matrix.py 文件源码

def check_covmat_fast(C,N=None,eps=1e-6):
    '''
    Verify that matrix M is a size NxN precision or covariance matirx
    '''
    if not type(C)==np.ndarray:
        raise ValueError("Covariance matrix should be a 2D numpy array")
    if not len(C.shape)==2:
        raise ValueError("Covariance matrix should be a 2D numpy array")
    if N is None: 
        N = C.shape[0]
    if not C.shape==(N,N):
        raise ValueError("Expected size %d x %d matrix"%(N,N))
    if np.any(~np.isreal(C)):
        raise ValueError("Covariance matrices should not contain complex numbers")
    C = np.real(C)
    if np.any(~np.isfinite(C)):
        raise ValueError("Covariance matrix contains NaN or ±inf!")
    if not np.all(np.abs(C-C.T)<eps):
        raise ValueError("Covariance matrix is not symmetric up to precision %0.1e"%eps)
    try:
        ch = chol(C)
    except numpy.linalg.linalg.LinAlgError:
        # Check smallest eigenvalue if cholesky fails
        mine = np.real(scipy.linalg.decomp.eigh(C,eigvals=(0,0))[0][0])
        if np.any(mine<-eps):
            raise ValueError('Covariance matrix contains eigenvalue %0.3e<%0.3e'%(mine,-eps)) 
        if (mine<eps):
            C = C + np.eye(N)*(eps-mine)
    C = 0.5*(C+C.T)
    return C