将数据重塑为CSV

Question

我正在编写一个脚本来创建用于分析的csv文件。运行脚本时，它为OPA 5701提供1个csv文件，为6561提供1个。这是脚本的两个部分之间的唯一区别。

##Samplesheet for GS0005701
rows<-unique(samples$Sample_Name)
samplesheet<-rows
opa.panels<-sort(unique(samples$Pool_ID))
for ( i in 1:length(opa.panels)){
  samps<-samples[samples$Pool_ID == opa.panels[i],]
  idx<-match(samps$Sample_Name,rows)
  samplesheet<-cbind(samplesheet,samps$Sentrix_ID[idx],samps$Sentrix_Position[idx])
}
colnames(samplesheet)[2:(length(opa.panels)*2+1)]<-c("SentrixBarcode_A","SentrixPosition_A","SentrixBarcode_B","SentrixPosition_B","SentrixBarcode_C","SentrixPosition_C","SentrixBarcode_D","SentrixPosition_D")[1:(length(opa.panels)*2)]
colnames(samplesheet)[1]<-"Sample_Name"
idx<-match(rows,samples$Sample_Name)
samplesheet<-cbind(samplesheet,samples[idx,c("Sample_Group","NorTum","Sample")])
ss_header<-c("[Header]","Investigator Name,Sander","Project Name,HNPCC_NA_MYH","Experiment Name,OPA1+2+3+4","Date,5062012","[Manifests]")
for (i in 1:length(opa.panels)) ss_header<-c(ss_header,paste(LETTERS[i],opa.panels[i],sep=","))
ss_header<-c(ss_header,"[Data]")
writeLines(ss_header,"Samplesheet5701.csv")
write.table(samplesheet,file="Samplesheet5701.csv",sep=",",row.names=FALSE,quote=FALSE,append=TRUE,na="")

##Samplesheet for GS0006561-OPA
rows2<-unique(samples2$Sample_Name)
samplesheet2<-rows2
opa.panels2<-sort(unique(samples2$Pool_ID))
for ( j in 1:length(opa.panels2)){
  samps2<-samples2[samples2$Pool_ID == opa.panels2[j],]
  idx2<-match(samps2$Sample_Name,rows2)
  samplesheet2<-cbind(samplesheet2,samps2$Sentrix_ID[idx2],samps2$Sentrix_Position[idx2])
}
colnames(samplesheet2)[2:(length(opa.panels)*2+1)]<-c("SentrixBarcode_A","SentrixPosition_A","SentrixBarcode_B","SentrixPosition_B","SentrixBarcode_C","SentrixPosition_C","SentrixBarcode_D","SentrixPosition_D")[1:(length(opa.panels)*2)]
colnames(samplesheet2)[1]<-"Sample_Name"
idx2<-match(rows2,samples2$Sample_Name)
samplesheet2<-cbind(samplesheet2,samples2[idx2,c("Sample_Group","NorTum","Sample")])
ss_header<-c("[Header]","Investigator Name,Sander","Project Name,HNPCC_NA_MYH","Experiment Name,OPA1+2+3+4","Date,5062012","[Manifests]")
for (j in 1:length(opa.panels2)) ss_header<-c(ss_header,paste(LETTERS[j],opa.panels2[j],sep=","))
ss_header<-c(ss_header,"[Data]")
writeLines(ss_header,"samplesheet6561.csv")
write.table(samplesheet2,file="Samplesheet6561.csv",sep=",",row.names=FALSE,quote=FALSE,append=TRUE,na="")

## Samplesheet GS0005701部件创建data.frame。而## Samplesheet GS0006561创建matrix。使用相同的代码和相同的输入数据。

输入数据如下所示：

复制粘贴：

    Sample  Sample_Name Sample_Group    NorTum  Sentrix_ID  Sentrix_Position    Pool_ID Folderdate
1   00-04193    00-04193N   HNPCC_UV    N   1495421 R007_C012   GS0006564-OPA   Exp060410
2   00-04193    00-04193N   HNPCC_UV    N   1495447 R007_C012   GS0006562-OPA   Exp060410
3   00-04193    00-04193N   HNPCC_UV    N   1495447 R007_C006   GS0006561-OPA   Exp060410
4   00-04193    00-04193N   HNPCC_UV    N   1495421 R007_C006   GS0006563-OPA   Exp060410
5   00-04193    00-04193N   HNPCC_UV    N   1460498 R007_C005   GS0006561-OPA   Exp060516
6   00-04193    00-04193N   HNPCC_UV    N   1460498 R007_C012   GS0006564-OPA   Exp060516

我知道这是一个难以回答的问题，但我希望有人可以给我一个关于1代码如何创建data.frame而另一个是矩阵的提示。

非常感谢提前！

Answer 1

这个问题的正确答案是索引部分的交换。

idx<-match(samps$Sample_Name,rows)

更改为：

idx<-match(rows,samps$Sample_Code) 

因此行的长度与Sample_Code的长度相同。