充分利用列

Question

所有匹配值我有一个名为toy像这样一个数据帧：

toy<- structure(list(id = 1:10, Name = c("A", "B", "C", "D", "E", "F", 
"G", "H", "A", "A"), Alt = c("X|Y|a", "O|P|dev", "A|W|are", "M|Q|G", 
"H|f|j|i_m|am", "L|E|B|i|j", "x|C|xx|yy", NA, NA, NA), Place = c(1L, 
4L, 8L, 12L, 13L, 8L, 3L, 1L, 1L, 1L)), .Names = c("id", "Name", 
"Alt", "Place"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-10L), spec = structure(list(cols = structure(list(id = structure(list(), class = c("collector_integer", 
"collector")), Name = structure(list(), class = c("collector_character", 
"collector")), Alt = structure(list(), class = c("collector_character", 
"collector")), Place = structure(list(), class = c("collector_integer", 
"collector"))), .Names = c("id", "Name", "Alt", "Place")), default = structure(list(), class = c("collector_guess", 
"collector"))), .Names = c("cols", "default"), class = "col_spec")) 

我的目的是要找到在Name列也是在Alt列匹配字符。我曾尝试使用dplyr如下：

toy_sep<-toy %>% separate(Alt , into=LETTERS[1:5],sep="\\|",extra="merge",remove=FALSE) %>% gather(Alias_id,Alias,A:E) %>% mutate(Match=match(Alias,Name)) 

从这个输出等。无论有匹配的样子：

matches<-toy_sep[complete.cases(toy_sep),] 

它提供了接近我想要的东西。但问题是match返回第一个位置，而我想要所有的匹配。在示例1中，在A的matches数据框的匹配列中返回，但我想要所有的ID。 A的id为9和10（来自toy dataframe中的id列）以及1.感谢您使用base/data.table/dplyr的任何帮助

添加所需的输出。请注意，右上角单元格中的数字不需要用“|”分隔。 ：

d_out<-structure(list(id = c(3L, 5L, 6L, 7L, 4L, 6L), Name = c("C", 
"E", "F", "G", "D", "F"), Alt = c("A|W|are", "H|f|j|i_m|am", 
"L|E|B|i|j", "x|C|xx|yy", "M|Q|G", "L|E|B|i|j"), Place = c(8L, 
13L, 8L, 3L, 12L, 8L), Alias_id = c("A", "A", "B", "B", "C", 
"C"), Alias = c("A", "H", "E", "C", "G", "B"), Match = c("1|9|10", 
"8", "5", "3", "7", "2")), class = c("tbl_df", "tbl", "data.frame" 
), row.names = c(NA, -6L), .Names = c("id", "Name", "Alt", "Place", 
"Alias_id", "Alias", "Match"), spec = structure(list(cols = structure(list(
    id = structure(list(), class = c("collector_integer", "collector" 
    )), Name = structure(list(), class = c("collector_character", 
    "collector")), Alt = structure(list(), class = c("collector_character", 
    "collector")), Place = structure(list(), class = c("collector_integer", 
    "collector")), Alias_id = structure(list(), class = c("collector_character", 
    "collector")), Alias = structure(list(), class = c("collector_character", 
    "collector")), Match = structure(list(), class = c("collector_character", 
    "collector"))), .Names = c("id", "Name", "Alt", "Place", 
"Alias_id", "Alias", "Match")), default = structure(list(), class = c("collector_guess", 
"collector"))), .Names = c("cols", "default"), class = "col_spec")) 

Answer 1

试试这个。

toy_sep<-toy %>% 
    separate(Alt , 
      into=LETTERS[1:5], 
      sep="\\|", 
      extra="merge", 
      remove=FALSE) %>% 
    gather(Alias_id,Alias,A:E) %>% 
    mutate(Match=apply(t(Alias), 
        2, 
        FUN = function(x){ 
         ind=grep(x,toy$Name) 
         ifelse(!is.na(sum(ind))&length(ind) >= 1 , 
           paste0(ind,collapse = "|"), 
           NA) 
         } 
        ) 
     ) 
    matches<-toy_sep[complete.cases(toy_sep),]