import numpy as np
import operator
from os import listdir

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

group,labels = createDataSet()

def classify0(inX, dataSet, labels, k):  #用于分类的输入向量,训练样本集,标签向量,选择最近邻居的数目
    dataSetSize = dataSet.shape[0]  #读取矩阵第一维度的长度(行数)
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet #tile()把数组沿各个方向复制
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)  #对每一行进行求和
    distances = sqDistances**0.5         #求出距离
    sortedDistIndicies = distances.argsort()  #按数值从小到大排序的索引
    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]

classify0([0,0],group,labels,3)   # B

def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)  #文件行数
    returnMat = np.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
    
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')    

import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],
           15.0*np.array(datingLabels), 15.0*np.array(datingLabels))
plt.show()

def autoNorm(dataSet):      #将数字特征值转化为0到1的区间
    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))
    return normDataSet, ranges, minVals

normMat, ranges, minVals = autoNorm(datingDataMat)

def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)  #归一化数值
    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)))
    
datingClassTest()

def classifyPerson():
    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 = np.array([ffMiles,percentTats, iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person: ",
          resultList[classifierResult - 1])


classifyPerson()

def img2vector(filename):
    returnVect = np.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

testVector = img2vector('./testDigits/0_13.txt')
print(testVector[0,0:31])
print(testVector[0,32:63])

def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #获取训练集目录的文件名
    m = len(trainingFileList)
    trainingMat = np.zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #获得文件名
        classNumStr = int(fileStr.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]
        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)))

handwritingClassTest()