吴裕雄 python 机器学习——模型选择参数优化暴力搜索寻优GridSearchCV模型

Posted 2021-11-26 tszr

import scipy

from sklearn.datasets import load_digits
from sklearn.metrics import classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV,RandomizedSearchCV

#模型选择参数优化暴力搜索寻优GridSearchCV模型
def test_GridSearchCV():
    ‘‘‘
    测试 GridSearchCV 的用法。使用 LogisticRegression 作为分类器，主要优化 C、penalty、multi_class 等参数
    ‘‘‘
    ### 加载数据
    digits = load_digits()
    X_train,X_test,y_train,y_test=train_test_split(digits.data, digits.target,test_size=0.25,random_state=0,stratify=digits.target)
    #### 参数优化 ######
    tuned_parameters = [{‘penalty‘: [‘l1‘,‘l2‘],
                        ‘C‘: [0.01,0.05,0.1,0.5,1,5,10,50,100],
                        ‘solver‘:[‘liblinear‘],
                        ‘multi_class‘: [‘ovr‘]},
                        {‘penalty‘: [‘l2‘],
                        ‘C‘: [0.01,0.05,0.1,0.5,1,5,10,50,100],
                         ‘solver‘:[‘lbfgs‘],
                        ‘multi_class‘: [‘ovr‘,‘multinomial‘]},
                        ]
    clf=GridSearchCV(LogisticRegression(tol=1e-6),tuned_parameters,cv=10)
    clf.fit(X_train,y_train)
    print("Best parameters set found:",clf.best_params_)
    print("Grid scores:")
#     for params, mean_train_score, mean_test_score in clf.cv_results_.params,cv_results_.mean_train_score,cv_results_.mean_test_score:
#         print("\\t%0.3f (+/-%0.03f) for %s" % (mean_train_score, mean_test_score() * 2, params))
    print((clf.cv_results_["mean_train_score"], clf.cv_results_["mean_test_score"] * 2, clf.cv_results_["params"]))

    print("Optimized Score:",clf.score(X_test,y_test))
    print("Detailed classification report:")
    y_true, y_pred = y_test, clf.predict(X_test)
    print(classification_report(y_true, y_pred))
    
#调用test_GridSearchCV()
test_GridSearchCV()