深度学习算法第一课——KNN聚类的原理和实现

#为了避免数据内部的巧合让算法看起来很合理，让数据进行随机的打乱处理
import random
import csv
#读取
with open('Prostate_Cancer.csv','r') as file:
    reader = csv.DictReader(file)
    datas = [row for row in reader]

#分组
random.shuffle(datas)  #打乱数据顺序
n = len(datas)//3  #整除

test_set = datas[0:n]   #0到n为测试集
train_set = datas[n:]   #n之后为训练集

#距离（两点间距离公式）
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#csv文件里为字符串，要先转化为数字
        return res**0.5

K=5
def knn(data):
    #1.距离
    res=[
        {"result":train['diagnosis_result'],"distance":distance(data,train)}      #找到数据data和训练项train的距离
        for train in train_set      #把所有训练项遍历一边
    ]
    #2.排序--升序
    res = sorted(res, key=lambda item:['distance'])
    #3.取前K个
    res2 = res[0:K]

    #4.加权平均
    result = {'B':0,'M':0}  #权重

    #总距离
    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'

#测试阶段
correct = 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)))

运行结果：