kNN算法改进约会网站的配对效果

最新推荐文章于 2023-05-23 15:34:09 发布

Unin88

最新推荐文章于 2023-05-23 15:34:09 发布

阅读量1k

点赞数

本文链接：https://blog.youkuaiyun.com/Unin88/article/details/50524198

版权

#coding = utf-8
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt

def createDataset():
	group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]) #生成一个数组
	labels = ['A', 'A', 'B', 'B']#标签向量
	return group, labels

def classify0(inX, dataSet, labels, k): #分别为待分类向量，数据集，标签向量，k
	dataSetSize = dataSet.shape[0] #计算数据集行数
	diffMat = tile(inX, (dataSetSize, 1)) - dataSet
	sqDiffMat = diffMat ** 2
	sqDistances = sqDiffMat.sum(axis = 1)
	distances = sqDistances ** 0.5 #计算待分类向量和数据集每个向量的距离
	sortedDistIndicies = distances.argsort() #排序且返回的是升序元素的索引
	classCount = {} #创建空字典
	for i in range(k):
		voteIlabel = labels[sortedDistIndicies[i]]
		classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 #记录不同类别的分别有几个
	sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True) #按照键值对的