Day11 超参数调整

完整训练数据主要分为处理数据，训练集与测试集的划分，参数的调试等过程。

#模型 = 算法 + 实例化设置的外参（超参数）+训练得到的内参

#基本步骤：
#1.数据预处理
import pandas as pd  #处理数据
import numpy as np   #数值计算
import matplotlib.pyplot as plt  #绘制图表
import seaborn as sns #高级绘图表

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_csv('data.csv')
print(data.columns)

#找字符串列
discrete_features = data.select_dtypes(include=['object']).columns.tolist()

#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_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)

#独热编码
data = pd.get_dummies(data,columns=['Purpose'])
data2 = pd.read_csv('data.csv')
list_final = []
for i in data.columns:
    if i not in data2.columns:
        list_final.append(i)

for i in list_final:
    data[i] =data[i].astype(int)

#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)

#找连续变量
continuous_features = data.select_dtypes(include=['int64','float64']).columns.tolist()

#中位数或众数补全
for feature in continuous_features:
    mode_value = data[feature].mode()[0]
    data[feature].fillna(mode_value,inplace=True)


#2机器学习部分
#2.1划分训练集与测试集
from sklearn.model_selection import train_test_split
X= data.drop(['Credit Default'],axis=1)
y= data['Credit Default']
# X_train,X_temp,y_train,y_temp = train_test_split(X,y,test_size=0.2,random_state=42)
# X_val,X_test,y_val,y_test = train_test_split(X_temp,y_temp,test_size=0.5,random_state=42)

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

print("Data shapes:")
print("X_train:", X_train.shape)
print("y_train:", y_train.shape)
print("X_test:", X_test.shape)
print("y_test:", y_test.shape)


#2.2引入方法
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


#2.3 调参
#根据计算机的算力，如果算力够强，使用网格搜索，算力不够使用贝叶斯优化
#默认参数的随机森林
print('---------默认参数的随机森林---------')
import time
stat_time = time.time()
rf_model = RandomForestClassifier(random_state=42)
rf_model.fit(X_train,y_train)
rf_pred = rf_model.predict(X_test)
end_time = time.time()

print(f'训练耗时{end_time-stat_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))

#网格搜索优化
print('---------网格搜索优化的随机森林---------')
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=RandomForestClassifier(random_state=42),
                        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()
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_params_属性返回最佳参数组合
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网格搜索优化的随机森林 在测试集上的分类报告：")
print(classification_report(y_test,rf_pred))
print("网格搜索优化的随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test,rf_pred))

@浙大疏锦行