library(dplyr)
contributing_df_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/CONTRIBUTING_weekly_count_data.csv"
contributing_df = read.csv(contributing_df_filepath, header = TRUE) 

readme_df_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/README_weekly_count_data.csv"
readme_df = read.csv(readme_df_filepath, header = TRUE)

window_num <- 5
contributing_df <- contributing_df |>
  filter(week_index >= (- window_num) & week_index <= (window_num)) |>
  mutate(doc_type = "CONTRIBUTING")

readme_df <- readme_df |>
  filter(week_index >= (- window_num) & week_index <= (window_num)) |>
  mutate(doc_type = "README")

main_df <- rbind(contributing_df, readme_df)
main_df$log1p_count <- log1p(main_df$commit_count)

library(scales)
library(ggplot2)

expm1_trans <- trans_new(
  name = 'expm1',
  transform = function(x) expm1(x),
  inverse = function(x) log1p(x)
)

doctypeColors <-
  setNames( c('#5da2d8', '#c7756a')
            , c("CONTRIBUTING", "README"))

time_plot <- main_df |>
  ggplot(aes(x=week_index, y=commit_count, color=factor(doc_type))) +
  scale_y_continuous(trans = 'log1p', labels = scales::comma) +
  labs(x="Weekly Offset", y="Commit Count", color="Document Type: ") +
  scale_color_manual(values = doctypeColors) + 
  geom_smooth() +
  geom_vline(xintercept = 0)+
  theme_bw() +
  theme(legend.position = "top")
time_plot

ggsave(filename = "plots/cr-020325-gam-introduction.png", plot = time_plot, width = 9, height = 9, dpi = 800)