Sprint 1-3 Completed (Backend + Frontend): Backend (Sprint 1-2): - Implement 5-layer Agent framework (Query->Planner->Executor->Tools->Reflection) - Create agent_schema with 6 tables (agent_definitions, stages, prompts, sessions, traces, reflexion_rules) - Create protocol_schema with 2 tables (protocol_contexts, protocol_generations) - Implement Protocol Agent core services (Orchestrator, ContextService, PromptBuilder) - Integrate LLM service adapter (DeepSeek/Qwen/GPT-5/Claude) - 6 API endpoints with full authentication - 10/10 API tests passed Frontend (Sprint 3): - Add Protocol Agent entry in AgentHub (indigo theme card) - Implement ProtocolAgentPage with 3-column layout - Collapsible sidebar (Gemini style, 48px <-> 280px) - StatePanel with 5 stage cards (scientific_question, pico, study_design, sample_size, endpoints) - ChatArea with sync button and action cards integration - 100% prototype design restoration (608 lines CSS) - Detailed endpoints structure: baseline, exposure, outcomes, confounders Features: - 5-stage dialogue flow for research protocol design - Conversation-driven interaction with sync-to-protocol button - Real-time context state management - One-click protocol generation button (UI ready, backend pending) Database: - agent_schema: 6 tables for reusable Agent framework - protocol_schema: 2 tables for Protocol Agent - Seed data: 1 agent + 5 stages + 9 prompts + 4 reflexion rules Code Stats: - Backend: 13 files, 4338 lines - Frontend: 14 files, 2071 lines - Total: 27 files, 6409 lines Status: MVP core functionality completed, pending frontend-backend integration testing Next: Sprint 4 - One-click protocol generation + Word export
317 lines
6.0 KiB
Markdown
317 lines
6.0 KiB
Markdown
# 缺失值处理功能 - 自动化测试说明
|
||
|
||
## 📋 测试脚本功能
|
||
|
||
自动化测试脚本 `test_fillna_operations.py` 会自动测试缺失值处理的所有功能,包括:
|
||
|
||
### ✅ 18个测试用例
|
||
|
||
#### 基础测试(6个)
|
||
1. 均值填补数值列
|
||
2. 中位数填补偏态分布列
|
||
3. 众数填补分类列
|
||
4. 固定值填补(0)
|
||
5. 前向填充(ffill)⭐
|
||
6. 后向填充(bfill)⭐
|
||
|
||
#### MICE测试(4个)
|
||
7. MICE填补单列
|
||
8. MICE填补多列
|
||
9. MICE填补 - 不同迭代次数
|
||
10. MICE填补 - 自定义随机种子
|
||
|
||
#### 边界测试(4个)
|
||
11. 100%缺失的列
|
||
12. 0%缺失的列(无需填补)
|
||
13. 统计API功能
|
||
14. 特殊字符列名处理
|
||
|
||
#### 数据类型测试(4个)
|
||
15. 数值列(int/float)
|
||
16. 分类列(字符串)
|
||
17. 混合类型列
|
||
18. 性能测试(1000行)
|
||
|
||
---
|
||
|
||
## 🚀 快速开始
|
||
|
||
### 步骤1: 启动Python服务
|
||
|
||
```bash
|
||
cd AIclinicalresearch/extraction_service
|
||
python main.py
|
||
```
|
||
|
||
**确认服务启动成功**:看到 `Application startup complete` 或访问 `http://localhost:8001/health`
|
||
|
||
---
|
||
|
||
### 步骤2: 运行测试脚本
|
||
|
||
**方法1 - 在项目根目录运行**:
|
||
```bash
|
||
cd AIclinicalresearch
|
||
python tests/test_fillna_operations.py
|
||
```
|
||
|
||
**方法2 - 在tests目录运行**:
|
||
```bash
|
||
cd AIclinicalresearch/tests
|
||
python test_fillna_operations.py
|
||
```
|
||
|
||
---
|
||
|
||
## 📊 测试输出示例
|
||
|
||
```
|
||
╔══════════════════════════════════════════════════════════════════╗
|
||
║ ║
|
||
║ 缺失值处理功能 - 自动化测试脚本 v1.0 ║
|
||
║ ║
|
||
║ 测试内容: 18个测试用例 ║
|
||
║ - 6个基础填补测试 ║
|
||
║ - 4个MICE测试 ║
|
||
║ - 4个边界测试 ║
|
||
║ - 4个数据类型测试 ║
|
||
║ ║
|
||
╚══════════════════════════════════════════════════════════════════╝
|
||
|
||
================================================================================
|
||
缺失值处理功能 - 自动化测试
|
||
================================================================================
|
||
|
||
ℹ️ 检查Python服务状态...
|
||
✅ Python服务运行正常
|
||
|
||
ℹ️ 生成测试数据...
