[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
k-means聚类算法是一种经典的基于距离的聚类算法,它的基本思想就是先指定需要划分的簇的个数k,在数据集中选取k个数据作为初始的聚类中心,接着计算这k个聚类中心与其他数据之间存在的距离,根据最近邻原则,划分簇并继续调整,分别对新的聚类中心进行计算,直到算法收敛或者到达指定的迭代次数,算法流程如下:
算法流程图:
Python实现
import torch import random import numpy as np from sklearn import datasets def
kmeans(data, N_way, iteration): # data : N*S, N为样本数,S为特征维数,tensor # N_way : 类别数
#iteration:迭代次数 #初始化 N_way个聚类中心 N = data.shape[0] index = range(N) C = data[
random.sample(index, N_way),:] #C*S,C为类别,N为样本 D = torch.zeros(N_way, N)
#样本和类中心的距离矩阵 count = 0 while True: G = torch.zeros(N_way, N)
#类别硬化分矩阵,每行一个类别,每列一个样本 P = torch.zeros(N_way, N) #距离按列归一化矩阵,可用作软分类
#计算各个样本到各类的距离,及所属的类别 for i in range(N_way): c_i = C[i,:] c_i = c_i.unsqueeze(0).
expand(N, -1) d = (c_i - data)*(c_i - data) d = d.sum(dim=1) D[i,:] = d for i in
range(N): P[:,i] = D[:, i]/D[:, i].sum() index = torch.min(D[:, i], 0)[1] G[
index, i] = 1 #更新类中心 C = torch.mm(G,data) N = [] #每个簇样本数 for i in range(N_way):
num= len(torch.nonzero(G[i, :])) C[i, :] = C[i, :]/num N.append(num) #判断是否满足终止条件
if(count>iteration): break count += 1 return C,G,P if __name__ == '__main__':
iris= datasets.load_iris() n_sample, n_feature = iris.data.shape data = iris.
data data= data.astype(np.float32) data = torch.from_numpy(data) C,G,P = kmeans(
data,3,100) label = iris.target count = 0 for i in range(150): pre = torch.max(P
[:,i],0)[1] print(pre) if pre==label[i]: count += 1 print(count)