main.py 文件源码

def describe(name):
    """
    Describe the dataset
    """
    df = load_data(name)
    s = df.groupby(level=[0, 1]).size()
    print('Dataset               :', name)
    print('Users                 :', len(s.groupby(level=0)))
    print('Sessions/user         :', s.groupby(level=0).size().mean())
    print('Sample size           :', s.mean(), '+/-', s.std())
    print('Mean pp interval (ms) :',
          df.groupby(level=[0, 1]).apply(lambda x: x['timepress'].diff().dropna().mean()).mean())
    print('Mean duration (ms)    :',
          df.groupby(level=[0, 1]).apply(lambda x: (x['timerelease'] - x['timepress']).mean()).mean())

    for target in TARGETS[1:]:
        s = df.reset_index().groupby([target, 'session']).size().groupby(level=0).size()
        print(target)
        print(s / s.sum())
    return