|
|
import pandas as pd
|
|
|
import numpy as np
|
|
|
import joblib
|
|
|
from flask import Flask, request, jsonify, render_template_string
|
|
|
import os
|
|
|
|
|
|
# 添加项目根目录到Python路径
|
|
|
import sys
|
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
|
|
|
|
# 修改模型加载路径
|
|
|
MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'models')
|
|
|
|
|
|
from data.data_generator import preprocess_data
|
|
|
|
|
|
# 创建Flask应用
|
|
|
app = Flask(__name__)
|
|
|
|
|
|
# 全局变量存储模型和预处理器
|
|
|
model = None
|
|
|
scaler = None
|
|
|
le_education = None
|
|
|
le_home = None
|
|
|
le_purpose = None
|
|
|
explainer = None
|
|
|
|
|
|
def load_model():
|
|
|
"""
|
|
|
加载训练好的模型和预处理器
|
|
|
"""
|
|
|
global model, scaler, le_education, le_home, le_purpose, explainer
|
|
|
|
|
|
print("加载模型和预处理器...")
|
|
|
try:
|
|
|
model = joblib.load(os.path.join(MODEL_DIR, 'lightgbm_model.pkl'))
|
|
|
except:
|
|
|
# 如果LightGBM模型不存在，回退到XGBoost模型
|
|
|
model = joblib.load(os.path.join(MODEL_DIR, 'xgboost_model.pkl'))
|
|
|
|
|
|
scaler = joblib.load(os.path.join(MODEL_DIR, 'scaler.pkl'))
|
|
|
le_education = joblib.load(os.path.join(MODEL_DIR, 'le_education.pkl'))
|
|
|
le_home = joblib.load(os.path.join(MODEL_DIR, 'le_home.pkl'))
|
|
|
le_purpose = joblib.load(os.path.join(MODEL_DIR, 'le_purpose.pkl'))
|
|
|
|
|
|
try:
|
|
|
explainer = joblib.load(os.path.join(MODEL_DIR, 'shap_explainer.pkl'))
|
|
|
except:
|
|
|
explainer = None
|
|
|
|
|
|
print("模型加载完成!")
|
|
|
|
|
|
@app.route('/')
|
|
|
def home():
|
|
|
"""
|
|
|
主页
|
|
|
"""
|
|
|
return render_template_string('''
|
|
|
<!DOCTYPE html>
|
|
|
<html>
|
|
|
<head>
|
|
|
<title>可解释的信贷风险评估系统</title>
|
|
|
<meta charset="utf-8">
|
|
|
<style>
|
|
|
body { font-family: Arial, sans-serif; margin: 40px; background-color: #f5f5f5; }
|
|
|
.container { max-width: 800px; margin: 0 auto; background-color: white; padding: 20px; border-radius: 10px; box-shadow: 0 0 10px rgba(0,0,0,0.1); }
|
|
|
h1 { color: #333; text-align: center; }
|
|
|
form { margin: 20px 0; }
|
|
|
.form-group { margin-bottom: 15px; }
|
|
|
label { display: block; margin-bottom: 5px; font-weight: bold; }
|
|
|
input, select { width: 100%; padding: 8px; border: 1px solid #ddd; border-radius: 4px; box-sizing: border-box; }
|
|
|
button { background-color: #4CAF50; color: white; padding: 10px 20px; border: none; border-radius: 4px; cursor: pointer; width: 100%; }
|
|
|
button:hover { background-color: #45a049; }
|
|
|
.result { margin-top: 20px; padding: 15px; border-radius: 4px; }
|
|
|
.risk-high { background-color: #ffebee; border-left: 5px solid #f44336; }
|
|
|
.risk-medium { background-color: #fff3e0; border-left: 5px solid #ff9800; }
|
|
|
.risk-low { background-color: #e8f5e9; border-left: 5px solid #4caf50; }
|
|
|
.explanation { margin-top: 20px; padding: 15px; background-color: #e3f2fd; border-left: 5px solid #2196f3; border-radius: 0 4px 4px 0; }
|
|
|
</style>
|
|
|
</head>
|
|
|
<body>
|
|
|
<div class="container">
|
|
|
<h1>可解释的信贷风险评估系统</h1>
|
|
|
<form id="predictionForm">
|
|
|
<div class="form-group">
|
|
|
<label for="age">年龄:</label>
|
|
|
<input type="number" id="age" name="age" min="18" max="80" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="income">年收入:</label>
|
|
|
<input type="number" id="income" name="income" min="10000" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="employment_length">就业年限:</label>
