Closes the 5 community-heating variants in the heating-systems corpus
(community heating 1/2/3/4/6 on property 001431). Pre-slice the
mapper returned `MainHeatingDetail.main_fuel_type=''` for every
community-heating cert because §14.0 lodges no Fuel Type — only EES
'COM' + a Table 4a heat-network SAP code (301/302/304). The cascade
strict-raised `MissingMainFuelType` per S0380.132. The actual fuel
that bills the cascade lives in the §14.1 Community Heating/Heat
Network block, which the extractor was skipping entirely.
SAP 10.2 Table 12 (PDF p.189) defines the heat-network fuel codes:
Boilers + Mains Gas → 51 (heat from boilers — mains gas)
Boilers + Mineral oil → 53 (heat from boilers — oil)
Boilers + Coal → 54 (heat from boilers — coal)
Boilers + Biomass → 43 (heat from boilers — biomass)
Combined Heat and Power → 48 (heat from CHP; fuel-agnostic)
Heat pump + Electricity → 41 (heat from electric heat pump)
Per spec text the upstream fuel determines the boiler-side code; CHP
is fuel-agnostic at the Table 12 cost / CO2 / PE level.
Three layers wired:
1. Survey schema — new `CommunityHeating` dataclass alongside
`MainHeating2` carrying the §14.1 fields (heating_type,
community_heat_source, community_fuel_type, heating_controls_ees,
heating_controls_sap, chp_fuel_factor). Mutually exclusive with
`main_heating_2` at the §14.1 level. Attached as
`MainHeating.community_heating: Optional[CommunityHeating] = None`.
2. Extractor — new `_extract_community_heating()` method bracketed by
"14.1 Community Heating/Heat Network" / "14.2 Meters". Returns
None on individually-heated dwellings (no Community Heat Source
lodged). Wired into `_extract_main_heating()`.
3. Mapper — new `_resolve_community_heating_fuel_code(heat_source,
fuel)` dispatch helper + `_ELMHURST_COMMUNITY_BOILER_FUEL_TO_TABLE_12`
constant for the boiler upstream-fuel split. Wired in
`_map_elmhurst_sap_heating` after the EES-code-to-fuel dispatch
and before the strict-raise on absent SAP code.
Per the standard slice workflow + [[feedback-aaa-test-convention]]:
- 5 new AAA tests in `test_community_heating_mapper_resolves_table_12_
fuel_code` parametrized over the 5 corpus variants, asserting the
mapper resolves the expected Table 12 code per variant.
- The existing parametrized residual-pin test in
`test_heating_systems_corpus_residual_matches_pin` picks up the
5 community-heating variants with cascade-side residuals pinned as
forcing functions for follow-up slices:
variant dSAP dcost dCO2 dPE
CH1 (Boilers/Gas) +0.59 -£14 -787 -3827
CH2 (CHP/Gas) +4.50 -£104 -1430 +1506
CH3 (HP/Elec) +0.59 -£14 +1614 +11879
CH4 (CHP/Oil) +4.50 -£104 -4397 +495
CH6 (CHP/Coal) -3.52 +£81 -2935 +7865
These reflect open cascade-side work (SAP 10.2 Appendix C CHP/
boiler heat-fraction split missing — cascade treats CHP+Boilers as
100% CHP; community-HP COP cascade missing — cascade doesn't divide
delivered heat by COP for Table 12 code 41; heat-network overall
CO2/PE blended-factor cascade missing — cascade doesn't compute
worksheet rows (386)/(486)). Pinned per [[feedback-zero-error-strict]];
follow-up slices close gaps and re-pin smaller residuals.
- `_BLOCKED_BY_MISSING_MAIN_FUEL_TYPE` tuple now empty; the
blocked-tier test pytest-skipped via `pytest.mark.skipif` with a
reason naming this slice.
Test baseline at HEAD: 921 pass + 1 skipped (was 916 + 0 at
predecessor
|
||
|---|---|---|
| .. | ||
| address2UPRN | ||
| addresses | ||
| apis | ||
| app | ||
| bulk_address2uprn_combiner | ||
| categorisation | ||
| condition | ||
| diagnostics | ||
| docker | ||
| documents_parser | ||
| ecmk_fetcher | ||
| engine | ||
| epc_api | ||
| etl | ||
| export | ||
| magic_plan | ||
| ml_models | ||
| onboarders | ||
| ordnanceSurvey | ||
| pashub_fetcher | ||
| postcode_splitter | ||
| scripts | ||
| tests | ||
| utils | ||
| .env.example | ||
| .env.test | ||
| __init__.py | ||
| DbClient.py | ||
| Funding.py | ||
| OrdnanceSurvey.py | ||
| Outputs.py | ||
| package-lock.json | ||
| package.json | ||
| Property.py | ||
| README.md | ||
| run_curl.sh | ||
| run_local.sh | ||
| SearchEpc.py | ||
| test_event.json | ||
Backend
This is the api service that will supply the frontend with the insights that are driven by the machine learning and data modelling services.
Usage
Prerequisites
Python 3.8+ Poetry for managing project dependencies and virtual environment.
