rf.py 文件源码

def rf_from_cfg(cfg, seed):
    """
        Creates a random forest regressor from sklearn and fits the given data on it.
        This is the function-call we try to optimize. Chosen values are stored in
        the configuration (cfg).

        Parameters:
        -----------
        cfg: Configuration
            configuration chosen by smac
        seed: int or RandomState
            used to initialize the rf's random generator

        Returns:
        -----------
        np.mean(rmses): float
            mean of root mean square errors of random-forest test predictions
            per cv-fold
    """
    rfr = RandomForestRegressor(
        n_estimators=cfg["num_trees"],
        criterion=cfg["criterion"],
        min_samples_split=cfg["min_samples_to_split"],
        min_samples_leaf=cfg["min_samples_in_leaf"],
        min_weight_fraction_leaf=cfg["min_weight_frac_leaf"],
        max_features=cfg["max_features"],
        max_leaf_nodes=cfg["max_leaf_nodes"],
        bootstrap=cfg["do_bootstrapping"],
        random_state=seed)

    def rmse(y, y_pred):
        return np.sqrt(np.mean((y_pred - y)**2))
    # Creating root mean square error for sklearns crossvalidation
    rmse_scorer = make_scorer(rmse, greater_is_better=False)
    score = cross_val_score(rfr, boston.data, boston.target, cv=11, scoring=rmse_scorer)
    return -1 * np.mean(score)  # Because cross_validation sign-flips the score