library(tidytext)
library(wordcloud)
library(gutenbergr)
library(tidyverse)

# The Time Machine from Gutenberg
tidy_hgwells <- gutenberg_download(c(35)) %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words) %>%
  count(word)

# Wordcloud
tidy_hgwells %>%
  with(wordcloud(word, n, max.words = 100))

# 1.- Barchart
tidy_hgwells %>%
  top_n(20) %>%
  arrange(desc(n)) %>%
  ggplot(aes(as.factor(reorder(word, n)),n)) +
  geom_col() +
  coord_flip() +
  scale_colour_brewer(palette="BuPu", direction=1) +
  labs(x = "Term",y = "Frequency", label= "Frequency")

# 2.- Doughnut chart
library(plotly)
tidy_hgwells %>%
  top_n(20) %>%
  arrange(desc(n)) %>%
  plot_ly(labels = ~word, values = ~n, textposition = "outside",
          marker = list(color = brewer.pal(20, "Blues")),
          textinfo = 'label+percent', colors = n) %>%
  add_pie(hole = 0.6) %>%
  layout(showlegend = F)


# 3.- Treemap
library(treemap)
tidy_hgwells %>%
  top_n(15) %>%
  treemap(index = "word",vSize = "n", type = "index", title = "")

# 4.- Circle Packing
library(packcircles)

data <- tidy_hgwells %>%
  top_n(15) %>%
  arrange(desc(n))

packing <- circleProgressiveLayout(data$n, sizetype = 'area')
data <- cbind(data, packing)
dat.gg <- circleLayoutVertices(packing, npoints = 50)

ggplot() +
  geom_polygon(data = dat.gg, aes(x, y, group = id, fill=as.factor(id)),
               colour = "black", alpha = 0.6) +
  geom_text(data = data, aes(x, y, label = word)) +
  scale_size_continuous(range = c(1,4)) +
  theme_void() +
  theme(legend.position = "none") +
  coord_equal()