24_deb_pkg_gov/R/didAnalysis.R

# this is the file with the lmer multi-level rddAnalysis
library(tidyverse)
library(plyr) 
# 0 loading the readme data in 
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../final_data/deb_readme_did.csv")
# 1 preprocessing 
#colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
col_order <- c("upstream_vcs_link", "age_of_project", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
readme_df <- readme_df[,col_order]
readme_df$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
expanded_data <- expanded_data |>
  filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
  mutate(D = ifelse(week > 26, 1, 0))
#separate out the cleaning d
all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),]
mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),]
#find some EDA to identify which types of models might be the best for this
mean(all_actions_data$count)
median(all_actions_data$count)
table(all_actions_data$count)
var(all_actions_data$count)
qqnorm(all_actions_data$count)
y <- qunif(ppoints(length(all_actions_data$count)))
qqplot(all_actions_data$count, y)
# 3 rdd in lmer analysis
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
library(lme4)
flat_all_model <- lm(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project, REML=FALSE, data=all_actions_data)
summary(flat_all_model)
lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
summary(lmer_all_model)
lmer_residuals <- residuals(lmer_all_model)
qqnorm(lmer_residuals)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals)
# Performance: 
draft_mrg_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=mrg_actions_data)
summary(draft_mrg_model)
# Performance: 

library(merTools)
ICC(outcome="count", group="week", data=all_actions_data)
#testing for different types of models