Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 69ac507843530d76722471db7ddbf5f213a11aee

Authored by Efrain Gonzalez
1 parent ae780ea650
Exists in master

Don't use this code yet 

Updated to decrease time of search for cgeneID
Showing 1 changed file with 29 additions and 11 deletions   Show diff stats
... ... @@ -104,20 +104,38 @@ NAFIXING <- function(GIDNAM){
104 104 }
105 105  
106 106 #4#Function for changing the gene ID to gene name
107   -cgeneID <- function(GeneName,DATA){
108   - colGene <- dim(GeneName)[2]
109   - j <- 1
110   - for(j in 1:colGene){
111   - chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,])
112   - if(is.na(sum(chngsreq))==FALSE){
113   - if(sum(chngsreq) > 0){
114   - DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
  107 +cgeneID2 <- function(GeneName,DATA){
  108 + nj <- t(GeneName)
  109 + nq <- t(DATA)
  110 + colGene <- dim(nj)[2]
  111 + colDATA <- dim(nq)[2]
  112 + j <- 1
  113 + for(j in 1:colDATA){
  114 + #where is that gene id located within the GPL file
  115 + chngreq <- grep(paste0("^",nq[1,j],"$"),nj[1,])
  116 + if(is.na(sum(chngreq))==FALSE){
  117 + if(sum(chngreq) > 0){
  118 + nq[1,j] <- gsub(paste0("^",nq[1,j],"$"),nj[2,chngreq],nq[1,j])
  119 + }
115 120 }
  121 + j <- j + 1
116 122 }
117   - j = j+1
118   - }
119   - DATA
  123 + nq
120 124 }
  125 +#cgeneID <- function(GeneName,DATA){
  126 +# colGene <- dim(GeneName)[2]
  127 +# j <- 1
  128 +# for(j in 1:colGene){
  129 +# chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,])
  130 +# if(is.na(sum(chngsreq))==FALSE){
  131 +# if(sum(chngsreq) > 0){
  132 +# DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
  133 +# }
  134 +# }
  135 +# j = j+1
  136 +# }
  137 +# DATA
  138 +#}
121 139  
122 140 #5#Function for adjusting the gene names
123 141 gcnames <- function(DiData,usecol=1){