Merge pull request #10324 from gem/fix_consequences

Added utils/fix_consequences

debian/changelog

@@ -1,4 +1,6 @@
   [Michele Simionato]
+  * Added utils/fix_consequences to fix consequence.csv files
+    containing risk_ids rather than taxonomies, now invalid
   * Implemented quantiles in scenario_risk, visible in aggrisk_tags
   * Added checks on the consequence functions across taxonomies and perils
   * Fixed the taxonomy field in consequences.csv to be the exposure

utils/fix_consequences

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# vim: tabstop=4 shiftwidth=4 softtabstop=4
+#
+# Copyright (C) 2025, GEM Foundation
+#
+# OpenQuake is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+# 
+# OpenQuake is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+# 
+# You should have received a copy of the GNU Affero General Public License
+# along with OpenQuake.  If not, see <http://www.gnu.org/licenses/>.
+
+import pandas
+from openquake.baselib import sap
+
+
+# fix old consequence functions before engine version 3.23
+def main(taxonomy_mapping: str, consequences: str):
+    """
+    Use the taxonomy mapping to upgrade risk_id-based consequence functions
+    to taxonomy-based consequence functions
+    """
+    tmap = pandas.read_csv(taxonomy_mapping).set_index('conversion')
+    cons = pandas.read_csv(consequences).set_index('taxonomy')
+    cols = ['taxonomy'] + list(cons.columns)
+    df = cons.join(tmap, how='inner')[cols]
+    df.index.names = ['risk_id']
+    dfs = []
+    for _, grp in df.groupby(['taxonomy', 'consequence', 'loss_type']):
+        dfs.append(grp[0:1])  # take the first row
+    pandas.concat(dfs).to_csv(consequences)
+
+
+if __name__ == '__main__':
+    sap.run(main)