feat(dc): Complete Tool C quick action buttons Phase 1-2 - 7 functions
Summary: - Implement 7 quick action functions (filter, recode, binning, conditional, dropna, compute, pivot) - Refactor to pre-written Python functions architecture (stable and secure) - Add 7 Python operations modules with full type hints - Add 7 frontend Dialog components with user-friendly UI - Fix NaN serialization issues and auto type conversion - Update all related documentation Technical Details: - Python: operations/ module (filter.py, recode.py, binning.py, conditional.py, dropna.py, compute.py, pivot.py) - Backend: QuickActionService.ts with 7 execute methods - Frontend: 7 Dialog components with complete validation - Toolbar: Enable 7 quick action buttons Status: Phase 1-2 completed, basic testing passed, ready for further testing
This commit is contained in:
319
backend/test-tool-c-advanced-scenarios.mjs
Normal file
319
backend/test-tool-c-advanced-scenarios.mjs
Normal file
@@ -0,0 +1,319 @@
|
||||
/**
|
||||
* 工具C - 高级场景测试（含多重插补）
|
||||
*
|
||||
* 测试复杂的数据清洗场景：
|
||||
* - 多条件筛选+分组统计
|
||||
* - 时间序列计算
|
||||
* - 多重插补（Multiple Imputation）
|
||||
* - 复杂分类逻辑
|
||||
* - 数据探索（不生成代码）
|
||||
*
|
||||
* 运行命令：node test-tool-c-advanced-scenarios.mjs
|
||||
*/
|
||||
|
||||
import fetch from 'node-fetch';
|
||||
import FormData from 'form-data';
|
||||
import fs from 'fs';
|
||||
import path from 'path';
|
||||
import { fileURLToPath } from 'url';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
|
||||
// ==================== 配置 ====================
|
||||
|
||||
const API_BASE = 'http://localhost:3000/api/v1/dc/tool-c';
|
||||
const TEST_FILE = path.join(__dirname, 'uploads', 'test_data_advanced.xlsx'); // 需要准备测试数据
|
||||
|
||||
// ==================== 颜色输出 ====================
|
||||
|
||||
const colors = {
|
||||
reset: '\x1b[0m',
|
||||
bright: '\x1b[1m',
|
||||
red: '\x1b[31m',
|
||||
green: '\x1b[32m',
|
||||
yellow: '\x1b[33m',
|
||||
blue: '\x1b[34m',
|
||||
magenta: '\x1b[35m',
|
||||
cyan: '\x1b[36m',
|
||||
};
|
||||
|
||||
function log(message, color = 'reset') {
|
||||
console.log(`${colors[color]}${message}${colors.reset}`);
|
||||
}
|
||||
|
||||
// ==================== 高级测试场景 ====================
|
||||
|
||||
const advancedScenarios = [
|
||||
{
|
||||
id: 1,
|
||||
name: '多条件筛选+分组统计',
|
||||
message: '筛选出年龄≥18岁、性别为女、BMI≥28的患者，按年龄段（18-30, 30-50, 50+）分组统计人数',
|
||||
description: '测试复杂的多条件筛选和分组统计功能',
|
||||
expectedFeatures: ['条件筛选', 'BMI过滤', '年龄分组', 'value_counts'],
|
||||
},
|
||||
{
|
||||
id: 2,
|
||||
name: '时间序列计算',
|
||||
message: '计算每位患者的首次就诊日期和最近就诊日期，以及总就诊次数',
|
||||
description: '测试日期时间处理和分组聚合',
|
||||
expectedFeatures: ['pd.to_datetime', 'groupby', 'agg', '多列聚合'],
|
||||
},
|
||||
{
|
||||
id: 3,
|
||||
name: '多重插补（Multiple Imputation）- 基础版',
|
||||
message: '对年龄列的缺失值进行多重插补：生成5个插补数据集，每个数据集用不同的随机种子填补缺失值（基于正态分布）',
|
||||
description: '测试统计学中的多重插补方法（基础实现）',
|
||||
expectedFeatures: ['np.random.seed', 'np.random.normal', '循环生成多个数据集'],
|
||||
multipleOutputs: true,
|
||||
},
|
||||
{
|
||||
id: 4,
|
||||
name: '多重插补（MICE算法模拟）',
|
||||
