knn python_KNN Python实现

'''

k近邻(kNN)算法的工作机制比较简单，根据某种距离测度找出距离给定待测样本距离最小的k个训练样本，根据k个训练样本进行预测。

分类问题：k个点中出现频率最高的类别作为待测样本的类别

回归问题：通常以k个训练样本的平均值作为待测样本的预测值

kNN模型三要素：距离测度、k值的选择、分类或回归决策方式

'''

importnumpy as npclassKNNClassfier(object):def __init__(self, k=5, distance='euc'):

self.k=k

self.distance=distance

self.x=None

self.y=Nonedeffit(self,X, Y):'''

X : array-like [n_samples,shape]

Y : array-like [n_samples,1]

'''self.x=X

self.y=Ydefpredict(self,X_test):'''

X_test : array-like [n_samples,shape]

Y_test : array-like [n_samples,1]

output : array-like [n_samples,1]

'''output= np.zeros((X_test.shape[0],1))for i inrange(X_test.shape[0]):

dis=[]for j inrange(self.x.shape[0]):if self.distance == 'euc': #欧式距离

dis.append(np.linalg.norm(X_test[i]-self.x[j,:]))

labels=[]

index=sorted(range(len(dis)), key=dis.__getitem__)for j inrange(self.k):

labels.append(self.y[index[j]])

counts=[]for label inlabels:

counts.append(labels.count(label))

output[i]=labels[np.argmax(counts)]returnoutputdefscore(self,x,y):

pred=self.predict(x)

err= 0.0

for i inrange(x.shape[0]):if pred[i]!=y[i]:

err= err+1

return 1-float(err/x.shape[0])if __name__ == '__main__':from sklearn importdatasets

iris=datasets.load_iris()

x=iris.data

y=iris.target# x = np.array([[0.5,0.4],[0.1,0.2],[0.7,0.8],[0.2,0.1],[0.4,0.6],[0.9,0.9],[1,1]]).reshape(-1,2)

# y = np.array([0,1,0,1,0,1,1]).reshape(-1,1)

clf = KNNClassfier(k=3)

clf.fit(x,y)print('myknn score:',clf.score(x,y))from sklearn.neighbors importKNeighborsClassifier

clf_sklearn= KNeighborsClassifier(n_neighbors=3)

clf_sklearn.fit(x,y)print('sklearn score:',clf_sklearn.score(x,y))