Installation and setup
- Clone this directory and navigate into the project directory.
git clone https://github.com/Hestia-Homes/Model.git
cd backend
- For environment management, I'm using conda with pycharm which is a convenient setup for development on a mac M1 however using tools such as poetry or pipenv is also fine.
For example, to install conda and create a virtual environment for this project, run the following commands:
conda create -n backend python=3.10
conda activate backend
then enter the virtual environment and install the dependencies using conda.
conda install --file requirements/base.txt
- Duplicate .env.example and rename it to .env
cp .env.example .env
- Open .env and fill in the required environment variables.
Running the Application
from model/backend/ you can run with the following command:
uvicorn app.main:app --reload
Or run sh run_local.sh, which runs that same uvicorn command.
You application will be available at the designated url
API Documentation
FastAPI automatically generates interactive API documentation for your application. To access the docs, start your server and visit /docs in your browser. Alternatively, you can go to /redoc to view the documentation in the ReDoc format.
Building the lambda's backend docker image locally
To build the backend docker image locally, run the following command from the root of the project directory:
docker build -t fastapi-lambda-image:latest -f backend/docker/lambda.Dockerfile .
To check the size of the resulting image, run the following command:
docker images | grep fastapi-lambda-image
To run a shell inside the Docker container to inspect its contents, run:
docker run -it fastapi-lambda-image:latest /bin/bash
Running in lambda results in running in a slightly different format compared to running the fastapi application locally. If you want to run the fastapi application locally, in docker, we have a docker file which builds the same environment as in lambda but runs the fast api application with uvicorn.
Run
docker build -t fastapi-local-image:latest -f backend/docker/Dockerfile .
This will be the image. To run it, simply run
docker run -p 8000:8000 -v ~/.aws:/root/.aws fastapi-local-image:latest
This assumes you have a ~/.aws folder with your aws credentials in it. If you don't have this, you can run the following command with your aws access token exported into your environment.
docker run -p 8000:8000 -e AWS_ACCESS_KEY_ID -e AWS_SECRET_ACCESS_KEY -e AWS_DEFAULT_REGION fastapi-local-image:latest
Emulating the lambda locally
I have set up a script called run_local_lambda.sh which will allow you to emulate the lambda locally.
You need to have a .env file with the necessary environment variables at backend/env and also
and aws credentials file at ~/.aws/credentials, locally.
To run this, firstly run:
chmod +x run_lambda_local.sh
Now you can run the script with
./run_lambda_local.sh
In order to make a request to it, there is a specific format the request must be in, to
emuate lambda. If using postman, the url you want is http://localhost:8000/2015-03-31/functions/function/invocations
and you need to pass a body like this:
{
"httpMethod": "POST",
"body": "{\"portfolio_id\": 4, \"housing_type\": \"Private\", \"goal\": \"Increase EPC\", \"goal_value\": \"C\", \"trigger_file_path\": \"2/4/portfolio_plan_properties-20230724T093542483Z.csv\"}",
"path": "/v1/plan/trigger",
"resource": "/",
"headers": {
"Accept": "*/*",
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_TOKEN_HERE",
"x-api-key": "YOUR_API_KEY_HERE"
},
"requestContext": {},
"multiValueQueryStringParameters": null
}
Logs for the container can quickly be seen via Docker desktop
Testing
To run tests, run the following command from the root of the project directory:
pytest
Local Development
During local development, you may need to generate and use a dummy JWT to test protected endpoints of the application.
Generating a Dummy JWT
FastAPI provides a convenient way to generate a dummy JWT for testing. To generate a dummy JWT, follow the steps below:
Make sure your application is running in a local environment. The dummy token endpoint is only available in a local environment.
While your application is running, visit the /dummy-token endpoint using a tool like curl or any HTTP client like Postman.
For instance, if your server is running locally on port 8000, you can use curl to get a dummy token:
curl http://localhost:8000/local/dummy-token
You will receive a response containing the dummy JWT
{
"dummy_token": "<Your Dummy Token>"
}
Using the Dummy JWT
Once you've obtained a dummy JWT, you can use it to make requests to protected endpoints in your application:
-
When making a request, include an Authorization header with the value Bearer . Replace with the token you received from the /dummy-token endpoint.
-
Now you can make requests to the protected endpoints of the application.
Remember, the dummy JWT is meant for testing purposes only and should not be used in production environments. The /dummy-token endpoint is not available in non-local environments.
Custom Domain Setup for AWS API Gateway
Before you deploy your Serverless application for the first time, you need to set up a custom domain for AWS API Gateway. This is done using the sls create_domain command, which creates a custom domain in API Gateway that your services can use.
To set up a custom domain, use the following command:
sls create_domain --stage dev --aws-profile DevAdmin --verbose
Replace dev with the name of the stage you're deploying to. This command only needs to be run once per custom domain, and not every time you deploy your application. After running this command, you can associate your AWS Lambda functions with this domain using the customDomain configuration in your serverless.yml file.
This command requires the Serverless Domain Manager plugin, so make sure you have it installed and properly configured in your serverless.yml file.
