使用交叉验证法和网格搜索进行模型评估代码实践

坚持 ，坚持

一，代码

from sklearn.datasets import load_wine
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import ShuffleSplit
from sklearn.model_selection import LeaveOneOut
from sklearn.svm import SVC

wine = load_wine()
svc = SVC(kernel='linear')
# scores = cross_val_score(svc, wine.data, wine.target, cv=6)
# print('交叉验证得分：{}'.format(scores))
# print('交叉验证平均分：{}'.format(scores.mean()))

# shuffle_split = ShuffleSplit(test_size=.2, train_size=.7, n_splits=10)
# scores = cross_val_score(svc, wine.data, wine.target, cv=shuffle_split)
# print('随机拆分交叉验证模型得分：{}'.format(scores))

cv = LeaveOneOut()
scores = cross_val_score(svc, wine.data, wine.target, cv=cv)
print('迭代次数：{}'.format(scores))
print('模型平均分：{}'.format(scores.mean()))

import numpy as np
from sklearn.datasets import load_wine
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import Lasso
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

wine = load_wine()
X_train, X_test, y_train, y_test = train_test_split(
    wine.data, wine.target, random_state=0
)
best_score = 0
for alpha in [0.01, 0.1, 1.0, 10.0]:
    for max_iter in [100, 1000, 5000, 10000]:
        lasso = Lasso(alpha=alpha, max_iter=max_iter)
        scores = cross_val_score(lasso, X_train, y_train, cv=6)
        # lasso.fit(X_train, y_train)
        # score = lasso.score(X_test, y_test)
        score = np.mean(scores)
        if score > best_score:
            best_score = score
            best_parameters = {'alpha': alpha, '最大迭代次数': max_iter}
print('模型最高分为：{:.3f}'.format(best_score))
print('最佳参数设置：{}'.format(best_parameters))

params = {'alpha': [0.01, 0.1, 1.0, 10.0],
          'max_iter': [100, 1000, 5000, 10000]}
grid_search = GridSearchCV(lasso, params, cv=6)
grid_search.fit(X_train, y_train)
print('模型最高分为：{:.3f}'.format(grid_search.score(X_test, y_test)))
print('最佳参数设置：{}'.format(grid_search.best_params_))

二，效果

C:\Users\ccc\AppData\Local\Programs\Python\Python38\python.exe D:/Code/Metis-Org/app/service/time_series_detector/algorithm/ai_test.py
迭代次数：[1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 0. 1.
 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 0.
 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 0. 1. 1. 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1.
 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.]
模型平均分：0.9550561797752809

Process finished with exit code 0

C:\Users\ccc\AppData\Local\Programs\Python\Python38\python.exe D:/Code/Metis-Org/app/service/time_series_detector/algorithm/ai_test.py
模型最高分为：0.865
最佳参数设置：{'alpha': 0.01, '最大迭代次数': 100}
模型最高分为：0.819
最佳参数设置：{'alpha': 0.01, 'max_iter': 100}

Process finished with exit code 0