Skip to content

Hot fix PR to add expenditure and income to the aggregating API #143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 24, 2025
Merged

Hot fix PR to add expenditure and income to the aggregating API #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 27 additions & 3 deletions apps/baseline/serializers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1509,11 +1509,17 @@ class Meta:
"livelihood_activity_pk",
"wealth_group_category_code",
"population_estimate",
"product_cpc",
"product_common_name",
"slice_sum_kcals_consumed",
"sum_kcals_consumed",
"kcals_consumed_percent",
"product_cpc",
"product_common_name",
"sum_income",
"slice_sum_income",
"income_percent",
"sum_expenditure",
"slice_sum_expenditure",
"expenditure_percent",
)

# For each of these aggregates the following calculation columns are added:
Expand All @@ -1524,6 +1530,8 @@ class Meta:
# If no ordering is specified by the FilterSet, the results are ordered by percent descending in the order here.
aggregates = {
"kcals_consumed": Sum,
"income": Sum,
"expenditure": Sum,
}

# For each of these pairs, a URL parameter is created "slice_{field}", eg, ?slice_product=
Expand All @@ -1532,7 +1540,12 @@ class Meta:
# For example: (product=R0 OR product=L0) AND (strategy_type=MilkProd OR strategy_type=CropProd)
slice_fields = {
"product": "livelihood_strategies__product__cpc__istartswith",
# this parameter must be set to one of values (not labels) from LivelihoodStrategyType, eg, MilkProduction
"strategy_type": "livelihood_strategies__strategy_type__iexact",
# TODO: Support filter expressions on the right here, so we can slice on, for example, a
# WealthGroupCharacteristicValue where WealthGroupCharacteristic is some hard-coded value,
# eg, the slice on WGCV where WGC=PhoneOwnership, or on WGCV > 3 where WGC=HouseholdSize, eg:
# {"phone_ownership": lambda val: Q(wgcv__path=val, wgc__path__code="PhoneOwnership")}
}

livelihood_zone_name = DictQuerySetField("livelihood_zone_name")
Expand Down Expand Up @@ -1565,6 +1578,14 @@ class Meta:
sum_kcals_consumed = DictQuerySetField("sum_kcals_consumed")
kcals_consumed_percent = DictQuerySetField("kcals_consumed_percent")

slice_sum_income = DictQuerySetField("slice_sum_income")
sum_income = DictQuerySetField("sum_income")
income_percent = DictQuerySetField("income_percent")

slice_sum_expenditure = DictQuerySetField("slice_sum_expenditure")
sum_expenditure = DictQuerySetField("sum_expenditure")
expenditure_percent = DictQuerySetField("expenditure_percent")

def get_fields(self):
"""
User can specify fields= parameter to specify a field list, comma-delimited.
Expand Down Expand Up @@ -1621,12 +1642,15 @@ def field_to_database_path(field_name):
"livelihood_activity_pk": "livelihood_strategies__livelihoodactivity__pk",
"wealth_group_category_code": "livelihood_strategies__livelihoodactivity__wealth_group__wealth_group_category__code", # NOQA: E501
"kcals_consumed": "livelihood_strategies__livelihoodactivity__kcals_consumed",
"income": "livelihood_strategies__livelihoodactivity__income",
"expenditure": "livelihood_strategies__livelihoodactivity__expenditure",
"percentage_kcals": "livelihood_strategies__livelihoodactivity__percentage_kcals",
"livelihood_zone_name": f"livelihood_zone__name_{language_code}",
"source_organization_pk": "source_organization__pk",
"source_organization_name": "source_organization__name",
"country_pk": "livelihood_zone__country__pk",
"country_iso_en_name": "livelihood_zone__country__iso_en_name",
"product_cpc": "livelihood_strategies__product",
"product_cpc": "livelihood_strategies__product__cpc",
"strategy_type": "livelihood_strategies__strategy_type",
"product_common_name": f"livelihood_strategies__product__common_name_{language_code}",
}.get(field_name, field_name)
Expand Down
31 changes: 10 additions & 21 deletions apps/baseline/viewsets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from django.apps import apps
from django.conf import settings
from django.db import models
from django.db.models import F, OuterRef, Q, Subquery
from django.db.models import F, FloatField, Q, Subquery
from django.db.models.functions import Coalesce, NullIf
from django.utils.translation import override
from django_filters import rest_framework as filters
Expand Down Expand Up @@ -1770,24 +1770,9 @@ def global_aggregates(self):
"""
global_aggregates = {}
for field_name, aggregate in self.serializer_class.aggregates.items():
subquery = LivelihoodZoneBaseline.objects.all()

# The FilterSet applies the global filters, such as Wealth Group Category.
# We also need to apply these to the subquery that gets the kcal totals per LZB (eg, the kcal_percent
# denominator), to restrict the 100% value by, for example, wealth group.
subquery = self.filter_queryset(subquery)

# Join to outer query
subquery = subquery.filter(pk=OuterRef("pk"))

# Annotate with the aggregate expression, eg, sum_kcals_consumed
aggregate_field_name = self.serializer_class.aggregate_field_name(field_name, aggregate)
subquery = subquery.annotate(
**{aggregate_field_name: aggregate(self.serializer_class.field_to_database_path(field_name))}
).values(aggregate_field_name)[:1]

global_aggregates[aggregate_field_name] = Subquery(subquery)

field_path = self.serializer_class.field_to_database_path(field_name)
global_aggregates[aggregate_field_name] = aggregate(field_path, default=0, output_field=FloatField())
return global_aggregates

def get_slice_aggregates(self):
Expand All @@ -1803,7 +1788,9 @@ def get_slice_aggregates(self):
# Annotate the queryset with the aggregate, eg, slice_sum_kcals_consumed, applying the slice filters.
# This is then divided by, eg, sum_kcals_consumed for the percentage of the slice.
field_path = self.serializer_class.field_to_database_path(field_name)
slice_aggregates[aggregate_field_name] = aggregate(field_path, filter=slice_filter, default=0)
slice_aggregates[aggregate_field_name] = aggregate(
field_path, filter=slice_filter, default=0, output_field=FloatField()
)
return slice_aggregates

def get_slice_filters(self):
Expand All @@ -1825,8 +1812,10 @@ def get_calculations_on_aggregates(self):
for field_name, aggregate in self.serializer_class.aggregates.items():
slice_total = F(self.serializer_class.slice_aggregate_field_name(field_name, aggregate))
overall_total = F(self.serializer_class.aggregate_field_name(field_name, aggregate))
expr = slice_total * 100 / NullIf(overall_total, 0) # Protects against divide by zero
expr = Coalesce(expr, 0) # Zero if no LivActivities found for prod/strategy slice
# Protect against divide by zero (divide by null returns null without error)
expr = slice_total * 100 / NullIf(overall_total, 0)
# Zero if no LivActivities found for prod/strategy slice, rather than null:
expr = Coalesce(expr, 0, output_field=FloatField())
slice_percent_field_name = self.serializer_class.slice_percent_field_name(field_name, aggregate)
calcs_on_aggregates[slice_percent_field_name] = expr
return calcs_on_aggregates
Expand Down
Loading