100 lines
5.1 KiB
R
100 lines
5.1 KiB
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
|
|
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"),]
|
|
#find some EDA to identify which types of models might be the best for this
|
|
hist(log(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$count, y)
|
|
all_actions_data$logged_count <- log(all_actions_data$count)
|
|
all_actions_data$log1p_count <- log1p(all_actions_data$count)
|
|
# 3 rdd in lmer analysis
|
|
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
|
|
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
|
|
library(lme4)
|
|
# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
|
|
#making some random data
|
|
sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
|
|
expanded_sample_data <- expand_timeseries(sampled_data[1,])
|
|
for (i in 2:nrow(sampled_data)){
|
|
expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
|
|
}
|
|
windowed_sample_data <- expanded_sample_data |>
|
|
filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
|
|
mutate(D = ifelse(week > 27, 1, 0))
|
|
windowed_sample_data$scaled_project_age <- scale(windowed_sample_data$age_of_project)
|
|
windowed_sample_data$week_offset <- windowed_sample_data$week - 27
|
|
all_actions_sample_data <- windowed_sample_data[which(windowed_sample_data$observation_type == "all"),]
|
|
all_actions_sample_data$log1p_count <- log1p(all_actions_sample_data$count)
|
|
#test model
|
|
test_model <- lmer(log1p_count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link), data=all_actions_sample_data, REML=FALSE)
|
|
summary(test_model)
|
|
#plot results
|
|
p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
|
|
geom_point(size=3, show.legend = FALSE) +
|
|
geom_line(aes(y=predict(test_model)), show.legend = FALSE) +
|
|
theme_bw()
|
|
p
|
|
##end of the model testing and plotting section
|
|
library(optimx)
|
|
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)
|
|
random_effects <- ranef(all_model)
|
|
all_residuals <- residuals(all_model)
|
|
qqnorm(all_residuals)
|
|
# for visualization, may have to run model for each project and then identify top 5 projects for RDD graphs
|
|
mrg_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=mrg_actions_data, REML=FALSE)
|
|
summary(mrg_model)
|
|
mrg_residuals <- residuals(mrg_model)
|
|
qqnorm(mrg_residuals)
|
|
# Performance:
|
|
library(merTools)
|
|
ICC(outcome="count", group="week", data=all_actions_data)
|
|
#testing for different types of models
|
|
|