a5eda92a90
Closes the CO2 / PE residuals for CH1 (boiler community heating, SAP code 301) and CH3 (HP community heating, SAP code 304) via SAP 10.2 Table 4a (PDF p.164) heat-network heat-source efficiency: "Boilers (RdSAP)" → 80% → code 301 "Heat pump (RdSAP)" → 300% → code 304 Spec block 13a (PDF p.153) (467) "PE associated with heat source 2" = [(307b)+(310b)] × 100 / (467b) — i.e. fuel input = network_input × 100 / heat_source_eff before applying Table 12 PE factor. Block 12b (367) mirrors for CO2. The cascade meters network_input directly (eff = 1/DLF for the cost path via Table 12 heat-network rate), so PE / CO2 factors are scaled by 1/heat_source_eff at lookup time — mathematically equivalent to spec's (network_input / eff) × factor. Three changes: 1. New `_HEAT_NETWORK_HEAT_SOURCE_EFFICIENCY: Final[dict[int, float]]` keyed on SAP code: 301 → 0.80, 304 → 3.00. SAP 302 (CHP+boilers) is omitted — the 35%/65% split + displaced-electricity credit per spec block 13b (464)/(466)/(364)/(366) needs the .171 follow-up. 2. New `_heat_network_heat_source_efficiency_scaling(main)` helper returning 1.0 for non-heat-network mains + SAP 302, and 1/heat_source_eff for SAP 301 / 304. 3. Wired into `_main_heating_co2_factor_kg_per_kwh` and `_main_heating_primary_factor` non-electric branches (heat networks are non-electric per `_is_electric_main`). Both functions return `Table_12_factor × scaling` so the cascade's `network_input × scaled_factor` lands on the spec `(network_input / eff) × Table_12_factor`. Closures vs pre-S0380.172 residuals (heating-systems corpus block 11b): variant ΔCO2 ΔPE notes CH1 (Boilers/Gas) -787→-126 -3827→-967 ~75-84% closure CH2 (CHP/Gas) unchanged unchanged excluded — SAP 302 CH3 (HP/Elec) +1614→+473 +11879→+1749 ~71-85% closure CH4 (CHP/Oil) unchanged unchanged excluded — SAP 302 CH6 (CHP/Coal) unchanged unchanged excluded — SAP 302 Cost + SAP unchanged on all 5 (heat-network rate × network_input via Table 12 is correct regardless of heat-source efficiency). Residual CH1 / CH3 gap drivers (follow-up scope): - WHC=901 HW path: cascade reads cert-lodged "Mains gas" as HW fuel on community-heating certs; should fall through to main fuel for the heat-network so the scaling applies on HW side too. - Elmhurst 0.8523 multiplier on heat-network energy column (worksheet (467) energy = spec_formula × 0.8523 uniformly across non-CHP heat-network rows; mechanism not yet identified — spec divergence candidate for SAP_CALCULATOR.md §8). Cohort no-regression verified: 9 ASHP + 38 cohort-2 golden fixtures pass unchanged; the 41-variant heating-systems corpus has identical residuals for non-heat-network certs. The 2 closed CH variants are re-pinned at their new sub-1000 magnitudes. Test baseline at HEAD: 926 pass + 1 skipped (was 926 + 1 at predecessor a4b5f4e7; pin updates net to 0). Pyright net-zero on affected files (cert_to_inputs.py, test_heating_systems_corpus.py): 32 → 32. Per [[feedback-spec-citation-in-commits]] the dispatch table cites SAP 10.2 Table 4a (PDF p.164) verbatim row labels. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|---|---|---|
| .devcontainer | ||
| .github/workflows | ||
| .idea | ||
| .vscode | ||
| applications | ||
| asset_list | ||
| backend | ||
| backlog | ||
| datatypes | ||
| deployment/terraform | ||
| docs | ||
| domain | ||
| epr_data_exports | ||
| etl | ||
| infrastructure | ||
| model_data/requirements | ||
| orchestration | ||
| recommendations | ||
| repositories | ||
| scripts | ||
| sfr/principal_pitch | ||
| survey_report | ||
| tests | ||
| utilities | ||
| utils | ||
| .coveragerc | ||
| .dockerignore | ||
| .gitignore | ||
| __init__.py | ||
| ara_backend_design.md | ||
| BaseUtility.py | ||
| CLAUDE.md | ||
| conftest.py | ||
| CONTEXT.md | ||
| devcontainer.sh | ||
| Dockerfile.test | ||
| Dockerfile.test.dockerignore | ||
| Makefile | ||
| MEMORY.md | ||
| package-lock.json | ||
| package.json | ||
| pyproject.toml | ||
| pyrightconfig.json | ||
| pytest.ini | ||
| README.md | ||
| run_lambda_local.sh | ||
| serverless.yml | ||
| test.requirements.txt | ||
| tox.ini | ||
| UBIQUITOUS_LANGUAGE.md | ||
Model Repository
This repository contains the code pertaining to the development of the data science and machine learning products being utilised by Hestia.
The different folders in this repository relate to services that can be used independently, or can be imported and used as part of a larger application
Getting Started
Prerequisites
Dev Container Setup
This repo uses a Docker Compose-based dev container. The model-backend service joins a shared-dev Docker network so it can communicate with other local services (e.g. a frontend container) running on your machine.
VS Code users: The initializeCommand in devcontainer.json creates the shared-dev network automatically before the container starts. No manual step required — just open the repo and select Reopen in Container.
Non-VS Code / CI workflows: Run the following once before starting the container:
make dev-setup
This is idempotent and safe to re-run if the network already exists.
Folders
backend/
This folder contains the code for the fastapi backend service, which provides an interface to much of the functionality in this repository, for the frontend
model_data/
This folder contains related to the reading and preparation of assessment model data, including pulling out epc attributes
Testing
All tests can be run, against the configuration in pytest.ini running
pytest
This will run the complete panel of tests and report on coverage in the locations specified by the pytest.ini file.
To run tests in a specific service, e.g. inside of model_data, simply run
pytest --cov-config=model_data/.coveragerc --cov=model_data
This will produce the test results and coverage reports