Please note that the process of creating and associating a custom domain can take up to 40 minutes. Once the custom domain is created, it's immediately available for use in your Serverless applications.
Remember to replace DevAdmin with the profile that has appropriate permissions in your AWS account.
The --verbose flag is optional and is used to print detailed logs to the console.
Creating a CNAME Record in Google Domains
After deploying the AWS Lambda function for the first time, you need to set up a CNAME record in Google Domains to route traffic from your custom domain to the CloudFront distribution created by API Gateway. This will re-route traffic from your custom domain to the CloudFront distribution created by API Gateway, and therefore to your lambda. See here for AWS' documentation on this.
You can find the CloudFront domain by going to the API Gateway console and clicking on Custom Domain Names.
Here are the steps to create a CNAME record:
- Log in to Google Domains.
- Select the name of your domain.
- Open the menu, if it's not already open.
- Click "DNS."
- Scroll down to the "Custom resource records" section.
- In the "Name" field, enter your subdomain (e.g., api if your API is available at api.example.com).
- In the "Type" dropdown menu, select "CNAME."
- In the "TTL" field, enter 1H to set it to 1 hour (or another suitable value).
- In the "Data" field, enter the CloudFront domain that was created by API Gateway (you can find this in the API Gateway console, under Custom Domain Names).
- Click "Add."
This will direct any traffic from your custom domain to your AWS CloudFront distribution. Please note that DNS changes might take some time (up to 24-48 hours in some cases) to propagate across the internet.
Also, please make sure that your CloudFront distribution is configured to accept your custom domain as a valid domain name. In AWS API Gateway, under Custom Domain Names, make sure that your custom domain is listed and mapped to the appropriate API stage.
Remember to replace api and the CloudFront domain with your actual subdomain and CloudFront domain.
Certainly! Here's a detailed documentation for your README:
Deployment Troubleshooting for fastapi-lambda
Context:
When deploying the fastapi-lambda using Serverless Framework, you may encounter issues related to domain management,
especially if you're using a custom domain for your API. This documentation provides troubleshooting steps and details
on how to resolve potential conflicts.
Potential Issues & Solutions:
1. Conflict with Existing CloudFront Distribution:
Error Message:
csharpCopy code
One or more aliases specified for the distribution includes an incorrectly configured DNS record that points to another CloudFront distribution.
Cause: This can occur if there's an existing CNAME record in your DNS provider pointing to a CloudFront distribution.
Solution:
- Check your DNS provider (e.g., Google Domains) and verify the CNAME record for
api.dev.hestia.homes. - Temporarily remove or update the conflicting CNAME record.
- Run the
sls create_domaincommand again. - Update the DNS settings in your DNS provider based on the new configuration provided by
the
serverless-domain-managerplugin.
2. Conflict with Route53:
Error Message:
csharpCopy code
Deleting RestApi failed. Please remove all base path mappings related to the RestApi in your domains.
Cause: This can occur if there are residual AWS configurations, especially in Route53, from previous deployments.
Solution:
- Navigate to the AWS Route53 Console.
- Identify and delete any residual Hosted Zones or Record Sets related to
api.dev.hestia.homes. - Ensure that you have backed up any necessary configurations before deleting.
3. Other AWS Resources Conflicts:
You might encounter issues where AWS resources, such as S3 buckets or CloudFront distributions, are not properly deleted or are conflicting with new deployments.
Solution:
- Navigate to the respective AWS service dashboard.
- Manually identify and rectify any conflicting resources. This might involve emptying S3 buckets or deleting CloudFront distributions.
- Ensure backups and proper precautions before deleting any resources.
Additional Notes:
- Backup Configurations: Always backup your configurations before making changes. This ensures that you can revert to a previous state if needed.
- DNS Propagation: Remember that DNS changes can take some time to propagate globally. After making DNS changes, you might not see immediate effects.
- CloudFront Distributions: If you can't find a CloudFront distribution in the AWS CloudFront console, it's possible that it was automatically created by another AWS service like API Gateway. It might need to be managed or deleted from that service's dashboard.
After succesfully running creating the custom domain
After successfully creating the custom domain with the serverless-domain-manager plugin, you should add back the CNAME
record into Google Domains (or whatever platform is being used to manage domains now)
to ensure that the custom domain properly points to the CloudFront distribution managed by
AWS.
Here's what you should do:
-
Log in to Google Domains:
- Go to Google Domains.
- Navigate to the management page for
hestia.homes.
-
Add/Update the CNAME Record:
- Find the section for custom resource records.
- Add (or update if it already exists) a CNAME record for
api.dev. - Point it to the CloudFront distribution domain name (e.g.,
d2d269kjy1nyhz.cloudfront.net.). Ensure you include the trailing dot at the end. This can be found in API gateway
-
Check DNS Propagation:
- Keep in mind that DNS changes might take some time to propagate. You can use online tools like DNS Checker to verify the propagation status worldwide.
- Test your API endpoint
api.dev.hestia.homesto ensure it's resolving correctly and accessing your Lambda function.
By following these steps, you should have your custom domain properly configured and pointing to your AWS Lambda function via the CloudFront distribution