通过KNN查找离样本最近的邻居

最新推荐文章于 2025-01-03 08:00:00 发布

炼丹师666

最新推荐文章于 2025-01-03 08:00:00 发布

阅读量1.3k

点赞数 1

分类专栏：算法

本文链接：https://blog.youkuaiyun.com/wj1298250240/article/details/103610076

版权

通过KNN查找离样本最近的邻居

# 寻找离样本最近的邻居
from sklearn import datasets
from sklearn.neighbors import NearestNeighbors
from sklearn.preprocessing import StandardScaler
# 加载数据
iris = datasets.load_iris()
features = iris.data
# 标准化数据
standardizer = StandardScaler()
# features  特征标准化
features_standardized = standardizer.fit_transform(features)

nearest_neighbors = NearestNeighbors(n_neighbors=2).fit(features_standardized)
#nearest_neighbors_euclidian = NearestNeighbors(n_neighbors=2, metric='euclidian').fit(features_standardized)
# 创建测试数据
new_observation = [1, 1, 1, 1]

# 获取最近两个点的索引，距离
distances, indices = nearest_neighbors.kneighbors([new_observation])

# features_standardized[indices]  距离最近的两个值
indices
# 距离
distances
features_standardized[indices] 
array([[[1.03800476, 0.55861082, 1.10378283, 1.18556721],
        [0.79566902, 0.32841405, 0.76275827, 1.05393502]]])
# metric  设定距离指标
nearestneighbors_euclidean = NearestNeighbors(
    n_neighbors=2, metric='euclidean').fit(features_standardized)
# 查看距离
distances
array([[0.49140089, 0.74294782]