lang2vec.py 文件源码

def get_id_set(lang_codes):
    feature_database = np.load("family_features.npz")
    lang_codes = [ get_language_code(l, feature_database) for l in lang_codes ]
    all_languages = list(feature_database["langs"])
    feature_names = [ "ID_" + l.upper() for l in all_languages ]
    values = np.zeros((len(lang_codes), len(feature_names)))
    for i, lang_code in enumerate(lang_codes):
        feature_index = get_language_index(lang_code, feature_database)
        values[i, feature_index] = 1.0
    return feature_names, values