hestia-earth-models 0.65.2__tar.gz → 0.65.4__tar.gz

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hestia_earth_models
-Version: 0.65.2
+Version: 0.65.4
 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-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/agribalyse2016/fuelElectricity.py

@@ -3,12 +3,12 @@ Fuel and Electricity
 
 This model calculates fuel and electricity data from the number of hours each machine is operated for using.
 """
-from functools import reduce
 from hestia_earth.schema import TermTermType
 from hestia_earth.utils.model import filter_list_term_type
 from hestia_earth.utils.tools import flatten, list_sum, non_empty_list
 
 from hestia_earth.models.log import debugValues, logRequirements, logShouldRun, log_as_table
+from hestia_earth.models.utils import group_by
 from hestia_earth.models.utils.term import get_lookup_value
 from hestia_earth.models.utils.input import _new_input
 from . import MODEL
@@ -68,16 +68,6 @@ def _run_operation(cycle: dict):
     return exec
 
 
-def _group_operations(operations: list):
-    def grouper(group: dict, operation: dict):
-        input_term_id = operation.get('input').get('id')
-        group[input_term_id] = group.get(input_term_id, [])
-        group[input_term_id].append(operation)
-        return group
-
-    return reduce(grouper, operations, {})
-
-
 def _should_run_operation(cycle: dict):
     def exec(practice: dict):
         term = practice.get('term', {})
@@ -120,5 +110,5 @@ def _should_run(cycle: dict):
 def run(cycle: dict):
     should_run, operations = _should_run(cycle)
     # group operations by input to show logs as table
-    grouped_operations = _group_operations(operations)
+    grouped_operations = group_by(operations, ['input.id'])
     return flatten(map(_run_operation(cycle), grouped_operations.values())) if should_run else []

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/cache_sites.py

@@ -4,6 +4,7 @@ from pydash.objects import merge
 from hestia_earth.utils.api import download_hestia
 from hestia_earth.utils.tools import flatten
 
+from .log import logger
 from .utils import CACHE_KEY, cached_value
 from .utils.site import CACHE_YEARS_KEY
 from .site.pre_checks.cache_geospatialDatabase import (
@@ -146,6 +147,7 @@ def run(sites: list, years: list = None, include_region: bool = False):
     batches = range(0, len(unique_years), batch_size)
 
     for batch_index in batches:
+        logger.info(f"Processing sites in batch {batch_index + 1} of {len(batches)}...")
         sub_years = unique_years[batch_index:batch_index + batch_size]
         sites = _run(sites, sub_years, include_region, years_only=True)
 

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/cycle/completeness/__init__.py

@@ -31,7 +31,7 @@ def _run_model(model, cycle: dict):
 
 def _run(cycle: dict):
     values = non_empty_list([_run_model(model, cycle) for model in MODELS])
-    value = reduce(lambda prev, curr: {**prev, **curr}, values, cycle.get('completeness', {}))
+    value = reduce(lambda prev, curr: prev | curr, values, cycle.get('completeness', {}))
     keys = ','.join([next(iter(val)) for val in values])
     debugValues(cycle, model=MODEL, keys=keys)
     return value if len(values) > 0 else None

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/emepEea2019/nh3ToAirInorganicFertiliser.py

@@ -78,7 +78,7 @@ def _get_groupings():
 
     def get_grouping(groupings: dict, term_id: str):
         grouping = get_term_lookup(term_id, 'fertGroupingNitrogen')
-        return {**groupings, **({grouping: term_id} if len(grouping) > 0 else {})}
+        return groupings | ({grouping: term_id} if len(grouping) > 0 else {})
 
     return reduce(get_grouping, term_ids, {})
 

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/hestia/seed_emissions.py

@@ -19,7 +19,7 @@ from hestia_earth.utils.tools import non_empty_list, flatten, list_sum, safe_par
 from hestia_earth.utils.emission import cycle_emissions_in_system_boundary
 
 from hestia_earth.models.log import logRequirements, logShouldRun, log_as_table
-from hestia_earth.models.utils import _omit
+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
@@ -165,12 +165,7 @@ def _yield(country_id: str, end_year: int, product: dict):
 
 
 def _group_seed_inputs(inputs: list):
-    def _group_by(group: dict, input: dict):
-        term_id = input.get('term', {}).get('@id')
-        group[term_id] = group.get(term_id, []) + [input]
-        return group
-
-    grouped_inputs = reduce(_group_by, inputs, {})
+    grouped_inputs = group_by(inputs, ['term.@id'])
     return [
         inputs[0] | {'value': flatten([v.get('value') for v in inputs])}
         for inputs in grouped_inputs.values()

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/ipcc2019/croppingDuration.py

@@ -1,3 +1,8 @@
+"""
+`croppingDuration` can be added by the uploader for all crops, however the model `IPCC (2019)` will only run for
+`riceGrainInHusk` or `ricePlantFlooded`.
+The model will only run for rice crops as this is the only crop which requires the value for emission recalculations.
+"""
 from hestia_earth.schema import PracticeStatsDefinition
 from hestia_earth.utils.lookup import download_lookup, get_table_value, column_name
 from hestia_earth.utils.tools import safe_parse_float

