超参数调整专题

知识点回顾

网格搜索
随机搜索（简单介绍，非重点 实战中很少用到，可以不了解）
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）
time库的计时模块，方便后人查看代码运行时长

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

1.数据预处理

  

import pandas as pd
import pandas as pd   
import numpy as np     
import matplotlib.pyplot as plt    
import seaborn as sns 

 # 设置中文字体（解决中文显示问题）
plt.rcParams['font.sans-serif'] = ['SimHei']  # Windows系统常用黑体字体
plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号

data = pd.read_excel('data.xlsx')    #读取数据
 
# 先筛选字符串变量 
discrete_features = data.select_dtypes(include=['object']).columns.tolist()
# Home Ownership 标签编码
home_ownership_mapping = {
    'Own Home': 1,
    'Rent': 2,
    'Have Mortgage': 3,
    'Home Mortgage': 4
}
data['Home Ownership'] = data['Home Ownership'].map(home_ownership_mapping)

# Years in current job 标签编码
years_in_job_mapping = {
    '< 1 year': 1,
    '1 year': 2,
    '2 years': 3,
    '3 years': 4,
    '4 years': 5,
    '5 years': 6,
    '6 years': 7,
    '7 years': 8,
    '8 years': 9,
    '9 years': 10,
    '10+ years': 11
}
data['Years in current job'] = data['Years in current job'].map(years_in_job_mapping)
# Purpose 独热编码，记得需要将bool类型转换为数值
data = pd.get_dummies(data, columns=['Purpose'])
data2 = pd.read_excel("data.xlsx") # 重新读取数据，用来做列名对比
list_final = [] # 新建一个空列表，用于存放独热编码后新增的特征名
for i in data.columns:
    if i not in data2.columns:
       list_final.append(i) # 这里打印出来的就是独热编码后的特征名
for i in list_final:
    data[i] = data[i].astype(int) # 这里的i就是独热编码后的特征名
 
 
 
# Term 0 - 1 映射
term_mapping = {
    'Short Term': 0,
    'Long Term': 1
}
data['Term'] = data['Term'].map(term_mapping)
data.rename(columns={'Term': 'Long Term'}, inplace=True) # 重命名列
continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()  #把筛选出来的列名转换成列表
 
 # 连续特征用中位数补全
for feature in continuous_features:     
    mode_value = data[feature].mode()[0]            #获取该列的众数。
    data[feature].fillna(mode_value, inplace=True)          #用众数填充该列的缺失值，inplace=True表示直接在原数据上修改。

2.划分数据集 

from sklearn.model_selection import train_test_split
X = data.drop(['Credit Default'], axis=1)  # 特征，axis=1表示按列删除
y = data['Credit Default'] # 标签
# 按照8:2划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # 80%训练集，20%测试集

3.调参

from sklearn.ensemble import RandomForestClassifier #随机森林分类器
 
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score # 用于评估分类器性能的指标
from sklearn.metrics import classification_report, confusion_matrix #用于生成分类报告和混淆矩阵
import warnings #用于忽略警告信息
warnings.filterwarnings("ignore") # 忽略所有警告信息

# --- 1. 默认参数的随机森林 ---
print("--- 1. 默认参数随机森林 (训练集 -> 测试集) ---")
import time # time库，主要用于时间相关的操作，因为调参需要很长时间，记录下会帮助后人知道大概的时长
start_time = time.time() # 记录开始时间
rf_model = RandomForestClassifier(random_state=42)
rf_model.fit(X_train, y_train) # 在训练集上训练
rf_pred = rf_model.predict(X_test) # 在测试集上预测
end_time = time.time() # 记录结束时间
 
print(f"训练与预测耗时: {end_time - start_time:.4f} 秒")
print("\n默认随机森林 在测试集上的分类报告：")
print(classification_report(y_test, rf_pred))
print("默认随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, rf_pred))

