KNN算法，网格搜索，数据归一化

1. 调用KNN
2. 网格搜索
3. 数据归一化

import numpy as np 
import matplotlib.pyplot as plt

from sklearn import datasets 

# 以手写数据集为例
digits = datasets.load_digits() 
digits.keys()
dict_keys(['data', 'target', 'target_names', 'images', 'DESCR'])

分离出训练集和测试集

from sklearn.model_selection import train_test_split 
X_train, X_test, y_train, y_test = train_test_split(digits.data,digits.target,test_size=0.2, random_state=666)

数据归一化处理

from sklearn.preprocessing import StandardScaler #调出
standardscaler = StandardScaler()   #创建实例
standardscaler.fit(X_train)

#返回训练集的平均值
standardscaler.mean_

#返回训练集的标准差
standardscaler.scale_

#将X_train转换为归一化后的数据
X_train = standardscaler.transform(X_train)

#将X_test转换为归一化后的数据
X_test = standardscaler.transform(X_test)

网格搜索调参

# 首先定义要搜索的参数
# 二维数组内嵌套字典
# 每个字典内都是一组网格搜索，标明每个参数的取值范围
# 注意：p值只有在weights=distance时才有意义

param_grid = [
    {  # 需遍历10次
        'weights': ['uniform'], # 参数取值范围
        'n_neighbors': [i for i in range(1, 11)]  # 使用其他方式如np.arange()也可以
        # 这里没有p参数
    },
    {  # 需遍历50次
        'weights': ['distance'],
        'n_neighbors': [i for i in range(1, 11)],
        'p': [i for i in range(1, 6)]
    }
]

调出KNN训练器

from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier()  # 默认参数，创建空分类器

from sklearn.model_selection import GridSearchCV  # CV，使用交叉验证方式获得模型正确率
grid_search = GridSearchCV(knn_clf, param_grid, cv=5)  # 网格搜索参数

grid_search.fit(X_train, y_train)  

# 输出指定过的最佳参数 
grid_search.best_params_

#输出最佳准确率
grid_search.best_score_

KNN中的参数

KNN中第一个参数是k

best_score = 0  # 最高准确率
best_k = -1  # 最佳k值

for k in range(1, 11):    
    knn_clf = KNeighborsClassifier(n_neighbors=k)      
    knn_clf.fit(X_train, y_train)  # 训练    
    score = knn_clf.score(X_test, y_test) # 查看准确率   
         
    if score > best_score:        
       best_score = score        
       best_k = k
       
print('最佳准确率为：', best_score)
print('最佳k值为：', best_k)

另一个是 weights :uniform / distance
uniform 默认，统一只计算距离，权重一样
#distance, 增加权重考虑

best_score = 0.0  # 最高准确率
best_k = -1  # 最佳k值
best_weight = ''  # 距离或权重


for j in  ['uniform', 'distance']:
    for i in range(1, 11):
 
        knn_clf = KNeighborsClassifier(n_neighbors=i, weights=j) 
        knn_clf.fit(X_train, y_train)  # 训练
        score = knn_clf.score(X_test, y_test) # 查看准确率

        if score > best_score:
            best_score = score
            best_k = i
            best_weight = j

print('best_score = {}'.format(best_score))
print('best_k = {}'.format(best_k))
print('best_weight = {}'.format(best_weight))