如何从R中的数据框中提取关键词

install.packages("tm")  # 文本挖掘包
install.packages("SnowballC")  # 词干提取包
library(tm)
library(SnowballC)

corpus <- Corpus(VectorSource(df$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)  # 词干提取

dtm <- DocumentTermMatrix(corpus)

# 基于词频
term_freq <- colSums(as.matrix(dtm))
top_keywords <- head(sort(term_freq, decreasing = TRUE), 10)

# 基于TF-IDF
tdm <- TermDocumentMatrix(corpus)
tfidf <- weightTfIdf(tdm)
top_keywords <- head(sort(rowSums(as.matrix(tfidf)), decreasing = TRUE), 10)