机器学习实战_KNN

# -*- encoding:utf-8 -*-

'''
KNN 计算过程
1.对计算一致类别数据集中的点与当前点的距离
2.安装距离递增顺序排序
3.选取与当前点距离最小的k个点
4.确定k个点所在类别出现的概率
5.返回前k个点出现频率最高的类别作为当前点的预测分类
'''


from numpy import *
import operator
from os import listdir
import matplotlib.pyplot as plt
import matplotlib
def classify0(inX, dataSet, labels, k):
    # 4
    dataSetSize = dataSet.shape[0]
    # numpy.tile(A,B)函数:
    # 重复A，B次，这里的B可以时int类型也可以是元组类型。

    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    # 正数 --> 负数
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(iter(list(classCount.items())), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

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

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

def autoNorm(dataSet):
    '''
    newValue=(oldValue-min)/(max-min)
    min为最小值
    max为最大值
    :param dataSet:
    :return:
    '''
    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))
    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('data/datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        print(("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i])))
        if (classifierResult != datingLabels[i]): errorCount += 1.0
    print(("the total error rate is: %f" % (errorCount/float(numTestVecs))))
    print (errorCount)

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

def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print(("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)))
        if (classifierResult != classNumStr): errorCount += 1.0
    print(("\nthe total number of errors is: %d" % errorCount))
    print(("\nthe total error rate is: %f" % (errorCount/float(mTest))))

if __name__=='__main__':
    # value,labels=createDataSet()
    # print((classify0([0,0], value,labels,3)))

    datingDataMat,datingLabel=file2matrix('data/datingTestSet2.txt')
    norMat,ranges,minVals=autoNorm(datingDataMat)
    print(norMat)

    fig=plt.figure()
    ax=fig.add_subplot(111)
    ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
    plt.show()

    datingClassTest()

    handwritingClassTest()