python机器学习-乳腺癌细胞挖掘（博主亲自录制视频）

https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

# -*- coding: utf-8 -*-

# Import standard packages

import numpy as np

import pandas as pd

# additional packages

from statsmodels.sandbox.stats.runs import cochrans_q

obs = np.array([[1,1,0,1,0,1,1,1,0,0,1,1],

                [1,1,1,1,0,1,1,1,0,1,1,1],

                [1,1,0,0,0,1,1,0,1,0,1,1]])

def cochranQ(obs):

    '''Cochran's Q test: 12 subjects are asked to perform 3 tasks. The outcome of each task is "success" or

    "failure". The results are coded 0 for failure and 1 for success. In the example, subject 1 was successful

    in task 2, but failed tasks 1 and 3.

    Is there a difference between the performance on the three tasks?

    '''

    # I prefer a DataFrame here, as it indicates directly what the values mean

    df = pd.DataFrame(obs.T, columns = ['Diet1', 'Diet2', 'Diet3'])

    # --- >>> START stats <<< ---

    (Q, pVal) = cochrans_q(df)

    # --- >>> STOP stats <<< ---

    print('\nCOCHRAN\'S Q -----------------------------------------------------')

    print('Q = {0:5.3f}, p = {1:5.3f}'.format(Q, pVal))

    if pVal < 0.05:

        print("H1 wins,There is a significant difference between the three tasks.")  

    else:

       print("H0 wins,There was no significant change")

cochranQ(obs)