update to VE commit analysis

commit_analysis/commit_count_collation.R

@@ -3,7 +3,7 @@ library(dplyr)
 library(lubridate)
 library(tidyr)
 
-ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/visualeditor_commits.csv"
+ve_commit_fp <- "/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/mediawiki_core_commits.csv"
 
 transform_commit_data <- function(filepath){
   #basic, loading in the file 
@@ -131,8 +131,7 @@ 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/case1/announcement_0215_ve_weekly_commit_count_data.csv"
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/announcement_0215_core_weekly_commit_count_data.csv"
-project_id <- "test"
 
 write.csv(transformed, output_filepath, row.names = FALSE)
 

commit_analysis/commit_plotting.R

@@ -4,18 +4,24 @@ input_df <- read.csv(count_data_fp, header = TRUE)
 
 input_df$nonbot_commit_count <- input_df$commit_count - input_df$bot_commit_count
 
+window_num <- 19
+input_df <- input_df |>
+  filter(relative_week >= (- window_num) & relative_week <= (window_num))
+
 library(scales)
 library(ggplot2)
 
 time_plot <- input_df |>
-  ggplot(aes(x=relative_week, y=jenkins_commit_count)) +
+  ggplot(aes(x=relative_week, y=wikimedia_commit_count)) +
-  labs(x="Weekly Offset", y="Gerrit/Jenkins Commit Count") +
+  labs(x="Weekly Offset", y="Wikimedia Commit Count") +
   geom_smooth() +
   geom_vline(xintercept = 0)+
   theme_bw() +
   theme(legend.position = "top")
 time_plot
 
+library(dplyr)
+
 share_df <- input_df |>
   mutate(wikimedia_share = wikimedia_commit_count / nonbot_commit_count) |>
   mutate(wikia_share = wikia_commit_count / nonbot_commit_count) |>
@@ -25,7 +31,7 @@ share_df <- input_df |>
   drop_na()
 
 share_long <- share_df |>
-  select(relative_week, wikimedia_share, wikia_share, gerrit_share, mw_dev_share, other_share) |>
+  dplyr::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 |>
@@ -33,7 +39,7 @@ share_plot <- share_long |>
   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") +
+  ggtitle("Weekly Share of Nonbot Commit Count by Affiliation") +
   theme_bw() + 
   theme(legend.position = "top")
 share_plot

commit_analysis/models.R

@@ -1,5 +1,5 @@
 library(tidyverse)
-count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0215_ve_weekly_commit_count_data.csv"
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0215_core_weekly_commit_count_data.csv"
 input_df <- read.csv(count_data_fp, header = TRUE) 
 
 library(rdd)
@@ -18,23 +18,29 @@ get_optimal_bandwidth <- function(df){
 
 optimal_bandwidth <- get_optimal_bandwidth(input_df)
 
-window_num <- 19
+window_num <- 13
 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)
 
+library(MASS)
 
 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")
 
+long_df <- long_df |>
+  mutate(commit_share = lengthened_commit_count / (commit_count - bot_commit_count)) |>
+  mutate(log_commits = log1p(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,
@@ -42,4 +48,4 @@ mlm <- glmer.nb(lengthened_commit_count ~ before_after*relative_week + (before_a
 summary(mlm)
 ranefs <- ranef(mlm)
 print(ranefs)
-saveRDS(mlm, "021525_ve_event_mlm.rda")
+saveRDS(mlm, "021525_core-ve_event_mlm.rda")

mgaughan-rstudio-server_24263466.out

@@ -0,0 +1,18 @@
+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 ***