updating R scripts for commit analysis c2

commit_analysis/commit_count_collation.R

@@ -3,8 +3,26 @@ library(dplyr)
 library(lubridate)
 library(tidyr)
 library(purrr)
+library(stringr)
 
-ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/mediawiki_wmfconfig_commits.csv"
+ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/mediawiki_core_commits.csv"
+
+contains_http_but_not_url <- function(text) {
+  if (is.na(text)) {
+    return(FALSE)
+  }
+  # Split text by whitespace and check each word
+  words <- str_split(text, "\\s+")[[1]]
+  for (word in words) {
+    if (word == "http" || word == "https") {
+      return(TRUE)
+    }
+    if (str_detect(word, "http") && !str_detect(word, "^https?://") && !str_detect(word, "^http?://")) {
+      return(TRUE)
+    }
+  }
+  return(FALSE)
+}
 
 transform_commit_data <- function(filepath){
   #basic, loading in the file 
@@ -164,8 +182,169 @@ transform_commit_data <- function(filepath){
   return(weekly_commits)
 }
 
-transformed <- transform_commit_data(ve_commit_fp)
+transform_relevant_commit_data <- function(filepath){
-output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/event_0403_mediawiki_wmfconfig_weekly_commit_count_data.csv"
+  #basic, loading in the file 
+  df = read.csv(filepath, header = TRUE) 
+  temp_df <- df
+  dir_path = dirname(filepath)
+  file_name = basename(filepath)
+  
+  
+  # TODO: this is project/event specific
+  event_date <- as.Date("2013-08-28")
+  #event_date <- as.Date("2013-07-01")
+  #event_date <- as.Date("2013-04-25")
+  #event_date <- as.Date("2012-12-11")
+  
+  # isolate project id
+  project_id <- sub("_.*$", "", file_name)
+  
+  #make sure the dates are formatted correctly and state the project_id
+  df <- df |>
+    mutate(commit_date = ymd_hms(commit_date)) |>
+    mutate(project_id = project_id)
+  
+  #get information about project age either in the "present" 
+  #or at the time of first commit
+  oldest_commit_date <- min(as.Date(df$commit_date))
+  project_age <- as.numeric(as.Date("2025-02-10") - oldest_commit_date)
+  
+  #add that to the data 
+  df <- df |> 
+    mutate(age = project_age)
+  
+  #we are looking at weekly data, 6m before and 6m after
+  #start_date <- event_date %m-% months(6)
+  calculated_start_date <- event_date %m-% months(12)
+  start_date <- max(calculated_start_date, oldest_commit_date)
+  end_date <- event_date %m+% months(12)
+  
+  #getting the relative weeks to the publication date
+  relative_week <- function(date, ref_date) {
+    as.integer(as.numeric(difftime(date, ref_date, units = "days")) %/% 7)
+  }
+  
+  df <- df |>
+    mutate(relative_week = relative_week(commit_date, event_date))|>
+    mutate(mentions_http = if_else(sapply(message, contains_http_but_not_url), TRUE, FALSE)) |>
+    filter(mentions_http == TRUE)
+  #  arrange(relative_week) |>
+  #  group_by(author_email) |>
+  #  mutate(new_author = ifelse(row_number() <= 5, 1, 0),
+  #         new_author_wmf = if_else(grepl("@wikimedia", author_email), new_author, 0),
+  #         new_author_unaff = if_else(!grepl("@wikimedia", author_email), new_author, 0)) |>
+  #  ungroup()
+  
+  # cut the df to all before 06-01-2013
+  # group by author_email 
+  # list all author_emails with >5 commits 
+  # for big df: if author not in the list, 'new' author
+  old_author_list <- df |>
+    filter(commit_date < as.Date("2013-08-01"))|>
+    group_by(author_email) |>
+    summarise(commit_count = n()) |>
+    filter(commit_count > 5) |>
+    pull(author_email)
+  
+  # Label authors as 'new' if they are not in the old_author_list
+  df <- df |>
+    mutate(new_author = ifelse(author_email %in% old_author_list, 0, 1), 
+           new_author_wmf = if_else(grepl("@wikimedia", author_email), 
+                                    new_author, 0),
+           new_author_unaff = if_else(!grepl("@wikimedia", author_email) &
+                                        !grepl("l10n-bot@translatewiki.net|tools.libraryupgrader@tools.wmflabs.org", author_email),
+                                      new_author, 0))
+  
+  
+  #filler for when there are weeks without commits
+  all_weeks <- seq(relative_week(start_date, event_date), relative_week(end_date, event_date))
+  complete_weeks_df <- expand.grid(relative_week = all_weeks,
+                                   project_id = project_id,
+                                   age = project_age)
+  
+  
+  #for each week, get the list of unique authors that committed
+  #cumulative_authors <- df %>%
+  #  arrange(relative_week) %>%
+  #  group_by(relative_week) %>%
+  #  summarize(cumulative_author_emails = list(unique(author_email)), .groups = 'drop')
+  #same for each committer
+  #cumulative_committers <- df %>%
+  #  arrange(relative_week) %>%
+  #  group_by(relative_week) %>%
+  #  summarize(cumulative_committer_emails = list(unique(committer_email)), .groups = 'drop')
+  
+  #now cut out the commit data that we don't care about 
+  df <- df |>
+    filter(author_email != "jenkins-bot@gerrit.wikimedia.org")
+  
+  #in order:
+  # - we group by project, week, ages
+  # - and we summarize commit and authorship details
+  # - we then fill in information for missingness
+  # - and add in vars for before/after
+  # - and weekly index
+  weekly_commits <- df |>
+    group_by(project_id, relative_week, age) |>
+    summarise(commit_count = n(),
+              author_emails = list(unique(author_email)),
+              committer_emails = list(unique(committer_email)),
+              mediawiki_dev_commit_count = sum(grepl("@users.mediawiki.org", author_email)),
+              wikimedia_commit_count = sum(grepl("@wikimedia", author_email)),
+              wikia_commit_count = sum(grepl("@wikia-inc.com", author_email)),
+              bot_commit_count = sum(grepl("l10n-bot@translatewiki.net|tools.libraryupgrader@tools.wmflabs.org", author_email)),
+              wmf_new_commit_count = sum(new_author_wmf),
+              unaff_new_commit_count = sum(new_author_unaff),
+              .groups = 'drop') |>
+    right_join(complete_weeks_df, by=c("relative_week", "project_id", "age")) |>
+    replace_na(list(commit_count = 0)) |>
+    replace_na(list(wikimedia_commit_count = 0)) |>
+    replace_na(list(l10n_commit_count = 0)) |>
+    replace_na(list(jenkins_commit_count = 0)) |>
+    replace_na(list(mediawiki_dev_commit_count = 0)) |>
+    replace_na(list(wikia_commit_count = 0)) |>
+    replace_na(list(bot_commit_count = 0)) |>
+    replace_na(list(wmf_new_commit_count = 0)) |>
+    replace_na(list(unaff_new_commit_count = 0)) |>
+    mutate(before_after = if_else(relative_week < 0, 0, 1)) |>
+    select(-author_emails, -committer_emails)
+  # then, to get the authorship details in
+  # we check if the email data is present, if not we fill in blank 
+  # we bring in the information about authorship lists that we already had 
+  # then comparing the current week's author list with the previous week's cumulative list, or empty
+  #  ---- the length of that difference is the 'new' value
+  # then we delete out the author list information
+  #weekly_with_authorship <- weekly_commits |>
+  #  mutate(
+  #    author_emails = ifelse(is.na(author_emails), list(character()), author_emails),
+  #    committer_emails = ifelse(is.na(committer_emails), list(character()), committer_emails)
+  #  ) |>
+  #  left_join(cumulative_authors, by = "relative_week") |>
+  #  left_join(cumulative_committers, by = "relative_week") |>
+  #  mutate(new_author_emails = mapply(function(x, y) length(setdiff(x, y)), author_emails, lag(cumulative_author_emails, default = list(character(1)))),
+  #         new_committer_emails = mapply(function(x, y) length(setdiff(x, y)), committer_emails, lag(cumulative_committer_emails, default = list(character(1))))) 
+  
+  #weekly_with_authorship <- weekly_with_authorship |>
+  #  mutate(
+  #    wikimedia_author_emails = mapply(function(x) length(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x)), author_emails),
+  #    non_wikimedia_author_emails = mapply(function(x) length(x) - length(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x)), author_emails),
+  #    wikimedia_committer_emails = mapply(function(x) length(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x)), committer_emails),
+  #    non_wikimedia_committer_emails = mapply(function(x) length(x) - length(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x)), committer_emails),
+  #    new_wikimedia_authors = mapply(function(x, y) length(setdiff(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x, value = TRUE), grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", y, value = TRUE))), author_emails, lag(cumulative_author_emails, default = list(character(1)))),
+  #    new_non_wikimedia_authors = mapply(function(x, y) length(setdiff(x, y)) - length(setdiff(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x, value = TRUE), grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", y, value = TRUE))), author_emails, lag(cumulative_author_emails, default = list(character(1)))),
+  #    new_wikimedia_committers = mapply(function(x, y) length(setdiff(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x, value = TRUE), grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", y, value = TRUE))), committer_emails, lag(cumulative_committer_emails, default = list(character(1)))),
+  #    new_non_wikimedia_committers = mapply(function(x, y) length(setdiff(x, y)) - length(setdiff(grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", x, value = TRUE), grep("@wikimedia|@users.mediawiki.org|@wikia-inc.com", y, value = TRUE))), committer_emails, lag(cumulative_committer_emails, default = list(character(1))))
+  #  ) |>
+  
+  weekly_commits <- weekly_commits |>
+    filter(relative_week >= (-52) & relative_week <= 52 )
+  
+  #gracefully exit
+  return(weekly_commits)
+}
+
+transformed <- transform_relevant_commit_data(ve_commit_fp)
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/relevant_event_0404_mediawiki_core_weekly_commit_count_data.csv"
 
