view tools/stats/plot_from_lda.xml @ 2:c2a356708570

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:45:42 -0500
parents 9071e359b9a3
children
line wrap: on
line source

<tool id="plot_for_lda_output1" name="Draw ROC plot" version="1.0.1">
	<description>on "Perform LDA" output</description>
	<command interpreter="sh">r_wrapper.sh $script_file</command>

	<inputs>
		<param format="txt" name="input" type="data" label="Source file"> </param>
		<param name="my_title" size="30" type="text" value="My Figure" label="Title of your plot" help="See syntax below"> </param>
		<param name="X_axis" size="30" type="text" value="Text for X axis" label="Legend of X axis in your plot" help="See syntax below"> </param>
		<param name="Y_axis" size="30" type="text" value="Text for Y axis" label="Legend of Y axis in your plot" help="See syntax below"> </param>
	</inputs>
	<outputs>
		<data format="pdf" name="pdf_output" />
	</outputs>

	<tests>
		<test>
			<param name="input" value="lda_analy_output.txt"/>
			<param name="my_title" value="Test Plot1"/>
			<param name="X_axis" value="Test Plot2"/>
			<param name="Y_axis" value="Test Plot3"/>
			<output name="pdf_output" file="plot_for_lda_output.pdf"/>
		</test>
	</tests>

    <configfiles>
            <configfile name="script_file">

        rm(list = objects() )

        ############# FORMAT X DATA #########################
        format&lt;-function(data) {
            ind=NULL
            for(i in 1 : ncol(data)){
                if (is.na(data[nrow(data),i])) {
                    ind&lt;-c(ind,i)
                }
            }
            #print(is.null(ind))
            if (!is.null(ind)) {
                data&lt;-data[,-c(ind)]
            }

            data
        }

        ########GET RESPONSES ###############################
        get_resp&lt;- function(data) {
            resp1&lt;-as.vector(data[,ncol(data)])
                resp=numeric(length(resp1))
            for (i in 1:length(resp1)) {
                if (resp1[i]=="Control ") {
                    resp[i] = 0
                }
                if (resp1[i]=="XLMR ") {
                    resp[i] = 1
                }
            }
                return(resp)
        }

        ######## CHARS TO NUMBERS ###########################
        f_to_numbers&lt;- function(F) { 
            ind&lt;-NULL
            G&lt;-matrix(0,nrow(F), ncol(F))
            for (i in 1:nrow(F)) {
                for (j in 1:ncol(F)) {
                    G[i,j]&lt;-as.integer(F[i,j])
                }
            }
            return(G)
        }

        ###################NORMALIZING#########################
        norm &lt;- function(M, a=NULL, b=NULL) {
            C&lt;-NULL
            ind&lt;-NULL

            for (i in 1: ncol(M)) {
                if (sd(M[,i])!=0) {
                    M[,i]&lt;-(M[,i]-mean(M[,i]))/sd(M[,i])
                }
                #   else {print(mean(M[,i]))}   
            }
            return(M)
        }

        ##### LDA DIRECTIONS #################################
        lda_dec &lt;- function(data, k){
            priors=numeric(k)
            grandmean&lt;-numeric(ncol(data)-1)
            means=matrix(0,k,ncol(data)-1)
            B = matrix(0, ncol(data)-1, ncol(data)-1)
            N=nrow(data)
            for (i in 1:k){
                priors[i]=sum(data[,1]==i)/N
                grp=subset(data,data\$group==i)
                means[i,]=mean(grp[,2:ncol(data)])
                #print(means[i,])
                #print(priors[i])
                #print(priors[i]*means[i,])
                grandmean = priors[i]*means[i,] + grandmean           
            }

            for (i in 1:k) {
                B= B + priors[i]*((means[i,]-grandmean)%*%t(means[i,]-grandmean))
            }
    
            W = var(data[,2:ncol(data)])
            svdW = svd(W)
            inv_sqrtW =solve(svdW\$v %*% diag(sqrt(svdW\$d)) %*% t(svdW\$v))
            B_star= t(inv_sqrtW)%*%B%*%inv_sqrtW
            B_star_decomp = svd(B_star)
            directions  = inv_sqrtW%*%B_star_decomp\$v
            return( list(directions, B_star_decomp\$d) )                          
        }

        ################ NAIVE BAYES FOR 1D SIR OR LDA ##############
        naive_bayes_classifier &lt;- function(resp, tr_data, test_data, k=2, tau) {
            tr_data=data.frame(resp=resp, dir=tr_data)
            means=numeric(k)
            #print(k)
            cl=numeric(k)
            predclass=numeric(length(test_data))
            for (i in 1:k) {
                grp = subset(tr_data, resp==i)
                means[i] = mean(grp\$dir)
            #print(i, means[i])  
            }
            cutoff = tau*means[1]+(1-tau)*means[2] 
            #print(tau)
            #print(means)
            #print(cutoff)
            if (cutoff&gt;means[1]) {
               cl[1]=1 
               cl[2]=2
            }
            else {
               cl[1]=2 
               cl[2]=1
            }

            for (i in 1:length(test_data)) {

                if (test_data[i] &lt;= cutoff) {
                    predclass[i] = cl[1]
            }
                else {
                    predclass[i] = cl[2] 
            }  
                }
            #print(means)
            #print(mean(means))
            #X11()
            #plot(test_data,pch=predclass, col=resp) 
            predclass
        }

