data_io.py 文件源码

def inventory_data_dir(input_dir):
    ''' Inventory data, assuming flat directory structure, assuming a directory hierarchy'''
    training_names = ls(input_dir + '/*/*_train.data') # This supports subdirectory structures obtained by concatenating bundles
    for i in range(0,len(training_names)):
        name = training_names[i]
        training_names[i] = name[-name[::-1].index(filesep):-name[::-1].index('_')-1]
        check_dataset(os.path.join(input_dir, training_names[i]), training_names[i])
    return training_names