从语料库中删除特定单词
Remove specific words from a corpus
在这个过程之后如何从 myDfm 语料库中删除特定的词?
dflemma <-
spacy_parse(structure(df2$term, names = df2$id), lemma = TRUE, pos = FALSE) %>%
group_by(id = sub("(.+)-(.+)", "\1", doc_id)) %>%
summarise(text = paste(lemma, collapse = " "))
myCorpus <- corpus(dflemma[["text"]], docnames = dflemma[["id"]])
mystopwords <- c("can")
myDfm <- myCorpus %>%
tokens(remove_punct = TRUE, remove_numbers = TRUE, remove_symbols = TRUE) %>%
tokens_remove(pattern = c(stopwords(source = "smart"), mystopwords)) %>%
dfm(verbose = FALSE)
你想要
dfm_remove(myDfm, pattern = words_to_remove)
在这个过程之后如何从 myDfm 语料库中删除特定的词?
dflemma <-
spacy_parse(structure(df2$term, names = df2$id), lemma = TRUE, pos = FALSE) %>%
group_by(id = sub("(.+)-(.+)", "\1", doc_id)) %>%
summarise(text = paste(lemma, collapse = " "))
myCorpus <- corpus(dflemma[["text"]], docnames = dflemma[["id"]])
mystopwords <- c("can")
myDfm <- myCorpus %>%
tokens(remove_punct = TRUE, remove_numbers = TRUE, remove_symbols = TRUE) %>%
tokens_remove(pattern = c(stopwords(source = "smart"), mystopwords)) %>%
dfm(verbose = FALSE)
你想要
dfm_remove(myDfm, pattern = words_to_remove)