message: '对年龄、BMI、血压三列进行链式方程多重插补（MICE）：先用中位数初始填补，再迭代3轮，每轮用其他列预测填补当前列',
|
||||
description: '测试高级多重插补算法（MICE迭代填补）',
|
||||
expectedFeatures: ['多轮迭代', 'fillna', '分列填补', '链式方程'],
|
||||
},
|
||||
{
|
||||
id: 5,
|
||||
name: '复杂分类逻辑',
|
||||
message: '根据BMI和血压综合判断健康等级：BMI<24且收缩压<140为健康，BMI 24-28或收缩压140-160为预警，其他为危险',
|
||||
description: '测试多条件嵌套逻辑判断',
|
||||
expectedFeatures: ['np.where', '嵌套条件', '多变量判断'],
|
||||
},
|
||||
{
|
||||
id: 6,
|
||||
name: '数据探索（不生成代码）',
|
||||
message: '性别列有多少缺失值？年龄列的平均值是多少？BMI列的中位数是多少？',
|
||||
description: '测试数据探索问答能力（应直接回答，不生成代码）',
|
||||
expectedFeatures: ['直接回答', '不生成代码'],
|
||||
},
|
||||
{
|
||||
id: 7,
|
||||
name: '分层多重插补',
|
||||
message: '对年龄列的缺失值进行分层多重插补：按性别分组，男性用男性年龄均值填补，女性用女性年龄均值填补，生成3个插补数据集',
|
||||
description: '测试分层多重插补（考虑分组）',
|
||||
expectedFeatures: ['groupby', 'transform', '分组填补', '多次生成'],
|
||||
multipleOutputs: true,
|
||||
},
|
||||
{
|
||||
id: 8,
|
||||
name: '缺失模式分析',
|
||||
message: '分析数据集的缺失模式：统计每一列的缺失率，找出缺失率超过20%的列，并标记哪些行缺失值超过3个',
|
||||
description: '测试缺失值分析功能',
|
||||
expectedFeatures: ['isna()', 'sum()', 'mean()', '条件判断'],
|
||||
},
|
||||
];
|
||||
|
||||
// ==================== 辅助函数 ====================
|
||||
|
||||
async function uploadFile() {
|
||||
log('\n📤 步骤1: 上传测试文件...', 'cyan');
|
||||
|
||||
if (!fs.existsSync(TEST_FILE)) {
|
||||
log(`❌ 测试文件不存在: ${TEST_FILE}`, 'red');
|
||||
log('💡 提示：请创建测试数据文件，包含以下列：', 'yellow');
|
||||
log(' - patient_id（患者ID）', 'yellow');
|
||||
log(' - gender（性别：男/女）', 'yellow');
|
||||
log(' - age（年龄，带缺失值）', 'yellow');
|
||||
log(' - BMI（带缺失值）', 'yellow');
|
||||
log(' - systolic_bp（收缩压，带缺失值）', 'yellow');
|
||||
log(' - visit_date（就诊日期）', 'yellow');
|
||||
return null;
|
||||
}
|
||||
|
||||
const formData = new FormData();
|
||||
formData.append('file', fs.createReadStream(TEST_FILE));
|
||||
|
||||
const response = await fetch(`${API_BASE}/sessions/upload`, {
|
||||
method: 'POST',
|
||||
body: formData,
|
||||
});
|
||||
|
||||
const result = await response.json();
|
||||
|
||||
if (result.success) {
|
||||
log(`✅ 上传成功: Session ID = ${result.data.sessionId}`, 'green');
|
||||
log(` 文件: ${result.data.fileName}`, 'bright');
|
||||
log(` 数据: ${result.data.totalRows} 行 × ${result.data.totalCols} 列`, 'bright');
|
||||
return result.data.sessionId;
|
||||
} else {
|
||||
log(`❌ 上传失败: ${result.error}`, 'red');
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
async function testScenario(sessionId, scenario) {
|
||||
log(`\n${'='.repeat(80)}`, 'magenta');
|
||||
log(`📋 场景${scenario.id}: ${scenario.name}`, 'bright');
|
||||
log(`📝 描述: ${scenario.description}`, 'cyan');
|
||||
log(`💬 用户输入: "${scenario.message}"`, 'yellow');
|
||||
log(`${'='.repeat(80)}`, 'magenta');
|
||||
|
||||
try {
|
||||
const startTime = Date.now();
|
||||
|
||||
// 调用流式API
|
||||
const response = await fetch(`${API_BASE}/ai/stream-process`, {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({
|
||||
sessionId,
|
||||
message: scenario.message,
|
||||
maxRetries: 3,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`HTTP ${response.status}`);
|
||||
}
|
||||
|
||||
log('\n📡 流式响应:', 'cyan');
