Instructions to use medievalpufferfish/lst-rf-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use medievalpufferfish/lst-rf-model with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("medievalpufferfish/lst-rf-model", "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
| { | |
| "model": "RandomForestRegressor", | |
| "target": "lst_c", | |
| "features": [ | |
| "longitude", | |
| "latitude", | |
| "ndvi", | |
| "ndbi", | |
| "ndwi", | |
| "elevation", | |
| "albedo" | |
| ], | |
| "rf_params": { | |
| "n_estimators": 200, | |
| "max_depth": null, | |
| "min_samples_split": 2, | |
| "min_samples_leaf": 1, | |
| "max_features": "sqrt", | |
| "n_jobs": -1, | |
| "random_state": 42 | |
| }, | |
| "metrics": [ | |
| { | |
| "split": "Train", | |
| "rmse": 0.7877938475783137, | |
| "mae": 0.5133494894802572, | |
| "r2": 0.9890517145638135 | |
| }, | |
| { | |
| "split": "Test", | |
| "rmse": 2.072806683906037, | |
| "mae": 1.4002572231531145, | |
| "r2": 0.9287987733201019 | |
| } | |
| ], | |
| "feature_importances": { | |
| "longitude": 0.05998935520424381, | |
| "latitude": 0.030103474862694105, | |
| "ndvi": 0.2909687272371848, | |
| "ndbi": 0.05376698170625042, | |
| "ndwi": 0.2363828675258442, | |
| "elevation": 0.20189307315795518, | |
| "albedo": 0.12689552030582743 | |
| }, | |
| "cv_r2_mean": 0.9177935102345988, | |
| "cv_r2_std": 0.018256224465841075 | |
| } |