diff --git a/datasets/compress.sh b/datasets/compress.sh
index dd5f498..c24b800 100755
--- a/datasets/compress.sh
+++ b/datasets/compress.sh
@@ -1,6 +1,7 @@
 #!/bin/bash
 
 filenames=( $(ls job_codings_v3*.csv) )
+filenames=( ${filenames[@]} "clustering_progress.csv" )
 filenames=( ${filenames[@]} $(ls job_metadata*.csv) )
 filenames=( ${filenames[@]} $( ls job_similarities_*.csv ) )