Python学习历程

来源：互联网发布：bcd编码c语言编辑：程序博客网时间：2024/05/22 15:11

在简单实现KNN算法的时候遇到的问题

1、numpy.mat 与numpy.array

2、numpy.tile([a,b],(x,y)) 将[a,b] 在行上复制x次，在列上复制y次，如tile([1,1],(2,3)) = [ [2,3],[2,3]

[2,3],[2,3]

[2,3],[2,3] ]

3、python 自带的sorted()函数参数设置

4、KNN简单代码实现及注释：

import numpyimport operatorgroup = numpy.array([[1.0,1.1],[1.0,1.0],[0.0,0.0],[0.0,0.1]])labels = ['A','A','B','B']print(group)print(labels)def classfy0(inx,dataset,labels,k):    datasetsize = dataset.shape[0] #列数    diffMat = numpy.tile(inx,(datasetsize , 1))- dataset    #print(diffMat)    sqDiffmat = diffMat**2    #print(sqDiffmat)    sqDistance = sqDiffmat.sum(axis=1)#每一行的项都相加生成一行    #print(sqDistance)    distance = numpy.sqrt(sqDistance)#距离    sortedDistance = distance.argsort()    #print(sortedDistance)    classCount = {}    for i in range(k):        voteIlable = labels[sortedDistance[i]]#将labels中对应的特征设置到voteIable中        #print(voteIlable)        classCount[voteIlable] = classCount.get(voteIlable,0)+1        #print(classCount)    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)    return sortedClassCount[0][0]print("predict:%s" % classfy0([0,0.2],group,labels,3))

阅读全文

0 0