use papermill to print the notebook as it goes, update the download &…

… unzip commands for repeat runs

.github/workflows/release.yml

@@ -32,7 +32,7 @@ jobs:
     - name: Run Jupyter Notebook
       run: |
         source .venv/bin/activate
-        jupyter nbconvert --to notebook --execute omim_vs_orphanet_comparison.ipynb --output omim_vs_orphanet_comparison_output.ipynb --stdout
+        papermill omim_vs_orphanet_comparison.ipynb output/omim_vs_orphanet_comparison_output.ipynb --log-output        
 
     - name: Get Date for Release Tag
       run: echo "DATE=$(date +%Y-%m-%d)" >> $GITHUB_ENV

omim_vs_orphanet_comparison.ipynb

@@ -43,11 +43,11 @@
     }
    ],
    "source": [
-    "!wget https://data.monarchinitiative.org/monarch-kg/latest/monarch-kg.duckdb.gz\n",
-    "!gunzip monarch-kg.duckdb.gz\n",
-    "!wget https://data.monarchinitiative.org/monarch-kg/latest/phenio.db.gz # consider hpo.db.gz for speed\n",
-    "!gunzip phenio.db.gz\n",
-    "!mkdir output"
+    "!wget -q -nc https://data.monarchinitiative.org/monarch-kg/latest/monarch-kg.duckdb.gz\n",
+    "!gunzip -k monarch-kg.duckdb.gz  # Use -k to keep the original .gz file\n",
+    "!wget -q -nc https://data.monarchinitiative.org/monarch-kg/latest/phenio.db.gz  # consider hpo.db.gz for speed\n",
+    "!gunzip -k phenio.db.gz  # Use -k to keep the original .gz file\n",
+    "!mkdir -p output  # Use -p to avoid error if the directory already exists"
    ]
   },
   {

requirements.txt

@@ -3,3 +3,4 @@ duckdb
 pandas
 fastparquet
 semsimian
+papermill