minor updates

R/didCleaning.R

@@ -1,5 +1,6 @@
 library(plyr)
 library(tidyverse)
+library(rdd)
 
 
 #set wd, read in data
@@ -32,17 +33,46 @@ readme_df = readme_df[,!(names(readme_df) %in% drop)]
 # }
 # test_two
 #Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
-new_test <- readme_df[231,]
-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)
+# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
+## https://www.rdocumentation.org/packages/lme4/versions/1.1-35.2/topics/lmer
+new_test <- readme_df[9,]
+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(8)
+  })
+}
 
+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)
+#window_num <- 13
+
+#longer <- longer %>%
+#  filter(week >= (26 - window_num) & week <= (26 + window_num))
 #sapply(longer, class)
+#longer$biweekly <- ceiling(longer$week / 2)
+#longer <- longer %>%
+#  group_by(window, biweekly, observation_type) %>%
+#  summarise(biweekly_count = sum(count, na.rm = TRUE))
 
 #testing out analysis below
 longer[which(longer$observation_type == "all"),] |> 
@@ -60,4 +90,6 @@ longer[which(longer$observation_type == "all"),] |>
   mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
   ggplot(aes(x = week, y = count, color = D)) +
   geom_point() + 
-  geom_smooth(se = FALSE)
+  geom_smooth(se = TRUE) + 
+  geom_vline(xintercept = 26) 
+