作为联合对角化参数传递的数组结构错误

如何解决作为联合对角化参数传递的数组结构错误

我正在尝试使用以下函数中的 ffdiag (pybss) :

def ffdiag(X,max_lag = 10,eps = 1.0e-10,max_iter = 100):
    '''
    Blind source separation using FFDIAG.  This version does not require that
    the estimated mixing matrix be orthogonal.

    INPUT:
    ------
    X : array,required
        N_sig x t matrix of signal mixtures

    max_lag : int,optional
        maximum lag (in samples) for covariance matrix calculation

    eps : double,optional
        convergence criterion for matrix updates

    max_iter : int,optional
        maximum number of iterations/updates
    '''
    R_tau = linalg.lagged_covariance(X,max_lag)
    dim = len(R_tau[0])
    n_lags = len(R_tau.keys())
    W = zeros((dim,dim))
    V = eye(dim)
    C = R_tau
    niter = 0
    theta = 0.9
    iter_eps = 1.0

用 lagged_covariance 定义：

def lagged_covariance(X,max_lag):
    '''
    Generates a dictionary of lagged covariance matrices of matrix X,for
    lags 0,1,2,...,max_lag.

    INPUT:
    ------
    X : array,required
        N x t data matrix

    max_lag : integer,required
        covariance matrices will be computed for lags 0,max_lag

    OUTPUT:
    ------
    R_tau : dictionary,keyed on the lag,with values equal to the lagged
        covariance of X with the lagged version of itself.
    '''
    R_tau = {}
    t = X.shape[1]
    dim = X.shape[0]
    R_tau[0] = cov(X,X)[0:dim,dim::]
    for tau in range(1,max_lag+1):
        for i in range(tau,t):
            # create X(t) and X(t-tau)
            X_t = X[:,0:t-tau]

我收到以下错误：

/Users/henry/pybss/linalg.py",line 92,in lagged_covariance
    R_tau[0] = cov(X,dim::]
  File "<__array_function__ internals>",line 6,in cov
  File "/opt/intel/intelpython3/lib/python3.7/site-packages/numpy/lib/function_base.py",line 2371,in cov
    raise ValueError("m has more than 2 dimensions")
ValueError: m has more than 2 dimensions

在我的脚本中，我像这样调用 ffdiag :

# dimension
m=7
# number of matrices
n=2

# Load spectro and WL+GCph+XC
FISH_GCsp = np.loadtxt('Fisher_GCsp_flat.txt')
FISH_XC = np.loadtxt('Fisher_XC_GCph_WL_flat.txt')

# Marginalizing over uncommon parameters between the two matrices
COV_GCsp_first = np.linalg.inv(FISH_GCsp)
COV_XC_first = np.linalg.inv(FISH_XC)
COV_GCsp = COV_GCsp_first[0:m,0:m]
COV_XC = COV_XC_first[0:m,0:m]
# Invert to get Fisher matrix
FISH_sp = np.linalg.inv(COV_GCsp)
FISH_xc = np.linalg.inv(COV_XC)
# Drawing a random set of commuting matrices
C=np.zeros((n,m,m));
B=np.zeros((n,m));
C[0,:,:] = np.array(FISH_sp)
C[1,:] = np.array(FISH_xc)

[invV,B,ut] = ffdiag(C,10,1.0e-10,100)

但我不知道数组 C 是否定义良好：在任何情况下，我都必须传递 2 个大小为 7x7 的矩阵，但顺序是：

# dimension
m=7
# number of matrices
n=2

C=np.zeros((n,m));

或

C=np.zeros((m,n));
B=np.zeros((m,n));

或其他东西，因为上述两者似乎都不起作用。

正如你在 ffdiag 的定义中看到的，注意到：

INPUT:
        ------
        X : array,required
            N_sig x t matrix of signal mixtures

但我猜不出 X array 的结构是什么。