diff --git a/R/.Rhistory b/R/.Rhistory
index a4c3e0d..18b8514 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,512 +1,512 @@
-# need to calculate inter-class correlation coefficient?
-library(merTools)
-ICC(outcome="count", group="upstream_vcs_link", data=all_actions_data)
-ICC(outcome="count", group="week", data=all_actions_data)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + D * I(week - 26) + age_of_project |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-describe(all_actions_data)
-hist(all_actions_data$count)
-mean(all_actions_data$count)
-median(all_actions_data$count)
-mean(all_actions_data$count)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1+week|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1+D * I(week - 26)|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1+ upstream_vcs_link|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-draft_all_model <- lmer(count ~ (1 | D * I(week - 26) + age_of_project) + (1 |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + I(week - 26) |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + week |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + I(week - 26) |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-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)
-draft_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(draft_all_model)
-flat_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project, REML=FALSE, data=all_actions_data)
-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)
-draft_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(draft_all_model)
-#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$count)
-dist(all_actions_data$count)
-var(all_actions_data$count)
-sd(all_actions_data$count)
-qqplot(all_actions_data$count, all_actions_data$week)
-qqnorm(all_actions_data$count)
-y <- qunif(ppoints(length(all_actions_data$count)))
-qqplot(all_actions_data$count, y)
-qqnorm(all_actions_data$count)
-qqnorm(log(all_actions_data$count)
-qqnorm(log(all_actions_data$count))
-qqnorm(log(all_actions_data$count))
-qqplot(log(all_actions_data$count), y)
-qqnorm(all_actions_data$count)
-qqnorm(root(all_actions_data$count))
-qqnorm(log(all_actions_data$count))
-qqplot(log(all_actions_data$count), y)
-qqplot(all_actions_data$count, y)
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-summary(draft_all_model)
-# Performance:
-draft_mrg_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=mrg_actions_data)
-summary(draft_mrg_model)
-lmer_residuals <- residuals(lmer_all_model)
-lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(lmer_all_model)
-lmer_residuals <- residuals(lmer_all_model)
-qqnorm(lmer_residuals)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-summary(poisson_all_model)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-# this is the file with the lmer multi-level rddAnalysis
-library(tidyverse)
-library(plyr)
-# 0 loading the readme data in
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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$count)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
-summary(poisson_all_model)
-# 3 rdd in lmer analysis
-# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
-library(lme4)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scale(age_of_project) + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-qqnorm(poisson_residuals)
-qqnorm(poisson_residuals)
-#scale the age numbers
-expanded_data$scaled_project_age <- scale(expanded_data$age_of_project)
-#separate out the cleaning d
-all_actions_data <- expanded_data[which(expanded_data$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)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-# 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$after_mrg_ct), ", ")
-drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
-# 2 some expansion needs to happens for each project
-expand_timeseries <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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))
-# 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 >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week > 26, 1, 0))
-#scale the age numbers
-windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
-#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"),]
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-# 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)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-#logistic regression mixed effects
-log_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link),data=all_actions_data, family = binomial)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(scale(count) ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), control=glmerControl(optimizer="bobyqa"))
-#logistic regression mixed effects
-log_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link),data=all_actions_data, family = binomial)
-qqnorm(poisson_residuals)
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-#logistic regression mixed effects (doesn't work)
-log_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + upstream_vcs_link |upstream_vcs_link),data=all_actions_data, family = binomial)
-#logistic regression mixed effects (doesn't work)
-log_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link),data=all_actions_data, family = binomial)
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + upstream_vcs_link |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-#if I'm reading the residuals right, the poisson is better?
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D ||upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (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) + scaled_project_age + (D ||upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_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) + scaled_project_age + (D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-# 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 >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week > 26, 1, 0))
-#scale the age numbers
-windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
-#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"),]
-#if I'm reading the residuals right, the poisson is better?
-# there's a conversation to be had between whether (D |upstream_vcs_link) or (D || upstream_vcs_link)
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_test_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_test_model)
-summary(poisson_all_model)
-summary(poisson_test_model)
-poisson_test_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D ||upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_test_model)
-summary(poisson_all_model)
-summary(poisson_test_model)
-summary(poisson_all_model)
-summary(poisson_test_model)
-poisson_testing_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 | upstream_vcs_link) +  (0 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_testing_model)
-#| label: packages
-#| echo: true
-library(tidyverse)
-library(tidytext)
-library(textdata)
-library(textstem)
-library(tidymodels)
-#| label: packages
-#| echo: true
-library(tidyverse)
-library(tidytext)
-library(textdata)
-library(textstem)
-library(tidymodels)
-#| label: data 1
-#| echo: true
-#|
-reviews_df <- read_csv("data/rotten_tomatoes_critic_reviews.csv")
-reviews_df |> head(2) |> kableExtra::kable()
-summary(poisson_test_model)
-summary(poisson_all_model)
-summary(poisson_all_model)
-summary(poisson_test_model)
-#if I'm reading the residuals right, the poisson is better?
