机器学习基础KNN分类算法

咸鱼跟书学机器学习ing（0.0）然后数据包可以去https://www.manning.com/books/machine-learning-in-action下

#-*-coding:UTF-8-*-

import operator  #运算符模块
from numpy import *  #科学计算包
import matplotlib  #绘图库
import matplotlib.pyplot as plt
from os import listdir      #列出给定目录的文件名


#创造训练集
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


#将文本记录转成numpy的解析函数
def file2matrix(filename):
    #得到文件行数
    fr = open(filename)
    array0Lines = fr.readlines()
    numberOfLines = len(array0Lines)
    #创建返回的numpy矩阵
    returnMat = zeros((numberOfLines, 3))  #选取前三个元素作为特征值
    classLabelVector = []
    index = 0
    for line in array0Lines:
        line = line.strip()  #默认去掉line前面的空格和回车
        listFromLine = line.split('\t')  #将line按照制表符分割开
        returnMat[index, :] = listFromLine[0:3]
        #选取最后一列元素存储，必须int否则会当做字符串
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector


#绘图，使用矩阵的第二列和第三列数据绘制散点图
def show(DataMat, DataLabels):
    fig = plt.figure()
    ax = fig.add_subplot(111)
    #利用分类标记个性化标记散点图上的点
    ax.scatter(DataMat[:, 1], DataMat[:, 0], 15.0 * array(DataLabels),
               15.0 * array(DataLabels))
    plt.show()


#归一化特征值，即将各个特征值化成等权重(都化为[0,1]的值)
def autoNorm(dataSet):
    minVals = dataSet.min(0)  #选取每列最小值
    maxVals = dataSet.max(0)  #选取每列最大值
    ranges = maxVals - minVals  #可能的取值范围
    normDataSet = zeros(shape(dataSet))  #新的返回矩阵
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m, 1))
    normDataSet = normDataSet / tile(ranges, (m, 1))  #特征值相除
    return normDataSet, ranges, minVals


#分类
def classify0(inX, dataSet, labels, k):
    #计算欧式距离 d=sqrt((x1-x2)^2+(y1-y2)^2)
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet  #将inX重复shape行，1列
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)  #axis=0表示列求和，axis=1表示行求和
    distances = sqDistances**0.5

    #选取距离最小的k个点
    sortedDistIndicies = distances.argsort()  #排序索引
    classCount = {}  #建立字典存储每个类的数目
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    #排序(逆序)
    # key=operator.itemgetter(1)函数表示选取对象第一个域的值进行排序
    sortedClassCount = sorted(
        classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


#分类器验证函数
def datingClassTest():
    hoRatio = 0.10  #选取抽样数据的比例
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat = autoNorm(datingDataMat)[0]
    m = normMat.shape[0]
    numTestVecs = int(m * hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        #本来应该随机选取数据，但是这里的数据本身是随机的所以直接选取
        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
    if numTestVecs != 0:  #考虑到numTestVecs==0时不能除
        print("the total error rate is: %f" %
              (errorCount / float(numTestVecs)))


#输入数据预测函数
def classifyPerson():
    #类别
    resultList = ["not at all", "in small doses", "in large doses"]

    percentTats = float(input("Percentage of time spent playing video games?"))
    ffMiles = float(input("Frequent flier miles earned per year?"))
    iceCream = float(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])


#将32*32的二进制图像矩阵转化成1*1024的向量
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

#手写数字识别
def handwritingClassTest():
    hwLabels = []
    trainingFileList = os.listdir('trainingDigits')  #获取目录内容
    m = len(trainingFileList)
    trainingMat = zeros((m, 1024))
    for i in range(m):  #从文件名解析分类数字
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = os.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('\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')
show(autoNorm(datingDataMat)[0], datingLabels)

datingClassTest()

classifyPerson()
'''

还有还有，学着python现在敲代码都不爱打分号了0.0