lang2vec.py 文件源码

def get_concatenated_sets(lang_codes, feature_set_str):
    feature_set_parts = feature_set_str.split("+")
    feature_names = []
    feature_values = np.ndarray((len(lang_codes),0))
    for feature_set_part in feature_set_parts:
        more_feature_names, more_feature_values = get_union_sets(lang_codes, feature_set_part)
        feature_names += more_feature_names
        feature_values = np.concatenate([feature_values, more_feature_values], axis=1)
    return feature_names, feature_values