I do the following
我做了以下几点
library(data.table)
library(stringr)
dt <- data.table(string_column = paste(sample(c(letters, " "), 500000, replace = TRUE)
, sample(c(letters, " "), 500000, replace = TRUE)
, sample(1:500000)
, sep = " "), key = "string_column")
split_res <- dt[, list(name = unlist(str_split(string_column, '\s+'))), by = string_column]
library(data.tab