K-Means - 基于numpy实现程序

本文之编写程序涉及到API介绍,程序的完整实现,具体算法原理请查看之前所写的K-Means算法介绍

一、基础准备

1、python 基础

random.uniform
方法将随机生成下一个实数,它在[x,y]范围内。

print(random.uniform(2,6))
#uniform(5, 10) 的随机数为 :  6.98774810047
#uniform(7, 14) 的随机数为 :  12.2243345905

2、numpy 基础

mat
matrices,将数组转换成矩阵运算

data = [[2,6],[3,6]]
print(data)
#>>[[2, 6], [3, 6]]
print(np.mat(data))
#>>[[2 6]
 [3 6]]

二、完整程序

# -*- coding: utf-8 -*-
from numpy import *
import time
import matplotlib.pyplot as plt


# 计算距离
def euclDistance(vector1, vector2):
    return sqrt(sum(power(vector2 - vector1, 2)))


# 获取初始值
def initCentroids(dataSet, k):
    numSamples, dim = dataSet.shape
    centroids = zeros((k, dim))
    for i in range(k):
        index = int(random.uniform(0, numSamples))
        centroids[i, :] = dataSet[index, :]
    return centroids


# 聚类
def kmeans(dataSet, k):
    numSamples = dataSet.shape[0]
    clusterAssment = mat(zeros((numSamples, 2)))
    clusterChanged = True

    #获取初始聚类中心
    centroids = initCentroids(dataSet, k)

    # 不断迭代,指导聚类中点没有变化
    while clusterChanged:
        clusterChanged = False
        for i in range(numSamples):
            minDist = 100000.0
            minIndex = 0
            for j in range(k):
                #计算出距离
                distance = euclDistance(centroids[j, :], dataSet[i, :])
                #求出最短的聚类点
                if distance < minDist:
                    minDist = distance
                    minIndex = j

            # 如果该点聚类有变化,则重新赋值
            if clusterAssment[i, 0] != minIndex:
                clusterChanged = True
                clusterAssment[i, :] = minIndex, minDist ** 2

        # 更新聚类中心点
        for j in range(k):
            pointsInCluster = dataSet[nonzero(clusterAssment[:, 0].A == j)[0]]
            centroids[j, :] = mean(pointsInCluster, axis=0)

    print('聚类完毕')
    return centroids, clusterAssment

#展示数据
def showCluster(dataSet, k, centroids, clusterAssment):
    numSamples, dim = dataSet.shape
    if 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()


if __name__ == '__main__':
    print("加载数据")
    dataSet = []
    fileIn = open('data\\testData.txt')
    for line in fileIn.readlines():
        lineArr = line.strip().split(' ')
        dataSet.append([float(lineArr[0]), float(lineArr[1])])

    #转化为矩阵
    dataSet = mat(dataSet)
    k = 4
    centroids, clusterAssment = kmeans(dataSet, k)
    # 最后结果
    print(centroids)
    print("显示数据")
    showCluster(dataSet, k, centroids, clusterAssment)

推荐阅读更多精彩内容