如何获得此数据帧的相关性？

Question

这是数据帧-

                                        load        lmp
read_year read_month trading_block                     
2017      3           0             0.018033  27.832902
                      1             0.023771  34.044462
          4           0             0.017487  25.136200
                      1             0.023570  33.487529
          5           0             0.018008  24.085170
                      1             0.024557  36.357774
          6           0             0.021342  22.528570
                      1             0.028840  31.127481
          7           0             0.022381  24.076738
                      1             0.031395  37.653610
          8           0             0.021408  22.171804
                      1             0.030574  32.599279
          9           0             0.019850  24.391908
                      1             0.027178  39.192316
          10          0             0.017754  25.593717
                      1             0.023717  34.941795
          11         -1             0.014916  18.443703
                      0             0.015961  25.708624
                      1             0.020092  33.650612
          12          0             0.016170  28.675776
                      1             0.020008  36.851096
2018      1           0             0.015894  49.115699
                      1             0.019224  59.492227
          2           0             0.015765  23.719127
                      1             0.019607  29.572859
          3           0             0.016970  29.240378
                      1             0.021500  36.516138
          4           0             0.016267  31.317317
                      1             0.022204  39.404220
          5           0             0.017652  27.454792
                      1             0.024314  41.900247

索引部分是让我失望的地方。我最终需要的是这样的东西-

 trading_block  read_month  Correlation Coefficient
             0           1                 0.740597
             0           2                 0.744560
             0           3                 0.300000
             0           4                 0.325736
             0           5                 0.300000
             0           6                 0.846745
             0           7                 0.784101
             0           8                 0.684961
             0           9                 0.796357
             0          10                 0.758172
             0          11                 0.577991
             0          12                 0.684050
             1           1                 0.556274
             1           2                 0.328713
             1           3                 0.300000
             1           4                 0.300000
             1           5                 0.300000
             1           6                 0.639870
             1           7                 0.591472
             1           8                 0.658894
             1           9                 0.615737
             1          10                 0.500315
             1          11                 0.300000
             1          12                 0.346552

我之前已经做过数学，尽管过于复杂，而且有一种简单的方法可以做到，我只是不知道它是什么。我假设我需要一个groupyby函数或类似的东西。

这是等式-

X线是每个月reading的平均值，而trading_block是0或1，如下所示-

    hour_ending  read_date  read_month  read_year   reading  trading_block
0             1 2017-03-23           3       2017  0.019582              0
1             2 2017-03-23           3       2017  0.019460              0
2             3 2017-03-23           3       2017  0.018888              0
3             4 2017-03-23           3       2017  0.018940              0
4             5 2017-03-23           3       2017  0.019114              0
5             6 2017-03-23           3       2017  0.020050              0
6             7 2017-03-23           3       2017  0.022545              0
7             8 2017-03-23           3       2017  0.024053              1
8             9 2017-03-23           3       2017  0.026028              1
9            10 2017-03-23           3       2017  0.027726              1
10           11 2017-03-23           3       2017  0.029251              1
11           12 2017-03-23           3       2017  0.028887              1
12           13 2017-03-23           3       2017  0.027397              1
13           14 2017-03-23           3       2017  0.027536              1
14           15 2017-03-23           3       2017  0.026253              1
15           16 2017-03-23           3       2017  0.025872              1
16           17 2017-03-23           3       2017  0.024746              1
17           18 2017-03-23           3       2017  0.023481              1
18           19 2017-03-23           3       2017  0.022701              1
19           20 2017-03-23           3       2017  0.023377              1