library(tidyverse)
entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0217_extensions_ve_weekly_commit_count_data.csv"
entest_df <- read.csv(entest_fp, header = TRUE) |> mutate(rd_event = "en-testing")

widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0217_extensions_ve_weekly_commit_count_data.csv"
widetest_df <- read.csv(widetest_fp, header = TRUE) |> mutate(rd_event = "wide-testing")

event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0217_extensions_ve_weekly_commit_count_data.csv"
event_df <- read.csv(event_fp, header = TRUE) |> mutate(rd_event = "default")

#input_df <- bind_rows(entest_df, widetest_df, event_df)
#dropping the event (2013-07-01) from the modeling
input_df <- bind_rows(entest_df, widetest_df)

input_df <- input_df |>
  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) |>
  dplyr::select(-mediawiki_dev_commit_count) |>
  dplyr::select(-wikia_commit_count)

#get into mlm format
long_df <- input_df |>
  pivot_longer(cols = c(other_commit_count, wikimedia_commit_count),
               names_to = "commit_type",
               values_to = "lengthened_commit_count")

intermediate_long_df <- long_df |>
  mutate(commit_share = lengthened_commit_count / (nonbot_commit_count)) |>
  mutate(log_commits = log1p(lengthened_commit_count))|>
  mutate(scaled_long_commits = lengthened_commit_count / 10) 

intermediate_long_df <- intermediate_long_df |>
  drop_na()

window_num <- 4
final_long_df <- intermediate_long_df |>
  filter(relative_week >= (- window_num) & relative_week <= (window_num)) 

commit_plot <- final_long_df |>
  ggplot(aes(x=relative_week, 
              y=lengthened_commit_count, 
              color=commit_type,
              linetype = rd_event)) +
  geom_line() +
  geom_point() + 
  labs(x = "Relative Week", y = "Nonbot Commits", linetype = "Testing Event", color="Commit Author Affiliation") +
  scale_linetype_discrete(labels = c("enwiki testing (2012-12-12)", "wide testing (2013-04-25)")) + 
  scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
  ggtitle("VisualEditor Nonbot Commit Count Around Opt-In Testing Events (by Affiliation)") +
  theme_bw() + 
  theme(legend.position = "top")
commit_plot

total_commit_plot <- final_long_df |>
  filter(commit_type == "other_commit_count")|>
  ggplot(aes(x=relative_week, 
             y=nonbot_commit_count, 
             linetype = rd_event)) +
  geom_line() +
  geom_point() + 
  labs(x = "Relative Week", y = "Nonbot Commit Count", linetype = "Testing Event") +
  scale_linetype_discrete(labels = c("enwiki testing (2012-12-12)", "wide testing (2013-04-25)")) + 
  ggtitle("VisualEditor Nonbot Commit Count Around Opt-In Testing Events") +
  theme_bw() + 
  theme(legend.position = "top")
total_commit_plot

commit_share_plot <- final_long_df |>
  ggplot(aes(x=relative_week, 
             y=commit_share, 
             color=commit_type,
             linetype = rd_event)) +
  geom_line() +
  geom_point() + 
  labs(x = "Relative Week", y = "Share of Nonbot Commits", linetype = "Testing Event", color="Commit Author Affiliation") +
  scale_linetype_discrete(labels = c("enwiki testing (2012-12-12)", "wide testing (2013-04-25)")) + 
  scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
  ggtitle("VisualEditor Nonbot Commit Share Around Opt-In Testing Events") +
  theme_bw() + 
  theme(legend.position = "top")
commit_share_plot