hestia-earth-models 0.70.5__py3-none-any.whl → 0.71.0__py3-none-any.whl

hestia_earth/models/hestia/management.py

@@ -135,9 +135,9 @@ def management(data: dict):
     return node
 
 
-def _get_cycle_duration(cycle: dict, land_cover_id: str):
+def _get_cycle_duration(cycle: dict, land_cover_id: str = None):
     cycle_duration = cycle.get('cycleDuration')
-    lookup_value = None if cycle_duration else safe_parse_float(get_table_value(
+    lookup_value = None if cycle_duration or not land_cover_id else safe_parse_float(get_table_value(
         download_lookup("crop.csv"),
         column_name('landCoverTermId'),
         land_cover_id,
@@ -157,7 +157,7 @@ def _gap_filled_date_obj(date_str: str, mode: str = DatestrGapfillMode.END) -> d
     )
 
 
-def _gap_filled_start_date(land_cover_id: str, end_date: str, cycle: dict) -> dict:
+def _gap_filled_start_date(cycle: dict, end_date: str, land_cover_id: str = None) -> dict:
     """If possible, gap-fill the startDate based on the endDate - cycleDuration"""
     cycle_duration = _get_cycle_duration(cycle, land_cover_id)
     return {
@@ -216,9 +216,9 @@ def _get_relevant_items(cycle: dict, item_name: str, term_types: List[TermTermTy
         _include_with_date_gap_fill(cycle, ["startDate", "endDate"]) |
         _include(
             _gap_filled_start_date(
-                land_cover_id=get_landCover_term_id(item.get('term', {})),
+                cycle=cycle,
                 end_date=item.get("endDate") if "endDate" in item else cycle.get("endDate", ""),
-                cycle=cycle
+                land_cover_id=get_landCover_term_id(item.get('term', {})),
             ) if "startDate" not in item else {},
             "startDate"
         ) |
@@ -255,12 +255,17 @@ def _run_from_siteType(site: dict, cycle: dict):
     site_type = site.get('siteType')
     site_type_id = get_landCover_term_id_from_site_type(site_type) if site_type not in _SKIP_LAND_COVER_SITE_TYPES \
         else None
+    start_date = cycle.get('startDate') or _gap_filled_start_date(
+        cycle=cycle,
+        end_date=cycle.get('endDate'),
+        land_cover_id=site_type_id
+    ).get('startDate')
 
-    should_run = all([site_type_id])
+    should_run = all([site_type_id, start_date])
     return [{
         'id': site_type_id,
         'value': 100,
-        'startDate': cycle.get('startDate'),
+        'startDate': start_date,
         'endDate': cycle.get('endDate')
     }] if should_run else []
 

hestia_earth/models/hestia/seed_emissions.py

@@ -98,6 +98,23 @@ def _run(cycle: dict, economicValueShare: float, total_yield: float, seed_input:
     ]
 
 
+def _map_group_emissions(group_id: str, required_emission_term_ids: list, emission_ids: list):
+    lookup = download_lookup('emission.csv')
+    emissions = list(filter(
+        lambda id: id in required_emission_term_ids,
+        find_term_ids_by(lookup, column_name('inputProductionGroupId'), group_id)
+    ))
+    included_emissions = list(filter(lambda v: v in emission_ids, emissions))
+    missing_emissions = list(filter(lambda v: v not in emission_ids, emissions))
+    return {
+        'id': group_id,
+        'total-emissions': len(emissions),
+        'included-emissions': len(included_emissions),
+        'missing-emissions': '-'.join(missing_emissions),
+        'is-valid': len(emissions) == len(included_emissions)
+    }
+
+
 def _filter_emissions(cycle: dict):
     required_emission_term_ids = cycle_emissions_in_system_boundary(cycle)
 
@@ -117,31 +134,12 @@ def _filter_emissions(cycle: dict):
     group_ids = set([v.get('group-id') for v in emissions if v.get('group-id')])
 
     # for each group, get the list of all required emissions
-    lookup = download_lookup('emission.csv')
     emissions_per_group = [
-        {
-            'id': group_id,
-            'emissions': list(filter(
-                lambda id: id in required_emission_term_ids,
-                find_term_ids_by(lookup, column_name('inputProductionGroupId'), group_id)
-            ))
-        }
+        _map_group_emissions(group_id, required_emission_term_ids, emission_ids)
         for group_id in group_ids
     ]
-    emissions_per_group = [
-        {
-            'id': group.get('id'),
-            'total-emissions': len(group.get('emissions', [])),
-            'included-emissions': len(list(filter(lambda v: v in emission_ids, group.get('emissions', [])))),
-            'missing-emissions': '-'.join(list(filter(lambda v: v not in emission_ids, group.get('emissions', []))))
-        }
-        for group in emissions_per_group
-    ]
     # only keep groups that have all emissions present in the Cycle
-    valid_groups = list(filter(
-        lambda group: group.get('total-emissions') == group.get('included-emissions'),
-        emissions_per_group
-    ))
+    valid_groups = list(filter(lambda group: group.get('is-valid'), emissions_per_group))
     valid_group_ids = set([v.get('id') for v in valid_groups])
 
     # finally, only return emissions which groups are valid
@@ -273,6 +271,12 @@ def _should_run(cycle: dict):
 
         logShouldRun(cycle, MODEL, term_id, should_run, methodTier=TIER, model_key=MODEL_KEY)
 
+        # log missing emissions to show in the logs
+        for group in emissions_per_group:
+            if not group.get('is-valid'):
+                logShouldRun(cycle, MODEL, term_id, False,
+                             methodTier=TIER, model_key=MODEL_KEY, emission_id=group.get('id'))
+
     return should_run, total_economicValueShare, total_yield, grouped_seed_inputs, grouped_emissions