scaled variables for poisson

R/.Rhistory

@@ -1,313 +1,367 @@
-window_num <- 10
+link <- readme_df[i,]$upstream_vcs_link
-longer <- longer %>%
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
-filter(week >= (26 - window_num) & week <= (26 + window_num))
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
-#testing out analysis below
+ages <- c(ages, age)
-longer[which(longer$observation_type == "all"),] |>
+if (length(project) != 1){
-ggplot(aes(x = week, y = count)) +
+project
-geom_point() +
+break
-geom_vline(xintercept = 26)
+} else {
-longer[which(longer$observation_type == "all"),] |>
+projects <- c(projects, project)
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = FALSE) +
-geom_vline(xintercept = 26)
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
-#   print(as.numeric(unlist(entry)))
-#   iterator <- iterator + 1
-# }
-# test_two
-#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-new_test <- readme_df[697,]
-longer <- new_test |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-window_num <- 27
-longer <- longer %>%
-filter(week >= (26 - window_num) & week <= (26 + window_num))
-#testing out analysis below
-longer[which(longer$observation_type == "all"),] |>
-ggplot(aes(x = week, y = count)) +
-geom_point() +
-geom_vline(xintercept = 26)
-longer[which(longer$observation_type == "all"),] |>
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = FALSE) +
-geom_vline(xintercept = 26)
-window_num <- 13
-longer <- longer %>%
-filter(week >= (26 - window_num) & week <= (26 + window_num))
-#testing out analysis below
-longer[which(longer$observation_type == "all"),] |>
-ggplot(aes(x = week, y = count)) +
-geom_point() +
-geom_vline(xintercept = 26)
-longer[which(longer$observation_type == "all"),] |>
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = FALSE) +
-geom_vline(xintercept = 26)
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = TRUE) +
-geom_vline(xintercept = 26)
-#testing out analysis below
-longer[which(longer$observation_type == "all"),] |>
-ggplot(aes(x = week, y = count)) +
-geom_point() +
-geom_vline(xintercept = 25.5)
-longer[which(longer$observation_type == "all"),] |>
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = TRUE) +
-geom_vline(xintercept = 25.5)
-#testing out analysis below
-longer[which(longer$observation_type == "all"),] |>
-ggplot(aes(x = week, y = count)) +
-geom_point() +
-geom_vline(xintercept = 26)
-longer[which(longer$observation_type == "all"),] |>
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = TRUE) +
-geom_vline(xintercept = 26)
-library(rdd-package)
-library(rdd)
-library(rdd)
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
-#   print(as.numeric(unlist(entry)))
-#   iterator <- iterator + 1
-# }
-# test_two
-#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-new_test <- readme_df[697,]
-longer <- new_test |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-#longer <- longer %>%
-#  filter(week >= (26 - window_num) & week <= (26 + window_num))
-IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-#testing out analysis below
-longer[which(longer$observation_type == "all"),] |>
-ggplot(aes(x = week, y = count)) +
-geom_point() +
-geom_vline(xintercept = 26)
-longer[which(longer$observation_type == "all"),] |>
-mutate(D = ifelse(week >= 26, 1, 0)) |>
-lm(formula = count ~ D * I(week - 26)) |>
-summary()
-longer[which(longer$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = TRUE) +
-geom_vline(xintercept = 26)
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
-#   print(as.numeric(unlist(entry)))
-#   iterator <- iterator + 1
-# }
-# test_two
-#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-new_test <- readme_df[0,]
-longer <- new_test |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-#longer <- longer %>%
-#  filter(week >= (26 - window_num) & week <= (26 + window_num))
-IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
-#   print(as.numeric(unlist(entry)))
-#   iterator <- iterator + 1
-# }
-# test_two
-#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-new_test <- readme_df[3,]
-longer <- new_test |>
-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 %>%
-#  filter(week >= (26 - window_num) & week <= (26 + window_num))
-IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
-#   print(as.numeric(unlist(entry)))
-#   iterator <- iterator + 1
-# }
-# test_two
-#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
-new_test <- readme_df[9,]
-longer <- new_test |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-#longer <- longer %>%
-#  filter(week >= (26 - window_num) & week <= (26 + window_num))
-IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-get_optimal_window <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-optimal_bandwidth <- IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-return(optimal_bandwidth)
 }
-bandwidths <- c()
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+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")
+ages <- c()
+projects <- c()
 for (i in 1:nrow(readme_df)){
-bandwidths <- c(bandwidths, get_optimal_window(readme_df[i,]))
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
 }
-bandwidths
-mean(bandwidths)
-median(bandwidths)
-get_optimal_window <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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"),]
-optimal_bandwidth <- IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-return(optimal_bandwidth)
 }
-bandwidths <- c()
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
 for (i in 1:nrow(readme_df)){
-bandwidths <- c(bandwidths, get_optimal_window(readme_df[i,]))
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
 }
-mean(bandwidths)
+}
-median(bandwidths)
