机器学习各个算法5---KNN

实施kNN算法

相关函数

from numpy import *
import operator   #本模块主要包括一些Python内部操作符对应的函数
import matplotlib
import matplotlib.pyplot as plt
from os import listdir
# import py_compile
# py_compile.compile('MLIAkNN.py')   #Python 中的pyc文件的用途---http://blog.csdn.net/yu132563/article/details/40922049
#http://blog.csdn.net/carolzhang8406/article/details/6342174

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

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]#shape函数可以查看矩阵或者数组的维数，[0]为行数，即样本数
    diffMat = tile(inX, (dataSetSize,1))-dataSet #tile为重复inX，按照后面元组的数
    sqDiffMat = diffMat**2  #矩阵的各个元素求平方
    sqDistance = sqDiffMat.sum(axis=1) #axis=1表示针对某一行求和（把所有列加起来）
    distance = sqDistance**0.5 #对每一个元素开平方
    sortedDistIndicies = distance.argsort()#argsort函数返回的是数组值从小到大的索引值
    classCount={} #Map
    for i in range(k):  #取前k个
        votelabel = labels[sortedDistIndicies[i]]  #局部变量
        classCount[votelabel] = classCount.get(votelabel,0)+1
        # get() 函数返回指定键的值，如果值不在字典中返回默认值,此处默认值为0
    sortedClassCount = sorted(classCount.iteritems(),key=operator.itemgetter(1)
                              ,reverse=True)
    #sorted返回一个重新排序的Map
    #reverse=True表示倒序，从大到小；classCount.iteritems()迭代器，
    #operator模块提供的itemgetter函数用于获取对象的哪些维的数据，此处为第1维，即按照
    #第二个元素的值对元组进行排序，此处即标签累加个数
    #sortedClassCount还是一个Map
    return sortedClassCount[0][0]  #返回最大一个的key

测试代码

import MLIAkNN
group, labels = MLIAkNN.createDataSet()
print group
print labels

print MLIAkNN.classify0([0,0],group,labels,3)

结果

[[ 1.   1.1]
 [ 1.   1. ]
 [ 0.   0. ]
 [ 0.   0.1]]
['A', 'A', 'B', 'B']
B

约会数据可视化

相关函数

#读取及解析文本文件,返回训练样本矩阵和类标签向量
def file2matrix(filename):
    fr = open(filename)
    arrayLines = fr.readlines()#readlines() 方法用于读取所有行(直到结束符 EOF)并返回列表
    numberLine = len(arrayLines)
    returnMat = zeros((numberLine,3)) #3维特征  返回来一个给定形状和类型的用0填充的数组,
    #returnMat元素在这里已经有数据类型了
    #(numberLine,3)为元组，shape
    classLabelVector = []  #列表
    index = 0
    for line in arrayLines:
        line = line.strip()  #strip()同时去掉左右两边的空格
        listFromLine = line.split('\t')#根据制表符进行分割
        returnMat[index,:] = listFromLine[0:3]  #注意这里不包括3
        classLabelVector.append(int(listFromLine[-1])) #-1表示最后一个元素
        index +=1
    return returnMat, classLabelVector

测试代码

#图像化观察
fig = plt.figure()
ax = fig.add_subplot(111)  #111表示1行1列第一个
ax.scatter(datingDataMat[:,1],datingDataMat[:,2], 15.0*array(map(int,datingLabels)), 
           15.0*array(map(int,datingLabels)))  #第2，3列数据
plt.show()

结果

实际测试

相关函数

#归一化处理
def autoNorm(dataSet):
    minVals = dataSet.min(0)  #这里的0表示针对每一列，取所有行的最小值,minVals是数组
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))#矩阵有一个shape属性，是一个(行，列)形式的元组
    m = dataSet.shape[0]  #行数
    normDataSet = dataSet - tile(minVals, (m,1))  #原来是一个行向量，现在复制m行
    normDataSet = normDataSet/tile(ranges, (m,1))  #没问题   /特征值相除
    return normDataSet, ranges, minVals

# normMat, ranges, minVals = autoNorm(datingDataMat)
# print normMat
# print ranges
# print minVals
    
#测试算法函数，90%作为训练集，10%作为测试集
def datingClassTest():
    hoRatio = 0.10      #hold out 10%
    datingDataMat,datingLabels = file2matrix('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

测试代码

#数据标准化处理
normMat, ranges, minVals =  MLIAkNN.autoNorm(datingDataMat)
print normMat
print ranges
print minVals

#测试算法
MLIAkNN.datingClassTest()

结果

the classifier came back with: 1, the real answer is: 1
the classifier came back with: 2, the real answer is: 2
the classifier came back with: 1, the real answer is: 1
the classifier came back with: 3, the real answer is: 3
the classifier came back with: 3, the real answer is: 3
the classifier came back with: 2, the real answer is: 2
the classifier came back with: 1, the real answer is: 1
the classifier came back with: 3, the real answer is: 1
the total error rate is: 0.050000
5.0

具体使用分类器来进行预判 喜欢度

相关函数

#使用算法:构建完整可用系统
#Python 每行代码太长了（PEP8中建议为80个字符）会用 \来换下一行接着写，突出逻辑或者避免出现滚动条，忽略就是了。
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    percentTats =float(raw_input("percentage of time spent playing video games?")) 
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt') 
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print "you will probably like this person:", resultList[classifierResult-1]

测试代码

#具体使用
MLIAkNN.classifyPerson()

结果

frequent flier miles earned per year?10000
percentage of time spent playing video games?10
liters of ice cream consumed per year?0.5
you will probably like this person: in small doses

手写数字识别

相关函数

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))

测试代码

#手写数字识别
MLIAkNN.handwritingClassTest()

结果

he classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9
the classifier came back with: 9, the real answer is: 9


the total number of errors is: 11


the total error rate is: 0.011628