Python day15-CSDN博客

数据地址：Student Habits vs Academic Performance (kaggle.com)

和以前一样，处理数据的代码如下：

import pandas as pd   
import numpy as np     
import matplotlib.pyplot as plt    
import seaborn as sns   
import warnings
warnings.filterwarnings("ignore")

plt.rcParams['font.sans-serif'] = ['SimHei']  
plt.rcParams['axes.unicode_minus'] = False    
data = pd.read_csv('student_habits_performance.csv')   


discrete_features = data.select_dtypes(include=['object']).columns.tolist()
parental_education_level_mapping = {
    'None': 1,
    'High School': 2,
    'Bachelor': 3,
    'Master': 4
}
data['parental_education_level'] = data['parental_education_level'].map(parental_education_level_mapping)

internet_quality_mapping = {
    'Poor': 1,
    'Average': 2,
    'Good': 3
}
data['internet_quality'] = data['internet_quality'].map(internet_quality_mapping)

data = pd.get_dummies(data, columns=['diet_quality'])
data2 = pd.read_csv("student_habits_performance.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)

gender_mapping = {
    'Female': 0,
    'Male': 1
}
data['gender'] = data['gender'].map(gender_mapping)
data.rename(columns={'gender': 'isMale'}, inplace=True) # 重命名列

continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist() 
for feature in continuous_features:     
    mode_value = data[feature].mode()[0]           
    data[feature].fillna(mode_value, inplace=True)          

from sklearn.model_selection import train_test_split
X = data.drop(['exam_score'], axis=1)
y = data['exam_score']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

后面的比较类似：默认的baseline+shap画图

import shap
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier 
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score 
from sklearn.metrics import classification_report, confusion_matrix 
import warnings 
warnings.filterwarnings("ignore") 
import time

print("--- 1. 默认参数随机森林 (训练集 -> 测试集) ---") 
start_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))



explainer = shap.TreeExplainer(rf_model)
shap_values = explainer.shap_values(X_test)

print("shap特征重要性条形图")
shap.summary_plot(shap_values[:,:,0],X_test,plot_type="bar",show=False)
plt.title("SHAP feature importance(Bar plot)")
plt.show()


print("SHAP特征重要性小提琴图")
shap.summary_plot(shap_values[:,:,0],X_test,plot_type="violin",show=False,max_display=10)
plt.title("SHAP feature importance(Violin plot)")
plt.show()