手写kmean

n=20 m=2 X=np.random.randn(n,m) def kmeans(X,h,min_err=0.000001,max_iter=1000000000): n,m=X.shape err,iter=1,1 c0=X[:h,:] while True: clusters=[np.zeros([0,m]) for i in range(h)] for i in range(n): sub=np.tile(X[i,:],[h,1])-c0 dist=np.sum(sub**2,1) j=np.argmin(dist) clusters[j]=np.concatenate([clusters[j],X[i,None]],0) c1=np.zeros_like(c0) for i in range(h): c1[i,:]=np.mean(clusters[i],0) err=np.sum(np.sum((c0-c1)**2,1),0) iter+=1 c0=c1 print(err) if iter>max_iter or err<min_err: break return c0 pt=kmeans(X,10) plt.scatter(X[:,0],X[:,1],c='r') plt.scatter(pt[:,0],pt[:,1],c='g')