#-*- coding: utf-8 -*-
__author__ = 'Rossie'
from numpy import *
import operator

'''構(gòu)造數(shù)據(jù)'''
def createDataSet():
  characters=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
  labels=['A','A','B','B']
  return characters,labels

'''從文件中讀取數(shù)據(jù)，將文本記錄轉(zhuǎn)換為矩陣，提取其中特征和類標(biāo)'''
def file2matrix(filename):
  fr=open(filename)
  arrayOLines=fr.readlines()
  numberOfLines=len(arrayOLines)    #得到文件行數(shù)
  returnMat=zeros((numberOfLines,3))   #創(chuàng)建以零填充的numberOfLines*3的NumPy矩陣
  classLabelVector=[]
  index=0
  for line in arrayOLines:       #解析文件數(shù)據(jù)到列表
    line=line.strip()
    listFromLine=line.split('\t')
    returnMat[index, :]=listFromLine[0:3]
    classLabelVector.append(listFromLine[-1])
    index+=1
  return returnMat,classLabelVector   #返回特征矩陣和類標(biāo)集合

'''歸一化數(shù)字特征值到0-1范圍'''
'''輸入為特征值矩陣'''
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
  
def classify(sample,dataSet,labels,k):
  dataSetSize=dataSet.shape[0]   #數(shù)據(jù)集行數(shù)即數(shù)據(jù)集記錄數(shù)
  '''距離計算'''
  diffMat=tile(sample,(dataSetSize,1))-dataSet     #樣本與原先所有樣本的差值矩陣
  sqDiffMat=diffMat**2   #差值矩陣平方
  sqDistances=sqDiffMat.sum(axis=1)    #計算每一行上元素的和
  distances=sqDistances**0.5  #開方
  sortedDistIndicies=distances.argsort()   #按distances中元素進行升序排序后得到的對應(yīng)下標(biāo)的列表
  '''選擇距離最小的k個點'''
  classCount={}
  for i in range(k):
    voteIlabel=labels[sortedDistIndicies[i]]
    classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
  '''從大到小排序'''
  sortedClassCount=sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
  return sortedClassCount[0][0]

'''針對約會網(wǎng)站數(shù)據(jù)的測試代碼'''
def datingClassTest():
  hoRatio=0.20     #測試樣例數(shù)據(jù)比例
  datingDataMat,datingLabels=file2matrix('datingTestSet1.txt')
  normMat, ranges, minVals=autoNorm(datingDataMat)
  m =normMat.shape[0]
  numTestVecs=int(m*hoRatio)
  errorCount=0.0
  k=4
  for i in range(numTestVecs):
    classifierResult=classify(normMat[i, : ],normMat[numTestVecs:m, : ],datingLabels[numTestVecs:m],k)
    print("The classifier came back with: %s, thereal answer is: %s" %(classifierResult, datingLabels[i]))
    if(classifierResult!= datingLabels [i] ) :
      errorCount += 1.0
  print("the total error rate is: %f" % (errorCount/float(numTestVecs)))

def main():
  sample=[0,0]#簡單樣本測試
  sampleText = [39948,6.830795,1.213342]#文本中向量樣本測試
  k=3
  group,labels=createDataSet()
  label1=classify(sample,group,labels,k)#簡單樣本的分類結(jié)果
  fileN = "datingTestSet.txt"
  matrix,label = file2matrix(fileN)
  label2 =classify(sampleText,matrix,label,k)#文本樣本的分類結(jié)果
  print("ClassifiedLabel of the simple sample:"+label1)
  print("Classified Label of the textsample:"+label2)



if __name__=='__main__':
  main()
  #datingClassTest()