tuner.py 文件源码

def tune_xgb_params_randomized(estimator_cls,
                               label: np.ndarray,
                               metric_sklearn: str,
                               n_jobs: int,
                               params: dict,
                               strat_folds: StratifiedKFold,
                               train: np.ndarray,
                               n_iter: int = 20,
                               verbosity_level: int = 10,
                               **kwargs):
    """
    :param estimator_cls:
        The class type of the estimator to instantiate - either an XGBClassifier or an XGBRegressor.
    :param label:
        An array-like containing the labels of the classification or regression problem.
    :param metric_sklearn:
        The evaluation metric to be passed to scikit-learn's GridSearchCV - see
        http://scikit-learn.org/stable/modules/model_evaluation.html
        for the options this can take - e.g. 'neg_mean_squared_error' for RMSE.
    :param n_jobs:
        The number of jobs to run simultaneously.
    :param params:
        A dictionary of XGB parameters.
    :param strat_folds:
        A StratifiedKFold object to cross validate the parameters.
    :param train:
        An array-like containing the training input samples.
    :param n_iter:
        An optional parameter to control the number of parameter settings that are sampled.
    :param n_jobs:
        An optional parameter to control the amount of parallel jobs - defaults to the amount of CPUs available.
    :param verbosity_level:
        An optional parameter to control the verbosity of the grid searching - defaults to the most verbose option.
    :param kwargs:
        Parameter distributions may be controlled through keyword arguments - e.g. to sample uniformly between 0.5 and 0.7 for
        colsample_bytree, supply colsample_bytree_loc=0.5 and colsample_bytree_scale=0.2.
    :return:
        A dictionary of tuned parameters and a list of the parameters found at each step with their respective scores.
    """
    params_copy = clean_params_for_sk(params)
    param_distributions = {
        'colsample_bytree': uniform(kwargs.get('colsample_bytree_loc', 0.2), kwargs.get('colsample_bytree_scale', 0.8)),
        'gamma': uniform(kwargs.get('gamma_loc', 0), kwargs.get('gamma_scale', 0.9)),
        'max_depth': sp_randint(kwargs.get('max_depth_low', 2), kwargs.get('max_depth_high', 11)),
        'min_child_weight': sp_randint(kwargs.get('min_child_weight_low', 1), kwargs.get('min_child_weight_high', 11)),
        'reg_alpha': halfnorm(kwargs.get('reg_alpha_loc', 0), kwargs.get('reg_alpha_scale', 5)),
        'reg_lambda': halfnorm(kwargs.get('reg_alpha_loc', 0), kwargs.get('reg_alpha_scale', 5)),
        'subsample': uniform(kwargs.get('subsample_loc', 0.2), kwargs.get('subsample_scale', 0.8))
    }

    rand_search = RandomizedSearchCV(
        cv=strat_folds.split(train, label),
        estimator=estimator_cls(**params_copy),
        n_iter=n_iter,
        n_jobs=n_jobs,
        param_distributions=param_distributions,
        scoring=metric_sklearn,
        verbose=verbosity_level
    )
    rand_search.fit(train, label)
    return rand_search.best_params_, [(rand_search.best_params_, rand_search.best_score_)]