bayesian_encode_fourlevel_withint.py 文件源码

def runET(train_X, train_y, test_X, test_y=None, validation=1, n_est_val=50, depth_val=None, split_val=2, leaf_val=1, feat_val='auto', jobs_val=4, random_state_val=0):
        clf = ensemble.ExtraTreesClassifier(
                n_estimators = n_est_val,
                max_depth = depth_val,
                min_samples_split = split_val,
                min_samples_leaf = leaf_val,
                max_features = feat_val,
                criterion='entropy',
                n_jobs = jobs_val,
                random_state = random_state_val)
        clf.fit(train_X, train_y)
        pred_train_y = clf.predict_proba(train_X)[:,1]
        pred_test_y = clf.predict_proba(test_X)[:,1]

        if validation:
                train_loss = log_loss(train_y, pred_train_y)
                loss = log_loss(test_y, pred_test_y)
                print "Train, Test loss : ", train_loss, loss
                return pred_test_y, loss
        else:
                return pred_test_y