util_xgb.py 文件源码

def data_pre_process(train_path, test_path, label, drop_list=None):
    train_dataset = pandas.read_csv(train_path)
    if drop_list:
        train_dataset = train_dataset.drop(drop_list, axis=1)
    y_train = train_dataset[label].astype(int)
    print y_train.dtypes
    X_train = train_dataset.drop(label, axis=1)
    test_dataset = pandas.read_csv(test_path)
    if drop_list:
        test_dataset = test_dataset.drop(drop_list, axis=1)
    y_test = test_dataset[label].astype(int)
    print y_test.dtypes
    X_test = test_dataset.drop(label, axis=1)
    dtrain = xgb.DMatrix(X_train, label=y_train)
    dtest = xgb.DMatrix(X_test, label=y_test)
    return dtrain, dtest