代码:
import copy
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (16, 9) # 画布大小
plt.style.use('ggplot') # 画布背景
# 显示中文设置...
plt.rcParams['font.sans-serif'] = ['SimHei'] # 替换sans-serif字体
plt.rcParams['axes.unicode_minus'] = False # 解决坐标轴负数的负号显示问题
def distance(a, b, ax = 1): # 按行计算两点欧氏距离
return np.linalg.norm(a - b, ord = 2, axis = ax)
'''
'''
data = pd.read_csv('./xclara.csv')
f1 = data['V1'].values
f2 = data['V2'].values
X = np.array(list((zip(f1, f2)))) # 数据点
print("X.shape: ", X.shape)
# X.shape: (3000, 2)
K = 3
C_x = np.random.randint(0, np.max(X)-20, size=K)
C_y = np.random.randint(0, np.max(X)-20, size=K)
C = np.array(list(zip(C_x, C_y)), dtype = np.float32) # 聚类中心
print("C.shape: ", C.shape)
# C.shape: (3, 2)
C_old = np.zeros(C.shape)
clusters = np.zeros(len(X)) # 各数据点属于的聚类中心
iteration_flag = distance(C, C_old)
tmp = 1
while iteration_flag.any() != 0 and tmp < 20:
for i in range(len(X)):
distances = distance(X[i], C) # 求该点和各聚类中心的距离
cluster = np.argmin(distances) # argmin: Returns the indices of the minimum values along an axis.
clusters[i] = cluster
C_old = copy.deepcopy(C)
for i in range(K):
points = [X[j] for j in range(len(X)) if clusters[j] == i]
C[i] = np.mean(points, axis = 0)
print('循环次数 %d 次' % tmp)
tmp += 1
iteration_flag = distance(C, C_old)
print("新中心与旧中心点的距离:", iteration_flag)
colors = ['r', 'g', 'b', 'y', 'c', 'm']
fig, ax = plt.subplots()
for i in range(K):
points = np.array([X[j] for j in range(len(X)) if clusters[j] == i])
ax.scatter(points[:, 0], points[:, 1], s = 7, c = colors[i])
ax.scatter(C[:, 0], C[:, 1], marker='*', s = 200, c = 'black')
plt.show()
效果: