hestia-earth-models 0.74.5__tar.gz → 0.74.7__tar.gz

{hestia_earth_models-0.74.5 → hestia_earth_models-0.74.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hestia_earth_models
-Version: 0.74.5
+Version: 0.74.7
 Summary: HESTIA's set of modules for filling gaps in the activity data using external datasets (e.g. populating soil properties with a geospatial dataset using provided coordinates) and internal lookups (e.g. populating machinery use from fuel use). Includes rules for when gaps should be filled versus not (e.g. never gap fill yield, gap fill crop residue if yield provided etc.).
 Home-page: https://gitlab.com/hestia-earth/hestia-engine-models
 Author: HESTIA Team

{hestia_earth_models-0.74.5 → hestia_earth_models-0.74.7}/hestia_earth/models/hestia/default_resourceUse.py

@@ -1,4 +1,4 @@
-from hestia_earth.schema import IndicatorMethodTier, TermTermType
+from hestia_earth.schema import TermTermType
 from hestia_earth.utils.tools import flatten, safe_parse_float
 
 from hestia_earth.models.log import logRequirements, logShouldRun, debugValues
@@ -8,6 +8,8 @@ from hestia_earth.models.utils.indicator import _new_indicator
 from hestia_earth.models.utils.background_emissions import no_gap_filled_background_emissions
 from hestia_earth.models.utils.term import get_lookup_value
 from hestia_earth.models.utils.input import unique_background_inputs
+from hestia_earth.models.utils.impact_assessment import get_product
+from hestia_earth.models.utils.crop import get_landCover_term_id
 from . import MODEL
 
 REQUIREMENTS = {
@@ -29,8 +31,7 @@ REQUIREMENTS = {
 RETURNS = {
     "Indicator": [{
         "value": "",
-        "inputs": "",
-        "methodTier": "background"
+        "inputs": ""
     }]
 }
 LOOKUPS = {
@@ -38,14 +39,12 @@ LOOKUPS = {
     "organicFertiliser": "backgroundEmissionsResourceUseDefaultValue"
 }
 MODEL_KEY = 'default_resourceUse'
-TIER = IndicatorMethodTier.BACKGROUND.value
 
 
-def _indicator(term_id: str, value: float, input: dict):
-    indicator = _new_indicator(term_id, MODEL)
+def _indicator(term_id: str, value: float, input: dict, land_cover_id: str):
+    indicator = _new_indicator(term_id, MODEL, land_cover_id)
     indicator['value'] = value
     indicator['inputs'] = [input]
-    indicator['methodTier'] = TIER
     return indicator
 
 
@@ -53,8 +52,12 @@ def _default_value(input: dict):
     return safe_parse_float(get_lookup_value(input.get('term', {}), LOOKUPS['organicFertiliser']), default=None)
 
 
-def _run_input(impact: dict):
+def _run_input(impact: dict, land_cover_id: str):
     required_resourceUse_term_ids = background_emissions_in_system_boundary(impact, TermTermType.RESOURCEUSE)
+    # remove landTransformation as need `previousLandCover` to be valid
+    required_resourceUse_term_ids = [
+        v for v in required_resourceUse_term_ids if not v.startswith('landTransformation')
+    ]
 
     def run(input: dict):
         input_term = input.get('input').get('term')
@@ -62,14 +65,14 @@ def _run_input(impact: dict):
         value = input.get('default-value-from-lookup')
 
         for emission_id in required_resourceUse_term_ids:
-            logShouldRun(impact, MODEL, term_id, True, methodTier=TIER, model_key=MODEL_KEY, emission_id=emission_id)
+            logShouldRun(impact, MODEL, term_id, True, model_key=MODEL_KEY, emission_id=emission_id)
             debugValues(impact, model=MODEL, term=emission_id,
                         value=value,
                         coefficient=1,
                         input=term_id)
 
         return [
-            _indicator(term_id, value, input_term) for term_id in required_resourceUse_term_ids
+            _indicator(term_id, value, input_term, land_cover_id) for term_id in required_resourceUse_term_ids
         ]
 
     return run
@@ -95,18 +98,21 @@ def _should_run(impact: dict):
         ])
     ]
 
-    should_run = all([bool(valid_inputs)])
+    landCover_term_id = get_landCover_term_id(get_product(impact).get("term", {}))
+
+    should_run = all([bool(valid_inputs), landCover_term_id])
 
     for input in inputs:
         term_id = input.get('input').get('term', {}).get('@id')
 
         logRequirements(impact, model=MODEL, term=term_id, model_key=MODEL_KEY,
-                        **_omit(input, ['input', 'input-value']))
-        logShouldRun(impact, MODEL, term_id, should_run, methodTier=TIER, model_key=MODEL_KEY)
+                        **_omit(input, ['input', 'input-value']),
+                        landCover_term_id=landCover_term_id)
+        logShouldRun(impact, MODEL, term_id, should_run, model_key=MODEL_KEY)
 
-    return should_run, valid_inputs
+    return should_run, valid_inputs, landCover_term_id
 
 
 def run(impact: dict):
-    should_run, grouped_inputs = _should_run(impact)
-    return flatten(map(_run_input(impact), grouped_inputs)) if should_run else []
+    should_run, grouped_inputs, landCover_term_id = _should_run(impact)
+    return flatten(map(_run_input(impact, landCover_term_id), grouped_inputs)) if should_run else []

{hestia_earth_models-0.74.5 → hestia_earth_models-0.74.7}/hestia_earth/models/hestia/landOccupationDuringCycle.py

