hestia-earth-models 0.70.3__tar.gz → 0.70.4__tar.gz

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hestia_earth_models
-Version: 0.70.3
+Version: 0.70.4
 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-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/geospatialDatabase/altitude.py

@@ -27,6 +27,7 @@ EE_PARAMS = {
     'collection': 'USGS/GMTED2010_FULL',
     'ee_type': 'raster',
     'band_name': 'med',
+    'reducer': 'mode',
     'is_image': True
 }
 BIBLIO_TITLE = 'An Enhanced Global Elevation Model Generalized From Multiple Higher Resolution Source Datasets'

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/geospatialDatabase/clayContent.py

@@ -92,14 +92,14 @@ def _run(site: dict):
 def _should_run(site: dict):
     contains_geospatial_data = has_geospatial_data(site)
     below_max_area_size = should_download(TERM_ID, site)
-    has_original_texture_measurements = has_original_by_ids(site.get('measurements', []), SOIL_TEXTURE_IDS)
+    has_no_original_texture_measurements = not has_original_by_ids(site.get('measurements', []), SOIL_TEXTURE_IDS)
 
     logRequirements(site, model=MODEL, term=TERM_ID,
                     contains_geospatial_data=contains_geospatial_data,
                     below_max_area_size=below_max_area_size,
-                    has_original_texture_measurements=has_original_texture_measurements)
+                    has_no_original_texture_measurements=has_no_original_texture_measurements)
 
-    should_run = all([contains_geospatial_data, below_max_area_size, not has_original_texture_measurements])
+    should_run = all([contains_geospatial_data, below_max_area_size, has_no_original_texture_measurements])
     logShouldRun(site, MODEL, TERM_ID, should_run)
     return should_run
 

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/geospatialDatabase/sandContent.py

@@ -92,14 +92,14 @@ def _run(site: dict):
 def _should_run(site: dict):
     contains_geospatial_data = has_geospatial_data(site)
     below_max_area_size = should_download(TERM_ID, site)
-    has_original_texture_measurements = has_original_by_ids(site.get('measurements', []), SOIL_TEXTURE_IDS)
+    has_no_original_texture_measurements = not has_original_by_ids(site.get('measurements', []), SOIL_TEXTURE_IDS)
 
     logRequirements(site, model=MODEL, term=TERM_ID,
                     contains_geospatial_data=contains_geospatial_data,
                     below_max_area_size=below_max_area_size,
-                    has_original_texture_measurements=has_original_texture_measurements)
+                    has_no_original_texture_measurements=has_no_original_texture_measurements)
 
-    should_run = all([contains_geospatial_data, below_max_area_size, not has_original_texture_measurements])
+    should_run = all([contains_geospatial_data, below_max_area_size, has_no_original_texture_measurements])
     logShouldRun(site, MODEL, TERM_ID, should_run)
     return should_run
 

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/geospatialDatabase/utils.py

@@ -157,8 +157,7 @@ def _get_cached_data(term: str, site: dict, data: dict):
         isinstance(cache, dict),
         cache_sub_key
     ]) else cache
-    if value is not None:
-        debugValues(site, model=MODEL, term=term, value_from_cache=value)
+    debugValues(site, model=MODEL, term=term, value_from_cache=value)
     return value
 
 

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/hestia/landCover.py

@@ -16,7 +16,7 @@ from hestia_earth.models.utils.constant import DAYS_IN_YEAR
 from hestia_earth.models.utils.management import _new_management
 from hestia_earth.models.utils.term import get_lookup_value
 from hestia_earth.models.utils.lookup import get_region_lookup_value
-from hestia_earth.models.utils.blank_node import _node_date, DatestrFormat, _gapfill_datestr, DatestrGapfillMode
+from hestia_earth.models.utils.blank_node import DatestrFormat, _gapfill_datestr, DatestrGapfillMode
 from .utils import (
     IPCC_LAND_USE_CATEGORY_ANNUAL,
     IPCC_LAND_USE_CATEGORY_PERENNIAL,
@@ -410,8 +410,15 @@ def _get_faostat_name(term: dict) -> str:
     return _get_lookup_with_cache(term, "cropGroupingFaostatArea")
 
 
+def _get_most_common_or_alphabetically_first(crop_terms: list) -> str:
+    histogram = {term: crop_terms.count(term) for term in crop_terms}
+    max_freq = max(histogram.values())
+    # Sorted; to be deterministic
+    return sorted([term for term, freq in histogram.items() if freq == max_freq])[0]
+
+
 def _get_complete_faostat_to_crop_mapping() -> dict:
-    """Returns mapping in the format: {faostat_name: IPPC_LAND_USE_CATEGORY, ...}"""
+    """Returns mapping in the format: {faostat_name: IPCC_LAND_USE_CATEGORY, ...}"""
     lookup = download_lookup("crop.csv")
     mappings = defaultdict(list)
     for crop_term_id in [row[0] for row in lookup]:
@@ -421,7 +428,7 @@ def _get_complete_faostat_to_crop_mapping() -> dict:
         if key:
             mappings[key].append(crop_ipcc_land_use_category(crop_term_id=crop_term_id, lookup_term_type="crop"))
     return {
-        fao_name: max(set(crop_terms), key=crop_terms.count)
+        fao_name: _get_most_common_or_alphabetically_first(crop_terms)
         for fao_name, crop_terms in mappings.items()
     }
 
@@ -758,26 +765,32 @@ def _collect_land_use_types(nodes: list) -> list:
             "id": node.get("term", {}).get("@id"),
             "land-use-type": _get_land_use_term_from_node(node),
             "endDate": _gapfill_datestr(datestr=node.get("endDate"), mode=DatestrGapfillMode.END)[:10],
-            "startDate": _gapfill_datestr(
-                datestr=node.get("startDate"), mode=DatestrGapfillMode.START
-            )[:10] if node.get("startDate") else None
+            "startDate": _gapfill_datestr(datestr=node.get("startDate"), mode=DatestrGapfillMode.START)[:10]
         } for node in nodes
     ]
 
 
-def _no_prior_land_cover_data(nodes: list, node: dict) -> bool:
+def _no_prior_land_cover_data(nodes: list, target_node: dict) -> bool:
+    """
+    Returns true if there are no nodes whose start & end dates the target_node falls within,
+    including a tolerance.
+    """
     target_date = (
-        datetime.strptime(node.get('startDate') or node.get('endDate'), DatestrFormat.YEAR_MONTH_DAY.value)
+        datetime.strptime(target_node.get('startDate') or target_node.get('endDate'),
+                          DatestrFormat.YEAR_MONTH_DAY.value)
         - timedelta(days=DEFAULT_WINDOW_IN_YEARS * DAYS_IN_YEAR)
     )
+    tolerance = timedelta(days=DATE_TOLERANCE_IN_YEARS * DAYS_IN_YEAR)
     previous_nodes = [
         node for node in nodes
-        if abs(_node_date(node) - target_date) < timedelta(days=DATE_TOLERANCE_IN_YEARS * DAYS_IN_YEAR)
+        if datetime.strptime(node.get("startDate"), DatestrFormat.YEAR_MONTH_DAY.value) - tolerance
+        < target_date <
+        datetime.strptime(node.get("endDate"), DatestrFormat.YEAR_MONTH_DAY.value) + tolerance
     ]
     return len(previous_nodes) == 0
 
 
-def _should_run(site: dict) -> tuple[bool, dict]:
+def _should_run(site: dict) -> tuple[bool, list, dict]:
     management_nodes = _collect_land_use_types(
         [
             node for node in filter_list_term_type(site.get("management", []), TermTermType.LANDCOVER)
@@ -795,8 +808,8 @@ def _should_run(site: dict) -> tuple[bool, dict]:
     land_use_type = relevant_nodes[0].get("land-use-type") if relevant_nodes else None
 
     has_no_prior_land_cover_data = _no_prior_land_cover_data(
-        nodes=relevant_nodes,
-        node=relevant_nodes[-1:][0]
+        nodes=management_nodes,
+        target_node=relevant_nodes[-1:][0]
     ) if relevant_nodes else None
 
     should_run_nodes, site_area = _should_run_historical_land_use_change(

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/ipcc2019/ch4ToAirOrganicSoilCultivation.py

