Python3入门机器学习经典算法与应用——knn算法网格搜索

本文链接：https://blog.youkuaiyun.com/e891377/article/details/109639167

本文介绍使用网格搜索优化KNN算法的超参数，包括邻居数量、权重类型及距离度量方式等，并展示了不同设置下的搜索效率对比。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

knn算法网格搜索

06 网格搜索和更多kNN中的超参数

import numpy as np
from sklearn import datasets

digits = datasets.load_digits()
X = digits.data
y = digits.target

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)

from sklearn.neighbors import KNeighborsClassifier

sk_knn_clf = KNeighborsClassifier(n_neighbors=4, weights="uniform")
sk_knn_clf.fit(X_train, y_train)
sk_knn_clf.score(X_test, y_test)

0.9916666666666667

Grid Search

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()

from sklearn.model_selection import GridSearchCV

grid_search = GridSearchCV(knn_clf, param_grid)

%%time
grid_search.fit(X_train, y_train)

Wall time: 1min 27s





GridSearchCV(cv=None, error_score=nan,
             estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30,
                                            metric='minkowski',
                                            metric_params=None, n_jobs=None,
                                            n_neighbors=5, p=2,
                                            weights='uniform'),
             iid='deprecated', n_jobs=None,
             param_grid=[{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                          'weights': ['uniform']},
                         {'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                          'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
             scoring=None, verbose=0)

grid_search.best_estimator_

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
                     metric_params=None, n_jobs=None, n_neighbors=1, p=2,
                     weights='uniform')

grid_search.best_score_

0.9860820751064653

%%time
grid_search = GridSearchCV(knn_clf, param_grid, n_jobs=-1, verbose=2)
grid_search.fit(X_train, y_train)

Fitting 5 folds for each of 60 candidates, totalling 300 fits


[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.
[Parallel(n_jobs=-1)]: Done  25 tasks      | elapsed:    2.3s
[Parallel(n_jobs=-1)]: Done 146 tasks      | elapsed:    7.6s


Wall time: 16.8 s


[Parallel(n_jobs=-1)]: Done 300 out of 300 | elapsed:   16.7s finished





GridSearchCV(cv=None, error_score=nan,
             estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30,
                                            metric='minkowski',
                                            metric_params=None, n_jobs=None,
                                            n_neighbors=5, p=2,
                                            weights='uniform'),
             iid='deprecated', n_jobs=-1,
             param_grid=[{'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                          'weights': ['uniform']},
                         {'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                          'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
             scoring=None, verbose=2)