|
|
|
<input type="number" id="employment_length" name="employment_length" min="0" max="40" step="0.1" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="loan_amount">贷款金额:</label>
|
|
|
<input type="number" id="loan_amount" name="loan_amount" min="1000" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="credit_score">信用评分:</label>
|
|
|
<input type="number" id="credit_score" name="credit_score" min="300" max="850" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="debt_to_income">债务收入比:</label>
|
|
|
<input type="number" id="debt_to_income" name="debt_to_income" min="0" max="1" step="0.01" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="num_credit_lines">信贷账户数量:</label>
|
|
|
<input type="number" id="num_credit_lines" name="num_credit_lines" min="0" max="15" required>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="education">教育水平:</label>
|
|
|
<select id="education" name="education" required>
|
|
|
<option value="High School">高中</option>
|
|
|
<option value="Bachelor">学士</option>
|
|
|
<option value="Master">硕士</option>
|
|
|
<option value="PhD">博士</option>
|
|
|
</select>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="home_ownership">房产情况:</label>
|
|
|
<select id="home_ownership" name="home_ownership" required>
|
|
|
<option value="Rent">租房</option>
|
|
|
<option value="Mortgage">抵押</option>
|
|
|
<option value="Own">自有</option>
|
|
|
<option value="Other">其他</option>
|
|
|
</select>
|
|
|
</div>
|
|
|
<div class="form-group">
|
|
|
<label for="loan_purpose">贷款目的:</label>
|
|
|
<select id="loan_purpose" name="loan_purpose" required>
|
|
|
<option value="Debt Consolidation">债务整合</option>
|
|
|
<option value="Home Improvement">房屋改善</option>
|
|
|
<option value="Business">商业</option>
|
|
|
<option value="Personal">个人</option>
|
|
|
<option value="Medical">医疗</option>
|
|
|
</select>
|
|
|
</div>
|
|
|
<button type="submit">评估风险</button>
|
|
|
</form>
|
|
|
<div id="result"></div>
|
|
|
</div>
|
|
|
<script>
|
|
|
document.getElementById('predictionForm').addEventListener('submit', function(e) {
|
|
|
e.preventDefault();
|
|
|
const formData = new FormData(this);
|
|
|
const data = {};
|
|
|
for (let [key, value] of formData.entries()) {
|
|
|
data[key] = value;
|
|
|
}
|
|
|
|
|
|
fetch('/predict', {
|
|
|
method: 'POST',
|
|
|
headers: {
|
|
|
'Content-Type': 'application/json',
|
|
|
},
|
|
|
body: JSON.stringify(data)
|
|
|
})
|
|
|
.then(response => response.json())
|
|
|
.then(data => {
|
|
|
let riskClass = 'risk-low';
|
|
|
if (data.risk_probability > 0.5) {
|
|
|
riskClass = 'risk-high';
|
|
|
} else if (data.risk_probability > 0.2) {
|
|
|
riskClass = 'risk-medium';
|
|
|
}
|
|
|
|
|
|
let explanationHtml = '';
|
|
|
if (data.explanation) {
|
|
|
explanationHtml = `
|
|
|
<div class="explanation">
|
|
|
<h3>决策解释</h3>
|
|
|
<p>以下特征对本次风险评估结果产生了重要影响：</p>
|
|
|
<ul>
|
|
|
${data.explanation.map(item => `<li>${item.feature}: ${item.effect}</li>`).join('')}
|
|
|
</ul>
|
|
|
</div>
|
|
|
`;
|
|
|
}
|
|
|
|
|
|
document.getElementById('result').innerHTML = `
|
|
|
<div class="result ${riskClass}">
|
|
|
<h3>风险评估结果</h3>
|
|
|
<p><strong>违约概率:</strong> ${(data.risk_probability * 100).toFixed(2)}%</p>
|
|
|
<p><strong>风险等级:</strong> ${riskClass === 'risk-high' ? '高风险' : riskClass === 'risk-medium' ? '中等风险' : '低风险'}</p>
|
|
|
<p><strong>建议:</strong> ${data.recommendation}</p>
