python机器学习实战1：实现k-近邻算法

首先分享一下链接：http://pan.baidu.com/s/1jIsS8HC 密码：rfew，
里面有kNN当中使用的数据集。这个系列的教程可能更注重机器学习的算法，没有使用深度框架，主要是从低层的一些函数进行编程。一方面可以加深对机器学习的理解，另外一方面增加python的编程能力，能够更好的学会处理自己的数据。

#coding:utf-8
#首先先导入相关的数据库，这里使用的主要是Numpy和matplotlib，里面函数的定义LZ都已经给出了，具体想要如何调用函数就看小伙伴们的需要了
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt 
import os  

#首先基本的学会创建一个数据集
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

#主要的就是这个分类器啦！kNN分类器，有四个参数，输入，训练数据，标签，k类，这主要就是计算对应的欧氏距离
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = 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.iteritems(), key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]

#在这个代码中使用的数据集是要转化成矩阵的形式，所以这个函数就是构造对应的矩阵
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, 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

#这个函数主要就是画图的啦，如果使用可以看到训练集的数据分布哦
def create_fig():
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0 * array(datingLabels), 15.0 * array(datingLabels))
    plt.show()

#对数据进行预处理，为什么要进行归一化，因为如果一个数据集是体重和身高，如果不对数据进行归一化，体重的均值在60kg,身高在1.75m，那么明显可以看出体重的权重会更大些，所以在特征权重均等的情况下，应该对原始数据进行归一化
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

#测试一下咯
def datingClassTest():
    hoRatio = 0.50
    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):
        classfierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :],\
                                    datingLabels[numTestVecs:m], 3)
        print "the classfier came back with: %d, the real answer is: %d"\
            %(classfierResult, datingLabels[i])
        if (classfierResult != datingLabels[i]): errorCount += 1.0
    print "the total error rate is %f" %(errorCount / float(numTestVecs))

#这个函数主要就是针对输入来判断到底是哪一个类别的
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    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])
    classfierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
    print "you will probably like this person: ", resultList[classfierResult - 1]

#要把图片转化成向量，怎么转化呢？
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

#定义手写数字测试的函数
def handwritingClassTest():
    hwLabels = []
    trainingFileList = os.listdir('./digits/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('./digits/trainingDigits/%s' % fileNameStr)
    testFileList = os.listdir('./digits/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('./digits/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))

# group, labels = createDataSet()
# print classify0([0, 0], group, labels, 3)
# datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
# normMat, ranges, minVals = autoNorm(datingDataMat)
# # print datingDataMat[:, 1], datingLabels
# print normMat, ranges, minVals
# create_fig()

# classifyPerson()
# testVector = img2vector('./digits/testDigits/0_13.txt')
# print testVector
handwritingClassTest()
# fr = open('./digits/testDigits/0_13.txt')

哈哈，还不错哦，我们还学会了怎么批量读取文件O(∩_∩)O