 write.csv(transformed, output_filepath, row.names = FALSE)
 

commit_analysis/commit_plotting.R

@@ -1,5 +1,5 @@
 library(tidyverse)
-count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/event_0403_mediawiki_core_weekly_commit_count_data.csv"
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/relevant_event_0404_mediawiki_core_weekly_commit_count_data.csv"
 input_df <- read.csv(count_data_fp, header = TRUE) 
 
 input_df$nonbot_commit_count <- input_df$commit_count - input_df$bot_commit_count
@@ -20,14 +20,14 @@ new_authors <- long_df |>
   ggplot(aes(x=relative_week, 
              y=lengthened_commit_count, 
              color=factor(commit_type))) +
-  geom_line() +
   geom_point() + 
+  geom_line() +
   labs(x = "Relative Week", y = "Commits", color="Commit Type") +
   scale_color_manual(values = affiliationColors,
                      labels = c("nonbot_commit_count" = "Total Nonbot Commits",
                                 "unaff_new_commit_count" = "New Unaffiliated Commits",
                                 "wmf_new_commit_count" = "New WMF Commits")) +
-  ggtitle("MW-core Commits Around HTTPS as-default ('New' contributors <= 5 commits before 08-01-2013)") +
+  ggtitle("relevant MW-core Commits Around HTTPS as-default ('New' contributors <= 5 commits before 08-01-2013)") +
   theme_bw() + 
   theme(legend.position = "top")
 new_authors