网格搜索，随机搜索

最新推荐文章于 2025-02-22 18:56:06 发布

Unicorn .

最新推荐文章于 2025-02-22 18:56:06 发布

阅读量790

点赞数

分类专栏：机器学习文章标签： python 大数据

本文链接：https://blog.csdn.net/qq_52096207/article/details/123936285

版权

机器学习专栏收录该内容

8 篇文章

订阅专栏

本文介绍了两种常用的机器学习模型参数调优方法：网格搜索（GridSearchCV）和随机搜索（RandomizedSearchCV）。通过示例展示了如何在鸢尾花数据集上应用这两种方法调整SVM模型的参数，包括参数设置、模型训练以及结果评估。最终，找到最优模型参数，以提高模型的预测性能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

调参的工具

网格搜索

导入需要的库

from sklearn import svm
from sklearn import datasets
from sklearn.model_selection import GridSearchCV
import pandas as pd 
from sklearn.datasets import load_iris

iris=datasets.load_iris()
parrameters={'kernel':('linear','rbf'),'C':[1,10]}#模型参数
svc=svm.SVC(probability=True)
clf=GridSearchCV(svc,parrameters)
clf.fit(iris.data,iris.target)

GridSearchCV(cv=None, error_score=nan,
             estimator=SVC(C=1.0, break_ties=False, cache_size=200,
                           class_weight=None, coef0=0.0,
                           decision_function_shape='ovr', degree=3,
                           gamma='scale', kernel='rbf', max_iter=-1,
                           probability=True, random_state=None, shrinking=True,
                           tol=0.001, verbose=False),
             iid='deprecated', n_jobs=None,
             param_grid={'C': [1, 10], 'kernel': ('linear', 'rbf')},
             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,
             scoring=None, verbose=0)

print(clf.cv_results_)

{'mean_fit_time': array([0.00120158, 0.00120668, 0.00139761, 0.00099792]), 'std_fit_time': array([3.76263297e-04, 3.77709886e-04, 1.01544355e-03, 2.90693166e-05]), 'mean_score_time': array([0.        , 0.00039043, 0.0001986 , 0.        ]), 'std_score_time': array([0.        , 0.00047848, 0.00039721, 0.        ]), 'param_C': masked_array(data=[1, 1, 10, 10],
             mask=[False, False, False, False],
       fill_value='?',
            dtype=object), 'param_kernel': masked_array(data=['linear', 'rbf', 'linear', 'rbf'],
             mask=[False, False, False, False],
       fill_value='?',
            dtype=object), 'params': [{'C': 1, 'kernel': 'linear'}, {'C': 1, 'kernel': 'rbf'}, {'C': 10, 'kernel': 'linear'}, {'C': 10, 'kernel': 'rbf'}], 'split0_test_score': array([0.96666667, 0.96666667, 1.        , 0.96666667]), 'split1_test_score': array([1.        , 0.96666667, 1.        , 1.        ]), 'split2_test_score': array([0.96666667, 0.96666667, 0.9       , 0.96666667]), 'split3_test_score': array([0.96666667, 0.93333333, 0.96666667, 0.96666667]), 'split4_test_score': array([1., 1., 1., 1.]), 'mean_test_score': array([0.98      , 0.96666667, 0.97333333, 0.98      ]), 'std_test_score': array([0.01632993, 0.02108185, 0.03887301, 0.01632993]), 'rank_test_score': array([1, 4, 3, 1])}

#显示所有拟合模型的参数设定
pd.DataFrame(clf.cv_results_)

	mean_fit_time	std_fit_time	mean_score_time	std_score_time	param_C	param_kernel	params	split0_test_score	split1_test_score	split2_test_score	split3_test_score	split4_test_score	mean_test_score	std_test_score	rank_test_score
0	0.001202	0.000376	0.000000	0.000000	1	linear	{'C': 1, 'kernel': 'linear'}	0.966667	1.000000	0.966667	0.966667	1.0	0.980000	0.016330	1
1	0.001207	0.000378	0.000390	0.000478	1	rbf	{'C': 1, 'kernel': 'rbf'}	0.966667	0.966667	0.966667	0.933333	1.0	0.966667	0.021082	4
2	0.001398	0.001015	0.000199	0.000397	10	linear	{'C': 10, 'kernel': 'linear'}	1.000000	1.000000	0.900000	0.966667	1.0	0.973333	0.038873	3
3	0.000998	0.000029	0.000000	0.000000	10	rbf	{'C': 10, 'kernel': 'rbf'}	0.966667	1.000000	0.966667	0.966667	1.0	0.980000	0.016330	1

最优模型结果

clf.best_params_#最优模型

{'C': 1, 'kernel': 'linear'}

估计样本的类别

print(clf.decision_function(iris.data))#估计样本的类别

[[ 2.24627744  1.2980152  -0.30616012]
 [ 2.23781119  1.29663601 -0.30453043]
 [ 2.24548583  1.2968967  -0.30542241]

…

随机搜索

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-15Z3kXC0-1648963649100)(attachment:image.png)]
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-nun7VvbU-1648963649101)(attachment:image-2.png)]

import scipy.stats as stats
from sklearn import datasets
from sklearn.model_selection import RandomizedSearchCV
import pandas as pd 
from sklearn.svm import SVC

iris=datasets.load_iris()
parrameters={'kernel':('linear','rbf'),
            'C':stats.expon(scale=100),
            'gamma':stats.expon(scale=.1),
            'class_weight':('balanced',None)}
svc=SVC()
clf=RandomizedSearchCV(svc,parrameters)
clf.fit(iris.data,iris.target)
pd.DataFrame(clf.cv_results_)

clf.best_params_

{'C': 333.0779879298101,
 'class_weight': None,
 'gamma': 0.004641512813065941,
 'kernel': 'rbf'}