+#set wd, read in data
-bandwidths <- c()
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
 for (i in 1:nrow(readme_df)){
-bandwidth <- get_optimal_window(readme_df[i,])
+link <- readme_df[i,]$upstream_vcs_link
-bandwidths <- c(bandwidths, bandwidth)
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
 }
-mean(bandwidths)
-median(bandwidths)
-get_optimal_window <- 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)
-#this below line makes the code specific to the all-commits data
-longer <- longer[which(longer$observation_type == "all"),]
-result <- tryCatch({
-optimal_bandwidth <- IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-return(optimal_bandwidth)
-}, error = function(e){
-return(8)
-})
 }
-bandwidths <- c()
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
 for (i in 1:nrow(readme_df)){
-bandwidth <- get_optimal_window(readme_df[i,])
+link <- readme_df[i,]$upstream_vcs_link
-bandwidths <- c(bandwidths, bandwidth)
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
 }
-mean(bandwidths)
+}
-median(bandwidths)
+#set wd, read in data
-mode(bandwidths)
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
-table(bandwidths)
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
-mean(bandwidths) #
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
-median(bandwidths)
+full_df <- read_csv("../final_data/deb_full_data.csv")
-# this is the file with the lmer multi-level rddAnalysis
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+length(ages)
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(readme_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+length(ages)
+readme_df$age_of_project = full_df$age_of_project[full_df$upstream_vcs_link == readme_df$upstream_vcs_link]
+View(readme_df)
+readme_df$age_of_project = ages
+View(readme_df)
+write.csv(readme_df, "deb_readme_data_4_19.csv", row.names=FALSE)
+#preprocessing for readme_df
+colnames(contributing_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(contributing_df)){
+link <- readme_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+contributing_df$age_of_project = ages
+write.csv(contributing_df, "deb_contributing_data_4_19.csv", row.names=FALSE)
+View(contributing_df)
+View(contributing_df)
+View(readme_df)
+View(contributing_df)
+View(contributing_df)
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+View(contributing_df)
+#preprocessing for readme_df
+colnames(contributing_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(contributing_df)){
+link <- contributing_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(contributing_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(contributing_df)){
+link <- contributing_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+#set wd, read in data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
+full_df <- read_csv("../final_data/deb_full_data.csv")
+#preprocessing for readme_df
+colnames(contributing_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+ages <- c()
+projects <- c()
+for (i in 1:nrow(contributing_df)){
+link <- contributing_df[i,]$upstream_vcs_link
+age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
+project <- full_df$project_name[full_df$upstream_vcs_link == link]
+ages <- c(ages, age)
+if (length(project) != 1){
+project
+break
+} else {
+projects <- c(projects, project)
+}
+}
+contributing_df$age_of_project = ages
+write.csv(contributing_df, "deb_contributing_data_4_19.csv", row.names=FALSE)
+# 0 loading the readme data in
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
 # 0 loading the readme data in
 try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
 readme_df <- read_csv("../final_data/deb_readme_did.csv")
+View(readme_df)
 # 1 preprocessing
-colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
+#colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
-col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+col_order <- c("upstream_vcs_link", "age_of_project", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
 readme_df <- readme_df[,col_order]
 readme_df$ct_before_all <- str_split(gsub("[][]","", readme_df$before_all_ct), ", ")
+View(readme_df)
+View(readme_df)
 readme_df$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$after_mrg_ct), ", ")
 drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
 readme_df = readme_df[,!(names(readme_df) %in% drop)]
+View(readme_df)
 # 2 some expansion needs to happens for each project
 expand_timeseries <- function(project_row) {
 longer <- project_row |>
@@ -326,131 +380,6 @@ for (i in 2:nrow(readme_df)){
 expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
 }
 View(expanded_data)
-View(expanded_data)
-View(expanded_data)
-View(expanded_data)
-View(expanded_data)
-get_optimal_window <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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$count)
-#this below line makes the code specific to the all-commits data
-longer <- longer[which(longer$observation_type == "all"),]
-result <- tryCatch({
-#Imbens-Kalyanaraman Optimal Bandwidth Calculation
-optimal_bandwidth <- IKbandwidth(longer$week, longer$count, cutpoint = 26, verbose = FALSE, kernel = "triangular")
-return(optimal_bandwidth)
-}, error = function(e){
-return(9)
-})
-}
-#this just gets the optimal bandwith window for each project and then appends to lists
-bandwidths <- c()
-for (i in 1:nrow(readme_df)){
-bandwidth <- get_optimal_window(readme_df[i,])
-bandwidths <- c(bandwidths, bandwidth)
-}
-mean(bandwidths) #8.574233
-median(bandwidths) #8.363088
-table(bandwidths)
-#filter out the timewindows
-window_num <- 8
-expanded_data |>
-filter(week >= (26 - window_num) & week <= (26 + window_num))
-expanded_data |>
