From 634f60b6a8d3fabd96d38dbbf1b55ab9b3aa44ad Mon Sep 17 00:00:00 2001
From: mjgaughan <mgaughan@proton.me>
Date: Tue, 23 Apr 2024 09:55:37 -0500
Subject: [PATCH] recent updates to model formula

---
 R/.Rhistory           | 132 +++++++++++++++++++++---------------------
 R/readmeRDDAnalysis.R |   3 +-
 2 files changed, 68 insertions(+), 67 deletions(-)

diff --git a/R/.Rhistory b/R/.Rhistory
index 08586d1..a4c3e0d 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,69 +1,3 @@
-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$observation_type == "all"),]
-return(longer)
-}
-expanded_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
-}
-View(expanded_data)
-# this is the file with the lmer multi-level rddAnalysis
-library(tidyverse)
-library(plyr)
-# 0 loading the readme data in
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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$observation_type == "all"),]
-return(longer)
-}
-expanded_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
-}
-#filter out the windows of time that we're looking at
-window_num <- 8
-expanded_data <- expanded_data |>
-filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week > 26, 1, 0))
-#separate out the cleaning
-all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),]
-mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),]
-draft_all_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-# 3 rdd in lmer analysis
-# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
-library(lme4)
-draft_all_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-draft_all_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_all_model)
-ICC(outcome="count", group="upstream_vcs_link", data=all_actions_data)
 # need to calculate inter-class correlation coefficient?
 library(merTools)
 ICC(outcome="count", group="upstream_vcs_link", data=all_actions_data)
@@ -510,3 +444,69 @@ poisson_mrg_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_pr
 summary(poisson_mrg_model)
 poisson_mrg_residuals <- residuals(poisson_mrg_model)
 qqnorm(poisson_mrg_residuals)
+# this is the file with the lmer multi-level rddAnalysis
+library(tidyverse)
+library(plyr)
+# 0 loading the readme data in
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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)
+# 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)
diff --git a/R/readmeRDDAnalysis.R b/R/readmeRDDAnalysis.R
index 33a8ae7..a57e4e3 100644
--- a/R/readmeRDDAnalysis.R
+++ b/R/readmeRDDAnalysis.R
@@ -54,7 +54,8 @@ qqplot(all_actions_data$count, y)
 # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
 library(lme4)
 # 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"))
+# (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), data=all_actions_data, family = poisson(link = "log"))
 summary(poisson_all_model)
 poisson_residuals <- residuals(poisson_all_model)
 qqnorm(poisson_residuals)