Regex 从两个文件中匹配单词并提取匹配的单词

我有以下数据框：

dataFrame <- data.frame(sent = c(1,1,2,2,3,3,3,4,5), word = c("good printer", "wireless easy", "just right size",
                                                          "size perfect weight", "worth price", "website great tablet",
                                                          "pan nice tablet", "great price", "product easy install"), val = c(1,2,3,4,5,6,7,8,9))

然后我会说：

nouns <- c("printer", "wireless", "weight", "price", "tablet")

---

这里有一个使用

stringi

包的简单解决方案（

size

不在您的

名词

列表中）

库（stringi）
转换（数据帧，
extract=stri_extract_all（单词，
正则表达式=粘贴（名词，collapse=“|”），
简化=真）
#发送字val摘录
#1台好的打印机1台打印机
#2 1无线轻松2无线
#3 2正合适的尺寸3
#4 2尺码完美重量4重量
#价值价
#6 3网站大平板电脑6平板电脑
#7 3潘尼斯片7片
#价格太高了
#9 5产品易于安装9

这是另一种解决方案。稍微复杂一点，但它也会删除名词和dataFrame$word之间不匹配的行

require(stringr)
dataFrame <- data.frame("sent" = c(1,1,2,2,3,3,3,4,5),
                            "word" = c("good printer", "wireless easy", "just right size",
                                       "size perfect weight", "worth price", "website great tablet",
                                       "pan nice tablet", "great price", "product easy install"),
                            val = c(1,2,3,4,5,6,7,8,9))

    nouns <- c("printer", "wireless", "weight", "price", "tablet")

    test <- character()
    df.del <- list()

    for (i in 1:nrow(dataFrame)) {
        if(length(intersect(nouns, unlist(strsplit(as.character(dataFrame$word[i]), " ")))) == 0) {
            df.del <- rbind(df.del, i)
        } else {
            test <- rbind(test,
                          intersect(nouns, unlist(strsplit(as.character(dataFrame$word[i]), " "))))
        }
    }

    dataFrame <- dataFrame[-c(unlist(df.del)), ]
    dataFrame <- cbind(dataFrame, test)
    names(dataFrame)[4] <- "extract"

---

下面是另一个使用循环函数和if语句的解决方案

word<-dataFrame$word
dat<-NULL
extract<-c(rep(c("remove"), each=length(word)))
n<-length(word) 
m<-length(nouns)

for (i in 1:n) {
g<-as.character(word[i])
for (j in 1:m) {
dat<-grepl(nouns[j], g)
if(dat == TRUE) {extract[i] <- nouns[j]} 
}
}

dataFrame$extract <- extract

#  sent                 word val  extract
#1    1         good printer   1  printer
#2    1        wireless easy   2 wireless
#3    2      just right size   3   remove
#4    2  size perfect weight   4   weight
#5    3          worth price   5    price
#6    3 website great tablet   6   tablet
#7    3      pan nice tablet   7   tablet
#8    4          great price   8    price
#9    5 product easy install   9   remove

---

word你不是在一小时前问了一个非常类似的问题吗？你如何回应它的评论？我已经结束了另一个问题，请不要发布同一个问题两次。对此表示抱歉，我想更改任务，但不幸的是复制了该问题。有趣的问题！我想知道您需要确保单词列中的每个单元格只能出现一个名词。实际上，我发现@David Arenburg解决方案在名词列表中两个单词匹配的情况下自动提供第二列，例如，如果dataFrame[5,2]的值为“tablet price”而不是“worth price”。很好的解决方案！非常感谢，大卫工作得很好。这就是我要找的。
library(stringi)
transform(dataFrame, 
          extract = stri_extract_all(word, 
          regex = paste(nouns, collapse = "|"), 
          simplify = TRUE))

#   sent                 word val  extract
# 1    1         good printer   1  printer
# 2    1        wireless easy   2 wireless
# 3    2      just right size   3     <NA>
# 4    2  size perfect weight   4   weight
# 5    3          worth price   5    price
# 6    3 website great tablet   6   tablet
# 7    3      pan nice tablet   7   tablet
# 8    4          great price   8    price
# 9    5 product easy install   9     <NA>

require(stringr)
dataFrame <- data.frame("sent" = c(1,1,2,2,3,3,3,4,5),
                            "word" = c("good printer", "wireless easy", "just right size",
                                       "size perfect weight", "worth price", "website great tablet",
                                       "pan nice tablet", "great price", "product easy install"),
                            val = c(1,2,3,4,5,6,7,8,9))

    nouns <- c("printer", "wireless", "weight", "price", "tablet")

    test <- character()
    df.del <- list()

    for (i in 1:nrow(dataFrame)) {
        if(length(intersect(nouns, unlist(strsplit(as.character(dataFrame$word[i]), " ")))) == 0) {
            df.del <- rbind(df.del, i)
        } else {
            test <- rbind(test,
                          intersect(nouns, unlist(strsplit(as.character(dataFrame$word[i]), " "))))
        }
    }

    dataFrame <- dataFrame[-c(unlist(df.del)), ]
    dataFrame <- cbind(dataFrame, test)
    names(dataFrame)[4] <- "extract"

  sent                 word val  extract
1    1         good printer   1  printer
2    1        wireless easy   2 wireless
4    2  size perfect weight   4   weight
5    3          worth price   5    price
6    3 website great tablet   6   tablet
7    3      pan nice tablet   7   tablet
8    4          great price   8    price

word<-dataFrame$word
dat<-NULL
extract<-c(rep(c("remove"), each=length(word)))
n<-length(word) 
m<-length(nouns)

for (i in 1:n) {
g<-as.character(word[i])
for (j in 1:m) {
dat<-grepl(nouns[j], g)
if(dat == TRUE) {extract[i] <- nouns[j]} 
}
}

dataFrame$extract <- extract

#  sent                 word val  extract
#1    1         good printer   1  printer
#2    1        wireless easy   2 wireless
#3    2      just right size   3   remove
#4    2  size perfect weight   4   weight
#5    3          worth price   5    price
#6    3 website great tablet   6   tablet
#7    3      pan nice tablet   7   tablet
#8    4          great price   8    price
#9    5 product easy install   9   remove