打卡第十一天

1. 网格搜索
2. 随机搜索（简单介绍，非重点 实战中很少用到，可以不了解）
3. 贝叶斯优化（2种实现逻辑，以及如何避开必须用交叉验证的问题）
4. time库的计时模块，方便后人查看代码运行时长 

今日作业： 对于信贷数据的其他模型，如LightGBM和KNN 尝试用下贝叶斯优化和网格搜索

X = data.drop(['Credit Default'], axis = 1) 
Y = data['Credit Default']
X_train,  X_test, y_train, y_test = train_test_split(X, Y, test_size = 0.2, random_state = 42)
print(f"训练集形状={X_train.shape},测试集形状={X_test.shape}")

lgb_model = lgb.LGBMClassifier(random_state = 42)
lgb_model.fit(X_train, y_train)
lgb_pred = lgb_model.predict(X_test)
print("\nLightGBM 分类报告：")
print(classification_report(y_test, lgb_pred))
print("LightGBM 混淆矩阵：")
print(confusion_matrix(y_test, lgb_pred))
lgb_accuracy = accuracy_score(y_test, lgb_pred)
lgb_precision = precision_score(y_test, lgb_pred)
lgb_recall = recall_score(y_test, lgb_pred)
lgb_f1 = f1_score(y_test, lgb_pred)
print("LGBM 模型评估指标：")
print(f"准确率：{lgb_accuracy:.4f}")
print(f"精确率：{lgb_precision:.4f}")
print(f"召回率：{lgb_recall:.4f}")
print("--- 1.默认参数lightgbm (训练集 -> 测试集) ---")
import time
start_time = time.time()
lgb_model = lgb.LGBMClassifier(random_state=42)
lgb_model.fit(X_train, y_train)
lgb_pred = lgb_model.predict(X_test)
end_time = time.time()
print(f"训练与预测耗时: {end_time - start_time:.4f} 秒")
print("\n默认lightgbm 在测试集上的分类报告：")
print(classification_report(y_test, lgb_pred))
print("默认lightgbm 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, lgb_pred))

训练与预测耗时: 0.1345 秒

默认lightgbm 在测试集上的分类报告：
precision recall f1-score support
0 0.77 0.95 0.85 1059
1 0.72 0.31 0.44 441

accuary 0.76

macro avg 0.75 0.63 0.64 1500
weighted avg 0.75 0.76 0.73 1500

默认lightgbm 在测试集上的混淆矩阵：
[[1006 53]
[ 303 138]]

使用网格搜索的方法进行优化

X = data.drop(['Credit Default'], axis = 1) 
Y = data['Credit Default']
X_train,  X_test, y_train, y_test = train_test_split(X, Y, test_size = 0.2, random_state = 42)
print(f"训练集形状={X_train.shape},测试集形状={X_test.shape}")


print("\n--- 2.网格搜索优化lightgbm (训练集 -> 测试集) ---")
import time 
from sklearn.model_selection import GridSearchCV
param_grid ={
    'n_estimators': [50, 100, 200],
    'max_depth': [None, 10, 20, 30],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4]
}
grid_search = GridSearchCV(estimator=lgb.LGBMClassifier(random_state=42),
                           param_grid=param_grid,
                           cv=5,
                           n_jobs=-1,
                           scoring='accuracy')
start_time = time.time()
grid_search.fit(X_train, y_train)
end_time = time.time()
print(f"网格搜索耗时: {end_time - start_time:.4f} 秒")
print("最佳参数: ", grid_search.best_params_)
best_model = grid_search.best_estimator_
best_pred = best_model.predict(X_test)
print("\n网格搜索优化后的lightgbm 在测试集上的分类报告：")
print(classification_report(y_test, best_pred))
print("网格搜索优化后的lightgbm 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, best_pred))

没有结果，不知道是不是电脑带不动的原因，把代码发给AI，AI说我的代码可以正常跑，但是就是跑不动，还报错，我真服了。。。。。

贝叶斯优化

from skopt import BayesSearchCV
from skopt.space import Integer
import lightgbm as lgb
lgb.LGBMClassifier()
from sklearn.metrics import classification_report, confusion_matrix
import time

# 定义要搜索的参数空间
search_space = {
    'n_estimators': Integer(50, 200),
    'max_depth': Integer(10, 30),
    'min_samples_split': Integer(2, 10),
    'min_samples_leaf': Integer(1, 4)
}

# 创建贝叶斯优化搜索对象
bayes_search = BayesSearchCV(
    estimator=lgb.LGBMClassifier(random_state=42),
    search_spaces=search_space,
    n_iter=32,  # 迭代次数，可根据需要调整
    cv=5, # 5折交叉验证，这个参数是必须的，不能设置为1，否则就是在训练集上做预测了
    n_jobs=-1,
    scoring='accuracy'
)

start_time = time.time()
# 在训练集上进行贝叶斯优化搜索
bayes_search.fit(X_train, y_train)
end_time = time.time()

print(f"贝叶斯优化耗时: {end_time - start_time:.4f} 秒")
print("最佳参数: ", bayes_search.best_params_)

# 使用最佳参数的模型进行预测
best_model = bayes_search.best_estimator_
best_pred = best_model.predict(X_test)

print("\n贝叶斯优化后的lightgbm 在测试集上的分类报告：")
print(classification_report(y_test, best_pred))
print("贝叶斯优化后的lightgbm 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, best_pred))

过程：定义要搜索的参数空间，创造贝叶斯优化搜索对象，在训练集上进行贝叶斯优化搜索，用最佳参数模型在测试集上进行预测。@浙大疏锦行