KNN分类鸢尾花数据集

最新推荐文章于 2023-08-07 23:24:42 发布

weixin_44871574

最新推荐文章于 2023-08-07 23:24:42 发布

阅读量165

点赞数

文章标签： python 机器学习

本文链接：https://blog.csdn.net/weixin_44871574/article/details/107063951

版权

from sklearn import datasets
from sklearn.model_selection import train_test_split
import numpy as np
from collections import Counter
iris = datasets.load_iris()
X=iris.data
y=iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=1)
def test(trainset,testdata,k,lables):
    sqdiffMat=(trainset-testdata)**2
    distances=np.sum(sqdiffMat,axis=1)**0.5
    SequentialIndex=np.argsort(distances)
    klables=[]
    for i in range(k):
        klables.append(lables[SequentialIndex[i]])
    labledict=Counter(klables)
    testclass=labledict.most_common(1)[0][0]
    return testclass
y_pred=[]
for i in range(len(y_test)):
    y_pred.append(test(X_train,X_test[i],10,y_train))
print("IRIS:Number of mislabeled points out of a total %d points : %d, Acc: %f%%"
     % (X_test.shape[0], (y_test != y_pred).sum(),(y_test == y_pred).sum()/X_test.shape[0]))