<Python><有监督>kNN--近邻分类算法

有监督的kNN近邻算法：

（1）计算已知类别数据集中的点与当前点之间的距离

（2）按照距离递增次序排序

（3）选取与当前点距离最小的k个点

（4）确定前k个点所在类别的出现频率

（5）返回前k个点出现频率最高的类别作为当前点的预测分类

#数据样例

1 2:a

1 3:a

1 4:a

1 5:b

6 2:b

6 3:b

100 200:c

101 199:c

300 444:d

299 50:d

1000 10000:d

#版本0：纯python

"kNN"
from math import sqrt
from collections import Counter

distance=lambda a,b:sqrt(sum(map(lambda ai,bi:pow(ai-bi,2),a,b))) if len(a)==len(b) else "Error0:data length match fail"
distance2=lambda a,b:distance([int(i) for i in a.split()],[int(i) for i in b.split()])  # for strings
#print(distance2('1 2 4 7 8','2 5 5 6 110'))
readData=lambda file:{line.split(':')[0]:line.strip().split(':')[1] for line in open(file)}
#print(readData())

def judgeSpot(fileIn='test0.txt',x='1 2',num=5):
    distanceDict,data={},readData(fileIn)
    for k in data:
        distanceDict[str(distance2(x,k))]=data[k]
    # sortDistance=sorted(distanceDict.items(),key=lambda x:float(x[0]))[:num]
    # kindDict=[item[1] for item in sortDistance]
    return sorted(dict(Counter(item[1] for item in sorted(distanceDict.items(),key=lambda x:float(x[0]))[:num])).items(),key=lambda x:x[1],reverse=True)[0][0]
#print(judgeSpot('1000 10000','test0.txt'),)

def judgeSpot2(dataIn,x='1 2',num=5):
    distanceDict,data={},dataIn
    for k in data:
        distanceDict[str(distance2(x,k))]=data[k]
    # sortDistance=sorted(distanceDict.items(),key=lambda x:float(x[0]))[:num]
    # kindDict=[item[1] for item in sortDistance]
    return sorted(dict(Counter(item[1] for item in sorted(distanceDict.items(),key=lambda x:float(x[0]))[:num])).items(),key=lambda x:x[1],reverse=True)[0][0]
print(judgeSpot('test0.txt','1000 10000'),)

#Rate of Right
def rateRight(fileIn='test0.txt',num=5):
    countRight,data=0,readData(fileIn)
    for k in data:
        if judgeSpot2(data,k,num)==data[k]:
            countRight+=1
    return countRight/float(len(open(fileIn).readlines()))
print(rateRight())

#版本1：numpy版 （待实现）

搜索

复制