--- 1. 默认参数随机森林 (训练集 -> 测试集) ---
训练与预测耗时: 0.8787 秒

默认随机森林 在测试集上的分类报告：
              precision    recall  f1-score   support

           0       0.77      0.97      0.86      1059
           1       0.79      0.30      0.43       441

    accuracy                           0.77      1500
   macro avg       0.78      0.63      0.64      1500
weighted avg       0.77      0.77      0.73      1500

默认随机森林 在测试集上的混淆矩阵：
[[1023   36]
 [ 309  132]]

# --- 2. 网格搜索优化随机森林 ---
print("\n--- 2. 网格搜索优化随机森林 (训练集 -> 测试集) ---")
from sklearn.model_selection import GridSearchCV
 
# 定义要搜索的参数网格
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]
}
 
# 创建网格搜索对象
grid_search = GridSearchCV(estimator=RandomForestClassifier(random_state=42), # 随机森林分类器
                           param_grid=param_grid, # 参数网格
                           cv=5, # 5折交叉验证
                           n_jobs=-1, # 使用所有可用的CPU核心进行并行计算
                           scoring='accuracy') # 使用准确率作为评分标准
 
start_time = time.time()
# 在训练集上进行网格搜索
grid_search.fit(X_train, y_train) # 在训练集上训练，模型实例化和训练的方法都被封装在这个网格搜索对象里了
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_params_属性返回最佳参数组合
 
# 使用最佳参数的模型进行预测
best_model = grid_search.best_estimator_ # 获取最佳模型
best_pred = best_model.predict(X_test) # 在测试集上进行预测
 
print("\n网格搜索优化后的随机森林 在测试集上的分类报告：")
print(classification_report(y_test, best_pred))
print("网格搜索优化后的随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, best_pred))

--- 2. 网格搜索优化随机森林 (训练集 -> 测试集) ---
网格搜索耗时: 92.9777 秒
最佳参数:  {'max_depth': 20, 'min_samples_leaf': 1, 'min_samples_split': 2, 'n_estimators': 200}

网格搜索优化后的随机森林 在测试集上的分类报告：
              precision    recall  f1-score   support

           0       0.76      0.97      0.86      1059
           1       0.80      0.28      0.42       441

    accuracy                           0.77      1500
   macro avg       0.78      0.63      0.64      1500
weighted avg       0.77      0.77      0.73      1500

网格搜索优化后的随机森林 在测试集上的混淆矩阵：
[[1028   31]
 [ 317  124]]

# --- 2. 贝叶斯优化随机森林 ---
print("\n--- 2. 贝叶斯优化随机森林 (训练集 -> 测试集) ---")
from bayes_opt import BayesianOptimization
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report, confusion_matrix
import time
import numpy as np
 
# 假设 X_train, y_train, X_test, y_test 已经定义好
# 定义目标函数，这里使用交叉验证来评估模型性能
def rf_eval(n_estimators, max_depth, min_samples_split, min_samples_leaf):
    n_estimators = int(n_estimators)
    max_depth = int(max_depth)
    min_samples_split = int(min_samples_split)
    min_samples_leaf = int(min_samples_leaf)
    model = RandomForestClassifier(
        n_estimators=n_estimators,
        max_depth=max_depth,
        min_samples_split=min_samples_split,
        min_samples_leaf=min_samples_leaf,
        random_state=42
    )
    scores = cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy')
    return np.mean(scores)
 
# 定义要搜索的参数空间
pbounds_rf = {
    'n_estimators': (50, 200),
   'max_depth': (10, 30),
   'min_samples_split': (2, 10),
   'min_samples_leaf': (1, 4)
}
 
# 创建贝叶斯优化对象，设置 verbose=2 显示详细迭代信息
optimizer_rf = BayesianOptimization(
    f=rf_eval, # 目标函数
    pbounds=pbounds_rf, # 参数空间
    random_state=42, # 随机种子
    verbose=2  # 显示详细迭代信息
)
 
start_time = time.time()
# 开始贝叶斯优化
optimizer_rf.maximize(
    init_points=5,  # 初始随机采样点数
    n_iter=32  # 迭代次数
)
end_time = time.time()
 
print(f"贝叶斯优化耗时: {end_time - start_time:.4f} 秒")
print("最佳参数: ", optimizer_rf.max['params'])
 
