import numpy as np import time import matplotlib.pyplot as plt import kmeans ## step 1: load data print("step 1: load data...") dataSet = [] fileIn = open('testSet.txt') for line in fileIn.readlines(): lineArr = line.strip().split('\t') dataSet.append([float(lineArr[0]), float(lineArr[1])]) ## step 2: clustering... print("step 2: clustering...") dataSet = np.mat(dataSet) k = 4 centroids, clusterAssment = kmeans.kmeans(dataSet, k) ## step 3: show the result print("step 3: show the result...") kmeans.showCluster(dataSet, k, centroids, clusterAssment)
from numpy import * import time import matplotlib.pyplot as plt import kmeans ## step 1: load data print ("step 1: load data...") dataSet = [] fileIn = open('D:/AI/Assignment4/realdata.txt') for line in fileIn.readlines(): lineArr = line.strip().split('\t') dataSet.append([float(lineArr[0]), float(lineArr[1])]) ## step 2: clustering... print ("step 2: clustering..." ) dataSet = mat(dataSet) k = 4 centroids, clusterAssment = kmeans.kmeans(dataSet, k) ## step 3: show the result print ("step 3: show the result...") kmeans.showCluster(dataSet, k, centroids, clusterAssment)
# Date : 2013-12-25 # HomePage : http://blog.csdn.net/zouxy09 # Email : [email protected] ################################################# from numpy import * import time import matplotlib.pyplot as plt from kmeans import kmeans from kmeans import showCluster # step 1: load data print "step 1: load data..." dataSet = [] fileIn = open('testSet.txt') for line in fileIn.readlines(): lineArr = line.strip().split('\t') dataSet.append([float(lineArr[0]), float(lineArr[1])]) # step 2: clustering... print "step 2: clustering..." dataSet = mat(dataSet) for i in xrange(dataSet.shape[0]): plt.plot(dataSet[i, 0], dataSet[i, 1], 'or') plt.show() k = 4 centroids, clusterAssment = kmeans(dataSet, k) # step 3: show the result print "step 3: show the result..." showCluster(dataSet, k, centroids, clusterAssment)