Python：找到Nx2矩阵的协方差矩阵

Question

I'm trying to compute a covariance matrix for an Nx2 matrix called X by hand (I know that there is a cov() function, but I want to calculate it by hand). The code I'm trying to implement is:

N=len(X)
S=numpy.zeros(2*2).reshape((2,2))
sumx=numpy.zeros(N*2).reshape((N,2))
b1=numpy.zeros(N*1).reshape((N,1))
b2=numpy.zeros(N*1).reshape((N,1))

for n in range(1,N):
    for i in range(0,N):
        b1[i]=(X[n,i]-mean(X[i,:]))

    for j in range(0,2):
        b2[j]=(X[n,j]-mean(X[:,j]))

    btot=b1v*b2v
    bsum=sum(btot)
    S=bsum/(N-1)
print S

but this doesn't work! Sorry I am fairly new to python, so it may be a simple thing I am getting wrong.

The error throws up from saying

b1[i]=(X[n,i]-mean(X[i,:]))

IndexError: index 2 is out of bounds for axis 1 with size 2

UPDATE:

Where X is along the lines of:

[[  1.89235582e-01   1.91920908e+01]
 [  6.53377180e-02   1.78733112e+01]
 [  7.71620860e-02   1.79439764e+01]
 [  8.69048860e-02   1.80507024e+01]
 [  1.94832532e-01   1.85183166e+01]
 [  1.84917732e-01   1.86287646e+01]
  ...]

Answer 1

You're missing a closing parenthesis on the following line:

b1=(X[n,i]-mean(X[i,:])

Also on this line:

b2=(X[n,j]-mean(X[:,j])

When you get syntax errors on a given line, it is often a good idea to look for unclosed delimiters (quotes, parentheses, braces, etc.) on the previous line.