knn算法学习笔记

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import numpy as np
from numpy import *
import operator


#添加测试数据
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


# print createDataSet()
group,labels =  createDataSet()
# print group
# print "----------"
# print labels




def knn_classify(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]  #只想读取 dataSet 第一维度长度，使用shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet #将 inX 扩展为 4 行，组成一个4行两列的矩阵，与数据集每行做减
    sqDiffMat = diffMat**2 #计算出来上述每个差每个特征距离的平方
    sqDistances = sqDiffMat.sum(axis=1) #计算出每个点与点每个特征下的距离之平方和
    distances = sqDistances**0.5 #由平方和计算出来两点间的欧氏距离
    sortedDistIndicies = distances.argsort() #返回排序后元素在原对象中的下标
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]] # 取回在labels标签集中相应位置的标签
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1  # 计算某个类别标签出现的次数，其中get方法表示有
        # voteIlabel这个标签出现就在原来的基础上加1，没有就返回一个0值
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) #operator.itemgetter函数
    # 获取的不是值，而是定义了一个函数，通过该函数作用到对象上才能获取值。operator.itemgetter的形式通过classCount的第一个域排序
    return sortedClassCount[0][0]


# print knn_classify([8,0],group,labels,3)


def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector


# subdataSet,
dataSet,dataLabels = file2matrix('datingTestSet2.txt')
# print dataSet,dataLabels




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))   #element wise divide
    return normDataSet, ranges, minVals


# normMat,ranges,minvals = autoNorm(dataSet)


# print normMat
# print ranges
# print minvals




# hoRatio = 0.2      #hold out 10%
# datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
# print datingDataMat
# print datingLabels
# normMat, ranges, minVals = autoNorm(datingDataMat)
# m = normMat.shape[0]
# numTestVecs = int(m*hoRatio)
# errorCount = 0.0
# for i in range(numTestVecs):
#     classifierResult = knn_classify(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))
# print errorCount


# print datingClassTest()


resultlist = ['not at all','in small doses','in large doses']
percentTats = float(raw_input("times play video games ?:" ))
miles = float(raw_input("frequent per year ?:" ))
creame = float(raw_input("ice creame per year ?:" ))
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([miles,percentTats,creame])
classifierResult = knn_classify((inArr-minVals)/ranges,normMat,datingLabels,3)

print resultlist[classifierResult-1]

代码和数据来源 《机器学习实战》