网格搜索最佳的超参数（KNN算法）

sklearn中提供的方法Grid search

首先定义要搜索的参数集合

#这里列表中的每一个字典都是要搜索的一个参数集合
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)]
    }
]

# -*- coding:utf-8  -*-
import matplotlib
import matplotlib.pyplot as plt
#数据集库
from sklearn import datasets
#数据集划分
from sklearn.model_selection import train_test_split
#knn
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
#加载手写数字数据集
digits = datasets.load_digits()
X = digits.data #数据
y = digits.target#数据标签

#将数据集划分为训练集和测试集，测试集的比例为总数的20%
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=666)

# Grid search

# 首先定义搜索的参数,里面字典的键就是参数的名称，值对应的列表是参数的取值范围
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)]
    }
]
knn_clf = KNeighborsClassifier()
#网格搜素的对象
#n_jobs指的是使用计算机的几个核,verbose是训练过程中的输出
grid_search = GridSearchCV(knn_clf,param_grid,n_jobs=-1,verbose=2)
grid_search.fit(X_train,y_train)

print(grid_search.best_estimator_)
#正确率
print(grid_search.best_score_)
#最佳参数打印
print(grid_search.best_params_)

#得到最佳分类器
knn_clf = grid_search.best_estimator_

输出