# Tidy Text Mining
# Chapter 2

library(tidyverse)
library(tidytext)
library(janeaustenr)
library(stringr)
library(reshape2)

library(sentimentr)  

mytext <- c(
  'do you like it?  But I hate really bad dogs',
  'I am the best friend.',
  'Do you really like it?  I\'m not a fan'
)

# by sentence

mytext <- get_sentences(mytext)
sentiment(mytext)

# by group

sentiment_by(mytext)

# 2012 debate

out <- with(
  presidential_debates_2012, 
  sentiment_by(
    get_sentences(dialogue), 
    list(person, time)
  )
)

plot(out)

# tidy_books

tidy_books <- austen_books() %>%
  group_by(book) %>%
  mutate(linenumber = row_number(),
         chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]", 
                                                 ignore_case = TRUE)))) %>%
  ungroup() %>%
  unnest_tokens(word, text)

library(wordcloud)

tidy_books %>%
  anti_join(stop_words) %>%
  count(word) %>%
  with(wordcloud(word, n, max.words = 100))

tidy_books %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  acast(word ~ sentiment, value.var = "n", fill = 0) %>%
  comparison.cloud(colors = c("gray20", "gray80"),
                   max.words = 100)