tunemodels.py 文件源码

def runGridSearch(self, model):
        logging.debug("run grid search on model: {}".format(model.__class__.__name__))
        logging.debug("cross validation strategy: {}".format(model.holdout_split))
        logging.debug("used features: {}".format(model.usedFeatures))
        logging.debug("tuned parameters: {}".format(model.getTunedParamterOptions()))

        features,labels,cv = model.getFeaturesLabel()
        # do grid search
        if self.do_random_gridsearch:
            estimator = RandomizedSearchCV(model.clf, model.getTunedParamterOptions(), cv=cv, n_jobs=self.n_jobs,
                       scoring=mean_absolute_percentage_error_scoring, verbose = 500, n_iter=self.n_iter_randomsearch)
        else:
            estimator = GridSearchCV(model.clf, model.getTunedParamterOptions(), cv=cv,n_jobs=-self.n_jobs, 
                                     fit_params=model.get_fit_params(),
                       scoring=mean_absolute_percentage_error_scoring, verbose = 500)
        estimator.fit(features, labels)
        model.clf = estimator.best_estimator_
        model.save_final_model = True
        model.save_model()

#         model.dispFeatureImportance()
        logging.debug('estimaator parameters: {}'.format(estimator.get_params))
        logging.debug('Best parameters: {}'.format(estimator.best_params_))
        logging.debug('Best Scores: {}'.format(-estimator.best_score_))
        logging.debug('Score grid: {}'.format(estimator.grid_scores_ ))
        for i in estimator.grid_scores_ :
            logging.debug('parameters: {}'.format(i.parameters ))
            logging.debug('mean_validation_score: {}'.format(np.absolute(i.mean_validation_score)))
            logging.debug('cv_validation_scores: {}'.format(np.absolute(i.cv_validation_scores) ))



        return