0,0 +1,164 @@
+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]
+arg10 <- args[10]
+library(caret)
+library(doMC)
+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$outcome <- dataY
+    				} 
+    
+predictorNames <- names(rawData)[names(rawData) != "outcome"]
+   
+dx <- rawData[,1:length(rawData)-1]
+dy <- rawData[,length(rawData)]
+corrThresh <- as.numeric(arg8)
+highCorr <- findCorrelation(cor(dx, use = "pairwise.complete.obs"),corrThresh)
+dx <- dx[, -highCorr]
+subsets <- seq(1,length(dx),by=5)
+normalization <- preProcess(dx)
+dx <- predict(normalization, dx)
+dx <- as.data.frame(dx)
+
+if (arg4 == "lmFuncs"){
+ctrl1 <- rfeControl(functions = lmFuncs,
+                   method = arg5 ,
+                   repeats = as.numeric(arg6),
+                   number = as.numeric(arg7),
+                   verbose = FALSE)
+} else if(arg4 == "rfFuncs"){
+ctrl1 <- rfeControl(functions = rfFuncs,
+                   method = arg5 ,
+                   repeats = as.numeric(arg6),
+                   number = as.numeric(arg7),
+                   verbose = FALSE)
+}else if (arg4 == "treebagFuncs"){
+ctrl1 <- rfeControl(functions = treebagFuncs,
+                   method = arg5 ,
+                   repeats = as.numeric(arg6),
+                   number = as.numeric(arg7),
+                   verbose = FALSE)
+}else {
+
+ctrl1 <- rfeControl(functions = nbFuncs,
+                   method = arg5 ,
+                   repeats = as.numeric(arg6),
+                   number = as.numeric(arg7),
+                   verbose = FALSE)
+}
+
+
+
+if (as.numeric(arg10) == 1){ 
+Profile <- rfe(dx, dy,sizes = subsets,rfeControl = ctrl1)
+
+pred11 <- predictors(Profile)
+save(Profile,file=arg2)
+dataX <- rawData[,pred11]
+dataY <- rawData$outcome
+
+save(dataX,dataY,file=arg3)
+rm(dataX)
+rm(dataY)
+} else if (as.numeric(arg10) > 1){
+registerDoMC(cores = as.numeric(arg10))
+
+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)
+} else { stop("something went wrong. please see the parameters")}  
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/feature_selection.xml	Fri Jun 01 05:16:19 2018 -0400
@@ -0,0 +1,96 @@
+<tool id="feature_selection" name="Feature Selector" version="1.0">
+<description>
+ 	This tool selects best features which are used as input for model building.     
+</description>
+
+<requirements>
+    	<requirement type="package" version="3.2.1">R</requirement>
+    	<requirement type="package" version="1.0">carettools</requirement>
+</requirements>
+
+<stdio>
+        <exit_code range="1:" />
+</stdio>
+
+<command interpreter="Rscript">feature_selection.R $input $profile $finalset $function1 $resampling $repeat $number $corcutoff $SAMPLING \${GALAXY_SLOTS:-1} >/dev/null 2>&amp;1 </command>
+
+<inputs>
+	<param name="input"  type="data" format="rdata" label="Select input data file" help="input .RData file" />
+	<param name="SAMPLING" type="select"  label="Select Sampling Method for imbalanced data" help="Defualt is with No sampling. you may choose downsample or upsample" >
+                <option value="garBage" selected="true">No Sampling</option>
+                <option value="downsampling">downsample</option>
+                <option value="upsampling">upsample</option>
+        </param>
+	<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="5">5</option>
+               <option value="7">7</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="data" name="profile"  label="$function1-profile" />
+	<data format="rdata" name="finalset" label="Selected_feature.RData "/>
+</outputs>
+
+<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" />
+          <param name="SAMPLING"  value="garb" />
+          <param name="cores"  value="1" />
+          <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>
+
+<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>
+
+
+
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Fri Jun 01 05:16:19 2018 -0400
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="R" version="3.2.1">
+	    <repository changeset_revision="d9f7d84125b7" name="package_r_3_2_1" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu/" />
+    </package>
+    <package name="carettools" version="1.0">
+	    <repository changeset_revision="d8ebc06d55ca" name="package_carettools_1_0" owner="anmoljh" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu/" />
+    </package>
+</tool_dependency>