使用R中的tm包清理dataframe中的列

install.packages("tm")
library(tm)

data <- data.frame(text = c("This is a sample text.", "Another sample text."), 
                   stringsAsFactors = FALSE)

corpus <- Corpus(VectorSource(data$text))

corpus <- tm_map(corpus, content_transformer(tolower))  # 转换为小写
corpus <- tm_map(corpus, removePunctuation)  # 去除标点符号
corpus <- tm_map(corpus, removeNumbers)  # 去除数字
corpus <- tm_map(corpus, removeWords, stopwords("english"))  # 去除英文停用词

corpus <- tm_map(corpus, stemDocument)  # 词干化处理
# 或者使用词形还原处理
# corpus <- tm_map(corpus, PlainTextDocument)
# corpus <- tm_map(corpus, removePunctuation)
# corpus <- tm_map(corpus, removeNumbers)
# corpus <- tm_map(corpus, removeWords, stopwords("english"))
# corpus <- tm_map(corpus, lemmatize_strings)

tdm <- TermDocumentMatrix(corpus)
# 或者使用DTM
# dtm <- DocumentTermMatrix(corpus)