R使用for循环

如何解决R使用for循环

我有以下数据帧列表。

list(structure(list(SrlNo = c(248L,273L,282L,284L),VendorCode = c("V001889","V000590","V001578","V001836"),SiteDetails = c("value add sites as per annexure","milan et mega bus shelter","backdrop","black drop with black masking"
),City = c("","","")),.Names = c("SrlNo","VendorCode","SiteDetails","City"),row.names = c("248","273","282","284"
),class = "data.frame"),structure(list(SrlNo = 59135:59136,VendorCode = c("V000072","V000072"),SiteDetails = c("transportation charges-gst- rece cost for 24 paragana(south)","transportation charges-gst- rece  cost for 24 paragana (south)"
    ),City = c("24 Paragana(South)","24 Paragana(South)")),row.names = c("59127","59128"),structure(list(SrlNo = c(34595L,34609L,34661L,34678L),VendorCode = c("V002446","V000931","V000094","V002240"),SiteDetails = c("taki road","barasat flyover","madhyamgram flyover fcg chowrasta","madhyamgram bt college"
),City = c("24 Pargana North","24 Pargana North","24 Pargana North")),row.names = c("34587","34601","34653","34670"),class = "data.frame"))

使用agrep，我试图将相似的探测站点详细信息分组在一起。我正在使用以下代码：

for (e in ern) {
  x <- e$SiteDetails
  x <- x[x!=""]
  groups <- list()
  i <- 1
  while(length(x) > 0)
  {
    id <- agrep(x[1],x,ignore.case = TRUE,max.distance = 0.001)
    groups[[i]] <- x[id]
    x <- x[-id]
    i <- i + 1
  }
  Indx <- 1:length(groups)
  aa <- with(e,rep(Indx,vapply(groups,length,1L)))
  bb <- unlist(groups)
  cc <- data.frame(aa,bb)
  #cbind(e,group=cc$aa[match(e$SiteDetails,cc$bb)])
  e$group <- cc$aa[match(e$SiteDetails,cc$bb)]
  #print(cc$aa[match(e$SiteDetails,cc$bb)])
  #print(e$VendorCode)
}

使用上面的代码，我遍历列表中的每个数据框，对站点详细信息列进行分组，并且能够打印分组值。但是，当我要将组附加到数据帧时，没有响应/也没有错误。我无法在for循环中创建一个名为group的新列。

e$group <- cc$aa[match(e$SiteDetails,cc$bb)]

我已经尝试了上述行的各种组合，例如ern[[e]]和cbind，但是它们不起作用。

解决方法

您的e循环中的for与原始ern列表没有任何联系，因此，无法在列表中添加任何新信息。您应该改为遍历列表的索引。

for (e in seq_along(ern)) {
  x <- ern[[e]]$SiteDetails
  x <- x[x!=""]
  groups <- list()
  i <- 1
  while(length(x) > 0)
  {
    id <- agrep(x[1],x,ignore.case = TRUE,max.distance = 0.001)
    groups[[i]] <- x[id]
    x <- x[-id]
    i <- i + 1
  }
  Indx <- 1:length(groups)
  aa <- with(ern[[e]],rep(Indx,vapply(groups,length,1L)))
  bb <- unlist(groups)
  cc <- data.frame(aa,bb)
  ern[[e]]$group <- cc$aa[match(ern[[e]]$SiteDetails,cc$bb)]
}

然后，它在group的每个数据帧中返回一个称为ern的新列。

ern
#[[1]]
#    SrlNo VendorCode                     SiteDetails City group
#248   248    V001889 value add sites as per annexure          1
#273   273    V000590       milan et mega bus shelter          2
#282   282    V001578                        backdrop          3
#284   284    V001836   black drop with black masking          4

#[[2]]
#      SrlNo VendorCode                                                    SiteDetails               City group
#59127 59135    V000072   transportation charges-gst- rece cost for 24 paragana(south) 24 Paragana(South)     1
#59128 59136    V000072 transportation charges-gst- rece  cost for 24 paragana (south) 24 Paragana(South)     2

#[[3]]
#      SrlNo VendorCode                       SiteDetails             City group
#34587 34595    V002446                         taki road 24 Pargana North     1
#34601 34609    V000931                   barasat flyover 24 Pargana North     2
#34653 34661    V000094 madhyamgram flyover fcg chowrasta 24 Pargana North     3
#34670 34678    V002240            madhyamgram bt college 24 Pargana North     4