Python3入门机器学习（四）(补)- sklearn 中使用knn算法的总结整理

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y)

from sklearn.preprocessing import StandardScaler
standardScaler = StandardScaler()
# 存放了均值方差归一化所对应的信息
standardScaler.fit(X_train)
X_train = standardScaler.transform(X_train)
X_test = standardScaler.transform(X_test)

from sklearn.neighbors import KNeighborsClassifier
sklearn_knn_clf = KNeighborsClassifier(n_neighbors=6)

sklearn_knn_clf.fit(X_train,y_train)

sklearn_knn_clf.score(X_test,y_test)

y_predict = sklearn_knn_clf.predict(X_test)

# array<dict<参数名：参数可能的取值>>
param_grid =[
    {
        'weights':['uniform'],
        'n_neighbors': [i for i in range(1,11)]
    },
    {
        'weights':['distance'],
        'n_neighbors': [i for i in range(1,11)],
        'p': [i for i in range(1,6)]
    }
]

# 先new一个默认的Classifier对象
knn_clf = KNeighborsClassifier()

# 调用GridSearchCV创建网格搜索对象，传入参数为Classifier对象以及参数列表
from sklearn.model_selection import GridSearchCV

grid_search = GridSearchCV(knn_clf,param_grid)

# 调用fit方法执行网格搜索
%%time
grid_search.fit(X_train,y_train)

# 获得最好的评估结果，返回的是KNeighborsClassifier对象，可以直接拿来做机器学习预测了
grid_search.best_estimator_

# 最好的分数
grid_search.best_score_

# 最好的参数
grid_search.best_params_