zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Prevented data points with fewer than N observations from going off the edge of the plots 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@2257 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
rpoplin 2009-12-04 13:55:43 +00:00
parent 58937bf9ba
commit 2508deca37
2 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
R/plot_residualError_OtherCovariate.R
View File

@ -54,8 +54,12 @@ pdf(outfile, height=7, width=7)
hst=subset(data.frame(e$Covariate, e$nBases), e.nBases != 0)
hst2=subset(data.frame(f$Covariate, f$nBases), f.nBases != 0)
if( is.numeric(c$Covariate) ) {
plot(hst$e.Covariate, hst$e.nBases, type="h", lwd=2, main=paste(covariateName,"histogram"), xlab=covariateName, ylab="Count",yaxt="n",xlim=c(min(c$Covariate),max(c$Covariate)))
points(hst2$f.Covariate, hst2$f.nBases, type="h", lwd=2, col="cornflowerblue")
if( length(hst$e.Covariate) == 0 ) {
plot(hst2$f.Covariate, hst2$f.nBases, type="h", lwd=2, col="cornflowerblue", main=paste(covariateName,"histogram"), xlab=covariateName, ylab="Count",yaxt="n",xlim=c(min(c$Covariate),max(c$Covariate)))
} else {
plot(hst$e.Covariate, hst$e.nBases, type="h", lwd=2, main=paste(covariateName,"histogram"), xlab=covariateName, ylab="Count",yaxt="n",xlim=c(min(c$Covariate),max(c$Covariate)))
points(hst2$f.Covariate, hst2$f.nBases, type="h", lwd=2, col="cornflowerblue")
}
axis(2,axTicks(2), format(axTicks(2), scientific=F))
} else { # Dinuc (and other non-numeric covariates) are different to make their plots look nice
hst=subset(data.frame(c$Covariate, c$nBases), c.nBases != 0)

2
R/plot_residualError_QualityScoreCovariate.R
View File

@ -21,7 +21,7 @@ e <- rbind(d.good, d.1000, d.10000)
rmseGood = sqrt(sum((d.good$Qempirical-d.good$Qreported)^2 * d.good$nBases) / sum(d.good$nBases) )
rmseAll = sqrt(sum((e$Qempirical-e$Qreported)^2 * e$nBases) / sum(e$nBases) )
theTitle = paste("RMSE_good = ", round(rmseGood,digits=3), ", RMSE_all = ", round(rmseAll,digits=3))
if (length(t$nBases) == length(d.good$nBases) ) {
if( length(t$nBases) - length(f$nBases) == length(d.good$nBases) ) {
theTitle = paste("RMSE = ", round(rmseAll,digits=3));
}
plot(d.good$Qreported, d.good$Qempirical, type="p", col="blue", main=theTitle, xlim=c(0,40), ylim=c(0,40), pch=16, xlab="Reported quality score", ylab="Empirical quality score")