library(tidyverse)
main_csv <-"~/analysis_data/120725_unified.csv"
main_df <- read.csv(main_csv, header = TRUE) 

author_closer <- main_df |>
  filter(comment_type == "task_description") |>
  filter(author_closer == "True") 
table(author_closer$isAuthorWMF)


new_authors_summary <- main_df |>
  filter(comment_type == "task_description") |>
  group_by(source, AuthorPHID) |>
  summarise(
    task_count = n(),
    first_task = min(week_index)
  ) |>
  group_by(first_task, source) |>
  summarise(
    new_authors_count = n()
  )
ggplot(new_authors_summary, aes(x = first_task, y = new_authors_count)) +
  facet_grid(source ~ ., 
             scales = "free_y",
             labeller = labeller(source = c("c1" = "VisualEditor", 
                                            "c2" = "HTTPS-login", 
                                            "c3" = "HTTP-deprecation"))) + 
  geom_col() +
  labs(
    x = "Date of first task",
    y = "Number of tasks created",
    title = "Task count by Author's first task date"
  ) +
  theme_minimal()