snapshot.py 文件源码

def linkage(df, n_groups):
    # create the distance matrix based on the forbenius norm: |A-B|_F where A is
    # a 24 x N matrix with N the number of timeseries inside the dataframe df
    # TODO: We can save have time as we only need the upper triangle once as the
    # distance matrix is symmetric
    if True:
        Y = np.empty((n_groups, n_groups,))
        Y[:] = np.NAN
        for i in range(len(Y)):
            for j in range(len(Y[i,:])):
                A = df.loc[i+1].values
                B = df.loc[j+1].values
                #print('Computing distance of:{},{}'.format(i,j))
                Y[i,j] = norm(A-B, ord='fro')

    # condensed distance matrix as vector for linkage (upper triangle as a vector)
    y = Y[np.triu_indices(n_groups, 1)]
    # create linkage matrix with wards algorithm an euclidean norm
    Z = hac.linkage(y, method='ward', metric='euclidean')
    # R = hac.inconsistent(Z, d=10)
    return Z