knn分类器寻找最佳K值

knn分类器寻找最佳K值

网格搜索
pipe管道

​
# 寻找最佳的K值
from sklearn.neighbors import KNeighborsClassifier
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.model_selection import GridSearchCV
# 加载数据
iris = datasets.load_iris()
features = iris.data
target = iris.target
​
# 标准化
standardizer = StandardScaler()
features_standardized = standardizer.fit_transform(features)
​
# n_neighbors=5  邻居确定为5
knn = KNeighborsClassifier(n_neighbors=5, n_jobs=-1)
​
# 创建一个流水线， pipe管道
pipe = Pipeline([("standardizer", standardizer), ("knn", knn)])
​
# 创建列表
search_space = [{"knn__n_neighbors": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]}]
​
# 网格搜索
classifier = GridSearchCV(
    pipe, search_space, cv=5, verbose=0).fit(features_standardized, target)
​
# 查看最佳值
classifier.best_estimator_.get_params()["knn__n_neighbors"]
6