Question

我正在寻找关于下面MWE目标的最佳重做实现的一些建议，该目标实际上必须使用agrep检查列表中的每个元素与另一个列表中的每个元素;这个例子是2x2，但我的实际问题是2,500x75,000 - 所以任何有关并行化的提示都可能有用。

text<-c("The quack brown fox jumps over a lazy dog.", "Pack my box with five dozzen liquor jugs.")
texts<-data.frame(text, stringsAsFactors = FALSE)

words<-c("quick","dozen")
search<-data.frame(words, stringsAsFactors = FALSE)

texts$match<-""
for (i in 1:nrow(search)) {
  print(i)
  for (j in 1:nrow(texts)) {
    print(j)
    temp<- agrep(search$words[i], texts$text[j], max.distance = 0.1, costs = NULL,
                  ignore.case = TRUE, value = TRUE, fixed = TRUE,
                  useBytes = FALSE)
    #   print(temp)
    if (!((length(temp) == 0) && (typeof(temp) == "character"))) {
      texts$match[j]<-paste0(texts$match[j], search$words[i],';')
    }
    rm(temp)
  }
}
texts
                                        text  match
1 The quack brown fox jumps over a lazy dog. quick;
2  Pack my box with five dozzen liquor jugs. dozen;

Answer 1

你至少可以使用agrep的第二个参数中的向量来删除第二个循环。

text<-c("The quack brown fox jumps over a lazy dog.", "Pack my box with five dozzen liquor jugs.")
texts<-data.frame(text, stringsAsFactors = FALSE)

words<-c("quick","dozen")
search<-data.frame(words, stringsAsFactors = FALSE)

texts$matchs <- ""
for (i in 1:nrow(search)) { # i <- 1
  print(i)
    temp<- agrepl(search$words[i], texts$text, max.distance = 0.1, costs = NULL,
                 ignore.case = TRUE, fixed = TRUE,
                 useBytes = FALSE)
    #   print(temp)
    if (max(temp) == 1 ) {
      texts$matchs[temp] <- paste(texts$matchs[temp], search$words[i], sep = ';')
    }

}

两个列表之间的模糊匹配 - 提高效率的双循环

1 个答案: