# -*- coding:cp936 -*-

 #===============================================================================

 # 设计KNN最近邻分类器：

 #     找出每个元素在数据集中的最近邻的K个数据，统计这K个数据所属的类，所属类最多的那个类就是该元素所属的类

 #===============================================================================

 import numpy as np

 def loadHaiLunData(f_name):

     with open(f_name) as fHandle:

         fLines = fHandle.readlines()

         dataLines = len(fLines)

         label  = []

         dataSetMat = np.zeros((dataLines,3))

         for i in range(dataLines):

             lineList = fLines[i].strip().split('\t')

             dataSetMat[i,:] = lineList[0:3]

             label.append(int(lineList[-1]))

         return dataSetMat,label

 def dataNorm(dataSet):

     numOfEle = dataSet.shape[0]

     minEle = dataSet.min(0)

     maxEle = dataSet.max(0)

     normedData = (dataSet-np.tile(minEle,(numOfEle,1)))/np.tile(maxEle-minEle,(numOfEle,1))

     return normedData

 def classifyKnn(inX, dataSet, label, k):

     #===========================================================================

     # inX：输入向量

     # dataSet:保存数据特征的数组，每一行为若干个特征的参数，与label对应

     # label：表明当前这个数据集中的每一个元素属于哪一类

     # k：设定最近邻的个数

     #===========================================================================

     #首先对数据集进行归一化

 #     dataSet = dataNorm(dataSet)

     numOfEle = dataSet.shape[0]

     index = 0

     diffDistance = dataSet - np.tile(inX, (numOfEle,1))

     diffDistance = diffDistance**2

     squareDistance = diffDistance.sum(1)

 #     squareDistance = squareDistance**0.5

     knnIndex = squareDistance.argsort()

     #统计最近的k个近邻的label，看哪个label类别最多就可将该训练元素判为对应类

     staticDict = {}

     for i in range(k):

         staticDict[label[knnIndex[i]]]=staticDict.get(label[knnIndex[i]],0)+1

     itemList = staticDict.items()

     argmax = np.argmax(itemList, axis = 0)

     return itemList[argmax[1]][0]

 def testHaiLunClassify(k = 3, hRatio = 0.5):

     dataSet,label = loadHaiLunData('datingTestSet2.txt')

 #     hRatio = 0.5

     totalNum = dataSet.shape[0]

     testNum = int(totalNum*hRatio)

     dataNormed = dataNorm(dataSet)

     errorClass = 0

     for i in range(testNum):

         classRes = classifyKnn(dataNormed[i,:], dataNormed[testNum:,:], label[testNum:], k)

         if classRes != label[i]:

             errorClass += 1

 #             print "classify error, No. %d should be label %d but got %d"%(i, label[i],classRes)

     errorRate = errorClass/float(testNum)

 #     print

 #     print "Error rate: %f"%(errorRate)

     return errorRate

 if __name__ == '__main__':

     errorList = []

     kRange = range(1,50,1)

     for k in kRange:

         errorList.append(testHaiLunClassify(k))

     print errorList

     import matplotlib.pyplot as  plt

     fig = plt.figure(1)

 #     ax  = fig.add_subplot(111)

     plt.plot(kRange, errorList,'rs-')

     plt.show()