{
    "seed": 0,
    "debug": "false",
    "device": "cpu",

    "log_folder": "logs/",

    "data_folder": "data/",
    "cvfold": 4,
    "ecfp" : {
        "radius": 3,
        "fpsize": 8192
    },
    "merge_train_val": "true",
    "descriptors": ["ecfps", "tox", "maccs", "rdkit_descrs"],
    "feature_selection": {
        "use": "true",
        "min_var": 0.01,
        "max_corr": 0.95,
        "max_features": -1,
        "min_var__feature_keys": ["ecfps", "tox", "maccs", "rdkit_descrs"],
        "max_corr__feature_keys": ["ecfps", "tox", "maccs", "rdkit_descrs"],
        "min_var__independent_keys": "false",
        "max_corr__independent_keys": "false"
    },
    "feature_quantilization": {
        "use": "true",
        "feature_keys": ["rdkit_descrs"]
    },
    "max_samples": -1,
    "scaler": "standard",
    "preprocessor_path": "checkpoints/preprocessor.joblib",

    "ckpt_path": "checkpoints/rf_alltasks.joblib",
    "model_config": {
        "NR-AR": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 5,
            "n_estimators": 1000
        },
        "NR-AR-LBD": {
            "max_depth": 12,
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 5,
            "n_estimators": 1000
        },
        "NR-AhR": {
            "max_depth": "none",
            "max_features": "log2",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "NR-Aromatase": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 4,
            "min_samples_split": 12,
            "n_estimators": 1000
        },
        "NR-ER": {
            "max_depth": 10,
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "NR-ER-LBD": {
            "max_depth": 8,
            "max_features": "sqrt",
            "min_samples_leaf": 2,
            "min_samples_split": 5,
            "n_estimators": 1000
        },
        "NR-PPAR-gamma": {
            "max_depth": "none",
            "max_features": "log2",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "SR-ARE": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 5,
            "n_estimators": 1000
        },
        "SR-ATAD5": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "SR-HSE": {
            "max_depth": 16,
            "max_features": "log2",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "SR-MMP": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 2,
            "min_samples_split": 2,
            "n_estimators": 1000
        },
        "SR-p53": {
            "max_depth": "none",
            "max_features": "sqrt",
            "min_samples_leaf": 1,
            "min_samples_split": 2,
            "n_estimators": 1000
        }
    }
}