R Notebook

tuesdata = tidytuesdayR::tt_load('2020-05-05')
villagers = tuesdata$villagers
villagers[,"phrase_len"] = stringr::str_length(villagers$phrase)
villagers[,"phrase_words"] = stringr::str_count(villagers$phrase, " ") + 1
villagers$personality = as.factor(villagers$personality)

pacman::p_load(tidyverse,dplyr)
phrase_len_by_personality = villagers[,c("personality","phrase_len")] %>%
  group_by(personality) %>% summarise_each(funs(mean, sd))

phrase_words_by_personality = villagers[,c("personality","phrase_words")] %>%
  group_by(personality) %>% summarise_each(funs(mean, sd))

aov_words = glm(villagers$phrase_words ~ villagers$personality)
aov_len = glm(villagers$phrase_len ~ villagers$personality)
summary(aov_words)
summary(aov_len)

villagers %>% ggplot(., aes(x = phrase_len)) + geom_bar(stat = "count") + 
  ggtitle(label = "Distribution of AC:NH Villager Catchphrase Lengths") + 
  ggthemes::theme_excel_new()

ggplot(phrase_len_by_personality, aes(x = personality, y = mean)) +
                                       geom_bar(stat="identity") +
                                       geom_errorbar(aes(ymin = mean - sd, ymax = mean + sd), width = .2) +
                                       theme_bw() +
  labs(x = "Personality", y = "Phrase Length", title = "Phrase Length by Personality",
       caption = "There is no personality type with a catch phrase length significantly different from the others.")

ggplot(phrase_words_by_personality, aes(x = personality, y = mean)) +
  geom_bar(stat="identity") +
  geom_errorbar(aes(ymin = mean - sd, ymax = mean + sd), width = .2) +
  theme_bw()