首先感謝https://blog.csdn.net/u012162613/article/details/41768407的分享!
所謂KNN就是對那個你要預測的點,找出其k個鄰居,也就是距離他最近的k個點,這k個樣本中出現頻率最高的類別即作爲測試樣本的類別。
那麼,這個距離一般用什麼來計算呢?
一般有歐式距離、標準化歐式距離、馬氏距離、餘弦距離。
這裏我們採用歐式距離:
即N維歐氏空間中兩點x1,x2之間的距離:
下面採用knn來對手寫數字識別進行處理,在此之前先分析一下knn的優缺點。
優點:
算法簡單,易於實現,不需要參數估計,不需要事先訓練。
缺點:
計算量特別大,而且訓練樣本必須存儲在本地,內存開銷也特別大(數據量稍微大一點就不適合我這種lowb單機的玩家T^T)
K:取值一般不大於20
'''
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 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')
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits')
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]
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))