Numpy Python 等效于 MATLAB corr

如何解决Numpy Python 等效于 MATLAB corr

目标是计算两个数组的相关性。特别是 polyval 输出与另一个时间序列之间的相关性。

给定信号

y_ax = [7.8625913,7.7713094,7.6833806,7.5997391,7.5211883,7.4483986,7.3819046,7.3221073,7.2692747,7.2235470,7.1849418,7.1533613,7.1286001,7.1103559,7.0982385,7.0917811,7.0904517,7.0936642,7.1007910,7.1111741,7.1241360,7.1389918,7.1550579,7.1716633,7.1881566,7.2039142,7.2183490,7.2309117,7.2410989,7.2484550,7.2525721,7.2530937,7.2497110,7.2421637,7.2302341,7.2137470,7.1925621,7.1665707,7.1356878,7.0998487,7.0590014,7.0131001,6.9621005,6.9059525,6.8445964,6.7779589,6.7059474,6.6284504,6.5453324,6.4564347,6.3615761,6.2605534,6.1531439,6.0391097,5.9182019,5.7901659,5.6547484,5.5117044,5.3608050,5.2018456,5.0346560,4.8591075,4.6751242,4.4826899,4.2818580,4.0727611,3.8556159,3.6307325,3.3985188,3.1594861,2.9142516,2.6635408,2.4081881,2.1491354,1.8874279,1.6242117,1.3607255,1.0982931,0.83831298] 


x_ax = [6210,6211,6212,6213,6214,6215,6216,6217,6218,6219,6220,6221,6222,6223,6224,6225,6226,6227,6228,6229,6230,6231,6232,6233,6234,6235,6236,6237,6238,6239,6240,6241,6242,6243,6244,6245,6246,6247,6248,6249,6250,6251,6252,6253,6254,6255,6256,6257,6258,6259,6260,6261,6262,6263,6264,6265,6266,6267,6268,6269,6270,6271,6272,6273,6274,6275,6276,6277,6278,6279,6280,6281,6282,6283,6284,6285,6286,6287,6288] 

在 MATLAB 中，这可以实现为

[p,S,mu] = polyfit(x_ax,y_ax,1);
     ffit  = polyval(p,x_ax,mu);
   cor_val = corr(y_ax,ffit )

cor_val 等价于 0.85406816

同样，前两步可以使用Numpy

y_ax=np.array(y_ax)
x_ax=np.array(x_ax)
coefs = np.polyfit ( x_ax,1 )
ffit = np.polyval(coefs,x_ax)

但是，使用 Numpy correlate 如下

cor_val = np.correlate(y_ax,ffit)

不产生由 Matlab corr 返回的值。

我尝试了所有 3 种 Numpy correlate 模式 {'valid','same','full'}，但都没有产生与 Matlab 相同的结果。

我可以知道，MATLAB corr 的什么参数或 Numpy Python 等价物

解决方法

您可以改用 np.corrcoef()。

In [63]: y_ax = [7.8625913,7.7713094,7.6833806,7.5997391,7.5211883,7.4483986,7.3819046,7.3221073,7.2692747,7.2235470,7.1849418,7.1533613
    ...:,7.1286001,7.1103559,7.0982385,7.0917811,7.0904517,7.0936642,7.1007910,7.1111741,7.1241360,7.1389918,7.1550579,7.1716633,7.18
    ...: 81566,7.2039142,7.2183490,7.2309117,7.2410989,7.2484550,7.2525721,7.2530937,7.2497110,7.2421637,7.2302341,7.2137470,...: 7.1925621,7.1665707,7.1356878,7.0998487,7.0590014,7.0131001,6.9621005,6.9059525,6.8445964,6.7779589,6.7059474,6.62845
    ...: 04,6.5453324,6.4564347,6.3615761,6.2605534,6.1531439,6.0391097,5.9182019,5.7901659,5.6547484,5.5117044,5.3608050,5.2
    ...: 018456,5.0346560,4.8591075,4.6751242,4.4826899,4.2818580,4.0727611,3.8556159,3.6307325,3.3985188,3.1594861,2.9142516,...:  2.6635408,2.4081881,2.1491354,1.8874279,1.6242117,1.3607255,1.0982931,0.83831298]

In [64]: x_ax = [6210,6211,6212,6213,6214,6215,6216,6217,6218,6219,6220,6221,6222,6223,6224,6225,6226,6227,6228,6229,...: 6230,6231,6232,6233,6234,6235,6236,6237,6238,6239,6240,6241,6242,6243,6244,6245,6246,6247,6248,6249,6250,62
    ...: 51,6252,6253,6254,6255,6256,6257,6258,6259,6260,6261,6262,6263,6264,6265,6266,6267,6268,6269,6270,6271,6272
    ...:,6273,6274,6275,6276,6277,6278,6279,6280,6281,6282,6283,6284,6285,6286,6287,6288]
In [65]: np.corrcoef(y_ax,x_ax)
Out[65]: 
array([[ 1.,-0.85406816],[-0.85406816,1.        ]])