        ################# EXTENDED ERROR RATES #################
        ext_error_rate &lt;- function(predclass, actualclass,msg=c("you forgot the message"), pr=1) {
                 er=sum(predclass != actualclass)/length(predclass)

                 matr&lt;-data.frame(predclass=predclass,actualclass=actualclass)
                 escapes = subset(matr, actualclass==1)
                 subjects = subset(matr, actualclass==2)      
                 er_esc=sum(escapes\$predclass != escapes\$actualclass)/length(escapes\$predclass) 
                 er_subj=sum(subjects\$predclass != subjects\$actualclass)/length(subjects\$predclass)   

                 if (pr==1) {
        #             print(paste(c(msg, 'overall : ', (1-er)*100, "%."),collapse=" "))
        #             print(paste(c(msg, 'within escapes : ', (1-er_esc)*100, "%."),collapse=" "))
        #             print(paste(c(msg, 'within subjects: ', (1-er_subj)*100, "%."),collapse=" ")) 
            }
            return(c((1-er)*100, (1-er_esc)*100, (1-er_subj)*100))                                                                                    
        }

        ## Main Function ##

	files_alias&lt;-c("${my_title}")
	tau=seq(0,1,by=0.005)
	nfiles=1
	f = c("${input}")

	rez_ext&lt;-list()
	for (i in 1:nfiles) {
		rez_ext[[i]]&lt;-dget(paste(f[i], sep="",collapse=""))
	}

	tau&lt;-tau[1:(length(tau)-1)]
	for (i in 1:nfiles) {
		rez_ext[[i]]&lt;-rez_ext[[i]][,1:(length(tau)-1)]
	}

	######## OPTIMAIL TAU ###########################

	#rez_ext

	rate&lt;-c("Optimal tau","Tr total", "Tr Y", "Tr X")

	m_tr&lt;-numeric(nfiles)
	m_xp22&lt;-numeric(nfiles)
	m_x&lt;-numeric(nfiles)

	for (i in 1:nfiles) {
		r&lt;-rez_ext[[i]]
		#tr
	#	rate&lt;-rbind(rate, c(files_alias[i]," "," "," ") )
		mm&lt;-which((r[3,])==max(r[3,]))

		m_tr[i]&lt;-mm[1]
		rate&lt;-rbind(rate,c(tau[m_tr[i]],r[,m_tr[i]]))
	}
	print(rate)

	pdf(file= paste("${pdf_output}"))

	plot(rez_ext[[i]][2,]~rez_ext[[i]][3,], xlim=c(0,100), ylim=c(0,100), xlab="${X_axis}   [1-FP(False Positive)]", ylab="${Y_axis}   [1-FP(False Positive)]", type="l", lty=1, col="blue", xaxt='n', yaxt='n')
	for (i in 1:nfiles) {
		lines(rez_ext[[i]][2,]~rez_ext[[i]][3,], xlab="${X_axis}   [1-FP(False Positive)]", ylab="${Y_axis}   [1-FP(False Positive)]", type="l", lty=1, col=i)   
		# pt=c(r,)
		points(x=rez_ext[[i]][3,m_tr[i]],y=rez_ext[[i]][2,m_tr[i]], pch=16, col=i)  
	}


	title(main="${my_title}", adj=0, cex.main=1.1)
	axis(2, at=c(0,20,40,60,80,100), labels=c('0','20','40','60','80','100%'))
	axis(1, at=c(0,20,40,60,80,100), labels=c('0','20','40','60','80','100%')) 

	#leg=c("10 kb","50 kb","100 kb")
	#legend("bottomleft",legend=leg , col=c(1,2,3), lty=c(1,1,1))

	#dev.off()

		</configfile>
	</configfiles>


	<help>
.. class:: infomark

**What it does**

This tool generates a Receiver Operating Characteristic (ROC) plot that shows LDA classification success rates for different values of the tuning parameter tau as Figure 3 in Carrel et al., 2006 (PMID: 17009873).

*Carrel L, Park C, Tyekucheva S, Dunn J, Chiaromonte F, et al. (2006) Genomic Environment Predicts Expression Patterns on the Human Inactive X Chromosome. PLoS Genet 2(9): e151. doi:10.1371/journal.pgen.0020151*

-----

.. class:: warningmark

**Note**

- Output from "Perform LDA" tool is used as input file for this tool.

</help>



</tool>