first analysis of VE commit data

.sh_history

@@ -8,3 +8,8 @@ cd ..
 ls
 ls commit_data
 ls commit_data/visualeditor
+cd /mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/
+ls
+rm event_0215_ve_weekly_commit_count_data.csv
+rm announcement_0215_ve_weekly_commit_count_data.csv
+ls

commit_analysis/commit_count_collation.R

@@ -1,8 +1,9 @@
-library(tidyverse)
+#library(tidyverse)
 library(dplyr)
 library(lubridate)
+library(tidyr)
 
-ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/commit_data/visualeditor/VisualEditor_2012-01-01_to_2014-12-31.csv"
+ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/visualeditor_commits.csv"
 
 transform_commit_data <- function(filepath){
   #basic, loading in the file 
@@ -13,7 +14,8 @@ transform_commit_data <- function(filepath){
 
   
   # TODO: this is project/event specific
-  event_date <- as.Date("2013-07-01")
+  #event_date <- as.Date("2013-07-01")
+  event_date <- as.Date("2013-06-06")
   
   # isolate project id
   project_id <- sub("_.*$", "", file_name)
@@ -52,6 +54,7 @@ transform_commit_data <- function(filepath){
                                    project_id = project_id,
                                    age = project_age)
 
+  
   #for each week, get the list of unique authors that committed
   cumulative_authors <- df %>%
     arrange(relative_week) %>%
@@ -79,9 +82,10 @@ transform_commit_data <- function(filepath){
               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.org", author_email)),
-              l10n_commit_count = sum(grepl("l10n-bot@translatewiki.net", author_email)),
-              jenkins_commit_count = sum(grepl("@gerrit.wikimedia.org", author_email)),
+              wikimedia_commit_count = sum(grepl("@wikimedia.org|@wikimedia.de", 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)),
+              jenkins_commit_count = sum(grepl("jenkins-bot@gerrit.wikimedia.org|gerrit@wikimedia.org", author_email)),
               .groups = 'drop') |>
     right_join(complete_weeks_df, by=c("relative_week", "project_id", "age")) |>
     replace_na(list(commit_count = 0)) |>
@@ -89,6 +93,7 @@ transform_commit_data <- function(filepath){
     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)) |>
     mutate(before_after = if_else(relative_week < 0, 0, 1)) 
   # then, to get the authorship details in
   # we check if the email data is present, if not we fill in blank 
@@ -126,8 +131,8 @@ transform_commit_data <- function(filepath){
 
 test <- read.csv(ve_commit_fp, header = TRUE) 
 transformed <- transform_commit_data(ve_commit_fp)
-output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/commit_data/visualeditor/0210_ve_weekly_count_data.csv"
-
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/announcement_0215_ve_weekly_commit_count_data.csv"
+project_id <- "test"
 
 write.csv(transformed, output_filepath, row.names = FALSE)
 

commit_analysis/commit_plotting.R

@@ -0,0 +1,40 @@
+library(tidyverse)
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0215_ve_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
+
+library(scales)
+library(ggplot2)
+
+time_plot <- input_df |>
+  ggplot(aes(x=relative_week, y=jenkins_commit_count)) +
+  labs(x="Weekly Offset", y="Gerrit/Jenkins Commit Count") +
+  geom_smooth() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot
+
+share_df <- input_df |>
+  mutate(wikimedia_share = wikimedia_commit_count / nonbot_commit_count) |>
+  mutate(wikia_share = wikia_commit_count / nonbot_commit_count) |>
+  mutate(gerrit_share = jenkins_commit_count / nonbot_commit_count) |> 
+  mutate(mw_dev_share = mediawiki_dev_commit_count / nonbot_commit_count) |>
+  mutate(other_share = (nonbot_commit_count - jenkins_commit_count - wikia_commit_count - wikimedia_commit_count - mediawiki_dev_commit_count) / nonbot_commit_count)|>
+  drop_na()
+
+share_long <- share_df |>
+  select(relative_week, wikimedia_share, wikia_share, gerrit_share, mw_dev_share, other_share) |>
+  pivot_longer(cols = c(wikimedia_share, wikia_share, gerrit_share, mw_dev_share, other_share), names_to = "category", values_to = "share")
+
+share_plot <- share_long |>
+  ggplot(aes(x=relative_week, y=share, color=category)) +
+  geom_smooth() +
+  geom_vline(xintercept = 0)+
+  labs(x = "Relative Week", y = "Share of Nonbot Commit Count", color = "Affiliation") +
+  ggtitle("Weekly Share of Nonbot Commit Count by Category") +
+  theme_bw() + 
+  theme(legend.position = "top")
+share_plot
+

commit_analysis/mlm.R

@@ -1,18 +0,0 @@
-count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/commit_data/visualeditor/0210_ve_weekly_count_data.csv"
-input_df <- read_csv(count_data_fp)
-
-input_df$nonbot_commit_count <- input_df$commit_count - input_df$l10n_commit_count - input_df$jenkins_commit_count
-
-input_df <- input_df |>
-  filter(relative_week < 79)
-library(scales)
-library(ggplot2)
-
-time_plot <- input_df |>
-  ggplot(aes(x=relative_week, y=wikimedia_commit_count)) +
-  labs(x="Weekly Offset", y="WMF Commit Count") +
-  geom_smooth() +
-  geom_vline(xintercept = 0)+
-  theme_bw() +
-  theme(legend.position = "top")
-time_plot

commit_analysis/models.R

@@ -0,0 +1,45 @@
+library(tidyverse)
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0215_ve_weekly_commit_count_data.csv"
+input_df <- read.csv(count_data_fp, header = TRUE) 
+
+library(rdd)
+
+var(input_df$commit_count) # 1253.343
+mean(input_df$commit_count) # 44.92381
+median(input_df$commit_count) # 39.5
+
+get_optimal_bandwidth <- function(df){
+  bw <- tryCatch({
+    IKbandwidth(df$relative_week, df$commit_count, cutpoint = 0, verbose = FALSE, kernel = "triangular")
+  }, error = function(e) {
+    NA
+  })
+}
+
+optimal_bandwidth <- get_optimal_bandwidth(input_df)
+
+window_num <- 19
+input_df <- input_df |>
+  filter(relative_week >= (- window_num) & relative_week <= (window_num)) |>
+  mutate(other_commit_count = commit_count - bot_commit_count - mediawiki_dev_commit_count - wikia_commit_count - wikimedia_commit_count - jenkins_commit_count)
+
+
+simple_model <- glm.nb(commit_count~before_after*relative_week, data=input_df)
+summary(simple_model)
+
+library(lme4)
+library(dplyr)
+#get into mlm format
+long_df <- input_df |>
+  pivot_longer(cols = c(other_commit_count, wikimedia_commit_count, jenkins_commit_count, wikia_commit_count, mediawiki_dev_commit_count),
+               names_to = "commit_type",
+               values_to = "lengthened_commit_count")
+
+mlm <- glmer.nb(lengthened_commit_count ~ before_after*relative_week + (before_after*relative_week|commit_type),
+                control=glmerControl(optimizer="bobyqa",
+                                     optCtrl=list(maxfun=2e5)), nAGQ=0,
+                data=long_df)
+summary(mlm)
+ranefs <- ranef(mlm)
+print(ranefs)
+saveRDS(mlm, "021525_ve_event_mlm.rda")