|
|
|
</div>
|
|
|
${explanationHtml}
|
|
|
`;
|
|
|
})
|
|
|
.catch(error => {
|
|
|
console.error('Error:', error);
|
|
|
document.getElementById('result').innerHTML = '<div class="result risk-high"><p>评估出错，请重试。</p></div>';
|
|
|
});
|
|
|
});
|
|
|
</script>
|
|
|
</body>
|
|
|
</html>
|
|
|
''')
|
|
|
|
|
|
@app.route('/predict', methods=['POST'])
|
|
|
def predict():
|
|
|
"""
|
|
|
预测信贷风险
|
|
|
"""
|
|
|
global model, scaler, le_education, le_home, le_purpose, explainer
|
|
|
|
|
|
try:
|
|
|
# 获取请求数据
|
|
|
data = request.get_json()
|
|
|
|
|
|
# 创建DataFrame
|
|
|
df = pd.DataFrame([{
|
|
|
'age': float(data['age']),
|
|
|
'income': float(data['income']),
|
|
|
'employment_length': float(data['employment_length']),
|
|
|
'loan_amount': float(data['loan_amount']),
|
|
|
'credit_score': float(data['credit_score']),
|
|
|
'debt_to_income': float(data['debt_to_income']),
|
|
|
'num_credit_lines': int(data['num_credit_lines']),
|
|
|
'education': data['education'],
|
|
|
'home_ownership': data['home_ownership'],
|
|
|
'loan_purpose': data['loan_purpose'],
|
|
|
'default': 0 # 占位符
|
|
|
}])
|
|
|
|
|
|
# 删除目标变量
|
|
|
df = df.drop('default', axis=1)
|
|
|
|
|
|
# 编码分类变量
|
|
|
df['education'] = le_education.transform(df['education'])
|
|
|
df['home_ownership'] = le_home.transform(df['home_ownership'])
|
|
|
df['loan_purpose'] = le_purpose.transform(df['loan_purpose'])
|
|
|
|
|
|
# 标准化数值特征
|
|
|
df_scaled = scaler.transform(df)
|
|
|
df_scaled = pd.DataFrame(df_scaled, columns=df.columns)
|
|
|
|
|
|
# 预测
|
|
|
risk_probability = model.predict_proba(df_scaled)[0][1]
|
|
|
|
|
|
# 生成建议
|
|
|
if risk_probability > 0.5:
|
|
|
recommendation = "该客户违约风险较高，建议拒绝贷款申请或要求提供更多担保。"
|
|
|
elif risk_probability > 0.2:
|
|
|
recommendation = "该客户违约风险中等，建议谨慎审批，可考虑降低贷款额度或提高利率。"
|
|
|
else:
|
|
|
recommendation = "该客户违约风险较低，建议批准贷款申请。"
|
|
|
|
|
|
# 生成解释
|
|
|
explanation = None
|
|
|
if explainer is not None:
|
|
|
try:
|
|
|
# 计算SHAP值
|
|
|
shap_values = explainer.shap_values(df_scaled)
|
|
|
|
|
|
# 获取特征名称和SHAP值
|
|
|
feature_names = df.columns
|
|
|
shap_values_single = shap_values[0] if isinstance(shap_values, list) else shap_values
|
|
|
|
|
|
# 创建解释列表
|
|
|
explanation = []
|
|
|
for i, (feature, shap_val) in enumerate(zip(feature_names, shap_values_single[0])):
|
|
|
if abs(shap_val) > 0.01: # 只显示影响较大的特征
|
|
|
effect = "增加风险" if shap_val > 0 else "降低风险"
|
|
|
explanation.append({
|
|
|
"feature": feature,
|
|
|
"effect": effect,
|
|
|
"shap_value": shap_val
|
|
|
})
|
|
|
|
|
|
# 按SHAP值绝对值排序
|
|
|
explanation.sort(key=lambda x: abs(x["shap_value"]), reverse=True)
|
|
|
|
|
|
# 只保留前5个最重要的特征
|
|
|
explanation = explanation[:5]
|
|
|
|
|
|
# 格式化效果描述
|
|
|
for item in explanation:
|
|
|
item["effect"] = f"{item['effect']} (影响度: {abs(item['shap_value']):.3f})"
|
|
|
del item["shap_value"]
|
|
|
|
|
|
except Exception as e:
|
|
|
print(f"解释生成失败: {e}")
|
|
|
|
|
|
# 返回结果
|
|
|
result = {
|
|
|
'risk_probability': float(risk_probability),
|
|
|
'recommendation': recommendation
|
|
|
}
|
|
|
|
|
|
if explanation is not None:
|
|
|
result['explanation'] = explanation
|
|
|
|
|
|
return jsonify(result)
|
|
|
|
|
|
except Exception as e:
|
|
|
return jsonify({'error': str(e)}), 400
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
# 加载模型
|
|
|
load_model()
|
|
|
|
|
|
# 启动应用
|
|
|
app.run(debug=True, host='0.0.0.0', port=5000) |
