lang2vec.py 文件源码

def get_named_set(lang_codes, feature_set):
    if feature_set == 'id':
        return get_id_set(lang_codes)

    if feature_set not in FEATURE_SETS:
        print("ERROR: Invalid feature set " + feature_set, file=sys.stderr)
        sys.exit()

    filename, source, prefix = FEATURE_SETS[feature_set]
    feature_database = np.load(filename)
    lang_codes = [ get_language_code(l, feature_database) for l in lang_codes ]
    lang_indices = [ get_language_index(l, feature_database) for l in lang_codes ]
    feature_names = get_feature_names(prefix, feature_database)
    feature_indices = [ get_feature_index(f, feature_database) for f in feature_names ]
    source_index = get_source_index(source, feature_database)
    feature_values = feature_database["data"][lang_indices,:,:][:,feature_indices,:][:,:,source_index]
    feature_values = feature_values.squeeze(axis=2)
    return feature_names, feature_values