weighted correlation in python

Question

I am trying to using the weighted correlation function from here

def m(x, w):
    """Weighted Mean"""
    return np.sum(x * w) / np.sum(w)

def cov(x, y, w):
    """Weighted Covariance"""
    return np.sum(w * (x - m(x, w)) * (y - m(y, w))) / np.sum(w)

def corr(x, y, w):
    """Weighted Correlation"""
    return cov(x, y, w) / np.sqrt(cov(x, x, w) * cov(y, y, w))

This is the data that I am using

x = np.arange(78)
y = np.arange(21)
w = np.random.random((21,78)) # this is just an example matrix

# the key is to have a weight matrix that is of size (y.shape, x.shape)

Now when I try to compute the weighted correlation, I run into a ValueError: operands could not be broadcast together with shapes. Any suggestion on how can I modify the script to make it work for a dataset like this?

For reference, I am trying to implement the methods mentioned here in the heading Bayesian Replay Analysis http://www.buzsakilab.com/content/PDFs/Grosmark2016Supp.pdf

Answer 1

According to the Wikipedia link presented in the post you mention (see https://en.wikipedia.org/wiki/Pearson_correlation_coefficient#Weighted_correlation_coefficient), the size of the vectors x and y should be the same.