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/linkedImpactAssessment/freshwaterWithdrawalsInputsProduction.py

@@ -30,7 +30,8 @@ REQUIREMENTS = {
 }
 RETURNS = {
     "Indicator": [{
-        "value": ""
+        "value": "",
+        "inputs": ""
     }]
 }
 TERM_ID = 'freshwaterWithdrawalsInputsProduction'

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/linkedImpactAssessment/landOccupationInputsProduction.py

@@ -31,6 +31,7 @@ REQUIREMENTS = {
 RETURNS = {
     "Indicator": [{
         "value": "",
+        "inputs": "",
         "landCover": ""
     }]
 }

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/linkedImpactAssessment/landTransformation100YearAverageInputsProduction.py

@@ -31,6 +31,7 @@ REQUIREMENTS = {
 RETURNS = {
     "Indicator": [{
         "value": "",
+        "inputs": "",
         "landCover": "",
         "previousLandCover": ""
     }]

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/linkedImpactAssessment/landTransformation20YearAverageInputsProduction.py

@@ -31,6 +31,7 @@ REQUIREMENTS = {
 RETURNS = {
     "Indicator": [{
         "value": "",
+        "inputs": "",
         "landCover": "",
         "previousLandCover": ""
     }]

{hestia_earth_models-0.65.2 → hestia_earth_models-0.65.4}/hestia_earth/models/linkedImpactAssessment/utils.py

@@ -1,43 +1,42 @@
-from functools import reduce
 from hestia_earth.utils.tools import non_empty_list, flatten, list_sum
 
-from hestia_earth.models.log import log_as_table, logRequirements, logShouldRun
-from hestia_earth.models.utils import sum_values, _include
+from hestia_earth.models.log import log_as_table, debugValues, logRequirements, logShouldRun
+from hestia_earth.models.utils import group_by, sum_values, _include
 from hestia_earth.models.utils.indicator import _new_indicator
 from hestia_earth.models.utils.impact_assessment import get_product, convert_value_from_cycle
 from hestia_earth.models.utils.input import load_impacts
 from . import MODEL
 
 
-def _indicator(term_id: str, value: float):
+def _indicator(term_id: str, value: float, input: dict):
     indicator = _new_indicator(term_id, MODEL)
     indicator['value'] = value
+    indicator['inputs'] = [input]
     return indicator
 
 
-def _run_indicators(product: dict, term_id: str):
+def _run_indicators(impact_assessment: dict, product: dict, term_id: str):
     def run(values: list):
+        input = values[0].get('input').get('term', {})
         indicator = values[0].get('indicator')
         values_from_cycle = non_empty_list([
             list_sum(value.get('input').get('value')) * value.get('indicator').get('value')
             for value in values
         ])
         value = convert_value_from_cycle(product, sum_values(values_from_cycle), model=MODEL, term_id=term_id)
+
+        # show values per input in the logs
+        debugValues(impact_assessment, model=MODEL, term=term_id,
+                    value=value,
+                    coefficient=1,
+                    input=input.get('@id'))
+
         return (
-            _indicator(term_id, value) | _include(indicator, ['landCover', 'previousLandCover'])
+            _indicator(term_id, value, input) | _include(indicator, ['landCover', 'previousLandCover'])
         ) if value is not None else None
     return run
 
 
-def _group_indicator(group: dict, value: dict):
-    group_key = ';'.join(non_empty_list([
-        value.get('indicator').get('landCover', {}).get('@id'),
-        value.get('indicator').get('previousLandCover', {}).get('@id')
-    ]))
-    group[group_key] = group.get(group_key, []) + [value]
-    return group
-
-
 def _run_inputs_production(impact_assessment: dict, product: dict, term_id: str):
     cycle = impact_assessment.get('cycle', {})
 
@@ -61,11 +60,13 @@ def _run_inputs_production(impact_assessment: dict, product: dict, term_id: str)
         value
         for value in all_indicators
         if all([
-            value.get('indicator').get('value', -1) > 0,
-            list_sum(value.get('input').get('value', [-1]), 0) > 0
+            (value.get('indicator').get('value') or -1) > 0,
+            (list_sum(value.get('input').get('value')) or -1) > 0
         ])
     ]
-    grouped_indicators = reduce(_group_indicator, valid_indicators, {})
+    grouped_indicators = group_by(valid_indicators, [
+        'input.term.@id', 'indicator.landCover.@id', 'indicator.previousLandCover.@id'
+    ])
     has_indicators = bool(valid_indicators)
 
     logRequirements(impact_assessment, model=MODEL, term=term_id,
@@ -82,7 +83,9 @@ def _run_inputs_production(impact_assessment: dict, product: dict, term_id: str)
     should_run = all([has_indicators])
     logShouldRun(impact_assessment, MODEL, term_id, should_run)
 
-    return non_empty_list(flatten(map(_run_indicators(product, term_id), grouped_indicators.values())))
+    return non_empty_list(flatten(
+        map(_run_indicators(impact_assessment, product, term_id), grouped_indicators.values())
+    ))
 
 
 def _should_run_inputs_production(impact_assessment: dict, term_id: str):