updating things for the second case study

.sh_history

@@ -65,3 +65,12 @@ cd case1
 ls
 mv event_0314_bot_frameworks_weekly_commit_count_data.csv en-testing_0314_bot_frameworks_weekly_commit_count_data.csv
 ls
+cd ..
+cd case2
+ls
+mv core_2010-01-01_to_2024-12-31.csv mediawiki_core_commits.csv
+mv mediawiki-config_2010-01-01_to_2024-12-31.csv mediawiki_wmfconfig_commits.csv
+ls
+rm event_0403_mediawiki_core_weekly_commit_count_data.csv 
+rm event_0403_mediawiki_wmfconfig_weekly_commit_count_data.csv
+ls

commit_analysis/commit_count_collation.R

@@ -4,7 +4,7 @@ library(lubridate)
 library(tidyr)
 library(purrr)
 
-ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/mediawiki_core_commits.csv"
+ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/mediawiki_wmfconfig_commits.csv"
 
 transform_commit_data <- function(filepath){
   #basic, loading in the file 
@@ -15,7 +15,8 @@ transform_commit_data <- function(filepath){
 
   
   # TODO: this is project/event specific
-  event_date <- as.Date("2013-07-01")
+  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")
   
@@ -61,7 +62,7 @@ transform_commit_data <- function(filepath){
   # 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("2013-06-01"))|>
+    filter(commit_date < as.Date("2013-08-01"))|>
     group_by(author_email) |>
     summarise(commit_count = n()) |>
     filter(commit_count > 5) |>
@@ -164,7 +165,7 @@ transform_commit_data <- function(filepath){
 }
 
 transformed <- transform_commit_data(ve_commit_fp)
-output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0401_mediawiki_core_weekly_commit_count_data.csv"
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/event_0403_mediawiki_wmfconfig_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/case1/event_0401_mediawiki_core_weekly_commit_count_data.csv"
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case2/event_0403_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
@@ -27,13 +27,12 @@ new_authors <- long_df |>
                      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 Wide Release ('New' contributors <= 5 commits before 06-01-2013)") +
+  ggtitle("MW-core Commits Around HTTPS as-default ('New' contributors <= 5 commits before 08-01-2013)") +
   theme_bw() + 
   theme(legend.position = "top")
 new_authors
 
-ggsave(filename = "0401-core-event-new-commits.png", plot = new_authors, width = 12, height = 9, dpi = 800)
-
+ggsave(filename = "0403-https-core-event-new-commits.png", plot = new_authors, width = 12, height = 9, dpi = 800)
 
 
 window_num <- 12
@@ -73,7 +72,7 @@ commit_share_plot <- share_long |>
   geom_point() + 
   labs(x = "Relative Week", y = "Share of Nonbot Commits", color="Commit Author Affiliation") +
   scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
-  ggtitle("VisualEditor Nonbot Commit Share Around Opt-out Deployment") +
+  ggtitle("MW-core Nonbot Commit Share Around HTTPS-as-default") +
   theme_bw() + 
   theme(legend.position = "top")
 commit_share_plot

commit_analysis/testing-share-plotting.R

@@ -48,18 +48,18 @@ affiliationColors <-
   setNames( c('black','#5da2d8', '#c7756a')
             ,c("nonbot_commit_count","other_commit_count", "wikimedia_commit_count"))
 
+#  linetype = rd_event
 
 commit_plot <- final_long_df |>
   ggplot(aes(x=relative_week, 
               y=total_commit_count, 
-              color=factor(commit_type),
-              linetype = rd_event)) +
+              color=factor(commit_type))) +
   geom_line() +
   geom_point() + 
   labs(x = "Relative Week", y = "Commits", linetype = "Testing Event", color="Commit Author Affiliation") +
   scale_color_manual(values = affiliationColors,
                      labels = c("other_commit_count" = "Unaffiliated", "wikimedia_commit_count" = "WMF Affiliated")) + 
-  scale_linetype_discrete(labels = c("enwiki testing (2012-12-11)", "wide testing (2013-04-25)")) + 
+#  scale_linetype_discrete(labels = c("enwiki testing (2012-12-11)", "wide testing (2013-04-25)")) + 
   ggtitle("bot-frameworks Commits Around Wide Release (by Affiliation)") +
   theme_bw() + 
   theme(legend.position = "top")

mgaughan-rstudio-server_25101978.out

@@ -1,18 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3439:60937 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: Uoe+nDeFvcaRiOows2lT
-
-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 25101978
-slurmstepd: error: *** JOB 25101978 ON n3439 CANCELLED AT 2025-04-01T10:12:30 DUE TO TIME LIMIT ***

mgaughan-rstudio-server_25104883.out

@@ -1,17 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3439:60911 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: EKa4WB0aZn3MeC3Huz21
-
-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 25104883