python之k-means算法实现（待修正）

import numpy as np

# k-means算法的实现

# s = [[20, 5, 15], [9, 18, 10], [21, 10, 7], [17, 13, 25], [12, 21, 19]]

# 选定两点
# 1.求距离

# 两种类型
label1 = []
label2 = []

# 先假定两个中心点
mean1 = [20, 15, 14]
mean2 = [17, 19, 26]

ls = []


# 第一个参数是待聚合的数据，第二个和第三个参数分别是其中心点
def distance(t1, t2, t3):
    global label1;
    label1 = []
    global label2;
    label2 = []
    length = len(t1[0])
    for i in t1:
        distance1 = 0
        distance2 = 0
        count = 0
        while (count < length):
            distance1 = distance1 + (i[count] - t2[count]) ** 2
            distance2 = distance2 + (i[count] - t3[count]) ** 2
            count = count + 1
        if (distance1 > distance2):
            label1.append(i)
        else:
            label2.append(i)
    remeans(la1=label1, la2=label2)


# 2.重新计算中心值
def remeans(**label):
    flag = 0
    global mean1;
    mean1 = []
    global mean2;
    mean2 = []
    for key, value in label.items():
        index = 0
        for i in range(len(value[0])):
            temp = np.array(value)
            row = temp[:, index:index + 1]
            row = [i for j in row for i in j]
            length = len(row)
            count = sum(i for i in row)
            clx = count / length
            if (flag == 0):
                mean1.append(clx)
            else:
                mean2.append(clx)
            index = index + 1
        flag = flag + 1


# temp = np.array(temp)
# ls = np.array(ls)
# flag = 0
# while ((temp != ls).all() and flag < 20):

# 存储临时变量
temp1 = []
temp2 = []
flag = 0
t1 = [[20, 5, 15], [21, 10, 7], [17, 13, 25], [12, 22, 17], [21, 10, 7], [12, 21, 19]]
while (temp1 != mean1 and temp2 != mean2 and flag < 20):
    temp1 = mean1
    temp2 = mean2
    distance(t1, temp1, temp2)
    flag = flag + 1

print("class1", label1)
print("class", label2)