better debugging error and fix config YAML comment

jbloomlab · Feb 27, 2024 · 3098484 · 3098484
1 parent 0978b34
commit 3098484
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/SARS2-spike-predictor-phenos.ipynb b/SARS2-spike-predictor-phenos.ipynb
@@ -219,7 +219,9 @@
     "    .query(\"clade != 'other'\")\n",
     ")\n",
     "assert len(pango_growth) == pango_growth[\"clade\"].nunique()\n",
-    "assert set(pango_growth[\"clade\"]).issubset(pango_clades)\n",
+    "extra_growth_clades = set(pango_growth[\"clade\"]) - set(pango_clades)\n",
+    "if extra_growth_clades:\n",
+    "    raise ValueError(f\"some clades have growth data but are not defined {extra_growth_clades}\")\n",
     "\n",
     "print(f\"Read growth data for {len(pango_growth)} clades\")"
    ]

diff --git a/config.yaml b/config.yaml
@@ -38,7 +38,7 @@ pango_json: https://raw.githubusercontent.com/corneliusroemer/pango-sequences/ma
 # Pango clade growth estimates from https://github.com/nextstrain/forecasts-ncov/
 # Indicate a specific date or just latest version. Below specifies the latest version.
 # To specify a specific date, change the `latest` in the file name to the date, as in:
-# https://data.nextstrain.org/files/workflows/forecasts-ncov/gisaid/nextstrain_clades/global/mlr/2024-02-25_results.json
+# https://data.nextstrain.org/files/workflows/forecasts-ncov/gisaid/pango_lineages/global/mlr/2024-02-25_results.json
 pango_growth_json: https://data.nextstrain.org/files/workflows/forecasts-ncov/gisaid/pango_lineages/global/mlr/latest_results.json
 
 # Indicate whether each clade is descendant of each of these parent clades, according definitions in `pango_json`