R 将多个列表合并为一个，为级别分配名称并拆分

我有列表中的结构化数据，我想在一个列表中对其进行更改，并将V3拆分为多个列。我发现spiting专栏是基于“，”的，但它也会破坏标题

final <- structure(list(`1` = structure(list(V3 = structure(1L, .Label = "Some text one, 20:15 GMT, 16 April 2010, 341 words, (E)(D B)", 
                              class = "factor")), .Names = "V3", row.names = c(NA, -1L), class = "data.frame"), 
                        `2` = structure(list(V3 = structure(c(1L, 2L, 3L), .Label = c("Some text two, 18:50 GMT, 25 June 2010, 681 words, (E)(D M)", 
                                                                                      "Some text three, 20:00 GMT, 25 June 2010, 628 words, (E)(D B)",
                                                                                      "Some text four, 18:50 GMT, 25 June 2010, 677 words, (E)(D MN)"), 
                              class = "factor")), .Names = "V3", row.names = c(NA, -3L), class = "data.frame")), .Names = c("1", "2"))

---

您可以使用

base

尝试此解决方案：

result_list <- lapply(names(final),function(x){
    strings_use <- as.character(final[[x]]$V3)
    wordcount <- regmatches(strings_use,regexpr("[0-9]{1,} words",strings_use))
    split_list <- strsplit(strings_use,paste(paste0(" ",wordcount,", "),collapse = "|"))
    split_mat <- do.call("rbind",split_list)
    split_mat <- cbind(rep(x,nrow(split_mat)),split_mat, wordcount)
    split_mat[,c(1,2,4,3)]
})
result_mat <- as.data.frame(do.call("rbind",result_list),
    stringsAsFactors = F)
names(result_mat) <- c("List", "Title", "Words_count", "Source")

result_mat

#   List                                     Title Words_count    Source
# 1    1  Some text one, 20:15 GMT, 16 April 2010,   341 words  (E)(D B)
# 2    2   Some text two, 18:50 GMT, 25 June 2010,   681 words  (E)(D M)
# 3    2 Some text three, 20:00 GMT, 25 June 2010,   628 words  (E)(D B)
# 4    2  Some text four, 18:50 GMT, 25 June 2010,   677 words (E)(D MN)

---

result\u列表非常棒而且节省时间
result_list <- lapply(names(final),function(x){
    strings_use <- as.character(final[[x]]$V3)
    wordcount <- regmatches(strings_use,regexpr("[0-9]{1,} words",strings_use))
    split_list <- strsplit(strings_use,paste(paste0(" ",wordcount,", "),collapse = "|"))
    split_mat <- do.call("rbind",split_list)
    split_mat <- cbind(rep(x,nrow(split_mat)),split_mat, wordcount)
    split_mat[,c(1,2,4,3)]
})
result_mat <- as.data.frame(do.call("rbind",result_list),
    stringsAsFactors = F)
names(result_mat) <- c("List", "Title", "Words_count", "Source")

result_mat

#   List                                     Title Words_count    Source
# 1    1  Some text one, 20:15 GMT, 16 April 2010,   341 words  (E)(D B)
# 2    2   Some text two, 18:50 GMT, 25 June 2010,   681 words  (E)(D M)
# 3    2 Some text three, 20:00 GMT, 25 June 2010,   628 words  (E)(D B)
# 4    2  Some text four, 18:50 GMT, 25 June 2010,   677 words (E)(D MN)