Wprowadzenie do chmur słów

Eksploracja tekstu metodą Bag-of-Words w R

Ted Kwartler

Instructor

Prosta chmura słów

# Convert TDM to matrix
chardonnay_tdm <- TermDocumentMatrix(clean_chardonnay)
chardonnay_m <- as.matrix(chardonnay_tdm)


# Sum rows and sort by frequency
term_frequency <- rowSums(chardonnay_m)
word_freqs <- data.frame(term = names(term_frequency),
                         num = term_frequency)


# Make word cloud
wordcloud(word_freqs$term, word_freqs$num, 
          max.words = 100, colors = "red")

Wpływ stop słów

clean_corpus <- function(corpus){
  corpus <- tm_map(corpus, removePunctuation)
  corpus <- tm_map(corpus, stripWhitespace)
  corpus <- tm_map(corpus, removeNumbers)
  corpus <- tm_map(corpus, 
                   content_transformer(tolower))
  corpus <- tm_map(corpus, removeWords, 
                   c(stopwords("en"), "amp"))
  return(corpus)
}

Usuwanie mało informatywnych słów

clean_corpus <- function(corpus){
  corpus <- tm_map(corpus, removePunctuation)
  corpus <- tm_map(corpus, stripWhitespace)
  corpus <- tm_map(corpus, removeNumbers)
  corpus <- tm_map(corpus, 
                   content_transformer(tolower))

  corpus <- tm_map(corpus, removeWords, 
                   c(stopwords("en"), "amp", 
                    "chardonnay", "wine", "glass"))

  return(corpus)
}

Czas na ćwiczenia!

Eksploracja tekstu metodą Bag-of-Words w R