吴裕雄 python 机器学习-KNN算法（1）

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

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

data,labels = createDataSet()
print(data)
print(labels)

test = np.array([[0,0.5]])
result = classify0(test,data,labels,3)
print(result)

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    returnMat = []
    classLabelVector = []                       #prepare labels return   
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])
        classLabelVector.append(int(listFromLine[-1]))
    return np.array(returnMat),np.array(classLabelVector)

trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")
print(trainData[0:4])
print(trainLabel[0:4])

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)
print(ranges)
print(minVals)
print(normDataSet[0:4])
print(trainLabel[0:4])

testData = np.array([[0.5,0.3,0.5]])
result = classify0(testData, normDataSet, trainLabel, 5)
print(result)

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    returnMat = []
    classLabelVector = []                       #prepare labels return   
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])
        classLabelVector.append(listFromLine[-1])
    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)

def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet.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: %s, the real answer is: %s') % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]): 
            errorCount += 1.0
    print(('the total error rate is: %f') % (errorCount/float(numTestVecs)))
    print(errorCount)
    
datingClassTest()

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    returnMat = []
    classLabelVector = []                       #prepare labels return   
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])
        classLabelVector.append(listFromLine[-1])
    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

normDataSet, ranges, minVals = autoNorm(trainData)

def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet.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: %s, the real answer is: %s') % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]): 
            errorCount += 1.0
    print(('the total error rate is: %f') % (errorCount/float(numTestVecs)))
    print(errorCount)
    
datingClassTest()

................................................

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    returnMat = []
    classLabelVector = []                       #prepare labels return   
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])
        classLabelVector.append(int(listFromLine[-1]))
    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

def classifyPerson():
    resultList = ["not at all", "in samll doses", "in large doses"]
    percentTats = float(input("percentage of time spent playing video game?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))
    testData = np.array([percentTats,ffMiles,iceCream])
    trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")
    normDataSet, ranges, minVals = autoNorm(trainData)
    result = classify0((testData-minVals)/ranges, normDataSet, trainLabel, 3)
    print("You will probably like this person: ",resultList[result-1])
    
classifyPerson()

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    returnMat = []
    classLabelVector = []                       #prepare labels return   
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat.append([float(listFromLine[0]),float(listFromLine[1]),float(listFromLine[2])])
        classLabelVector.append(int(listFromLine[-1]))
    return np.array(returnMat),np.array(classLabelVector)

def autoNorm(dataSet):
    minVals = dataSet.min(0)
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals

def classifyPerson():
    resultList = ["not at all", "in samll doses", "in large doses"]
    percentTats = float(input("percentage of time spent playing video game?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))
    testData = np.array([percentTats,ffMiles,iceCream])
    trainData,trainLabel = file2matrix("D:\\LearningResource\\machinelearninginaction\\Ch02\\datingTestSet2.txt")
    normDataSet, ranges, minVals = autoNorm(trainData)
    result = classify0((testData-minVals)/ranges, normDataSet, trainLabel, 3)
    print("You will probably like this person: ",resultList[result-1])
    
classifyPerson()

import numpy as np
import operator as op
from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    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(classCount.items(), key=op.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def img2vector(filename):
    returnVect = []
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect.append(int(lineStr[j]))
    return np.array([returnVect])

def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('D:\\LearningResource\\machinelearninginaction\\Ch02\\trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = np.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('D:\\LearningResource\\machinelearninginaction\\Ch02\\trainingDigits\\%s' % fileNameStr)
    testFileList = listdir('D:\\LearningResource\\machinelearninginaction\\Ch02\\testDigits')        #iterate through the test set
    mTest = len(testFileList)
    errorCount = 0.0
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('D:\\LearningResource\\machinelearninginaction\\Ch02\\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)))
    
handwritingClassTest()

.......................................