@@ -16,8 +16,8 @@ from hestia_earth.models.utils.measurement import most_relevant_measurement_valu
 from hestia_earth.models.utils.site import valid_site_type
 
 from .organicSoilCultivation_utils import (
-    assign_ditch_category, assign_organic_soil_category, calc_emission, DitchCategory, get_ditch_frac,
-    get_emission_factor, OrganicSoilCategory, remap_categories, valid_eco_climate_zone
+    assign_ditch_category, assign_organic_soil_category, calc_emission, DitchCategory, format_nd_array, format_number,
+    get_ditch_frac, get_emission_factor, OrganicSoilCategory, remap_categories, valid_eco_climate_zone
 )
 from . import MODEL
 
@@ -224,11 +224,11 @@ def _should_run(cycle: dict):
         eco_climate_zone=eco_climate_zone,
         organic_soil_category=organic_soil_category,
         ditch_category=ditch_category,
-        emission_factor=f"{np.mean(emission_factor):.3f}",
-        ditch_factor=f"{np.mean(ditch_factor):.3f}",
-        ditch_frac=f"{np.mean(ditch_frac):.3f}",
-        land_occupation=land_occupation,
-        histosol=histosol
+        emission_factor=format_nd_array(emission_factor),
+        ditch_factor=format_nd_array(ditch_factor),
+        ditch_frac=format_nd_array(ditch_frac),
+        land_occupation=format_number(land_occupation),
+        histosol=format_number(histosol)
     )
 
     should_run = all([

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/ipcc2019/co2ToAirOrganicSoilCultivation.py

@@ -14,7 +14,8 @@ from hestia_earth.models.utils.measurement import most_relevant_measurement_valu
 from hestia_earth.models.utils.site import valid_site_type
 
 from .organicSoilCultivation_utils import (
-    assign_organic_soil_category, calc_emission, get_emission_factor, OrganicSoilCategory, valid_eco_climate_zone
+    assign_organic_soil_category, calc_emission, format_nd_array, format_number, get_emission_factor,
+    OrganicSoilCategory, valid_eco_climate_zone
 )
 from . import MODEL
 
@@ -182,9 +183,9 @@ def _should_run(cycle: dict):
         cycle, model=MODEL, term=TERM_ID,
         eco_climate_zone=eco_climate_zone,
         organic_soil_category=organic_soil_category,
-        emission_factor=f"{np.mean(emission_factor):.3f}",
-        land_occupation=land_occupation,
-        histosol=histosol
+        emission_factor=format_nd_array(emission_factor),
+        land_occupation=format_number(land_occupation),
+        histosol=format_number(histosol)
     )
 
     should_run = all([

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/ipcc2019/n2OToAirOrganicSoilCultivationDirect.py

@@ -8,8 +8,8 @@ from hestia_earth.models.utils.measurement import most_relevant_measurement_valu
 from hestia_earth.models.utils.site import valid_site_type
 
 from .organicSoilCultivation_utils import (
-    assign_organic_soil_category, calc_emission, get_emission_factor, OrganicSoilCategory, remap_categories,
-    valid_eco_climate_zone
+    assign_organic_soil_category, calc_emission, format_number, get_emission_factor, OrganicSoilCategory,
+    remap_categories, valid_eco_climate_zone
 )
 from . import MODEL
 
@@ -127,9 +127,9 @@ def _should_run(cycle: dict):
         cycle, model=MODEL, term=TERM_ID,
         eco_climate_zone=eco_climate_zone,
         organic_soil_category=organic_soil_category,
-        emission_factor=f"{emission_factor_mean} ± {emission_factor_sd}",
-        land_occupation=land_occupation,
-        histosol=histosol
+        emission_factor=f"{format_number(emission_factor_mean)} ± {format_number(emission_factor_sd)}",
+        land_occupation=format_number(land_occupation),
+        histosol=format_number(histosol)
     )
 
     should_run = all([
@@ -151,8 +151,8 @@ def _should_run(cycle: dict):
 
 
 def _run(emission_factor_mean: float, emission_factor_sd: float, histosol: float, land_occupation: float):
-    value = calc_emission(TERM_ID, emission_factor_mean, histosol, land_occupation)
-    sd = calc_emission(TERM_ID, emission_factor_sd, histosol, land_occupation)
+    value = round(calc_emission(TERM_ID, emission_factor_mean, histosol, land_occupation), 6)
+    sd = round(calc_emission(TERM_ID, emission_factor_sd, histosol, land_occupation), 6)
     return [_emission(value, sd)]
 