-filter(week >= (26 - window_num) & week <= (26 + window_num))
-# 3 rdd in lmer analysis
-library(lme4)
-draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, data=expanded_data[which(longer$observation_type == "all"),])
-expanded_data |>
-filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
-mutate(D = ifelse(week >= 26, 1, 0))
-# 3 rdd in lmer analysis
-library(lme4)
-draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, data=expanded_data[which(longer$observation_type == "all"),])
-summary(draft_model)
-View(expanded_data)
-#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))
-draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, data=expanded_data[which(longer$observation_type == "all"),])
-summary(draft_model)
-draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, REML=FALSE, data=expanded_data[which(longer$observation_type == "all"),])
-draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, REML=FALSE, data=expanded_data[which(longer$observation_type == "all"),])
-draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(longer$observation_type == "all"),])
-summary(draft_model)
-# this is the file with the lmer multi-level rddAnalysis
-# 0 loading the readme data in
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
-readme_df <- read_csv("../final_data/deb_readme_did.csv")
-# this is the file with the lmer multi-level rddAnalysis
-library(tidyverse)
-# 0 loading the readme data in
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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$observation_type == "all"),]
-return(longer)
-}
-expanded_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
-}
-library(plyr)
-# 2 some expansion needs to happens for each project
-expand_timeseries <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$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)
-draft_model <- lmer(count ~ D * I(week - 26) + (1|as.factor(upstream_vcs_link)), REML=FALSE, data=expanded_data[which(longer$observation_type == "all"),])
-draft_model <- lmer(count ~ D * I(week - 26) + (1|as.factor(upstream_vcs_link)), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
-draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
-summary(draft_model)
 # this is the file with the lmer multi-level rddAnalysis
 library(tidyverse)
 library(plyr)
@@ -458,8 +387,8 @@ library(plyr)
 try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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")
+#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")
+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), ", ")
@@ -484,29 +413,100 @@ 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
+#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))
-# 3 rdd in lmer analysis
-library(lme4)
-draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
-summary(draft_model)
-expanded_data <- expanded_data |>
-filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
 mutate(D = ifelse(week > 26, 1, 0))
+#separate out the cleaning
+all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),]
+mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),]
+draft_all_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=all_actions_data)
+summary(draft_all_model)
 # 3 rdd in lmer analysis
 # rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
 # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
 library(lme4)
-draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
+draft_all_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=all_actions_data)
-summary(draft_model)
-View(expanded_data)
-draft_all_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "all"),])
 summary(draft_all_model)
-draft_mrg_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(expanded_data$observation_type == "mrg"),])
+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)
+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) + (1|upstream_vcs_link), REML=TRUE, data=expanded_data[which(expanded_data$observation_type == "all"),])
+draft_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
 summary(draft_all_model)
+flat_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project, REML=FALSE, data=all_actions_data)
+flat_all_model <- lm(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project, REML=FALSE, data=all_actions_data)
+summary(flat_all_model)
+draft_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
 summary(draft_all_model)
+#find some EDA to identify which types of models might be the best for this
+mean(all_actions_data$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)

R/didAnalysis.R

@@ -36,6 +36,8 @@ window_num <- 8
 expanded_data <- expanded_data |>
   filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
   mutate(D = ifelse(week > 26, 1, 0))
+#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"),]
@@ -51,19 +53,19 @@ qqplot(all_actions_data$count, y)
 # rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
 # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
 library(lme4)
-flat_all_model <- lm(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) + scaled_project_age, REML=FALSE, data=all_actions_data)
 summary(flat_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)
+lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + 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) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
+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)
 # Performance: 
-draft_mrg_model <- lmer(count ~ D * I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), REML=FALSE, data=mrg_actions_data)
+draft_mrg_model <- lmer(count ~ D * I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), REML=FALSE, data=mrg_actions_data)
 summary(draft_mrg_model)
 # Performance: