机器学习实战第二章----KNN

from numpy import *
from os import listdir
import operator


def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘]
    return group, labels


# 对数据进行分类
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]          #shape[0]获取第一维的数目
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet       # tile??????
    sqDiffMat = diffMat**2
    # 求差的平方和
    sqDistance = sqDiffMat.sum(axis=1)        #axis=1？？？？？？？sum函数默认是axis=0列元素相加,axis=1是一行的元素求和
    #  求标准差
    distances = sqDistance**0.5
    # 距离排序
    sortDistIndicies = distances.argsort()    #argsort函数返回的是数组值从小到大的索引值
    # 定义元字典
    classCount = {}
    for i in range(k):
        # 获得前k个元素的标签
        voteIlabel = labels[sortDistIndicies[i]]
        # 计算前k个数据标签出现的次数
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1           #dict.get()???????????
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


# 读取文本文件数据
def file2matrix(filename):
    fr = open(filename)
    lines = fr.readlines()
    num_lines = len(lines)
    train_matrix = zeros((num_lines, 3))
    label_vector = []
    index = 0
    for line in lines:
        line = line.strip()
        line_list = line.split(‘\t‘)
        train_matrix[index, :] = line_list[0:3]        # 获取列表的前0,1,2列
        label_vector.append(int(line_list[-1]))       # 获取列表的最后一列
        index += 1
    return train_matrix, label_vector                 # add_subplot????????????????


#归一化函数
def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    # normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m, 1))      # minVals在列上重复一次（本身），在行上重复m次，从而形成m*3的向量
    normDataSet = normDataSet/tile(ranges, (m, 1))
    return normDataSet, ranges, minVals       # 归一化后的数据， 极差范围， 最小值


# 分类器测试函数
def datingClassTest():
    hoRatio = 0.10      #测试集比例
    datingDataMat, datingLabels = file2matrix(‘datingTestSet2.txt‘)
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errcount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 2)
        print("the classifier came back with :%d ,the real answer is :%d" % (classifierResult, datingLabels[i]))
        if(classifierResult != datingLabels[i]):
            errcount += 1.0
        print("the total error rate is: %f" %(errcount/float(numTestVecs)))


# 手写字符文件转换成向量
def img2vector(filename):
    returnVect = zeros((1, 1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0, 32*i+j] = int(lineStr[j])
    return returnVect


# 手写字符识别测试
def handwritingClassTest():
    hwlabels = []           # 定义手写字符标签
    trainingFileList = listdir(‘digits/trainingDigits‘)
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split(‘.‘)[0]
        classNumStr = fileStr.split(‘_‘)[0]
        hwlabels.append(classNumStr)
        # 把文件变成向量并赋值到trainingMat
        trainingMat[i, :] = img2vector(‘digits/trainingDigits/%s‘ % fileNameStr)
    testFileList = listdir(‘digits/testDigits‘)
    errcount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split(‘.‘)[0]
        classNumStr = int(fileStr.split(‘_‘)[0])
        vectorUnderTest = img2vector(‘digits/testDigits/%s‘ % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwlabels, 3)
        print(‘the classifier came back with : %d, the real answer is %d‘ % (int(classifierResult), classNumStr))
        if(int(classifierResult) != int(classNumStr)):
            errcount += 1
    print(‘\nthe total number of errors is %d‘ % errcount)
    print(‘\nthe total error rate is: %f‘ % float(errcount/mTest))