library(tidyverse)
library(plyr) 
#get the contrib data instead
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
#some preprocessing and expansion 
col_order <- c("upstream_vcs_link", "age_of_project", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
contrib_df <- contrib_df[,col_order]
contrib_df$ct_before_all <- str_split(gsub("[][]","", contrib_df$before_all_ct), ", ")
contrib_df$ct_after_all <- str_split(gsub("[][]","", contrib_df$after_all_ct), ", ")
contrib_df$ct_before_mrg <- str_split(gsub("[][]","", contrib_df$before_mrg_ct), ", ")
contrib_df$ct_after_mrg <- str_split(gsub("[][]","", contrib_df$after_mrg_ct), ", ")
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
contrib_df = contrib_df[,!(names(contrib_df) %in% drop)]
# 2 some expansion needs to happens for each project 
expand_timeseries <- function(project_row) {
  longer <- project_row |> 
    pivot_longer(cols = starts_with("ct"),
                 names_to = "window",
                 values_to = "count") |>
    unnest(count) 
  longer$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(contrib_df[1,])
for (i in 2:nrow(contrib_df)){
  expanded_data <- rbind(expanded_data, expand_timeseries(contrib_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))
#scale the age numbers 
windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
windowed_data$week_offset <- windowed_data$week - 27
#separate out the cleaning d
all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),]
#EDA?
#TKTK ---------------------
#imports for models 
library(lme4)
library(optimx)
#models -- TKTK need to be fixed
all_model <- lmer(log1p_count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE, control = lmerControl(
  optimizer ='optimx', optCtrl=list(method='L-BFGS-B')))
summary(all_model)
#identifying the quartiles of effect for D
all_model_ranef <- as.data.frame(ranef(all_model))
d_effect_ranef_all <- all_model_ranef[all_model_ranef$term=="D",]
d_effect_ranef_all$quartile <- ntile(d_effect_ranef_all$condval, 4)
#model residuals
all_residuals <- residuals(all_model)
qqnorm(all_residuals)
# mrg behavior for this
mrg_model <- lmer(log1p_count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE, control = lmerControl(
  optimizer ='optimx', optCtrl=list(method='L-BFGS-B')))
summary(mrg_model)
#identifying the quartiles of effect for D
mrg_model_ranef <- as.data.frame(ranef(mrg_model))
d_effect_ranef_mrg <- mrg_model_ranef[mrg_model_ranef$term=="D",]
d_effect_ranef_mrg$quartile <- ntile(d_effect_ranef_mrg$condval, 4)
#merge model residuals
mrg_residuals <- residuals(mrg_model)
qqnorm(mrg_residuals)