In jcrodriguez1989/thesimpsons: The Simpsons episodes dataset

library("thesimpsons")

This dataset contains the characters, locations, episode details, and script lines for approximately 600 Simpsons episodes, dating back to 1989. Data got from Kaggle.

This package contains four datasets:

characters: The Simpsons characters information.

head(characters)

episodes: metadata related to each The Simpsons episode.

head(episodes[, 1:6])

locations: The Simpsons world locations.

head(locations)

script_lines: the text spoken during each The Simpsons episode (including details about which character said it and where).

head(script_lines[, 1:4])

Examples

Race plot: spoken words by character by season

library("thesimpsons")
library("dplyr")
library("ggplot2")
library("gganimate")
library("hrbrthemes")

# merge script lines with characters and episodes data
script_lines %>%
  filter(!is.na(word_count)) %>%
  left_join(characters, by = c("character_id" = "id")) %>%
  left_join(episodes, by = c("episode_id" = "id")) -> script_lines_full

n_chars <- 10 # include only the 10 most speaking characters
script_lines_full %>%
  select(name, word_count, season) %>% # use just char name, word_count, season
  group_by(name, season) %>% # by name & season
  summarise(wc = sum(word_count)) %>% # get the sum of word counts
  mutate(wc_cs = cumsum(wc)) %>% # generate the cum sum of wc
  group_by(season) %>%
  mutate( # create the ranking (top 10 to plot)
    rank = min_rank(-wc_cs) * 1,
    val_lbl = paste0(" ", wc_cs)
  ) %>%
  filter(rank <= n_chars) -> char_wc_by_season

ggp <- ggplot(char_wc_by_season, aes(rank,
  group = name,
  fill = as.factor(name), color = as.factor(name)
))
ggp <- ggp + geom_tile(
  aes(y = wc_cs / 2, height = wc_cs, width = 0.9),
  alpha = 0.8, color = NA
)
ggp <- ggp + 
  geom_text(aes(y = 0, label = paste(name, " ")), vjust = 0.2, hjust = 1) +
  geom_text(aes(y = wc_cs, label = val_lbl, hjust = 0)) +
  coord_flip(clip = "off", expand = FALSE) +
  scale_x_reverse() +
  guides(color = FALSE, fill = FALSE) +
  labs(
    subtitle = "Words by seasons",
    title = "Season: {closest_state}",
    x = ""
  ) +
  theme_ipsum_rc() +
  theme(
    plot.title = element_text(hjust = 0, size = 22),
    axis.ticks.y = element_blank(),
    axis.text.y = element_blank(),
    axis.title.x = element_blank(),
    axis.text.x = element_blank(),
    axis.ticks.x = element_blank(),
    plot.margin = margin(1, 1, 1, 4, "cm")
  )

ggp <- ggp +
  transition_states(season, transition_length = 4, state_length = 1) +
  ease_aes("cubic-in-out")
animate(ggp, nframes = 100, fps = 30, duration = 18)