Efrain Gonzalez / Cleaning and Fixing Data with R

Download as
Browse Code ยป

Commit 39af88c5afa802b437df13de8a2b280baab041f2

Authored by Efrain Gonzalez
1 parent 8bfefd7afe
Exists in master

fixed issue with spaces and choosing the second name (UNTESTED)

Showing 1 changed file with 9 additions and 27 deletions   Show diff stats
... ... @@ -97,36 +97,18 @@ NAFIXING <- function(GIDNAM){
97 97 GIDNAM
98 98 }
99 99  
100   -##4#Function for changing the gene ID to gene name
101   -##cgeneID <- function(GeneName,DATA){
102   -## colGene <- dim(GeneName)[2]
103   -## j <- 1
104   -## for(j in 1:colGene){
105   -## chngsreq <- grep(GeneName[1,j],DATA[1,])
106   -## if(sum(chngsreq) > 0){
107   -## #DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq])
108   -## DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
109   -## }
110   -## j = j+1
111   -## }
112   -## DATA
113   -##}
114 100 #4#Function for changing the gene ID to gene name
115 101 cgeneID <- function(GeneName,DATA){
116 102 colGene <- dim(GeneName)[2]
117 103 j <- 1
118 104 for(j in 1:colGene){
119   - chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,])
120   - if(is.na(sum(chngsreq))==FALSE){
121   - if(sum(chngsreq) > 0){
122   - DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
123   - }
124   - }
125   - #if(sum(chngsreq) > 0){
126   - ##DATA[1,chngsreq] <- gsub(GeneName[1,j],GeneName[2,j],DATA[1,chngsreq])
127   - #DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
128   - #}
129   - j = j+1
  105 + chngsreq <- grep(paste0("^",GeneName[1,j],"$"),DATA[1,])
  106 + if(is.na(sum(chngsreq))==FALSE){
  107 + if(sum(chngsreq) > 0){
  108 + DATA[1,chngsreq] <- gsub(paste0("^",GeneName[1,j]),GeneName[2,j],DATA[1,chngsreq])
  109 + }
  110 + }
  111 + j = j+1
130 112 }
131 113 DATA
132 114 }
... ... @@ -138,9 +120,9 @@ gcnames &lt;- function(DiData,usecol=1){
138 120 nwnam <- rep("0",length.out=nuruns)
139 121 for(i in 1:nuruns){
140 122 if(length(strsplit(colnames(DiData)[i],"///")[[1]]) >= usecol){
141   - nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][usecol]
  123 + nwnam[i]=str_trim(strsplit(colnames(DiData)[i],"///")[[1]][usecol])
142 124 } else{
143   - nwnam[i]=strsplit(colnames(DiData)[i],"///")[[1]][1]
  125 + nwnam[i]=str_trim(strsplit(colnames(DiData)[i],"///")[[1]][1])
144 126 }
145 127  
146 128 }