基于python3的k-means代码实现

k-means算法是非监督学习的一种，其中k值是随机选取的，在本代码中是人为指定为2，准备聚两个类。算法描述：

1. 加载数据

2. 聚类

2.1、 初始化聚类中心，随机选取两个点作为聚类中心点。2.2、while直到clusterChanged=false2.3、计算每个点离中心点的距离，记录最小距离，并标识是属于哪个类。2.4、更新聚类集合的点。2.5、 更新聚类中心代码实现前先浏览一下数据，数据分布如下从数据分布可以看出，是7个点。代码实现分为两个python文件，一个是聚类的实现文件，k_means.py,一个是测试文件test_kmeans.py.

k_means.py

如下：“`# -- coding: utf-8 --“””Created on Thu Nov 17 16:13:56 2016@author: phl“””print(“k-means算法程序”)from numpy import *import timeimport matplotlib.pyplot as pltdef euclDistance(vector1, vector2):return sqrt(sum(power(vector2 - vector1, 2)))def initCentriods(dataSet,k):print(dataSet)numSamples,dim = dataSet.shape #dim列数centroids = zeros((k, dim))print(“行数：”,numSamples)print(“列数：”,dim)for i in range(k):index = int(random.uniform(0, numSamples))centroids[i, :] = dataSet[index, :]return centroidsdef kmeans(dataSet, k):numSamples = dataSet.shape[0] #dataSet.shape是几行几列的意思，这里是7行2列print(“行数：”,numSamples)clusterAssment = mat(zeros((numSamples, 2)))#初始化一个行两列的0矩阵clusterChanged = True## step 1: 初始化聚类中心centroids = initCentriods(dataSet, k)print(“随机初始化的两个点：”,centroids)## 循环遍历数据while clusterChanged:clusterChanged = Falsefor i in range(numSamples):minDist = 100000.0minIndex = 0## 循环遍历中心点## step 2:计算离中心点的距离for j in range(k):distance = euclDistance(centroids[j, :], dataSet[i, :])if distance < minDist:minDist = distanceminIndex = j #minIndex代表类别##更新聚类分配if clusterAssment[i,0] != minIndex:clusterChanged = TrueclusterAssment[i, :] = minIndex, minDist**2## step 4: 更新聚类中心for j in range(k):pointsInCluster = dataSet[nonzero(clusterAssment[:, 0].A == j)[0]]centroids[j, :] = mean(pointsInCluster, axis = 0)print(‘恭喜你，聚类完成’)return centroids, clusterAssmentdef showCluster(dataSet, k, centroids, clusterAssment):numSamples, dim = dataSet.shapeif dim != 2:print(“Sorry! I can not draw because the dimension of your data is not 2!”)return 1

mark = ['or', 'ob', 'og', 'ok', '^r', '+r', 'sr', 'dr', '<r', 'pr']
if k > len(mark):
print("Sorry! Your k is too large! please contact Zouxy")
return 1

# draw all samples
for i in range(numSamples):
markIndex = int(clusterAssment[i, 0])
plt.plot(dataSet[i, 0], dataSet[i, 1], mark[markIndex])

mark = ['Dr', 'Db', 'Dg', 'Dk', '^b', '+b', 'sb', 'db', '<b', 'pb']
# draw the centroids
for i in range(k):
plt.plot(centroids[i, 0], centroids[i, 1], mark[i], markersize = 12)
plt.show()

def showData(dataSet):x = []y = []plt.figure(figsize=(9,6))for i in dataSet:x.append([float(i[0])])y.append([float(i[1])])plt.scatter(x,y,c=”b”,s=25,alpha=0.4,marker=’o’)#T:散点的颜色#s：散点的大小#alpha:是透明程度plt.show()

test_kmeans.py

如下：

# -- coding: utf-8 --“””Created on Thu Nov 17 16:35:03 2016@author: phl“””from numpy import *import timeimport matplotlib.pyplot as pltfrom k_means import *print(“step 1: 加载数据”)dataSet = []fileIn = open(‘F:/python/testSet.txt’)for line in fileIn.readlines():lineArr = line.strip().split(‘\t’)dataSet.append([float(lineArr[0]), float(lineArr[1])])showData(dataSet)print(“step 2: 聚类”)dataSet = mat(dataSet) #mat是把数据格式化成列的形式[[1. 1.][1.5 2.][3. 4.][5. 7.]]k = 2centroids, clusterAssment = kmeans(dataSet, k)print(“step 3: 展示聚类结果”)showCluster(dataSet, k, centroids, clusterAssment) “`结果界面如下：