2024-04-15 14:38:41 +00:00
|
|
|
# this is the file with the lmer multi-level rddAnalysis
|
2024-04-16 00:36:11 +00:00
|
|
|
library(tidyverse)
|
|
|
|
|
library(plyr)
|
2024-04-15 14:38:41 +00:00
|
|
|
# 0 loading the readme data in
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
# 1 preprocessing
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$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 timewindows
|
|
|
|
|
window_num <- 8
|
|
|
|
|
expanded_data <- expanded_data |>
|
|
|
|
|
filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
|
|
|
|
|
mutate(D = ifelse(week >= 26, 1, 0))
|
|
|
|
|
# 3 rdd in lmer analysis
|
|
|
|
|
library(lme4)
|
2024-04-16 00:36:11 +00:00
|
|
|
draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
|
2024-04-15 14:38:41 +00:00
|
|
|
summary(draft_model)
|
