library(tidyverse)
library(plyr)
readme_df <- read_csv("110124_readme_strict_subset.csv")

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")

# 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$observation_type == "all"),]
  return(longer)
}
expanded_data <- expand_timeseries(readme_df[1,])
for (i in 2:nrow(readme_df)){
  expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
}
head(expanded_data)
#filter out the windows of time that we're looking at
window_num <- 8
windowed_data <- expanded_data |>
  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
  mutate(D = ifelse(week > 27, 1, 0))
#scale the age numbers 
windowed_data$scaled_project_age <- scale(windowed_data$age_in_days)
windowed_data$scaled_event_gap <- scale(windowed_data$event_gap)
windowed_data$week_offset <- windowed_data$week - 27
#break out the different types of commit actions that are studied
all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),]
#log the dependent 
all_actions_data$logged_count <- log(all_actions_data$count)
all_actions_data$log1p_count <- log1p(all_actions_data$count)
range(all_actions_data$log1p_count)


var(all_actions_data$log1p_count) 
mean (all_actions_data$log1p_count) 
sd(all_actions_data$log1p_count)
median(all_actions_data$log1p_count)
var(all_actions_data$count) 
mean (all_actions_data$count) 
sd (all_actions_data$count)
median(all_actions_data$count) 

library(lme4)
all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1,  control=glmerControl(optimizer="bobyqa", optCtrl=list(maxfun=1e5)))

summary(all_log1p_gmodel)
saveRDS(all_log1p_gmodel, "110224_log1p_readme_subset.rda")

all_gmodel <- glmer.nb(count ~ D * week_offset + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1,  control=glmerControl(optimizer="bobyqa", optCtrl=list(maxfun=1e5)))
summary(all_gmodel)
saveRDS(all_gmodel, "110224_readme_subset.rda")