KNN算法初学

import csv
import random
with open('Prostate_Cancer.csv','r') as file:
    reader=csv.DictReader(file)
    datas=[row for row in reader]
    
random.shuffle(datas)
n=len(datas)//3

test_set=datas[0:n]
train_set=datas[n:]

def distance(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

k=5
def knn(data):
    res=[
     {"result":train['diagnosis_result'],"distance":distance(data,train)}
     for train in train_set
    ]
    
    res=sorted(res,key=lambda item:item['distance'])
    
    res2=res[0:k]
    
    result={'B':0,'M':0}
    sum=0
    for r in res2:
        sum+=r['distance']
    
    for r in res2:
        result[r['result']]+=1-r['distance']/sum
    if result['B']>result['M']:
        return 'B'
    else:
        return 'M'
correct=0
# knn(test_set[0])
for test in test_set:
    result=test['diagnosis_result']
    result2=knn(test)
    if result==result2:
        correct+=1
       
print("准确率:{:.2f}%".format(100*correct/len(test_set)))

knn算法实现对癌症的预测，代码来自b站的knn算法视频，数据集是提前准备好的。
代码最后的结果：
代码解释
random.shuffle对数据集进行洗牌操作。
for key遍历csv文件里的参数。
输出结果比对真实是否患病并输出准确率。