progAss4.py 文件源码

def Mstep(dataSet,W):
    (N, M) = np.shape(dataSet)
    K = np.size(W,1)
    # Each column of MU represents the mean of a cluster. 
    # So, for K clusters, there will be K columns of MU
    # Each column,
    # mu_k = (1/N_k)*sum_{1}^{N}{w_{ik}*x_i} 
    N_k = np.sum(W,0)
    Alpha = N_k/np.sum(N_k)
    Mu = dataSet.T.dot(W).dot(np.diag(np.reciprocal(N_k)))
    # SIGMA is a 3-dimensional matrix of size MxMxK. 
    # It contains K covariances for each cluster
    Sigma = np.zeros([M,M,K])
    for k in range(K):
        datMeanSub = dataSet.T - Mu[0:,k][None].T.dot(np.ones([1,N]))
        Sigma[:,:,k] = (datMeanSub.dot(np.diag(W[0:,k])).dot(datMeanSub.T))/N_k[k]
    return Alpha,Mu,Sigma