# 使用最佳参数的模型进行预测
best_params = optimizer_rf.max['params']
best_model = RandomForestClassifier(
    n_estimators=int(best_params['n_estimators']),
    max_depth=int(best_params['max_depth']),
    min_samples_split=int(best_params['min_samples_split']),
    min_samples_leaf=int(best_params['min_samples_leaf']),
    random_state=42
)
best_model.fit(X_train, y_train)
best_pred = best_model.predict(X_test)
 
print("\n贝叶斯优化后的随机森林 在测试集上的分类报告：")
print(classification_report(y_test, best_pred))
print("贝叶斯优化后的随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, best_pred))

--- 2. 贝叶斯优化随机森林 (训练集 -> 测试集) ---
|   iter    |  target   | max_depth | min_sa... | min_sa... | n_esti... |
-------------------------------------------------------------------------
| [39m1        [39m | [39m0.7828   [39m | [39m17.49    [39m | [39m3.852    [39m | [39m7.856    [39m | [39m139.8    [39m |
| [39m2        [39m | [39m0.78     [39m | [39m13.12    [39m | [39m1.468    [39m | [39m2.465    [39m | [39m179.9    [39m |
| [39m3        [39m | [39m0.7817   [39m | [39m22.02    [39m | [39m3.124    [39m | [39m2.165    [39m | [39m195.5    [39m |
| [39m4        [39m | [39m0.7825   [39m | [39m26.65    [39m | [39m1.637    [39m | [39m3.455    [39m | [39m77.51    [39m |
| [39m5        [39m | [39m0.7822   [39m | [39m16.08    [39m | [39m2.574    [39m | [39m5.456    [39m | [39m93.68    [39m |
| [39m6        [39m | [39m0.7803   [39m | [39m17.93    [39m | [39m3.082    [39m | [39m5.915    [39m | [39m126.9    [39m |
| [39m7        [39m | [39m0.7772   [39m | [39m10.98    [39m | [39m1.055    [39m | [39m6.804    [39m | [39m158.6    [39m |
| [39m8        [39m | [39m0.7765   [39m | [39m10.09    [39m | [39m1.121    [39m | [39m5.732    [39m | [39m102.8    [39m |
| [39m9        [39m | [39m0.78     [39m | [39m29.42    [39m | [39m3.129    [39m | [39m9.951    [39m | [39m106.1    [39m |
| [39m10       [39m | [39m0.7822   [39m | [39m19.43    [39m | [39m1.481    [39m | [39m8.416    [39m | [39m64.48    [39m |
| [35m11       [39m | [35m0.783    [39m | [35m28.77    [39m | [35m3.119    [39m | [35m5.601    [39m | [35m199.8    [39m |
| [39m12       [39m | [39m0.7798   [39m | [39m26.76    [39m | [39m2.866    [39m | [39m4.587    [39m | [39m197.0    [39m |
| [39m13       [39m | [39m0.78     [39m | [39m13.87    [39m | [39m2.864    [39m | [39m3.986    [39m | [39m165.2    [39m |
| [39m14       [39m | [39m0.7782   [39m | [39m10.13    [39m | [39m2.378    [39m | [39m9.813    [39m | [39m129.0    [39m |
| [39m15       [39m | [39m0.7787   [39m | [39m24.85    [39m | [39m2.575    [39m | [39m4.403    [39m | [39m52.95    [39m |
| [39m16       [39m | [39m0.78     [39m | [39m27.74    [39m | [39m2.593    [39m | [39m4.055    [39m | [39m129.7    [39m |
| [39m17       [39m | [39m0.7805   [39m | [39m14.12    [39m | [39m3.91     [39m | [39m2.115    [39m | [39m60.42    [39m |
| [39m18       [39m | [39m0.7827   [39m | [39m18.97    [39m | [39m1.264    [39m | [39m2.414    [39m | [39m175.5    [39m |