-# there's a conversation to be had between whether (D |upstream_vcs_link) or (D || upstream_vcs_link)
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-poisson_test_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week ||upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_test_model)
-summary(poisson_all_model)
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + week |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-ICC(outcome="count", group="week", data=all_actions_data)
-library(merTools)
-ICC(outcome="count", group="week", data=all_actions_data)
-# 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 >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week > 26, 1, 0))
-#scale the age numbers
-windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
-#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"),]
-# for visualization, may have to run model for each project and then identify top 5 projects for RDD graphs
-#
-#
-poisson_mrg_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week |upstream_vcs_link), data=mrg_actions_data, family = poisson(link = "log"))
-summary(poisson_mrg_model)
-poisson_mrg_residuals <- residuals(poisson_mrg_model)
-qqnorm(poisson_mrg_residuals)
-# 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 >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week > 26, 1, 0))
-#scale the age numbers
-windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
-#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"),]
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-# (1 |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ (D + I(week - 26) + D:I(week - 26) + scaled_project_age | upstream_vcs_link) + (1 |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-# 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
-# (1 |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ (D + I(week - 26) + D:I(week - 26) + scaled_project_age | upstream_vcs_link) + (1 |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-# (1 |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D + I(week - 26) + D:I(week - 26) + scaled_project_age | upstream_vcs_link) + (1 |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-# (1 |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D | upstream_vcs_link) + (1 |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
+p
 # https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
 # (D |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week | upstream_vcs_link) + (1 |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset) |upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D |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)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+#test model
+test_model <- lmer(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)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
+#making some random data
+sampled_data <- readme_df[sample(nrow(readme_df), 8), ]
+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 >= (26 - window_num) & week <= (26 + window_num)) |>
+mutate(D = ifelse(week > 26, 1, 0))
+windowed_sample_data$scaled_project_age <- scale(windowed_sample_data$age_of_project)
+windowed_sample_data$week_offset <- windowed_sample_data$week - 26
+all_actions_sample_data <- windowed_sample_data[which(windowed_sample_data$observation_type == "all"),]
+#test model
+test_model <- lmer(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)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (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)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+guides(fill="none") +
+theme_bw()
+p
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme(legend.position="none") +
+theme_bw()
+p
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link)) +
+geom_point(size=3) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw(legend.position="none")
+p
+#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) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw(legend.position="none")
+p
+#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) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link)) +
+theme_bw()
+p
+#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) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+# 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 >= (26 - window_num) & week <= (26 + window_num)) |>
+mutate(D = ifelse(week > 26, 1, 0))
+windowed_sample_data$scaled_project_age <- scale(windowed_sample_data$age_of_project)
+windowed_sample_data$week_offset <- windowed_sample_data$week - 26
+all_actions_sample_data <- windowed_sample_data[which(windowed_sample_data$observation_type == "all"),]
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+##
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
+##
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (week_offset| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
+##
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+# 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"),]
+# 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$observation_type == "all"),]
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+summary(test_model)
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
+geom_point(size=3, show.legend = FALSE) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+##
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
+# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
+#making some random data
+sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
+expanded_sample_data <- expand_timeseries(sampled_data[1,])
+for (i in 2:nrow(sampled_data)){
+expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
+}
+windowed_sample_data <- expanded_sample_data |>
+filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+mutate(D = ifelse(week > 27, 1, 0))
+windowed_sample_data$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"),]
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+# 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$observation_type == "all"),]
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+summary(test_model)
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
+geom_point(size=3, show.legend = FALSE) +
+geom_line(aes(y=predict(test_model), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
+#making some random data
+sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
+expanded_sample_data <- expand_timeseries(sampled_data[1,])
+for (i in 2:nrow(sampled_data)){
+expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
+}
+windowed_sample_data <- expanded_sample_data |>
+filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+mutate(D = ifelse(week > 27, 1, 0))
+windowed_sample_data$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"),]
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#test model
+test_model <- lmer(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), group=upstream_vcs_link), show.legend = FALSE) +
+theme_bw()
+p
+#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
+# 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)
+summary(all_model)
+#test model
+test_model <- lmer(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
+#test model
+test_model <- lmer(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
+# 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"),]
+#test model
+test_model <- lmer(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
+#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=mean(predict(test_model)), show.legend = FALSE)) +
+theme_bw()
+p
+#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
+#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=mean(predict(test_model))), show.legend = FALSE) +
+theme_bw()
+p
+#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=median(predict(test_model))), show.legend = FALSE) +
+theme_bw()
+p
+#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
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset) + scaled_project_age|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
+#test model
+test_model <- lmer(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
+# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
+#making some random data
+sampled_data <- readme_df[sample(nrow(readme_df), 22), ]
+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"),]
+#test model
+test_model <- lmer(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
+# 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$observation_type == "all"),]
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+summary(test_model)
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
+geom_point(size=3, show.legend = FALSE) +
+geom_line(aes(y=predict(test_model)), show.legend = FALSE) +
+theme_bw()
+p
+# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
+#making some random data
+sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
+expanded_sample_data <- expand_timeseries(sampled_data[1,])
+for (i in 2:nrow(sampled_data)){
+expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
+}
+windowed_sample_data <- expanded_sample_data |>
+filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+mutate(D = ifelse(week > 27, 1, 0))
+windowed_sample_data$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"),]
+#test model
+test_model <- lmer(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
+summary(all_model)
+all_residuals <- residuals(all_model)
+qqnorm(all_residuals)
+mrg_residuals <- residuals(mrg_model)
+qqnorm(mrg_residuals)
+summary(all_model)
+##end of the model testing and plotting section
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=TRUE)
+summary(all_model)
+##end of the model testing and plotting section
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
diff --git a/R/readmeRDDAnalysis.R b/R/readmeRDDAnalysis.R
index bde791e..84200e5 100644
--- a/R/readmeRDDAnalysis.R
+++ b/R/readmeRDDAnalysis.R
@@ -43,13 +43,15 @@ windowed_data$week_offset <- windowed_data$week - 27
 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
-mean(all_actions_data$count)
+hist(log(all_actions_data$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
@@ -67,8 +69,9 @@ windowed_sample_data <- expanded_sample_data |>
 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(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+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) +
@@ -77,7 +80,7 @@ p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_
   theme_bw() 
 p
 ##end of the model testing and plotting section
-all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+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)
 summary(all_model)
 all_residuals <- residuals(all_model)
 qqnorm(all_residuals)
@@ -87,7 +90,6 @@ 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