机器学习_K近邻Python代码详解

k近邻优点：精度高、对异常值不敏感、无数据输入假定；
k近邻缺点：计算复杂度高、空间复杂度高


import numpy as np
import operator
from os import listdir

# k近邻分类器
def classify0(inx, dataset, labels, k):
    datasetsize = dataset.shape[0]   # 返回dataset第一维的长度，也就是行数
    diffmat = np.tile(inx, (datasetsize, 1))-dataset   # tile表示把inx行向量按列方向重复datasetsize次
    sqdiffmat = diffmat**2
    sqdistances = sqdiffmat.sum(axis=1)  # 按列求和
    distances = sqdistances**0.5
    sorteddistindicies = distances.argsort()  # 返回的是数组从小到大的索引值
    classcount = {}    # 定义一个空字典
    for i in range(k):
        votelabel = labels[sorteddistindicies[i]]  # 返回前k个距离最小的样本的标签值
        classcount[votelabel] = classcount.get(votelabel, 0)+1   # get 表示返回指定键的值
        # lambda表示输入classcount返回冒号右边的值，reverse=true表示按照降序排列
        sortedclasscount=sorted(classcount.items(), key=lambda classcount: classcount[1], reverse=true)
    return sortedclasscount[0][0]

# 把.txt文件转换成矩阵形式
def file2matrix(file):
    file = open(file) # 返回文件对象
    arr = file.readlines()  # 返回全部行，是list形式，每一行为list的一个元素
    number = len(arr)  # 返回对象长度
    returnmat = np.zeros((number,3))
    index = 0
    labelmat = []
    for line in arr:
        #line = line.strip('\n')
        #newline = line.split(' ')
        newline = line.strip('\n').split(' ') # 处理逐行数据，strip表示把头尾的'\n'去掉，split表示以空格来分割行数据
                                              #  然后把处理后的行数据返回到newline列表中
        returnmat[index,:] = newline[0:3] #表示列表的0,1,2列数据放到index行中
        labelmat.append(int(newline[-1]))
        index+=1
    return returnmat,labelmat

# 归一化
def autonorm(dataset):
    minvals = dataset.min(0)

    maxvals = dataset.max(0)
    ranges = maxvals-minvals
    normdataset = np.zeros(np.shape(dataset))
    m = normdataset.shape[0]
    a = normdataset
    a = np.tile(minvals, (m,1))
    normdataset = dataset-a
    normdataset = normdataset/np.tile(ranges,(m,1))
    return normdataset

# 把图像转化成向量的形式
def img2vector(filename):
    returnvect = np.zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        linestr = fr.readline() # readline()表示从首行开始，每次读取一行
        for j in range(32):
            returnvect[0,32*i+j] = int(linestr[j]) #int()函数用于将一个字符串或数字转换成整型
    return returnvect   # 一张图片转化成一行后的数组

# 手写数字识别系统的测试代码
def handwritingclasstest():
    hwlabels = []
    trainingfilelist = listdir('e:/workspace/digits/trainingdigits')
    m=len(trainingfilelist)
    trainingmat = np.zeros((m,1024))
    for i in range(m):
        filenamestr = trainingfilelist[i]  # 例如9_45.txt
        filestr = filenamestr.split('.')[0]  # split('.')通过.分隔符对字符串进行切片
        classnumstr = int(filestr.split('_')[0]) # split('_')通过_分隔符对字符串进行切片
        hwlabels.append(classnumstr)
        trainingmat[i,:] =img2vector('e:/workspace/digits/trainingdigits/%s' % filenamestr)
    testfilelist = listdir('e:/workspace/digits/testdigits')
    mtest = len(testfilelist)
    errorcount = 0
    for i in range(mtest):
        filenamestr = testfilelist[i]
        filestr = filenamestr.split('.')[0]
        classnumstr = int(filestr.split('_')[0])
        vectorundertest = img2vector('e:/workspace/digits/testdigits/%s' % filenamestr)
        classresult = classify0(vectorundertest,trainingmat,hwlabels,3)
        print('the classifier came back with: %d, the real answer is: %d' % (classresult,classnumstr))
        if (classresult != classnumstr):
            errorcount += 1.0
    print('\n the total number of errors is: %d' % (errorcount))
    print('\n the total error rate is: %f' % (errorcount/float(mtest)))

handwritingclasstest()