python实现kmeans聚类

import pandas as pd
import numpy as np
import random
import math
import matplotlib.pyplot as plt
 
# 这两行代码解决 plt 中文显示的问题
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
 
df = pd.read_excel('13信科学生成绩.xlsx')
data = np.array(df)
 
df.head(10)

# 输入数据
x = data.T[0]
y = data.T[1]
 
plt.scatter(x, y, s=50, c='r')  # 画散点图
plt.xlabel('平时')  # 横坐标轴标题
plt.ylabel('期末')  # 纵坐标轴标题
plt.show()

k=3
i = 1
 
min1 = data.min(axis = 0)
max1 = data.max(axis = 0)
 
#在数据最大最小值中随机生成k个初始聚类中心，保存为t
centre = np.empty((k,2))
for i in range(k):
    centre[i][0] = random.randint(min1[0],max1[0])#平时成绩
    centre[i][1] = random.randint(min1[1],max1[1])#期末成绩
 
while i<500:
    
    #计算欧氏距离
    def euclidean_distance(List,t):
        return math.sqrt(((List[0] - t[0])**2 + (List[1] - t[1])**2))
 
    #每个点到每个中心点的距离矩阵
    dis = np.empty((len(data),k))
    for i in range(len(data)):
        for j in range(k):
            dis[i][j] = euclidean_distance(data[i],centre[j])
    
    #初始化分类矩阵
    classify = []
    for i in range(k):
        classify.append([])
    
    #比较距离并分类
    for i in range(len(data)):
        List = dis[i].tolist()
        index = List.index(dis[i].min())
        classify[index].append(i)
    
    #构造新的中心点
    new_centre = np.empty((k,2))
    for i in range(len(classify)):
 
        new_centre[i][0] = np.sum(data[classify[i]][0])/len(classify[i])
        new_centre[i][1] = np.sum(data[classify[i]][1])/len(classify[i])
     
    #比较新的中心点和旧的中心点是否一样
    if (new_centre == centre).all():
        break
    else:
        centre = new_centre
        i = i + 1
 
# print('迭代次数为：',i)
print('聚类中心为：',new_centre)
print('分类情况为：',classify)

mark = ['or', 'ob', 'og', 'ok','sb', 'db', '<b', 'pb'] #红、蓝、绿、黑四种颜色的圆点
#mark=['sb', 'db', '<b', 'pb']
plt.figure(3)#创建图表1  
for i in range(0,k):
 
    x=[]
    y=[]
    for j in range(len(classify[i])):
        x.append(data[classify[i][j]][0])
        y.append(data[classify[i][j]][1])
 
    plt.xlim(xmax=105,xmin=45)
    plt.ylim(ymax=85,ymin=-5)
    plt.plot(x,y,mark[i])
    #plt.show()

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans  
from sklearn import metrics
 
df = pd.read_excel('13信科学生成绩.xlsx')
data = np.array(df)
y_pred=KMeans(n_clusters=3,random_state=9).fit_predict(data)
plt.scatter(data[:,0],data[:,1],c=y_pred)
plt.show()
print(metrics.calinski_harabasz_score(data,y_pred))