西电数据挖掘作业——kmeans图片聚类python实现

import numpy as np import pandas as pd from pandas import Series,DataFrame import matplotlib.pyplot as plt def getdata(data): with open(data) as f: data = [] datalist = f.readlines() for each in datalist: each = each.strip().split('\t') each = list(map(float,each)) data.append(each) data = np.array(data) return(data) def dist(A,B): return np.sqrt(np.sum(np.power(A - B ,2))) def randcent(data,k): n = np.shape(data)[1] cent = np.zeros((k,n)) for j in range(n): minj = min(data[:,j]) rangej =float(max(data[:,j]) - minj) cent[:,j:j+1] = minj + rangej *np.random.rand(k,1)#注意此索引可以获得一个二维数组，而若只是data[:,1]获得的仅仅是一维数组 return cent def KMeans(data,k,n,dist=dist, creatcent=randcent): m = np.shape(data)[0] labelmat = np.zeros((m,1)) cent = creatcent(data,k) num = 0 while num<n: num +=1 for i in range(m): mindist = np.inf minindex = -1 for j in range(k): distj =dist(data[i],cent[j]) if distj <mindist: mindist = distj minindex = j labelmat[i,0]=int(minindex) '''' for a in range(k): centa = data[np.nonzero(labelmat[:,0]==a)[0]] cent[a] = np.mean(centa,axis=0) ' return(cent,labelmat) ''' return(labelmat)