122 lines
4.5 KiB
R
122 lines
4.5 KiB
R
library(plyr)
|
|
library(tidyverse)
|
|
library(rdd)
|
|
|
|
|
|
#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)
|
|
}
|
|
}
|
|
contributing_df$age_of_project = ages
|
|
write.csv(contributing_df, "deb_contributing_data_4_19.csv", row.names=FALSE)
|
|
readme_df <- readme_df[,col_order]
|
|
readme_df$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$after_mrg_ct), ", ")
|
|
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
#preprocessing for contributing_df
|
|
|
|
|
|
# test <- readme_df$cnt_before_all
|
|
# as.numeric(unlist(test[1]))
|
|
# test_two <- c()
|
|
# iterator <- 0
|
|
# for (entry in test) {
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
# print(as.numeric(unlist(entry)))
|
|
# iterator <- iterator + 1
|
|
# }
|
|
# test_two
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
# https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
|
|
## https://www.rdocumentation.org/packages/lme4/versions/1.1-35.2/topics/lmer
|
|
new_test <- readme_df[9,]
|
|
get_optimal_window <- function(project_row) {
|
|
longer <- project_row |>
|
|
pivot_longer(cols = starts_with("ct"),
|
|
names_to = "window",
|
|
values_to = "count") |>
|
|
unnest(count)
|
|
longer$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){
|
|
#have tested it with multiple different error-values and all medians/means still hover around 8
|
|
return(8)
|
|
})
|
|
}
|
|
|
|
#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)
|
|
#from this, I think setting the bandwidth to 8 weeks, two months, the floor
|
|
# of both the median and mean calculations
|
|
|
|
|
|
#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$observation_type == "all"),] |>
|
|
ggplot(aes(x = week, y = count)) +
|
|
geom_point() +
|
|
geom_vline(xintercept = 26)
|
|
|
|
longer[which(longer$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)
|
|
|