|
||
✅ 生成了 5 个测试数据集
|
||
• numeric: 100 行 × 4 列
|
||
• categorical: 100 行 × 3 列
|
||
• timeseries: 100 行 × 3 列
|
||
• edge_cases: 10 行 × 4 列
|
||
• mixed: 100 行 × 4 列
|
||
|
||
[1/18] 均值填补数值列
|
||
--------------------------------------------------------------------------------
|
||
✅ 均值填补成功,缺失值已全部填补
|
||
✅ ✓ 新列位置正确(紧邻原列)
|
||
|
||
[2/18] 中位数填补偏态分布列
|
||
--------------------------------------------------------------------------------
|
||
✅ 中位数填补成功
|
||
|
||
...
|
||
|
||
================================================================================
|
||
测试总结
|
||
================================================================================
|
||
|
||
总测试数: 18
|
||
✅ 通过: 18
|
||
❌ 失败: 0
|
||
通过率: 100.0%
|
||
总耗时: 45.32秒
|
||
|
||
🎉 所有测试通过!
|
||
```
|
||
|
||
---
|
||
|
||
## 🔧 依赖安装
|
||
|
||
测试脚本需要以下Python包:
|
||
|
||
```bash
|
||
pip install pandas numpy requests
|
||
```
|
||
|
||
这些包在 `extraction_service/requirements.txt` 中已经包含。
|
||
|
||
---
|
||
|
||
## ⚙️ 配置
|
||
|
||
### 修改服务地址
|
||
|
||
如果Python服务不在默认端口 `8001`,修改脚本开头:
|
||
|
||
```python
|
||
PYTHON_SERVICE_URL = "http://localhost:8001" # 修改为你的端口
|
||
```
|
||
|
||
---
|
||
|
||
## 📝 测试结果说明
|
||
|
||
### 颜色含义
|
||
- 🟢 **绿色** (✅): 测试通过
|
||
- 🔴 **红色** (❌): 测试失败
|
||
- 🟡 **黄色** (⚠️): 警告信息
|
||
- 🔵 **蓝色** (ℹ️): 提示信息
|
||
|
||
### 通过标准
|
||
- ✅ API返回成功
|
||
- ✅ 新列创建正确
|
||
- ✅ 缺失值被正确填补
|
||
- ✅ 新列位置在原列旁边
|
||
|
||
---
|
||
|
||
## 🐛 常见问题
|
||
|
||
### 1. 无法连接到Python服务
|
||
**错误**: `无法连接到Python服务: Connection refused`
|
||
|
||
**解决**:
|
||
```bash
|
||
# 确保Python服务已启动
|
||
cd AIclinicalresearch/extraction_service
|
||
python main.py
|
||
```
|
||
|
||
---
|
||
|
||
### 2. 模块未找到
|
||
**错误**: `ModuleNotFoundError: No module named 'pandas'`
|
||
|
||
**解决**:
|
||
```bash
|
||
pip install pandas numpy requests
|
||
```
|
||
|
||
---
|
||
|
||
### 3. 部分测试失败
|
||
**现象**: 通过率 < 100%
|
||
|
||
**处理**:
|
||
1. 查看失败测试的具体错误信息
|
||
2. 检查Python服务日志
|
||
3. 确认数据格式是否正确
|
||
|
||
---
|
||
|
||
## 🔍 调试技巧
|
||
|
||
### 1. 单独运行某个测试
|
||
|
||
修改 `test_fillna_operations.py` 的 `run_all_tests()` 方法,只保留需要测试的用例:
|
||
|
||
```python
|
||
tests = [
|
||
(self.test_1_mean_fill, "基础"), # 只测试这一个
|
||
]
|
||
```
|
||
|
||
### 2. 查看详细日志
|
||
|
||
在测试函数中添加:
|
||
|
||
```python
|
||
print(json.dumps(result, indent=2, ensure_ascii=False))
|
||
```
|
||
|
||
### 3. 保存测试数据
|
||
|
||
在 `generate_test_data()` 中添加:
|
||
|
||
```python
|
||
df_numeric.to_excel('test_data/numeric_test.xlsx', index=False)
|
||
```
|
||
|
||
---
|
||
|
||
## 📈 性能基准
|
||
|
||
**参考值**(在普通笔记本上):
|
||
|
||
- **简单填补**(均值/中位数/众数): < 1秒
|
||
- **前向/后向填充**: < 1秒
|
||
- **MICE填补 100行**: 2-5秒
|
||
- **MICE填补 1000行**: 20-40秒
|
||
- **全部18个测试**: 45-60秒
|
||
|
||
---
|
||
|
||
## 🎯 下一步
|
||
|
||
测试通过后:
|
||
1. 在真实数据上测试
|
||
2. 测试前端集成
|
||
3. 性能优化(如有需要)
|
||
|
||
---
|
||
|
||
## 📞 技术支持
|
||
|
||
如有问题,请检查:
|
||
1. Python服务日志
|
||
2. 测试脚本输出
|
||
3. 开发文档:`工具C_缺失值处理_开发完成说明.md`
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|