initial gerrit analysis for ve

bot_activity_analysis/bot_activity_exploration.R

@@ -59,24 +59,25 @@ count_mean <- mean(combined_df$count) #628.119
 count_var_to_mean <- count_var / count_mean #2262140.471
 
 # the mean count values for each day
-summary_df <- combined_df |>
+wiki_summary_df <- combined_df |>
+  filter(date >= as.Date("2013-01-01") & date <= as.Date("2013-12-31")) |>
+  filter(wiki_db == "enwiki") |>
   group_by(date) |>
   summarize(
-    mean_count = mean(count),
+    sum_count = sum(count),
     median_count = median(count)
   )
 #plotting it
-p1 <- ggplot(summary_df, aes(x = date, y = median_count)) +
-  geom_line(color = "blue") +     # Line plot
-  geom_point(color = "red") +     # Points on the line
+p1 <- ggplot(wiki_summary_df, aes(x = date, y = sum_count)) +
+  geom_line(color = "blue") +     # Line plot    # Points on the line
   geom_vline(xintercept = as.Date("2013-07-01"), linetype = "dashed", color = "black") +
-  labs(title = "Median Bot Actions",
-       x = "Date",
-       y = "Median Count") +
+  labs(title = "enwiki Total Bot Actions",
+       x = "Date (daily)",
+       y = "Action Count") +
   theme_minimal()    
 p1
-p1_5 <- ggplot(summary_df, aes(x = date)) +
-  geom_smooth(aes(y = median_count), method = "loess", color = "red", fill = "red", alpha = 0.2, se = TRUE) +
+p1_5 <- ggplot(enwiki_summary_df, aes(x = date)) +
+  geom_smooth(aes(y = sum_count), method = "loess", color = "red", fill = "red", alpha = 0.2, se = TRUE) +
   #geom_point(color = "red") +     # Points on the line
   labs(title = "Median Bot Actions",
        x = "Date",

commit_analysis/commit_count_collation.R

@@ -36,9 +36,9 @@ transform_commit_data <- function(filepath){
   
   #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(24)
+  calculated_start_date <- event_date %m-% months(12)
   start_date <- max(calculated_start_date, oldest_commit_date)
-  end_date <- event_date %m+% months(24)
+  end_date <- event_date %m+% months(12)
   
   #getting the relative weeks to the publication date
   relative_week <- function(date, ref_date) {

gerrit_analysis/make_gerrit_count_data.R

@@ -0,0 +1,65 @@
+library(tidyverse)
+
+gerrit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/0214_ve_gerrit_test.csv"
+input_df <- read.csv(gerrit_fp, header = TRUE) 
+
+transform_gerrit_data <- function(data_fp, projects){
+  #loading in
+  df <- read.csv(data_fp, header = TRUE) 
+  #some initial pre-processing
+  df <- df |>
+    filter(project %in% projects) |>
+    mutate(created = ymd_hms(created)) |>
+    mutate(updated = ymd_hms(updated)) |>
+    mutate(submitted = ymd_hms(submitted))
+  
+  event_date <- as.Date("2013-07-01")
+  
+  oldest_created_date <- min(as.Date(df$created))
+  calculated_start_date <- event_date %m-% months(24)
+  start_date <- max(calculated_start_date, oldest_created_date)
+  end_date <- event_date %m+% months(24)
+  
+  relative_week <- function(date, ref_date) {
+    as.integer(as.numeric(difftime(date, ref_date, units = "days")) %/% 7)
+  }
+  
+  #going off of the created date 
+  df <- df |>
+    mutate(relative_week = relative_week(created, event_date)) |>
+    mutate(create_update_delta = as.numeric(difftime(updated, created, units="days")))
+  
+  
+  #creating filler zeros
+  unique_projects <- unique(df$project)
+  unique_statuses <- unique(df$status)
+  all_weeks <- seq(relative_week(start_date, event_date), relative_week(end_date, event_date))
+  complete_weeks_df <- expand.grid(
+    project = unique_projects,
+    relative_week = all_weeks,
+    status = unique_statuses
+  )
+  
+  weekly_commits <- df |>
+    group_by(project, relative_week, status) |>
+    summarise(task_count = n(),
+              avg_resolution_time = mean(create_update_delta, na.rm = TRUE),
+              avg_insertions = mean(insertions, na.rm=TRUE),
+              avg_deletions = mean(deletions, na.rm=TRUE),
+              .groups = 'drop') |>
+    right_join(complete_weeks_df, 
+               by=c("project", "relative_week", "status")) |>
+    replace_na(list(task_count = 0)) |>
+    replace_na(list(avg_resolution_time = 0 ))
+  
+  return(weekly_commits)
+}
+
+transformed_data <- transform_gerrit_data(gerrit_fp, c("VisualEditor/VisualEditor", 
+                                                       "mediawiki/extensions", 
+                                                       "mediawiki/core", 
+                                                       "mediawiki/extensions/VisualEditor"))
+
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0216_ve_gerrit_count.csv"
+
+write.csv(transformed_data, output_filepath, row.names = FALSE)

gerrit_analysis/plotting_gerrit.R

@@ -0,0 +1,61 @@
+library(tidyverse)
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0216_ve_gerrit_count.csv"
+input_df <- read.csv(count_data_fp, header = TRUE) 
+
+
+#window_num <- 19
+window_num <- 52
+input_df <- input_df |>
+  filter(relative_week >= (- window_num) & relative_week <= (window_num)) |>
+  mutate(parent_projects = if_else(project == "mediawiki/extensions/VisualEditor", 
+                                                       "mediawiki/extensions", project))
+
+library(scales)
+library(ggplot2)
+
+time_plot <- input_df |>
+  ggplot(aes(x=relative_week, y=task_count, color=parent_projects)) +
+  labs(x="Weekly Offset", y="New Gerrit Tasks Created", color = "Project") +
+  geom_smooth() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot
+
+
+abandoned_df <- input_df |>
+  filter(status == "ABANDONED")
+time_plot <- abandoned_df |>
+  ggplot(aes(x=relative_week, y=task_count, color=parent_projects)) +
+  labs(x="Weekly Offset", y="AbandonedGerrit Tasks Created", color = "Project") +
+  geom_line() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot
+
+
+delta_df <- input_df |>
+  filter(task_count != 0) |>
+  filter(relative_week >= (- 12)) 
+time_plot <- delta_df |>
+  ggplot(aes(x=relative_week, y=avg_resolution_time, color=parent_projects)) +
+  labs(x="Weekly Offset", y="Avg. (weekly) Time from task creation to last update (days)", color = "Project") +
+  geom_line() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot
+
+
+loc_df <- input_df |>
+  filter(task_count != 0) |>
+  filter(status != "ABANDONED")
+time_plot <- loc_df |>
+  ggplot(aes(x=relative_week, y=avg_deletions, color=parent_projects)) +
+  labs(x="Weekly Offset", y="Avg. LOC Deleted per Accepted Gerrit Task", color = "Project") +
+  geom_line() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot

mgaughan-rstudio-server_24263466.out

@@ -1,18 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3439:56403 mjilg@klone.hyak.uw.edu
-
-   and point your web browser to http://localhost:8787
-
-2. log in to RStudio Server using the following credentials:
-
-   user: mjilg
-   password: 8aREIl1dg0jceqBTNl9a
-
-When done using RStudio Server, terminate the job by:
-
-1. Exit the RStudio Session ("power" button in the top right corner of the RStudio window)
-2. Issue the following command on the login node:
-
-      scancel -f 24263466
-slurmstepd: error: *** JOB 24263466 ON n3439 CANCELLED AT 2025-02-15T16:52:54 ***