diff --git a/R/.Rhistory b/R/.Rhistory
index a8a84cc..b1eb01c 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,68 +1,3 @@
-geom_vline(xintercept = 26)
-window <- 26
-longer <- longer %>%
-filter(week >= (26 - window) & week <= (26 + window))
-window_num <- 26
-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$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = FALSE) +
-geom_vline(xintercept = 26)
-window_num <- 27
-longer <- longer %>%
-filter(week >= (26 - window_num) & week <= (26 + window_num))
-# test_two <- c()
-# iterator <- 0
-# for (entry in test) {
-#   readme_df$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[450,]
-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$observation_type == "all"),] |>
-select(count, week) |>
-mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
-ggplot(aes(x = week, y = count, color = D)) +
-geom_point() +
-geom_smooth(se = FALSE) +
-geom_vline(xintercept = 26)
-window_num <- 20
 longer <- longer %>%
 filter(week >= (26 - window_num) & week <= (26 + window_num))
 #testing out analysis below
@@ -510,3 +445,68 @@ draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, REML=FALSE, da
 draft_model <- lmer(count ~ D * I(week - 26) + upstream_vcs_link, REML=FALSE, data=expanded_data[which(longer$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)
diff --git a/R/didAnalysis.R b/R/didAnalysis.R
index baa9fe5..d3890d3 100644
--- a/R/didAnalysis.R
+++ b/R/didAnalysis.R
@@ -1,4 +1,6 @@
 # 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()$path)))
 readme_df <- read_csv("../final_data/deb_readme_did.csv")
@@ -36,5 +38,5 @@ expanded_data <- expanded_data |>
   mutate(D = ifelse(week >= 26, 1, 0))
 # 3 rdd in lmer analysis
 library(lme4)
-draft_model <- lmer(count ~ D * I(week - 26) + (1|upstream_vcs_link), REML=FALSE, data=expanded_data[which(longer$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)