#libraries
library(stringr)
readme_df <- read_csv("../final_data/deb_readme_did.csv")
readme_pop_df <- read_csv("../final_data/deb_readme_pop_change.csv")
readme_readability_df <- read_csv('../text_analysis/dwo_readability_readme.csv')
#get the readmeution count 
#some preprocessing and expansion 
col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
readme_df <- readme_df[,col_order]
readme_df$ct_before_all <- str_split(gsub("[][]","", readme_df$before_all_ct), ", ")
readme_df$ct_after_all <- str_split(gsub("[][]","", readme_df$after_all_ct), ", ")
readme_df$ct_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_ct), ", ")
readme_df$ct_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_ct), ", ")
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
readme_df = readme_df[,!(names(readme_df) %in% drop)]
# 2 some expansion needs to happens for each project 
expand_timeseries <- function(project_row) {
  longer <- project_row |> 
    pivot_longer(cols = starts_with("ct"),
                 names_to = "window",
                 values_to = "count") |>
    unnest(count) 
  longer$observation_type <- gsub("^.*_", "", longer$window)
  longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
  longer$count <- as.numeric(longer$count)
  #longer <- longer[which(longer$observation_type == "all"),]
  return(longer)
}
expanded_data <- expand_timeseries(readme_df[1,])
for (i in 2:nrow(readme_df)){
  expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
}
#filter out the windows of time that we're looking at
window_num <- 8
windowed_data <- expanded_data |>
  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
  mutate(D = ifelse(week > 27, 1, 0))

summed_data <- windowed_data |>
  filter(D==1) |>
  group_by(upstream_vcs_link) |>
  summarise_at(vars(count), list(summed_count=sum))

#concat dataframes into central data
readme_pop_df <- readme_pop_df |>
  mutate(project_name = map_chr(upstream_vcs_link, ~ {
    parts <- str_split(.x, pattern = "/")[[1]]
    if (length(parts) >= 1) {
      parts[length(parts)]  
    } else {
      NA_character_
    }
  }))
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/agateau/yokadi/issues/new", "project_name"] = "yokadi" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "http://github.com/voloko/twitter-stream/issues/new", "project_name"] = "twitter-stream" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/ai/autoprefixer-rails/issues/new", "project_name"] = "autoprefixer-rails" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/aquasync/ruby-ole/issues/new", "project_name"] = "ruby-ole" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/bluemonk/ipaddress/issues/new", "project_name"] = "ipaddress" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/ccocchi/rabl-rails/issues/new", "project_name"] = "rabl-rails" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/dejan/espeak-ruby/issues/new", "project_name"] = "espeak-ruby" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/hadley/plyr/issues/new", "project_name"] = "plyr" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/jfelchner/ruby-progressbar/issues/new", "project_name"] = "ruby-progressbar" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/sargon/trayer-srg/issues/new", "project_name"] = "trayer-srg" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/SciRuby/rb-gsl/issues/new", "project_name"] = "rb-gsl" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/solvespace/solvespace/issues/new", "project_name"] = "solvespace" 
readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/walling/unorm/issues/new", "project_name"] = "unorm" 
  
readme_readability_df <- readme_readability_df |>
  mutate(project_name = map_chr(filename, ~ {
    parts <- str_split(.x, pattern = "_")[[1]]
    if (length(parts) >= 1) {
      paste(head(parts, -1), collapse="_")
    } else {
      NA_character_
    }
  }))
readme_readability_df[readme_readability_df['filename'] == "yder_README_8md.html", "project_name"] = "yder" 
readme_readability_df[readme_readability_df['filename'] == "pg_filedump.git_README.pg_filedump", "project_name"] = "pg_filedump.git" 
readme_readability_df[readme_readability_df['filename'] == "openvas_UPGRADE_README", "project_name"] = "openvas" 
readme_readability_df[readme_readability_df['filename'] == "hyphen.git_README_hyph_en_US.txt", "project_name"] = "hyphen.git" 
readme_readability_df[readme_readability_df['filename'] == "cycle.git_README_ru.html", "project_name"] = "cycle.git" 
readme_readability_df[readme_readability_df['filename'] == "diffuse.git_README_ru", "project_name"] = "diffuse.git" 
readme_readability_df[readme_readability_df['filename'] == "CheMPS2_README_8md_source.html", "project_name"] = "CheMPS2" 
readme_readability_df[readme_readability_df['filename'] == "sleuthkit_README_win32.txt", "project_name"] = "sleuthkit" 
readme_readability_df[readme_readability_df['filename'] == "Lmod_README_lua_modulefiles.txt", "project_name"] = "Lmod" 
readme_readability_df[readme_readability_df['filename'] == "engauge_debian_README_for_osx", "project_name"] = "engauge_debian"

readme_total_df <- readme_pop_df |>
  join(readme_readability_df, by="project_name") 

readme_total_df <- readme_total_df|>
  join(summed_data, by="upstream_vcs_link")
#outcome variable that is number of commits by number of new readmeutors
readme_total_df$commit_by_contrib = NA
readme_total_df$commit_by_contrib = readme_total_df$summed_count * (readme_total_df$after_contrib_new + 1)
readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_contrib)
# test regressions
library(MASS)
lm1 <- glm.nb(logged_outcome~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = readme_total_df)
qqnorm(residuals(lm1))
summary(lm1)