feat: codified backtests, honest docs, belt-and-braces serving, perf fixes
CI/CD Pipeline - Northern Thailand Ping River Monitor / Code Quality (push) Successful in 13s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Test Suite (3.11) (push) Failing after 23s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Build Docker Image (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Integration Test with Services (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Staging (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Production (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Performance Test (push) Skipped
Documentation / Validate Documentation (push) Failing after 7s
Documentation / Generate API Documentation (push) Successful in 8s
Documentation / Build Sphinx Documentation (push) Successful in 15s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Cleanup (push) Successful in 1s
Documentation / Documentation Summary (push) Successful in 3s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Code Quality (push) Successful in 13s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Test Suite (3.11) (push) Failing after 23s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Build Docker Image (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Integration Test with Services (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Staging (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Production (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Performance Test (push) Skipped
Documentation / Validate Documentation (push) Failing after 7s
Documentation / Generate API Documentation (push) Successful in 8s
Documentation / Build Sphinx Documentation (push) Successful in 15s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Cleanup (push) Successful in 1s
Documentation / Documentation Summary (push) Successful in 3s
Retrained on the gap-filled DB (592k -> 976k rows) and re-examined the flood backtests, now reproducible via scripts/backtest_render.py (renders the three docs/img charts and gates on a >=12h 2024 first-alert lead — currently failing by design and documented as such). Findings, all documented in FLOOD_FORECASTING.md: the true 2024 crossing was 24 Sep 17:00 (8h earlier than recorded; confirmed against the independent HII sensor), the historical 24h-warning claim was partly a missing-data artifact, and retrained warn classifiers collapse on the filled grid (P.1 24h PR-AUC 0.900 -> 0.288) while regression MAE improves (11.3 -> 10.5 cm). Serving therefore becomes max(classifier, sigmoid(regression)) so alerting is never worse than the regression path; metrics table, head-gating tiers, honest-limits and runbook expectations all updated to the current model (hgb-v1+d2d0e65). Perf, from Locust load testing (scripts/locustfile.py + load_test.py): single-flight lock around /forecast inference (concurrent cache misses previously each ran ~18s inference and starved the shared thread pool; 200-user run after: 105 rps, 0.01% errors), and /measurements/latest + /health moved off the event loop (synchronous DB/network calls in async handlers were stalling every request under load).
This commit is contained in:
Binary file not shown.
|
Before Width: | Height: | Size: 109 KiB After Width: | Height: | Size: 118 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 119 KiB After Width: | Height: | Size: 147 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 127 KiB After Width: | Height: | Size: 141 KiB |
Reference in New Issue
Block a user