| [39m19       [39m | [39m0.7765   [39m | [39m11.66    [39m | [39m3.395    [39m | [39m9.376    [39m | [39m195.7    [39m |
| [39m20       [39m | [39m0.7793   [39m | [39m17.29    [39m | [39m1.86     [39m | [39m7.538    [39m | [39m150.1    [39m |
| [39m21       [39m | [39m0.7822   [39m | [39m19.36    [39m | [39m1.97     [39m | [39m8.328    [39m | [39m64.46    [39m |
| [39m22       [39m | [39m0.781    [39m | [39m29.96    [39m | [39m3.562    [39m | [39m7.921    [39m | [39m199.0    [39m |
| [39m23       [39m | [39m0.7808   [39m | [39m18.14    [39m | [39m2.653    [39m | [39m5.696    [39m | [39m138.2    [39m |
| [39m24       [39m | [39m0.7818   [39m | [39m15.49    [39m | [39m3.068    [39m | [39m9.806    [39m | [39m140.5    [39m |
| [39m25       [39m | [39m0.781    [39m | [39m19.36    [39m | [39m3.244    [39m | [39m9.495    [39m | [39m141.0    [39m |
| [39m26       [39m | [39m0.7808   [39m | [39m21.09    [39m | [39m2.187    [39m | [39m4.491    [39m | [39m174.4    [39m |
| [39m27       [39m | [39m0.7795   [39m | [39m14.4     [39m | [39m3.276    [39m | [39m6.276    [39m | [39m141.1    [39m |
| [39m28       [39m | [39m0.7813   [39m | [39m16.64    [39m | [39m2.866    [39m | [39m2.51     [39m | [39m175.8    [39m |
| [39m29       [39m | [39m0.7793   [39m | [39m28.99    [39m | [39m1.05     [39m | [39m4.297    [39m | [39m199.6    [39m |
| [35m30       [39m | [35m0.7837   [39m | [35m17.5     [39m | [35m2.553    [39m | [35m8.927    [39m | [35m138.6    [39m |
| [39m31       [39m | [39m0.7795   [39m | [39m16.56    [39m | [39m3.761    [39m | [39m9.857    [39m | [39m137.2    [39m |
| [39m32       [39m | [39m0.7793   [39m | [39m17.35    [39m | [39m1.551    [39m | [39m8.439    [39m | [39m138.9    [39m |
| [39m33       [39m | [39m0.7798   [39m | [39m17.38    [39m | [39m3.878    [39m | [39m8.473    [39m | [39m139.3    [39m |
| [39m34       [39m | [39m0.779    [39m | [39m24.33    [39m | [39m1.157    [39m | [39m5.795    [39m | [39m76.37    [39m |
| [39m35       [39m | [39m0.7825   [39m | [39m26.71    [39m | [39m1.621    [39m | [39m3.293    [39m | [39m77.47    [39m |
| [39m36       [39m | [39m0.7825   [39m | [39m29.04    [39m | [39m3.905    [39m | [39m5.19     [39m | [39m199.9    [39m |
| [39m37       [39m | [39m0.7825   [39m | [39m18.26    [39m | [39m2.861    [39m | [39m9.151    [39m | [39m138.7    [39m |
=========================================================================
贝叶斯优化耗时: 172.6407 秒
最佳参数:  {'max_depth': 17.502236740620297, 'min_samples_leaf': 2.5533082077180316, 'min_samples_split': 8.926771812562555, 'n_estimators': 138.5566475443472}

贝叶斯优化后的随机森林 在测试集上的分类报告：
              precision    recall  f1-score   support

           0       0.76      0.98      0.86      1059
           1       0.83      0.26      0.40       441

    accuracy                           0.77      1500
   macro avg       0.79      0.62      0.63      1500
weighted avg       0.78      0.77      0.72      1500

贝叶斯优化后的随机森林 在测试集上的混淆矩阵：
[[1035   24]
 [ 325  116]]

@浙大疏锦行