Tabular Classification
Laya
Safetensors
fraud-detection
fdb
system-one
typed-decisions
stacking
gradient-boosting
lora
modernbert
Instructions to use getSTEAV/system-one-fdb-ipblock with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use getSTEAV/system-one-fdb-ipblock with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download examples/quickstart.py from getSTEAV/system-one-fdb-ipblock: direct link, hf CLI and curl.
- Browser
- Download file 982 Bytes
-
https://huggingface.co/getSTEAV/system-one-fdb-ipblock/resolve/main/examples/quickstart.py
- Command line
-
hf download hf://getSTEAV/system-one-fdb-ipblock/examples/quickstart.py
-
curl -L -o quickstart.py https://huggingface.co/getSTEAV/system-one-fdb-ipblock/resolve/main/examples/quickstart.py
982 Bytes
| #!/usr/bin/env python3 | |
| """Score the first FDB test rows with the released pipeline: python examples/quickstart.py [n] | |
| Needs the FDB package, and Kaggle API credentials for the Kaggle-hosted sets (see system_one_fraud/fdb.py). | |
| """ | |
| import json | |
| import sys | |
| from pathlib import Path | |
| ROOT = Path(__file__).resolve().parents[1] | |
| sys.path.insert(0, str(ROOT)) | |
| from system_one_fraud import FraudPipeline # noqa: E402 | |
| from system_one_fraud.fdb import load_split # noqa: E402 | |
| n = int(sys.argv[1]) if len(sys.argv) > 1 else 8 | |
| key = json.loads((ROOT / "release.json").read_text())["set"] | |
| _, test, _ = load_split(key) | |
| rows = test.head(n) | |
| pipe = FraudPipeline.from_pretrained(ROOT) | |
| states, _ = pipe.states(rows) | |
| print("System One evidence for the first row:") | |
| print(json.dumps(states[0], indent=1, ensure_ascii=False)) | |
| ids = rows["EVENT_ID"] if "EVENT_ID" in rows.columns else rows.index | |
| for event_id, p in zip(ids, pipe.predict_proba(rows)): | |
| print(f"{event_id} probability = {p:.4f}") | |