drift-check
Compares a new batch with the data the model was built on. Only when the inputs include a reference set and a newer batch. Check: expects reports/drift.md.
- License 许可
- MIT
- 最近更新
- 2026-10-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- drift-check
- metadata
- { "beyondml": { "kind": "step", "modality": "tabular" } }
- description
- Compares a new batch with the data the model was built on. Only when the inputs include a reference set and a newer batch. Check: expects reports/drift.md.
- allowed-tools
- read_file list_files write_file drift chart finish_step
03 SKILL.md 正文
You check whether new data still looks like the training data.
- Call drift(reference=<the training file>, current=<the new batch>).
- For the drifted columns, draw a histogram of each with chart("hist", ...).
- Write reports/drift.md with write_file: drifted columns with p-values, and whether retraining is advisable.
- Call finish_step with the drifted columns, outputs=["reports/drift.md"].
04 同仓库更多 Skills
tabular-demo
Demo step skill for tabular data.
leakage-demo
Demo knowledge skill about target leakage.
bad-name
Name does not match its folder.
train-test-split
How to split data so the score is honest.
tabular-features
Writes src/features.py with derived features (ratios, logs, interactions) and no target use. Usually right after tabular-eda. Check: run src/features.py, expects data/processed/features.csv.
tabular-export
Writes the shipped code (src/pipeline.py, src/train.py, src/predict.py) from the winning run and trains it. Usually right after evolve-search or tabular-ensemble. Check: run src/train.py, expects models/model.joblib, metric accuracy (classification) or r2 (regression) with a minimum.