在名称级别创建长字符串

Question

我想按规则对级别名称进行修改，但我在下面有一个问题：

我的数据; intially DF变量是类矩阵我改变了它

df <- data.frame(x = c("P27C", "P31B", "P12E", "P3E", "P7A", "P7D", "P2A", "P7D", 
"P34", "P10C"), 
      y = rnorm(10), stringsAsFactors = F) 

s<-c("P27CvsP31B","P27CvsP3C","P27CvsP3E","P27CvsP6B","P27CvsP7A","P27CvsP7C", 
"P27DvsP27E","P27DvsP2B","P27DvsP31A","P27DvsP31B","P27DvsP3D","P27DvsP7D", 
"P27EvsP2A","P27EvsP2B","P27EvsP2E","P27EvsP2F","P27EvsP2G","P27EvsP34", 
"P7AvsP7H","P7BvsP7D","P7CvsP7G","P7DvsP7E","P7DvsP7F","P7DvsP7G","P7DvsP7H") 

df 

df$z <- lapply(df$x, grep, s, value = T) 

# gives you the matches but empty slots for a missing value like "P12E" 

df 

for (r in 1:nrow(df)) { 
    if (length(df$z[[r]]) == 0) { 
     df$z[[r]] <- df$x[[r]] 
     } 
    else { 
     df$z[[r]] <- df$z[[r]] 
    } 
} 

# restores the original name of unmatched values 

df$z 

#Rename but in list format!!! 

和我的期望的输出是：

 x   y                 z 
1 P27C 2.22354499 "P27CvsP31B, P27CvsP3C, P27CvsP3E, P27CvsP6B, P27CvsP7A, P27CvsP7C" 
2 P31B 0.89197064           "P27CvsP31B, P27DvsP31B" 
3 P12E -0.02313754                "P12E" 
4 P3E 0.69916446               "P27CvsP3E" 
5 P7A -0.44895512            "P27CvsP7A, P7AvsP7H" 
6 P7D 1.77619979  "P27DvsP7D, P7BvsP7D, P7DvsP7E, P7DvsP7F, P7DvsP7G, P7DvsP7H" 
7 P2A -0.18261732               "P27EvsP2A" 
8 P7D 0.12025524  "P27DvsP7D, P7BvsP7D, P7DvsP7E, P7DvsP7F, P7DvsP7G, P7DvsP7H" 
9 P34 -0.13434265               "P27EvsP34" 
10 P10C 0.19971201                "P10C" 

由于

Answer 1

看起来有点难看与嵌套sapply。它沿着df的x列循环，并与您的矢量s匹配所有条目，创建匹配结果列表。第二个sapply在该列表上循环并粘贴所有条目。如果没有匹配，则它返回一个空单元格，我们通过在其位置替换df$x条目来处理。

df$z <- sapply(sapply(df$x, function(i) s[grepl(i, s)]), paste, collapse = ',') 
df$z[df$z == ''] <- df$x[df$z == ''] 
df 

#  x   y               z 
#1 P27C -0.95290496 P27CvsP31B,P27CvsP3C,P27CvsP3E,P27CvsP6B,P27CvsP7A,P27CvsP7C 
#2 P31B 1.62237939          P27CvsP31B,P27DvsP31B 
#3 P12E 2.60014202               P12E 
#4 P3E 0.13964851             P27CvsP3E 
#5 P7A -1.35071967           P27CvsP7A,P7AvsP7H 
#6 P7D 0.79893102  P27DvsP7D,P7BvsP7D,P7DvsP7E,P7DvsP7F,P7DvsP7G,P7DvsP7H 
#7 P2A -1.55499584             P27EvsP2A 
#8 P7D 0.46372006  P27DvsP7D,P7BvsP7D,P7DvsP7E,P7DvsP7F,P7DvsP7G,P7DvsP7H 
#9 P34 0.05242956             P27EvsP34 
#10 P10C -0.20203180               P10C 

编辑

基于@ akrun的建议，与data.table一个选择是，

library(data.table) 
setDT(df)[, z := unlist(lapply(x, function(y) toString(grep(y, s, value = TRUE))))][z=="", z := x][]