Khalim Conn-Kowlessar
9eb70cede1
slice 14g: remote_bulk_fetcher extracts ZIP entries via HTTP Range (no full download)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 19:16:52 +00:00
Khalim Conn-Kowlessar
b676e05d49
slice 14f: train_baseline fits LightGBM per target, emits MAPE/R^2 + importance
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 18:47:49 +00:00
Khalim Conn-Kowlessar
23ba2ef271
slice 14e: write_training_dataset emits parquet + schema.json + manifest.json
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 18:43:31 +00:00
Khalim Conn-Kowlessar
20fd55d5a1
slice 14d: build_features wires bulk reader -> mapper -> EpcMlTransform
...
ijson use_float fixes Decimal/float coercion when streaming JSON.
pyright extraPaths so the new pkg type-checks against domna-domain.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 18:38:41 +00:00
Khalim Conn-Kowlessar
0ff9d546b8
slice 14c: BulkZipReader streams certs from gov bulk JSON ZIP
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 18:27:24 +00:00
Khalim Conn-Kowlessar
7a6c8b4f24
slice 14b: Storage protocol + LocalStorage impl
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 17:52:54 +00:00
Khalim Conn-Kowlessar
eb42cb88a1
slice 14a: ml_training_data pkg + sample.py (CSV filter + random sample)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 17:39:43 +00:00
Khalim Conn-Kowlessar
dfe9e3ddbe
added potential file scaffolding:
2026-05-15 10:56:53 +00:00
