k-近邻算法(kNN)小结
kNN简介
kNN算法是做分类问题的。思想如下：
KNN算法的思想总结一下：就是在训练集中数据和标签已知的情况下，输入测试数据，将测试数据的特征与训练集中对应的特征进行相互比较，找到训练集中与之最为相似的前K个数据，则该测试数据对应的类别就是K个数据中出现次数最多的那个分类，其算法的描述为：
- 计算测试数据与各个训练数据之间的距离；
- 按照距离的递增关系进行排序；
- 选取距离最小的K个点；
- 确定前K个点所在类别的出现频率；
- 返回前K个点中出现频率最高的类别作为测试数据的预测分类。
运用实例：
1. 使用k-近邻算法改进约会网站的配对效果。
2.手写数字识别系统的运用。(二维数据(m,n)特征转换为一维特征(1,m*n))
3.使用k-近邻算法分类爱情片和动作片。
'''
Created on Sep 16, 2010
kNN: k Nearest Neighbors
Input: inX: vector to compare to existing dataset (1xN)
dataSet: size m data set of known vectors (NxM)
labels: data set labels (1xM vector)
k: number of neighbors to use for comparison (should be an odd number)
Output: the most popular class label
@author: pbharrin
'''
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
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 file2matrix(filename):
love_dictionary={'largeDoses':3, 'smallDoses':2, 'didntLike':1}
fr = open(filename)
arrayOLines = fr.readlines()
numberOfLines = len(arrayOLines) #get the number of lines in the file
returnMat = zeros((numberOfLines,3)) #prepare matrix to return
classLabelVector = [] #prepare labels return
index = 0
for line in arrayOLines:
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:3]
if(listFromLine[-1].isdigit()):
classLabelVector.append(int(listFromLine[-1]))
else:
classLabelVector.append(love_dictionary.get(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
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
def datingClassTest():
hoRatio = 0.10 #hold out 10%
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') #load data setfrom file
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))
print errorCount
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(raw_input(\
"percentage of time spent playing video games?"))
ffMiles = float(raw_input("frequent flier miles earned per year?"))
iceCream = float(raw_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: %s" % resultList[classifierResult - 1]
def img2vector(filename):
returnVect = 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
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits') #load the training set
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits') #iterate through the test set
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
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))
