使用k-means(KNN)算法改进约会网站和手写字系统案例

直接上代码：

一：约会

from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

# 距离计算
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    # 求幂次方
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    # 求开方
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    # 选择距离最近的k个点
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    # 对结果排序
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createDataSet():
    # 初始化
    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)
    arrayOLines = fr.readlines()
    numberOLines = len(arrayOLines)
    returnMat = zeros((numberOLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        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):
    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))
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.10
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    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)))

'''
# 测试
group,labels =createDataSet()
result = classify0([0,0],group,labels,3)
print(result)
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()
'''
if __name__ == '__main__':
    datingClassTest()

改进：

from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

# 距离计算
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    # 求幂次方
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    # 求开方
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    # 选择距离最近的k个点
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    # 对结果排序
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createDataSet():
    # 初始化
    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)
    arrayOLines = fr.readlines()
    numberOLines = len(arrayOLines)
    returnMat = zeros((numberOLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        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):
    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))
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.05
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    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)))

def classifyPerson():
    resultList = ['not at all', 'in samall doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("feequent flier miles earned per year?"))
    iceCreqm = float(input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    intArr = array([ffMiles, percentTats, iceCreqm])
    classifierResult = classify0((intArr - minVals)/ranges, normMat, datingLabels, 3)
    print("You will probably like this person:", resultList[classifierResult - 1])

'''
# 测试
group,labels =createDataSet()
result = classify0([0,0],group,labels,3)
print(result)
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()
'''
if __name__ == '__main__':
    'datingClassTest()'
    classifyPerson()

二：手写字识别系统

from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

# 距离计算
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    # 求幂次方
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    # 求开方
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    classCount={}
    # 选择距离最近的k个点
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    # 对结果排序
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createDataSet():
    # 初始化
    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)
    arrayOLines = fr.readlines()
    numberOLines = len(arrayOLines)
    returnMat = zeros((numberOLines, 3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        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):
    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))
    return normDataSet, ranges, minVals

def datingClassTest():
    hoRatio = 0.05
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    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)))

def classifyPerson():
    resultList = ['not at all', 'in samall doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("feequent flier miles earned per year?"))
    iceCreqm = float(input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    intArr = array([ffMiles, percentTats, iceCreqm])
    classifierResult = classify0((intArr - minVals)/ranges, normMat, datingLabels, 3)
    print("You will probably like this person:", resultList[classifierResult - 1])

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')
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('trainingDigits/%s' %fileNameStr)
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        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("the total number of error is : %d" %errorCount)
        print("the total error rate is : %f" %(errorCount/float(mTest)))

'''
# 测试
group,labels =createDataSet()
result = classify0([0,0],group,labels,3)
print(result)
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()
'''
if __name__ == '__main__':
    'datingClassTest()'
    'classifyPerson()'
    handwritingClassTest()