# install.packages("bayesrules")

library(bayesrules)
library(dplyr)

data(fake_news)
# make it a tibble for the sake printing
fake_news <- tibble::as_tibble(fake_news)

fake_news |> glimpse()

# proportion of each type of article
fake_news |> 
    group_by(type) |> 
    summarise(
        n = n(), 
        prop = n / nrow(fake_news) # <- is there a NSE way
                                    # of getting total rows of 
                                    # original DF?
    )

# we can also do this with the tally function
fake_news|> 
    group_by(type) |> 
    tally() |> 
    mutate(prop = n / sum(n))

# usage of "!" in fake vs real articles
fake_news |> 
    group_by(type, title_has_excl) |> 
    summarise(
        total_usage_of_excl = n()
    ) |> 
    ungroup() |>
    group_by(type) |> 
    summarise(
        prop_excl_within_type = total_usage_of_excl / sum(total_usage_of_excl), 
        title_has_excl
    ) |> 
    filter(title_has_excl)

# suppose we get a new article that is titled