Mac 机器学习实战 k近邻算法实现过程

python3 环境下import KNN 后报错

Traceback (most recent call last):
File “”, line 1, in
ModuleNotFoundError: No module named ‘KNN’

解决：没有保存成.py 文件

kNN.py文件如下：

from numpy import*
import operator

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 classify0(inX,dataSet,labels,k):
//计算距离
	dataSetSize=dataSet.shape[0]
	diffMat=tile(inX,(dataSetSize,1))-dataSet
	sqDiffMat=diffMat**2
	sqDistances=sqDiffMat.sum(axis=1)//对每行求和 axis＝0 对列求和
	distances=sqDistances**0.5
	sortedDistIndicies=distances.argsort()
	classCount={}
	//选择距离最小的k个点
	for i in range(k):
		voteIlabel=labels[sortedDistIndicies[i]]
		classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
		//排序
	sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=True)//True按降序排列  默认升序
	return sortedClassCount[0][0]

改进约会网站实例

def file2matrix(filename):
    fr = open(filename)
    numberOfLines = len(fr.readlines())         
    returnMat = zeros((numberOfLines,3))        #创造任意维度数组 默认浮点型
    classLabelVector = []                      
    fr = open(filename)
    index = 0
    for line in fr.readlines():
        line = line.strip()					#去掉所有回车符
        listFromLine = line.split('\t')   #将整行数据划分成列表
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector