机器学习（三）——Kmeans

KMeans 非skleran 的实现代码

# -*- coding: utf-8 -*-
"""
Created on Thu May 10 10:12:53 2018
@author: lizihua
"""
from numpy import *
import matplotlib.pyplot as plt


# 加载数据
def loadDataSet(fileName):
    dataMat = []
    fr = open(fileName)
    for line in fr.readlines():
        curLine = line.strip().split('\t')
        fltLine = list(map(float, curLine))
        dataMat.append(fltLine)
    return dataMat


# 计算欧式距离
def distEclud(vecA, vecB):
    return sqrt(sum(power(vecA - vecB, 2)))


# 随机选取k个簇的质心
def randCent(dataSet, k):
    n = shape(dataSet)[1]
    centroids = mat(zeros((k, n)))
    for j in range(n):
        minJ = min(dataSet[:, j])
        rangeJ = float(max(dataSet[:, j]) - minJ)
        # random.rand(k,1)随机产生k行1列的array，数组的值的范围：[0,1)
        # min+(max-min)*(0,1)之间的数，保证了质心在数据集边界之内
        centroids[:, j] = minJ + rangeJ * random.rand(k, 1)
    return centroids


# K-means聚类算法
def kMeans(dataSet, k, distM=distEclud, createCent=randCent):
    m = shape(dataSet)[0]
    # 创建矩阵来存储每个点的簇的分配结果，第一列记录簇索引值，第二列存储误差（点到簇质心的距离）
    # 且默认所有点的簇都为0
    clusterAssment = mat(zeros((m, 2)))
    # 随机选取k个簇质心
    centroids = createCent(dataSet, k)
    # 标志变量clusterChanged，用以标志簇分配结果是否发生变化
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False
        # 对于每一个点，计算每个点与k个簇质心的距离，并每个点距离k个簇质心中的最小距离的那个簇
        for i in range(m):
            minDist = inf
            minIndex = -1
            for j in range(k):
                distJI = distM(centroids[j, :], dataSet[i, :])
                if distJI < minDist:
                    minDist = distJI
                    minIndex = j
            # 如果簇索引发生变化，则，标志变量clusterChanged为True
            if clusterAssment[i, 0] != minIndex:
                clusterChanged = True
            # 反之，则将离该点最近的簇索引和距离的平方存储到clusterAssment
            clusterAssment[i, :] = minIndex, minDist ** 2
        print("centroids:\n", centroids)
        # 遍历所有簇质心
        for cent in range(k):
            # 通过数组过滤来获得给定簇的所有点
            pstInClust = dataSet[nonzero(clusterAssment[:, 0].A == cent)[0]]
            # 计算所有点的均值
            centroids[cent, :] = mean(pstInClust, axis=0)
    # 返回类质心和分配结果
    return centroids, clusterAssment


def kMeansPlot(dataMat, centroids, clusterAssment):
    k = len(centroids)
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(centroids[:, 0].tolist(), centroids[:, 1].tolist(), marker='+', c='r')
    markers = ['o', 's', 'v', '*']
    colors = ['blue', 'green', 'yellow', 'red']
    for i in range(k):
        data_class = dataMat[nonzero(clusterAssment[:, 0].A == i)[0]]
        ax.scatter(data_class[:, 0].tolist(), data_class[:, 1].tolist(), marker=markers[i], c=colors[i])
    plt.show()


# 测试
if __name__ == "__main__":
    dataMat = mat(loadDataSet('testset.txt'))
#    print("簇质心：\n", randCent(dataMat, 2))
 #   print("距离：\n", distEclud(dataMat[0], dataMat[1]))  # 距离： 5.18463281668
    myCentroids, clustAssing = kMeans(dataMat, 4)
 #   print("类质心：\n", myCentroids)
  #  print("点分配结果：\n", clustAssing)
    kMeansPlot(dataMat, myCentroids, clustAssing)