Model/services/ml_training_data
Khalim Conn-Kowlessar fd8d71eb05 slice 15e: per-decile residuals reporting in train_baseline
Adds `_per_decile_residuals` and writes `residuals_<target>.json` next to
metrics.json. Buckets test-set rows by deciles of the true target value;
each bucket carries count + MAPE + MAE + mean residual + true_min/max.

Lets us tell whether errors concentrate in the tails of the true distribution
(e.g. SAP<40 / SAP>85) vs the mid-band — which the global MAPE alone hides.
Baseline for slice 16's MAPE-improvement ablations.
2026-05-17 11:18:40 +00:00
..
src/ml_training_data slice 15e: per-decile residuals reporting in train_baseline 2026-05-17 11:18:40 +00:00
tests slice 15e: per-decile residuals reporting in train_baseline 2026-05-17 11:18:40 +00:00
pyproject.toml slice 14g: remote_bulk_fetcher extracts ZIP entries via HTTP Range (no full download) 2026-05-16 19:16:52 +00:00