Commit Graph
8 Commits
Author SHA1 Message Date
Noel Sabia ac0d8984bb docs: correct reproduction and cache claims
ci / check (push) Successful in 28s
ci / check (pull_request) Successful in 30s
The small-model page said make small reproduced every number, but the
threshold table and several derived values only appear in the JSON payload.
Say what the commands actually print, fix the stale weather-cache docstring,
and lead the e2e evidence page with what it checks.
2026-11-14 09:12:29 +01:00
Noel Sabia 070ecd2a78 ci: fix Gitea runner setup and tighten docs
ci / check (push) Successful in 1m12s
Replace setup-python with setup-uv: the self-hosted Gitea runner lacks the
toolcache and lsb_release dependency, so the job failed before any project
step. uv installs its own Python 3.12; the checks are unchanged.

Align the README and docs with the committed artifacts: quick start serves
from baked artifacts, rebuild steps are separate, and the reference-model
comparison no longer overstates the result. Drop stale external-doc
references and comments that restated the code.
2026-11-14 09:10:47 +01:00
Noel Sabia 000aaed7a5 feat: per-sensor holdout metrics and small-model confusion matrix
- train.py emits per-sensor MAE/WAPE/R2 vs the seasonal-naive baseline
- small.py emits the full confusion matrix and per-sensor classifier metrics
- metrics.json now carries the small-model summary for paper support
- regenerate baked artifacts; tests assert the tables are internally consistent
2026-11-14 06:35:14 +01:00
Noel Sabia 8656d9bc8a feat: add /bootstrap snapshot, numeric UID 10001, CI gate
GET /bootstrap returns the 8 sensors, hourly series for all of them,
context, meta, and versions in the CONTRACT.md shape. Snapshot artifacts
are projected to contract fields once at boot; incomplete artifacts return
503. Adds tests for shape, sensor count, hourly alignment, and versions.

Dockerfile now creates UID/GID 10001, uses COPY --chown=10001:10001, and
runs as USER 10001:10001. Adds make check and a minimal Gitea Actions
workflow that runs the same local gate: uv sync --frozen, compileall, pytest.
2026-11-14 06:00:14 +01:00
Noel Sabia dc83825de0 fix: use exact 168-row lag for the seasonal-naive baseline
The baseline now reproduces mission/data.md exactly: MAE 5.40, WAPE 44.7%,
R2 0.462. The model's lag_week remains the previous observed same weekday/hour,
which handles sensor gaps and is documented in the model card.
2026-11-14 05:04:41 +01:00
Noel Sabia 939a8db482 feat: complete ML pipeline, FastAPI service, small model, tests, image
- finish the global HistGB bundle, scenario forecasts and 28-day ablation
- export sensors/series/forecasts/metrics/context plus baked weather frames
- add FastAPI health/meta/predict/simulate and background /train jobs
- add the p75 busy classifier, retraining from CSV, and hot-swap persistence
- add pytest coverage, multi-stage non-root Dockerfile, README and model card

Holdout: weather 7d MAE 3.32 / WAPE 27.5% / R2 0.777 vs seasonal naive
MAE 4.23 / WAPE 35.0% / R2 0.656 (5,350 eval rows).
2026-11-14 05:01:16 +01:00
Noel Sabia 68402803b2 feat: add pipeline and training entrypoints 2026-11-14 04:24:15 +01:00
Noel Sabia 2eeb1f937a chore: bootstrap ML-py scaffold 2026-11-14 04:16:22 +01:00