听了好几年的K近邻算法 今天终于接触到了
原理很简单 讲样本映射为多维空间中的点
无标签新样本 由空间中与其最近的K个点中数量最多的标签来定义
以下为暴力实现 高效算法留坑
from sklearn import datasetsdef cmp(elem):return elem[0]iris=datasets.load_iris()data=iris.datatarget=iris.targetnum_data,num_feature=data.shapenum_target=len(iris.target_names)data_train,target_train=[],[]#训练集大小为120data_test,target_test=[],[]#测试集大小为30for i in range(num_data):if i%5!=0:data_train.append(data[i])target_train.append(target[i])else:data_test.append(data[i])target_test.append(target[i])num_train,num_test=len(data_train),len(data_test)K=int(10)#只考虑最近的10个邻居#P=2count=int(0)for i in range(num_test):list=[]for j in range(num_train):val=0.0for k in range(num_feature):val+=(data_test[i][k]-data_train[j][k])*(data_test[i][k]-data_train[j][k])val=val**0.5"""for k in range(num_feature):val+=abs(data_test[i][k]-data_train[j][k])"""tmp=[]tmp.append(val)tmp.append(target_train[j])list.append(tmp)list.sort(key=cmp)vote=[]for j in range(num_target):vote.append(int(0))for j in range(K):id=int(list[j][1])vote[id]=vote[id]+1maxx,ans=int(-1),int(-1)for j in range(num_target):if maxx<vote[j]:maxx,ans=vote[j],jif ans==target_test[i]:count=count+1print(count,num_test)
