kernels.py 文件源码

def sq_dist(a, b=None):
    #mean-center for numerical stability
    D, n = a.shape[0], a.shape[1]
    if (b is None):
        mu = a.mean(axis=1)
        a -= mu[:, np.newaxis]
        b = a
        m = n
        aSq = np.sum(a**2, axis=0)
        bSq = aSq
    else:
        d, m = b.shape[0], b.shape[1]
        if (d != D): raise Exception('column lengths must agree')
        mu = (float(m)/float(m+n))*b.mean(axis=1) + (float(n)/float(m+n))*a.mean(axis=1)
        a -= mu[:, np.newaxis]
        b -= mu[:, np.newaxis]      
        aSq = np.sum(a**2, axis=0)
        bSq = np.sum(b**2, axis=0)

    C = np.tile(np.column_stack(aSq).T, (1, m)) + np.tile(bSq, (n, 1)) - 2*a.T.dot(b)
    C = np.maximum(C, 0)    #remove numerical noise
    return C

#evaluate 'power sums' of the individual terms in Z