library(tidyverse)
count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0217_extensions_ve_weekly_commit_count_data.csv"
input_df <- read.csv(count_data_fp, header = TRUE) 

input_df$nonbot_commit_count <- input_df$commit_count - input_df$bot_commit_count

window_num <- 52
input_df <- input_df |>
  filter(relative_week >= (- window_num) & relative_week <= (window_num)) |>
  mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
  mutate(other_commit_count = nonbot_commit_count - mediawiki_dev_commit_count - wikia_commit_count - wikimedia_commit_count) |>
  mutate(wikimedia_commit_count = wikimedia_commit_count + mediawiki_dev_commit_count + wikia_commit_count) |>
  select(-mediawiki_dev_commit_count) |>
  select(-wikia_commit_count)

library(scales)
library(ggplot2)

time_plot <- input_df |>
  ggplot(aes(x=relative_week, y=nonbot_commit_count)) +
  labs(x="Weekly Offset", y="Nonbot Commit Count") +
  geom_smooth() +
  geom_vline(xintercept = 0)+
  theme_bw() +
  theme(legend.position = "top")
time_plot

library(dplyr)

share_df <- input_df |>
  mutate(wikimedia_share = wikimedia_commit_count / nonbot_commit_count) |>
  mutate(other_share = other_commit_count / nonbot_commit_count)|>
  drop_na()

share_long <- share_df |>
  dplyr::select(relative_week, wikimedia_share, other_share) |>
  pivot_longer(cols = c(wikimedia_share, other_share), names_to = "category", values_to = "share")

share_plot <- share_long |>
  ggplot(aes(x=relative_week, y=share, color=category)) +
  geom_line() +
  geom_vline(xintercept = 0)+
  annotate("text", x = -7, y=1, label = "2012-12-12") +
  geom_vline(xintercept = 19)+
  annotate("text", x = 12, y=1, label = "2013-04-28") +
  geom_vline(xintercept = 28)+
  annotate("text", x = 35, y=1, label = "2013-07-01") +
  labs(x = "Relative Week", y = "Share of Nonbot Commit Count", color = "Affiliation") +
  ggtitle("VE Weekly Share of Nonbot Commit Count by Affiliation (enwiki opt-in testing 2012-12-12)") +
  theme_bw() + 
  theme(legend.position = "top")
share_plot