bad categorization data, some restructuring of the repo

p1-categorization.log

@@ -1,9 +0,0 @@
-starting the job at: Fri May 30 16:42:23 CDT 2025
-setting up the environment
-running the p1 categorization script
-cuda
-NVIDIA A100-SXM4-80GB
-_CudaDeviceProperties(name='NVIDIA A100-SXM4-80GB', major=8, minor=0, total_memory=81153MB, multi_processor_count=108, uuid=538f89e4-00a7-cb2f-926e-0455eeb36701, L2_cache_size=40MB)
-
Loading checkpoint shards:   0%|          | 0/6 [00:00<?, ?it/s]
Loading checkpoint shards:  17%|█▋        | 1/6 [00:00<00:03,  1.49it/s]
Loading checkpoint shards:  33%|███▎      | 2/6 [00:01<00:03,  1.22it/s]
Loading checkpoint shards:  50%|█████     | 3/6 [00:02<00:02,  1.10it/s]
Loading checkpoint shards:  67%|██████▋   | 4/6 [00:03<00:01,  1.09it/s]
Loading checkpoint shards:  83%|████████▎ | 5/6 [00:04<00:00,  1.05it/s]
Loading checkpoint shards: 100%|██████████| 6/6 [00:05<00:00,  1.22it/s]
Loading checkpoint shards: 100%|██████████| 6/6 [00:05<00:00,  1.17it/s]
-job finished, cleaning up
-job pau at: Fri May 30 18:29:50 CDT 2025

readme.txt

@@ -12,3 +12,11 @@ models\
 studies\
 - the pdf files for the final sample of studies
 
+containers\
+- requisite containers for running language analysis on HPC
+
+viz\
+- scripts for making visualizations out of any of our analyses
+
+successful_logs\
+- for posterity's sake, the logs of correct analyses

viz/sankey.R

@@ -0,0 +1,4 @@
+data <- read.csv("/home/mgaughan/git/adaptation-slr/cites/053025_olmo_categorized_citations.csv")
+
+# ggsankey
+# https://r-charts.com/flow/sankey-diagram-ggplot2/

viz/shell.nix

@@ -0,0 +1,21 @@
+{
+  pkgs ? import <nixpkgs> { },
+}:
+
+pkgs.mkShell {
+  name = "viz-playground-slr";
+  packages = with pkgs; [
+   pkgs.R
+   pkgs.rPackages.httr
+   pkgs.rPackages.ggplot2
+   pkgs.rPackages.tidytuesdayR
+   pkgs.rPackages.tidyverse
+   pkgs.rPackages.ggdist
+   pkgs.rPackages.scatterpie
+   git
+  ];
+  shellHook = ''
+  echo "trying to find a good quote for here"
+  '';
+}
+