 

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/ipcc2019/organicCarbonPerHa_tier_1.py

@@ -1346,7 +1346,7 @@ def _assign_ipcc_management_category(
         ipcc_land_use_category, IpccManagementCategory.NOT_RELEVANT
     )
 
-    land_cover_nodes = filter_list_term_type(management_nodes, [TermTermType.LANDCOVER])
+    land_cover_nodes = filter_list_term_type(management_nodes, [TermTermType.PASTUREMANAGEMENT])
     tillage_nodes = filter_list_term_type(management_nodes, [TermTermType.TILLAGE])
 
     should_run_ = any([
@@ -1461,7 +1461,7 @@ Value: Corresponding decision tree for IPCC management categories based on land
 """
 
 _IPCC_LAND_USE_CATEGORY_TO_DEFAULT_IPCC_MANAGEMENT_CATEGORY = {
-    IpccLandUseCategory.GRASSLAND: IpccManagementCategory.UNKNOWN,
+    IpccLandUseCategory.GRASSLAND: IpccManagementCategory.NOMINALLY_MANAGED,
     IpccLandUseCategory.ANNUAL_CROPS_WET: IpccManagementCategory.UNKNOWN,
     IpccLandUseCategory.ANNUAL_CROPS: IpccManagementCategory.UNKNOWN
 }

{hestia_earth_models-0.70.3 → hestia_earth_models-0.70.4}/hestia_earth/models/ipcc2019/organicSoilCultivation_utils.py

@@ -1,5 +1,6 @@
 from enum import Enum
 from typing import Literal
+import numpy as np
 
 from hestia_earth.schema import SiteSiteType
 from hestia_earth.utils.model import find_primary_product
@@ -22,8 +23,7 @@ _NETHERLANDS_TERM_ID = "GADM-NLD"
 
 _CONVERSION_FACTORS = {
     "co2ToAirOrganicSoilCultivation": 1000 * get_atomic_conversion(Units.KG_CO2, Units.TO_C),
-    "ch4ToAirOrganicSoilCultivation": 1000,
-    "n2OToAirOrganicSoilCultivationDirect": 1000 * get_atomic_conversion(Units.KG_N2O, Units.TO_N)
+    "n2OToAirOrganicSoilCultivationDirect": get_atomic_conversion(Units.KG_N2O, Units.TO_N)
 }
 _DEFAULT_FACTOR = {"value": 0}
 _EXCLUDED_ECO_CLIMATE_ZONES = [EcoClimateZone.POLAR_MOIST, EcoClimateZone.POLAR_DRY]
@@ -136,7 +136,7 @@ def calc_emission(
     """
     Calculate the emission and convert it to kg/ha-1.
     """
-    return emission_factor * land_occupation * histosol * _CONVERSION_FACTORS[emission_id] / 100
+    return emission_factor * land_occupation * histosol * _CONVERSION_FACTORS.get(emission_id, 1) / 100
 
 
 def remap_categories(
@@ -157,3 +157,11 @@ def valid_eco_climate_zone(
     Validate that the model should run for a specific eco-climate zone.
     """
     return isinstance(eco_climate_zone, EcoClimateZone) and eco_climate_zone not in _EXCLUDED_ECO_CLIMATE_ZONES
+
+
+def format_number(value) -> str:
+    return f"{value:.3g}" if isinstance(value, (float, int)) else "None"
+
+
+def format_nd_array(value) -> str:
+    return f"{np.mean(value):.3g} ± {np.std(value):.3g}" if isinstance(value, np.ndarray) else "None"