In [1]:

    

import numpy as np


    

In [38]:

    

# Calculating the covariance matrix or cross correlation
X = np.random.rand(50, 1000)


    

In [39]:

    

X.shape, X.dtype


    

    
Out[39]:





((50, 1000), dtype('float64'))

In [40]:

    

# cov = X @ X.T
cov = X.T @ X


    

In [41]:

    

cov.shape

import matplotlib.pyplot as mplt


    

In [42]:

    

mplt.imshow(cov)
mplt.show()


    

In [46]:

    

X.shape, X.mean(axis=0).shape
X_norm = (X - X.mean(axis=0))/ X.std(axis=0)


    

In [48]:

    

X_norm.shape
cov = X_norm.T @ X_norm


    

In [49]:

    

mplt.imshow(cov)
mplt.show()


    

In [ ]: