2024-04-08 02:00:01 +00:00
|
|
|
library(plyr)
|
2024-04-06 03:17:28 +00:00
|
|
|
library(tidyverse)
|
|
|
|
|
|
2024-04-08 02:00:01 +00:00
|
|
|
|
2024-04-06 03:17:28 +00:00
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$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$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
2024-04-09 01:20:50 +00:00
|
|
|
new_test <- readme_df[231,]
|
2024-04-06 03:17:28 +00:00
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
2024-04-08 02:00:01 +00:00
|
|
|
longer$observation_type <- gsub("^.*_", "", longer$window)
|
|
|
|
|
longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
|
2024-04-09 01:20:50 +00:00
|
|
|
longer$count <- as.numeric(longer$count)
|
|
|
|
|
|
|
|
|
|
#sapply(longer, class)
|
|
|
|
|
|
|
|
|
|
#testing out analysis below
|
|
|
|
|
longer[which(longer$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)
|