@@ -120,7 +120,7 @@ def _extract_site_data(cycle: dict, land_cover_id: dict):
         duration=cycle.get("siteDuration"),
         unused_duration=cycle.get("siteUnusedDuration"),
         country_id=site.get("country", {}).get("@id"),
-        land_cover_id=land_cover_id or get_landCover_term_id_from_site_type(site.get("siteType", {}))
+        land_cover_id=land_cover_id or get_landCover_term_id_from_site_type(site.get("siteType"))
     )
 
     is_valid = _should_run_site_data(site_data)
@@ -145,7 +145,7 @@ def _extract_other_sites_data(cycle: dict, land_cover_id: dict):
             duration=duration,
             unused_duration=unused_duration,
             country_id=site.get("country", {}).get("@id"),
-            land_cover_id=land_cover_id or get_landCover_term_id_from_site_type(site.get("siteType", {}))
+            land_cover_id=land_cover_id or get_landCover_term_id_from_site_type(site.get("siteType"))
         ) for (
             site,
             area,

{hestia_earth_models-0.74.5 → hestia_earth_models-0.74.7}/hestia_earth/models/hestia/seed_emissions.py

@@ -12,7 +12,7 @@ from hestia_earth.models.utils import _omit, group_by
 from hestia_earth.models.utils.emission import _new_emission
 from hestia_earth.models.utils.site import valid_site_type
 from hestia_earth.models.utils.cycle import cycle_end_year
-from hestia_earth.models.utils.crop import get_crop_grouping_faostat_production, get_landCover_term_id
+from hestia_earth.models.utils.crop import get_crop_lookup_value, get_landCover_term_id
 from hestia_earth.models.utils.completeness import _is_term_type_complete
 from hestia_earth.models.utils.term import get_lookup_value
 from hestia_earth.models.utils.lookup import get_region_lookup_value
@@ -59,6 +59,7 @@ LOOKUPS = {
     "crop": [
         "correspondingSeedTermIds",
         "cropGroupingFaostatProduction",
+        "cropGroupingFaostatProductionProxy",
         "global_economic_value_share",
         "landCoverTermId"
     ],
@@ -154,23 +155,38 @@ def _filter_emissions(cycle: dict):
     )), emissions_per_group
 
 
-def _evs(product: dict):
-    return safe_parse_float(
-        get_lookup_value(product.get('term', {}), 'global_economic_value_share', model=MODEL, model_key=MODEL_KEY),
-        default=None
-    ) or product.get('economicValueShare')
+def _crop_data(product: dict, country_id: str, end_year: int):
+    term = product.get('term', {})
+    term_id = term.get('@id')
 
+    crop_grouping = get_crop_lookup_value(MODEL, term_id, term_id, 'cropGroupingFaostatProduction')
+    crop_grouping_proxy = get_crop_lookup_value(MODEL, term_id, term_id, 'cropGroupingFaostatProductionProxy')
 
-def _faostat_yield(country_id: str, end_year: int, product: dict):
-    grouping = get_crop_grouping_faostat_production(MODEL, product.get('term', {}))
-    value = extract_grouped_data_closest_date(get_region_lookup_value(
+    faostat_yield = safe_parse_float(extract_grouped_data_closest_date(get_region_lookup_value(
         'region-crop-cropGroupingFaostatProduction-yield.csv',
         country_id,
-        grouping,
+        crop_grouping_proxy or crop_grouping,
         model=MODEL,
         model_key=MODEL_KEY
-    ), end_year)
-    return safe_parse_float(value, default=None)
+    ), end_year), default=None)
+
+    # when using proxy, we cannot use the lookup value as it won't correspond to the primary product
+    global_evs = None if crop_grouping_proxy else safe_parse_float(
+        get_lookup_value(product.get('term', {}), 'global_economic_value_share', model=MODEL, model_key=MODEL_KEY),
+        default=None
+    )
+    product_evs = product.get('economicValueShare')
+
+    return {
+        'product-id': term_id,
+        'seed-id': get_lookup_value(term, 'correspondingSeedTermIds', model=MODEL, model_key=MODEL_KEY) or None,
+        'economicValueShare': global_evs or product_evs,
+        'FAOSTAT-yield': faostat_yield,
+        'landCover-id': get_landCover_term_id(term, model=MODEL, model_key=MODEL_KEY)
+    } | (
+        # skip using product yield if proxy is used
+        {} if crop_grouping_proxy else {'product-yield': list_sum(product.get('value'))}
+    )
 
 
 def _group_seed_inputs(inputs: list):
@@ -191,18 +207,7 @@ def _should_run(cycle: dict):
     country_id = cycle.get('site', {}).get('country', {}).get('@id')
 
     # only keep the crop products that map to a seed
-    crop_products = [
-        {
-            'product': product.get('term', {}).get('@id'),
-            'seed-id': get_lookup_value(
-                product.get('term', {}), 'correspondingSeedTermIds', model=MODEL, model_key=MODEL_KEY) or None,
-            'economicValueShare': _evs(product),
-            'FAOSTAT-yield': _faostat_yield(country_id, end_year, product),
-            'product-yield': list_sum(product.get('value')),
-            'landCover-id': get_landCover_term_id(product.get('term', {}), model=MODEL, model_key=MODEL_KEY)
-        }
-        for product in crop_products
-    ]
+    crop_products = [_crop_data(product, country_id, end_year) for product in crop_products]
     valid_crop_products = [
         value for value in crop_products if all([
             value.get('seed-id'),