K-means实验

最新推荐文章于 2023-03-12 11:25:54 发布

ahyo

最新推荐文章于 2023-03-12 11:25:54 发布

阅读量122

点赞数

分类专栏：初学分享文章标签： kmeans python

本文链接：https://blog.csdn.net/yooppa/article/details/128244276

版权

初学分享专栏收录该内容

194 篇文章 3 订阅

订阅专栏

import random
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# 计算欧拉距离
def calcDis(dataSet, centroids, k):
    clalist=[]
    for data in dataSet:
        diff = np.tile(data, (k, 1)) - centroids  
        squaredDiff = diff ** 2     #平方
        squaredDist = np.sum(squaredDiff, axis=1)  
        distance = squaredDist ** 0.5  #开根号
        clalist.append(distance)
    clalist = np.array(clalist)  #返回一个每个点到质点的距离len(dateSet)*k的数组
    return clalist

# 计算质心
def classify(dataSet, centroids, k):
    # 计算样本到质心的距离
    clalist = calcDis(dataSet, centroids, k)
    # 分组并计算新的质心
    minDistIndices = np.argmin(clalist, axis=1)    #axis=1 表示求出每行的最小值的下标
    newCentroids = pd.DataFrame(dataSet).groupby(minDistIndices).mean() 
    newCentroids = newCentroids.values

    # 计算变化量
    changed = newCentroids - centroids

    return changed, newCentroids

# 使用k-means分类
def kmeans(dataSet, k):
    # 随机取质心
    centroids = random.sample(dataSet, k)

    # 更新质心 直到变化量全为0
    changed, newCentroids = classify(dataSet, centroids, k)
    while np.any(changed != 0):
        changed, newCentroids = classify(dataSet, newCentroids, k)

    centroids = sorted(newCentroids.tolist())   


    cluster = []#集群计算
    clalist = calcDis(dataSet, centroids, k)
    minDistIndices = np.argmin(clalist, axis=1)
    for i in range(k):
        cluster.append([])
    for i, j in enumerate(minDistIndices):   
        cluster[j].append(dataSet[i])

    return centroids, cluster

# 创建数据集
def createDataSet():
    return [[1, 3], [1, 2], [2, 2], [6, 4], [6, 3], [7, 4]]

if __name__=='__main__':
    dataset = createDataSet()
    centroids, cluster = kmeans(dataset, 4)
    print('质心为：%s' % centroids)
    print('集群为：%s' % cluster)
    for i in range(len(dataset)):
        plt.scatter(dataset[i][0],dataset[i][1], marker = 'o',color = 'green', s = 40 ,label = '原始点')
        #  记号形状       颜色      点的大小      设置标签
        for j in range(len(centroids)):
            plt.scatter(centroids[j][0],centroids[j][1],marker='x',color='red',s=50,label='质心')
            plt.show()