如何将无效索引固定为标量变量？

Question

我尝试编写K-means算法，并在以下行得到此错误：points = np.array ([x[j] for j in range (len (x)) if cluster [j] == i])有人可以帮忙吗？

from copy import deepcopy

def euclidean_distance (a, b, ax = 1):
    return np.linalg.norm (a - b , axis = ax)

c_prev = np.zeros (c.shape)
clusters = np.zeros (len(x))

distance_differences = euclidean_distance (c, c_prev)

while distance_differences.any () != 0:
    for i in range (len(x)):
        distances = euclidean_distance (x[i], c)
        cluster = np.argmin (distances)
        clusters [i] = cluster
    c_prev = deepcopy (c)
    for i in range (k):
        points = [x[j] for j in range (len(x)) if clusters [j] == i]
        if len(points) != 0:
            c[i] = np.mean (points, axis = 0)

    distance_differences = euclidean_distance (c, c_prev)

colors = ['b', 'r', 'y', 'g', 'c', 'm']
for i in range (k):
    points = np.array ([x[j] for j in range (len (x)) if cluster [j] == i])
    if len(points) > 0:
        plt.scatter (points [:, 0], points [:, 1], s= 10, c = colors [i])
    else:
        print ('Please regenerate your centeroids again')

plt.scatter (points [:, 0], points [:, 1], s= 10, c = colors [i])
plt.scatter(c[:, 0], c[:, 1], marker = '*', s =100, c ='k')
plt.show();

Answer 1

是的，您输入中有错字，

points = np.array ([x[j] for j in range (len (x)) if cluster [j] == i])

它应该读为，

points = np.array ([x[j] for j in range (len (x)) if clusters[j] == i])

因为cluster只是一个标量（即只有一个值），clusters是数组