Instructions to use saiyko/dispatch-desk-risk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use saiyko/dispatch-desk-risk with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("saiyko/dispatch-desk-risk", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Download config.json from saiyko/dispatch-desk-risk: direct link, hf CLI and curl.
- Browser
- Download file 2.25 kB
-
https://huggingface.co/saiyko/dispatch-desk-risk/resolve/main/config.json
- Command line
-
hf download hf://saiyko/dispatch-desk-risk/config.json
-
curl -L -o config.json https://huggingface.co/saiyko/dispatch-desk-risk/resolve/main/config.json
2.25 kB
| { | |
| "title": "Dispatch Desk · costly-decision risk", | |
| "description": "Predicts, when a crisis scene opens, the probability that this player will pick the costly option, from how they played so far. The game uses it to offer extra support.", | |
| "version": "2.0.0", | |
| "target": "maliyetli_secim", | |
| "classes": [ | |
| 0, | |
| 1 | |
| ], | |
| "class_labels": [ | |
| "not costly", | |
| "costly" | |
| ], | |
| "features": [ | |
| { | |
| "name": "seviye", | |
| "label": "Level (0 Just starting, 1 Know a bit, 2 Experienced)", | |
| "example": 1.0 | |
| }, | |
| { | |
| "name": "sahne_no", | |
| "label": "Crisis number (1-3)", | |
| "example": 2.0 | |
| }, | |
| { | |
| "name": "canli_bekleme_ort_dk", | |
| "label": "Average call wait in the previous live phase (sim. minutes)", | |
| "example": 3.11 | |
| }, | |
| { | |
| "name": "canli_en_yakin_orani", | |
| "label": "Share of assignments to the closest crew (0-1)", | |
| "example": 0.6 | |
| }, | |
| { | |
| "name": "canli_bekleyen", | |
| "label": "Calls still waiting at the alarm", | |
| "example": 1.0 | |
| }, | |
| { | |
| "name": "gorev_yanlis", | |
| "label": "Field tasks answered wrongly so far", | |
| "example": 1.0 | |
| }, | |
| { | |
| "name": "onceki_maliyetli", | |
| "label": "Costly choices in earlier crises (0-2)", | |
| "example": 0.0 | |
| }, | |
| { | |
| "name": "onceki_karar_suresi_sn", | |
| "label": "Seconds spent on the previous crisis (0 for Crisis 1)", | |
| "example": 3.5 | |
| } | |
| ], | |
| "decision_threshold": 0.5, | |
| "acceptance": { | |
| "metric": "roc_auc", | |
| "roc_auc_min": 0.7, | |
| "split": "stratified 70/30", | |
| "parity_tol": 0.0001 | |
| }, | |
| "coefficients": { | |
| "seviye": -0.1458, | |
| "sahne_no": -0.1381, | |
| "canli_bekleme_ort_dk": 0.7545, | |
| "canli_en_yakin_orani": 0.1981, | |
| "canli_bekleyen": 0.2938, | |
| "gorev_yanlis": 0.563, | |
| "onceki_maliyetli": 0.4521, | |
| "onceki_karar_suresi_sn": -0.7103, | |
| "intercept": 0.4913 | |
| }, | |
| "metrics": { | |
| "roc_auc": 0.761, | |
| "accuracy": 0.7179, | |
| "f1": 0.7737, | |
| "brier": 0.1926, | |
| "roc_auc_real_only": 0.2188, | |
| "n_test_real": 16, | |
| "n_rows": 648, | |
| "n_rows_real": 48, | |
| "n_sessions_real": 16, | |
| "positive_rate": 0.5802, | |
| "onnx_max_abs_diff": 8.49e-08 | |
| }, | |
| "seed": 13, | |
| "sklearn_version": "1.9.1", | |
| "python_version": "3.13.17" | |
| } | |