说明
未采用sklearn自带的knn算法（当时得分96.800%）进行建模改进大神的代码（96.400% ）提高到96.886%
代码
from numpy
import *
import operator
import csv
def toInt(array):
array=mat(array)
m,n=shape(array)
newArray=zeros((m,n))
for i
in xrange(m):
for j
in xrange(n):
newArray[i,j]=int(array[i,j])
return newArray
def loadTrainData():
l=[]
with open(
'train.csv')
as file:
lines=csv.reader(file)
for line
in lines:
l.append(line)
l.remove(l[
0])
l=array(l)
label=l[:,
0]
data=l[:,
1:]
return toInt(data),toInt(label)
def loadTestData():
l=[]
with open(
'test.csv')
as file:
lines=csv.reader(file)
for line
in lines:
l.append(line)
l.remove(l[
0])
data=array(l)
return toInt(data)
def classify(inX, dataSet, labels, k):
inX=mat(inX)
dataSet=mat(dataSet)
labels=mat(labels)
dataSetSize = dataSet.shape[
0]
diffMat = tile(inX, (dataSetSize,
1)) - dataSet
sqDiffMat = array(diffMat)**
2
sqDistances = sqDiffMat.sum(axis=
1)
distances = sqDistances**
0.5
sortedDistIndicies = distances.argsort()
classCount={}
for i
in range(k):
voteIlabel = labels[sortedDistIndicies[i],
0]
classCount[voteIlabel] = classCount.get(voteIlabel,
0) +
1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(
1), reverse=
True)
return sortedClassCount[
0][
0]
def saveResult(result):
with open(
'result.csv',
'wb')
as myFile:
myWriter=csv.writer(myFile)
for i
in result:
tmp=[]
tmp.append(i)
myWriter.writerow(tmp)
def handwritingClassTest():
trainData,trainLabel=loadTrainData()
testData=loadTestData()
m,n=shape(testData)
resultList=[]
for i
in range(m):
classifierResult = classify(testData[i], trainData, trainLabel.transpose(),
5)
resultList.append(classifierResult)
saveResult(resultList)
handwritingClassTest()
7月12日
源代码未变，将k值设置为3，准确率提高到了96.929%
