2020-10-21

一个简单的KNN算法，数据已上传

数据文件：https://download.csdn.net/download/weixin_39731450/12998036

代码：

import csv
import random
with open('prostate-cancer\Prostate_Cancer.csv', 'r')as file:
	read = csv.DictReader(file)
	datas = [row for row in read]
# 数据随机打乱
random.shuffle(datas)
#	分出测试数据
n = len(datas)//3
test_set = datas[0:n]
train_set = datas[n:]
# 距离
def distanse(d1, d2):
	res = 0
	for key in ("radius", "texture", "perimeter",	"area",	"smoothness", "compactness", "symmetry", "fractal_dimension"):
		res += (float(d1[key])-float(d2[key]))**2
	return res**0.5
# KNN
k = 5 # k个离得最近的
def KNN(data):
# 距离
	res = [
		{"result": train['diagnosis_result'], "distance": distanse(data,  train)}
		for train in trai