Question

我正在尝试组合两个表，并在两个表之间按组提取值。

我有test1表：

structure(list(Similarity = c(999L, 888L, 756L, 879L, 567L, 567L), Peak = c(797L, 833L,999L, 798L, 834L, 444L), Name = structure(c(2L, 5L, 6L, 1L, 3L, 4L), .Label = c("Benzene", "Cyclopentane", "Hexadecane", "Nafhtalene", "Tetradecene", "dodecadiene"), class = "factor"),Sample1 = c(22237L, 86032349L, NA, NA, NA, 3333L), Sample2 = c(444567L, 
NA, NA, NA, 115127L, 22222L)), .Names = c("Similarity", "Peak", "Name", "Sample1", "Sample2"), class = "data.frame", row.names = c(NA, -6L))

和test2表：

structure(list(Similarity = c(757L, 859L, 999L, 879L, 577L), 
Peak = c(798L, 797L, 999L, 834L, 833L), Name = structure(c(1L, 2L, 5L, 3L, 4L), .Label = c("Benzene", "Cyclopentane", "Hexadecane","Tetradecene", "dodecadiene"), class ="factor"),Sample3 = c(NA, 115127L, NA, NA, 86032349L), Sample4 = c(NA, 43359706L, NA,115127L, NA)),.Names = c("Similarity", "Peak", "Name", "Sample3", "Sample4"), class = "data.frame",row.names = c(NA, -5L))

当我合并两张桌子时：

cbind(test1,test2)

structure(list(Row.names = structure(c("1", "2", "3", "4", "5"), class ="AsIs"),Similarity.x = c(999L, 888L, 756L, 879L, 567L), Peak.x = c(797L, 833L, 999L, 798L, 834L), Name.x = structure(c(2L, 5L, 6L, 1L, 3L),.Label=c("Benzene","Cyclopentane","Hexadecane", "Nafhtalene", "Tetradecene", "dodecadiene"), class = "factor"), Sample1 = c(22237L, 86032349L, NA, NA, NA), Sample2 = c(444567L, NA, NA, NA, 115127L), Similarity.y = c(757L, 859L, 999L,879L, 577L), Peak.y = c(798L, 797L, 999L, 834L, 833L), Name.y = structure(c(1L,2L, 5L, 3L, 4L), .Label = c("Benzene", "Cyclopentane", "Hexadecane", "Tetradecene", "dodecadiene"), class = "factor"), Sample3 = c(NA, 115127L, NA, NA, 86032349L), Sample4 = c(NA, 43359706L, NA,115127L, NA)), .Names = c("Row.names", "Similarity.x", "Peak.x","Name.x", "Sample1", "Sample2", "Similarity.y", "Peak.y", "Name.y","Sample3", "Sample4"), row.names = c(NA, -5L), class = "data.frame")

我需要将名称相等的行组合在一起，维护相应的样本并提取最大相似度。

类似的东西：

structure(list(Similarity = c(757L, 859L, 999L, 879L, 577L, 567L), Peak = c(798L, 797L, 999L, 834L, 833L, 444L), Name = structure(c(1L, 2L, 6L, 3L, 5L, 4L), .Label = c("Benzene", "Cyclopentane", "Hexadecane","Nafhtalene", "Tetradecene", "dodecadiene"), class = "factor"), Sample1 = c(NA, 22237L, NA, NA, 86032349L, 3333L), Sample2 = c(NA,444567L, NA, 115127L, NA, 22222L), Sample3 = c(NA, 115127L,NA, NA, 86032349L, NA), Sample4 = c(NA, 43359706L, NA, 115127L,NA, NA)), .Names = c("Similarity", "Peak", "Name", "Sample1", "Sample2", "Sample3", "Sample4"), class ="data.frame", row.names = c(NA,-6L))

有什么建议吗？

Answer 1

> x <- merge(test1, test2, by='Name', all=TRUE)
> x$Similarity <- pmax(x$Similarity.x, x$Similarity.y, na.rm=TRUE)
> x$Peak <- x$Peak.x

> x[c('Name','Similarity', 'Peak', 'Sample1', 'Sample2', 'Sample3', 'Sample4')]
          Name Similarity Peak  Sample1 Sample2  Sample3  Sample4
1      Benzene        879  798       NA      NA       NA       NA
2 Cyclopentane        999  797    22237  444567   115127 43359706
3   Hexadecane        879  834       NA  115127       NA   115127
4   Nafhtalene        567  444     3333   22222       NA       NA
5  Tetradecene        888  833 86032349      NA 86032349       NA
6  dodecadiene        999  999       NA      NA       NA       NA

在R中按组合并两个表

1 个答案: