From 80c6e2ffba38d475ab17f20d3f687a260ab6f57d Mon Sep 17 00:00:00 2001
From: Matthew Gaughan <mjilg@klone-login03.hyak.local>
Date: Mon, 21 Apr 2025 11:52:30 -0700
Subject: [PATCH] stashing plots for CHASE presentation govdoc

---
 .sh_history                          | 14 +++++++++
 govdoc-cr-age-dist.R                 | 45 ++++++++++++++++++++++++++++
 mgaughan-rstudio-server_25494157.out | 17 +++++++++++
 3 files changed, 76 insertions(+)
 create mode 100644 govdoc-cr-age-dist.R
 create mode 100644 mgaughan-rstudio-server_25494157.out

diff --git a/.sh_history b/.sh_history
index 0d31a35..557db77 100644
--- a/.sh_history
+++ b/.sh_history
@@ -108,3 +108,17 @@ mv event_0401_extensions_ve_weekly_commit_count_data.csv 042125_stale_commits/
 mv event_0401_extensions_ve_weekly_commit_count_data.csv 042125_stale_counts/
 mv event_0401_mediawiki_core_weekly_commit_count_data.csv 042125_stale_counts/
 ls
+cd ..
+ls
+cd ..
+ls
+cd mw-repo-lifecycles
+ls
+cd ..
+ls
+cd govdoc-cr-data
+ls
+cd final_data
+ls
+cd metadata
+ls
diff --git a/govdoc-cr-age-dist.R b/govdoc-cr-age-dist.R
new file mode 100644
index 0000000..44c9ebd
--- /dev/null
+++ b/govdoc-cr-age-dist.R
@@ -0,0 +1,45 @@
+library(dplyr)
+contributing_df_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/CONTRIBUTING_weekly_count_data.csv"
+contributing_df = read.csv(contributing_df_filepath, header = TRUE) 
+
+readme_df_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/README_weekly_count_data.csv"
+readme_df = read.csv(readme_df_filepath, header = TRUE)
+
+combined_df <- bind_rows(
+  contributing_df %>%
+    group_by(project_id) %>%
+    select(project_id, age_at_commit) %>%
+    mutate(document = factor("CONTRIBUTING", levels = c("CONTRIBUTING", "README"))),
+  readme_df %>%
+    group_by(project_id) %>%
+    select(project_id, age_at_commit) %>%
+    mutate(document = factor("README", levels = c("CONTRIBUTING", "README")))
+)
+
+unique_combined_df <- combined_df %>%
+  distinct(project_id, age_at_commit, document)
+
+library(tidyverse)
+library(tidyquant)
+library(ggdist)
+library(ggthemes)
+library(ggplot2)
+
+age_raincloud <- unique_combined_df |>
+  ggplot(aes(x = factor(document), y = age_at_commit, fill = factor(document))) +
+  geom_boxplot(
+    width = 0.12,
+    # removing outliers
+    outlier.color = NA,
+    alpha = 0.5
+  ) +
+  ggplot::stat_dots(
+    # ploting on left side
+    side = "left",
+    # adjusting position
+    justification = 1.1,
+    # adjust grouping (binning) of observations
+    binwidth = 0.25
+  )
+
+age_raincloud
diff --git a/mgaughan-rstudio-server_25494157.out b/mgaughan-rstudio-server_25494157.out
new file mode 100644
index 0000000..c8956bc
--- /dev/null
+++ b/mgaughan-rstudio-server_25494157.out
@@ -0,0 +1,17 @@
+1. SSH tunnel from your workstation using the following command:
+
+   ssh -N -L 8787:n3439:46227 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: AJ9ua2VJPYQLsa6g6Fbq
+
+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 25494157