from numpy import *
import operator

# 示列：在约会网站上使用k-近邻算法
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

def classify0(inX, dataSet, labels, k):
    '''K-近邻算法'''
    dataSetSize = dataSet.shape[0]
    sortedDistIndicies = ((((tile(inX,(dataSetSize, 1))-dataSet)**2).sum(axis=1))**0.5).argsort()
    classCount = { }
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
        sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
        return sortedClassCount[0][0]

def file2matrix(filename):
    '''将文本记录转化为NumPy的解析程序'''
    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

def autoNorm(dataSet):
    '''归一化特征值'''
    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():
    '''分类器针对约会网站的测试代码'''
    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)))


def classifyPerson():
    '''约会网站预测函数'''
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("frequent of ice cream consumed 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])

# 示列：手写识别系统
from os import listdir
def img2vector(filename):
    '''准备数据：将图像转换为测试向量'''
    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():
    '''手写数字识别系统的测试代码'''
    hwLabels = []

    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        classNumStr = int(fileNameStr.split('.')[0].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]
        classNumStr = int(fileNameStr.split('.')[0].split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s'%fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came back with: %d, the real number 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)))