Remove specific characters from column names in r

Question

设置了包含数百个列的数据，列名看起来像这样的“ drop.loc1.genom1.tret1.gwas2.a”，我需要删除除loc1和tret1之外的所有内容-因此它将看起来像这样的“ loc1.trt1” “ ----任何提示或帮助将不胜感激，谢谢

Answer 1

Another option is to use strsplit :

sapply(strsplit(strings, "\\."), function(x)
    paste0(x[c(2, 4)], collapse = "."))
[1] "loc1.tret1"     "loc2.tret2"     "loc100.tret100"

---

Sample data

(From ManuelBickel's answer)

strings = c("drop.loc1.genom1.tret1.gwas2.a",
            "drop.loc2.genom1.tret2.gwas2.a",
            "drop.loc100.genom1.tret100.gwas2.a")

Answer 2

You might try something like..

UPDATE: Have updated the code with benchmark of all version proposed so far. In case @Onyambu posts an answer you should accept that one, since the approach is the fastest.

strings = c("drop.loc1.genom1.tret1.gwas2.a",
            "drop.loc2.genom1.tret2.gwas2.a",
            "drop.loc100.genom1.tret100.gwas2.a")
gsub("(^.*\\.)(loc\\d+)(\\..*\\.)(tret\\d+)(\\..*$)", "\\2.\\4", strings, perl = T)
[1] "loc1.tret1"     "loc2.tret2"     "loc100.tret100"

f1 = function(strings) {
  unname(sapply(strings, function(x)
    paste0(unlist(strsplit(x, "\\."))[c(2, 4)], collapse = ".")))
}

f2 = function(strings) {
  gsub("(^.*\\.)(loc\\d+)(\\..*\\.)(tret\\d+)(\\..*$)", "\\2.\\4", strings, perl = T)
}

f2b = function(strings) {
  sub(".*(loc\\d+).*(tret\\d+).*","\\1.\\2",strings)
}

microbenchmark::microbenchmark(
  f1(strings),
  f2(strings),
  f2b(strings)
)

# Unit: microseconds
#         expr    min      lq      mean median      uq      max neval
# f1(strings)  58.818 64.1475 136.31964 68.687 76.1880 5691.106   100
# f2(strings)  78.161 79.9380 106.08183 83.293 88.6215 2110.333   100
# f2b(strings) 27.238 29.6070  53.29592 32.765 35.1330 1872.299   100

Answer 3

You could used dplyr::rename_all() or dplyr::select_all() and gsub() using Onyambu's regex pattern from the comment to Manuel Bickel's answer:

library(dplyr)

# sample data
df <- data_frame(drop.loc1.genom1.tret1.gwas2.a = 1:2,
                 drop.loc23.genom2.tret2.gwas2.a = 3:4,
                 drop.loc3.genom3.tret34.gwas3.a = 5:6)

# both rename_all and select_all give the same results:
df %>% 
  rename_all(~gsub(".*(loc\\d+).*(tret\\d+).*","\\1.\\2", .))

df %>% 
  select_all(~gsub(".*(loc\\d+).*(tret\\d+).*","\\1.\\2", .))

# A tibble: 2 x 3
  loc1.tret1 loc23.tret2 loc3.tret34
       <int>       <int>       <int>
1          1           3           5
2          2           4           6