150 lines
7.2 KiB
R
150 lines
7.2 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$count)
|
|
# 3 rdd in lmer analysis
|
|
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
|
|
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
|
|
library(lme4)
|
|
# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
|
|
library(optimx)
|
|
library(lattice)
|
|
all_model <- lmer(log1p_count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE, control = lmerControl(
|
|
optimizer ='optimx', optCtrl=list(method='L-BFGS-B')))
|
|
summary_of_all <- summary(all_model)
|
|
#identifying the quartiles of effect for D
|
|
mmcm = coef(all_model)$upstream_vcs_link
|
|
fixed_impacts = fixef(all_model)
|
|
summary(all_model)$coef[,2]
|
|
variance_components <- VarCorr(all_model)
|
|
all_model_ranef_condvar <- ranef(all_model, condVar = TRUE)
|
|
dotplot(all_model_ranef_condvar)
|
|
test <- broom.mixed::tidy(all_model, effects = "ran_vals", conf.int = TRUE)
|
|
attr(all_model_ranef_condvar$upstream_vcs_link, "postVar")
|
|
|
|
all_coefficients <- coef(all_model)
|
|
all_standard_errors <- sqrt(diag(vcov(all_model)))[1]
|
|
|
|
var(all_actions_data$log1p_count) # 1.125429
|
|
mean (all_actions_data$log1p_count) # 0.6426873
|
|
|
|
#all_gmodel <- glmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, nAGQ=0, family = poisson)
|
|
#all_gmodel <- glmer.nb(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset) | upstream_vcs_link),
|
|
# control=glmerControl(optimizer="bobyqa",
|
|
# optCtrl=list(maxfun=2e5)), data=all_actions_data)
|
|
all_gmodel <- glmer.nb(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset) | upstream_vcs_link), data=all_actions_data, nAGQ=0, control=glmerControl(optimizer="bobyqa",
|
|
optCtrl=list(maxfun=1e5)))
|
|
summary(all_gmodel)
|
|
saveRDS(all_gmodel, "0509_gmodel.rda")
|
|
#readRDS(path)
|
|
library(broom.mixed)
|
|
test_condvals <- broom.mixed::tidy(all_gmodel, effects = "ran_vals", conf.int = TRUE)
|
|
test_glmer_ranef_D <- test_condvals [which(test_condvals $term == "D"),]
|
|
has_zero <- function(estimate, low, high){
|
|
return(ifelse((low < 0),ifelse((high > 0), 1, 0), 2))
|
|
}
|
|
test_glmer_ranef_D <- test_glmer_ranef_D |>
|
|
mutate(ranef_grouping = has_zero(estimate, conf.low, conf.high)) |>
|
|
mutate(rank = rank(estimate))
|
|
g <- test_glmer_ranef_D |>
|
|
ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
|
|
geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
|
|
theme_bw()
|
|
ggsave("0509caterpillar.png", g)
|
|
#below this groups the ranefs
|
|
"""
|
|
has_zero <- function(condval, condsd){
|
|
bounds <- condsd * 1.96
|
|
return(ifelse(((condval - bounds) < 0),ifelse(((condval + bounds) > 0), 1, 0), 2))
|
|
}
|
|
df_ranefs <- df_ranefs |>
|
|
mutate(ranef_grouping = has_zero(condval, condsd)) |>
|
|
mutate(rank = rank(condval))
|
|
D_df_ranef <- df_ranefs[which(df_ranefs$term == ),]
|
|
D_df_ranef <- D_df_ranef |>
|
|
mutate(rank = rank(condval))
|
|
hist(D_df_ranef$ranef_grouping)
|
|
#plot the ranefs
|
|
library(ggplot2)
|
|
D_df_ranef |>
|
|
ggplot(aes(x=rank, y=condval, col = as.factor(ranef_grouping))) +
|
|
geom_linerange(aes(ymin= condval - (1.96 * condsd), ymax= condval + (1.96 * condsd))) +
|
|
theme_bw()
|
|
"""
|
|
#d_effect_ranef_all <- all_model_ranef$upstream_vcs_link
|
|
#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 <- ranef(mrg_model, condVar=TRUE)
|
|
df_mrg_ranefs <- as.data.frame(mrg_model_ranef)
|
|
dotplot(mrg_model_ranef)
|
|
d_effect_ranef_mrg <- mrg_model_ranef[mrg_model_ranef$term=="D",]
|
|
d_effect_ranef_mrg$quartile <- ntile(d_effect_ranef_mrg$condval, 4)
|
|
#doing similar random effect analysis for this
|
|
df_mrg_ranefs <- df_mrg_ranefs |>
|
|
mutate(ranef_grouping = has_zero(condval, condsd)) |>
|
|
mutate(rank = rank(condval))
|
|
D_df_mrg_ranefs <- df_mrg_ranefs[which(df_mrg_ranefs$term == "D"),]
|
|
D_df_mrg_ranefs |>
|
|
ggplot(aes(x=rank, y=condval, col = as.factor(ranef_grouping))) +
|
|
geom_linerange(aes(ymin= condval - (1.96 * condsd), ymax= condval + (1.96 * condsd)))
|
|
#merge model residuals
|
|
mrg_residuals <- residuals(mrg_model)
|
|
qqnorm(mrg_residuals)
|
|
# Performance: |