kNN Code

• kNN是一种聚类算法，python的代码分类器函数思路
  即读取的数据为一个inX=[x,y,z]
  inX的第一列向量重复成inX的同型矩阵（利用tile）[[x,y,z],[x,y,z]......]
  作差
  平方后每个行相加，再开根号，欧氏距离
  这样就算出了inX与数据集中点的各个距离
  排序
  取最小的前k个
  然后计算标签频率
  最后确定这个inX的label
  物以类聚，人以群分

• KNN.py

from numpy import *
import operator

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):  #inX用于分类的输入向量，dataSet训练样本集，labels标签向量，k为选择最近邻居的数目
    dataSetSize = dataSet.shape[0] #得到矩阵的长
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet#tile重复inX，有dataSetSize个行，减去计算差值输入的数据的矩阵，也就是散布
    sqDiffMat = diffMat**2 #方差
    sqDistances = sqDiffMat.sum(axis = 1)   #[[],[],[],[]]中每个[]里的加起来变成一个值
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort() #返回数值从小到大的索引值
    classCount = {} #字典类型
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]] #根据排序结果的索引值返回靠近的前k个标签,这个在数据里已经给好了
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 #计算各个标签出现的频率
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse = True)
    # python3中：classCount.iteritems()修改为classCount.items()
    # sorted(iterable, cmp=None, key=None, reverse=False) --> new sorted list。
    # reverse默认升序 key关键字排序itemgetter（1）按照第一维度排序(0,1,2,3)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines() #读的每一行就是arrayOLines
    numberOfLines = len(arrayOLines) #数据行数
    returnMat = zeros((numberOfLines,3)) #创建返回矩阵
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip() #删除空白符
        listFromLine = line.split('\t') #把这行再分割
        returnMat[index,:] = listFromLine[0:3] #选取前三个元素存储在返回矩阵中
        classLabelVector.append(int(listFromLine[-1])) #最后一个元素其实就是标签，用数组存储
        index += 1
    return returnMat,classLabelVector

def autoNorm(dataSet): #归一
    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(): #测试函数
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')#原文中的数据label是字符串之后fileread读不进去
    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(): #判别是个什么样的人
    resultList = ['not at all','in small doses','in large doses'] #最后的三种结果，就是问题的答案
    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])

• KNN_Run.py

import KNN
import matplotlib
import matplotlib.pyplot as plt
#添加下面一条，绘制不同颜色 否则出现array未定义错误
from numpy import *

datingDataMat,datingLabels = KNN.file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1], datingDataMat[:, 2], 15.0*array(datingLabels), 15.0*array(datingLabels))
#ax.scatter(datingDataMat[:,0], datingDataMat[:, 1], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show() #显示图

按2-3列
按1-2列