final updates to commit analysis

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/case1/extensions_visualeditor_commits.csv"
 
 transform_commit_data <- function(filepath){
   #basic, loading in the file 
@@ -51,8 +51,7 @@ transform_commit_data <- function(filepath){
     mutate(relative_week = relative_week(commit_date, event_date)) |>
     arrange(relative_week) |>
     group_by(author_email) |>
-    mutate(first_commit_date = first(commit_date),
+    mutate(new_author = ifelse(row_number() <= 5, 1, 0),
-           new_author = as.numeric(difftime(commit_date, first_commit_date, units = "days") <= 7),
            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()
@@ -144,7 +143,7 @@ transform_commit_data <- function(filepath){
 }
 
 transformed <- transform_commit_data(ve_commit_fp)
-output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0316_extensions_ve_weekly_commit_count_data.csv"
 
 write.csv(transformed, output_filepath, row.names = FALSE)
 

commit_analysis/testing-share-plotting.R

@@ -1,17 +1,17 @@
 library(tidyverse)
-entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
+entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0314_bot_frameworks_weekly_commit_count_data.csv"
 entest_df <- read.csv(entest_fp, header = TRUE) |> mutate(rd_event = "en-testing")
 
-widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
+widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0314_bot_frameworks_weekly_commit_count_data.csv"
 widetest_df <- read.csv(widetest_fp, header = TRUE) |> mutate(rd_event = "wide-testing")
 
-event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_mediawiki_core_weekly_commit_count_data.csv"
+event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0314_bot_frameworks_weekly_commit_count_data.csv"
 event_df <- read.csv(event_fp, header = TRUE) |> mutate(rd_event = "default")
 
 #input_df <- bind_rows(entest_df, widetest_df, event_df)
 #dropping the event (2013-07-01) from the modeling
-input_df <- bind_rows(entest_df, widetest_df)
+#input_df <- bind_rows(entest_df, widetest_df)
-#input_df <- event_df
+input_df <- event_df
 
 input_df <- input_df |>
   mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
@@ -22,32 +22,37 @@ input_df <- input_df |>
 
 #get into mlm format
 long_df <- input_df |>
-  tidyr::pivot_longer(cols = c(other_commit_count, wikimedia_commit_count),
+  tidyr::pivot_longer(cols = c(nonbot_commit_count, other_commit_count, wikimedia_commit_count),
                names_to = "commit_type",
                values_to = "lengthened_commit_count")
+
+summarized_df <- long_df |>
+  group_by(relative_week, commit_type) |>
+  summarise(total_commit_count = sum(lengthened_commit_count, na.rm = TRUE)) |>
+  mutate(rd_event="release")
 #long_df <- input_df |>
 #  tidyr::pivot_longer(cols = c(wmf_ft_commit_count, unaff_ft_commit_count, nonbot_commit_count),
 #               names_to = "commit_type",
 #               values_to = "lengthened_commit_count")
 
-intermediate_long_df <- long_df |>
+#intermediate_long_df <- long_df |>
-  mutate(commit_share = lengthened_commit_count / (nonbot_commit_count)) |>
+#  mutate(commit_share = lengthened_commit_count / (nonbot_commit_count)) |>
-  mutate(log_commits = log1p(lengthened_commit_count))|>
+#  mutate(log_commits = log1p(lengthened_commit_count))|>
-  mutate(scaled_long_commits = lengthened_commit_count / 10) 
+#  mutate(scaled_long_commits = lengthened_commit_count / 10) 
 
 
 window_num <- 4
-final_long_df <- intermediate_long_df |>
+final_long_df <- summarized_df |>
   filter(relative_week >= (- window_num) & relative_week <= (window_num)) 
 
 affiliationColors <-
-  setNames( c('#5da2d8', '#c7756a')
+  setNames( c('black','#5da2d8', '#c7756a')
-            ,c("other_commit_count", "wikimedia_commit_count"))
+            ,c("nonbot_commit_count","other_commit_count", "wikimedia_commit_count"))
 
 
 commit_plot <- final_long_df |>
   ggplot(aes(x=relative_week, 
-              y=lengthened_commit_count, 
+              y=total_commit_count, 
               color=factor(commit_type),
               linetype = rd_event)) +
   geom_line() +
@@ -56,13 +61,13 @@ commit_plot <- final_long_df |>
   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)")) + 
-  ggtitle("mw-core Commits Around Opt-In Testing Events (by Affiliation)") +
+  ggtitle("bot-frameworks Commits Around Wide Release (by Affiliation)") +
   theme_bw() + 
   theme(legend.position = "top")
 commit_plot
 
 
-ggsave(filename = "0314-ve-core-testing-new-commits.png", plot = commit_plot, width = 15, height = 9, dpi = 800)
+ggsave(filename = "0316-bot-frameworks-commits-event.png", plot = commit_plot, width = 15, height = 9, dpi = 800)
 
 total_commit_plot <- final_long_df |>
   ggplot(aes(x=relative_week, 

mgaughan-rstudio-server_24842187.out

@@ -1,18 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3439:32903 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: bkiSrTlWE0y9QQnCxd2p
-
-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 24842187
-slurmstepd: error: *** JOB 24842187 ON n3439 CANCELLED AT 2025-03-14T14:28:50 ***