|
||||
let stepCount = 0;
|
||||
let lastStep = null;
|
||||
|
||||
// 读取SSE流
|
||||
const reader = response.body;
|
||||
let buffer = '';
|
||||
|
||||
for await (const chunk of reader) {
|
||||
buffer += chunk.toString();
|
||||
const lines = buffer.split('\n');
|
||||
buffer = lines.pop() || '';
|
||||
|
||||
for (const line of lines) {
|
||||
if (line.startsWith('data: ')) {
|
||||
const data = line.slice(6);
|
||||
|
||||
if (data === '[DONE]') {
|
||||
const duration = ((Date.now() - startTime) / 1000).toFixed(2);
|
||||
log(`\n✅ 场景${scenario.id}完成 (耗时: ${duration}秒)`, 'green');
|
||||
|
||||
// 分析结果
|
||||
if (lastStep) {
|
||||
if (lastStep.status === 'success') {
|
||||
log(` ✓ 执行成功`, 'green');
|
||||
if (lastStep.retryCount && lastStep.retryCount > 0) {
|
||||
log(` ⚠️ 重试次数: ${lastStep.retryCount + 1}`, 'yellow');
|
||||
}
|
||||
} else if (lastStep.status === 'failed') {
|
||||
log(` ✗ 执行失败: ${lastStep.error}`, 'red');
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
try {
|
||||
const step = JSON.parse(data);
|
||||
stepCount++;
|
||||
lastStep = step;
|
||||
|
||||
// 显示步骤（简化）
|
||||
const icon = step.status === 'success' ? '✅' :
|
||||
step.status === 'failed' ? '❌' :
|
||||
step.status === 'retrying' ? '🔄' : '⏳';
|
||||
log(` ${icon} Step ${step.step}: ${step.message}`, 'bright');
|
||||
|
||||
// 显示代码（Step 3）
|
||||
if (step.stepName === 'show_code' && step.data?.code) {
|
||||
log(`\n📝 生成的代码:`, 'cyan');
|
||||
console.log(step.data.code);
|
||||
log(`\n💡 解释: ${step.data.explanation}\n`, 'yellow');
|
||||
}
|
||||
|
||||
// 显示错误
|
||||
if (step.error) {
|
||||
log(` ⚠️ 错误: ${step.error.substring(0, 100)}...`, 'red');
|
||||
}
|
||||
} catch (e) {
|
||||
// 忽略解析错误
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return { success: true, steps: stepCount };
|
||||
} catch (error) {
|
||||
log(`\n❌ 场景${scenario.id}失败: ${error.message}`, 'red');
|
||||
return { success: false, error: error.message };
|
||||
}
|
||||
}
|
||||
|
||||
// ==================== 主测试函数 ====================
|
||||
|
||||
async function runAdvancedTests() {
|
||||
log('\n' + '='.repeat(80), 'bright');
|
||||
log('🧪 工具C高级场景测试（含多重插补）', 'bright');
|
||||
log('='.repeat(80) + '\n', 'bright');
|
||||
|
||||
// Step 1: 上传文件
|
||||
const sessionId = await uploadFile();
|
||||
if (!sessionId) {
|
||||
log('\n❌ 上传失败，测试终止', 'red');
|
||||
return;
|
||||
}
|
||||
|
||||
// Step 2: 运行所有场景
|
||||
const results = [];
|
||||
for (const scenario of advancedScenarios) {
|
||||
const result = await testScenario(sessionId, scenario);
|
||||
results.push({ scenario: scenario.name, ...result });
|
||||
|
||||
// 等待1秒，避免请求过快
|
||||
await new Promise(resolve => setTimeout(resolve, 1000));
|
||||
}
|
||||
|
||||
// Step 3: 生成测试报告
|
||||
log('\n' + '='.repeat(80), 'bright');
|
||||
log('📊 测试报告', 'bright');
|
||||
log('='.repeat(80), 'bright');
|
||||
|
||||
const successCount = results.filter(r => r.success).length;
|
||||
const failCount = results.filter(r => !r.success).length;
|
||||
|
||||
log(`\n✅ 成功: ${successCount}/${results.length}`, 'green');
|
||||
log(`❌ 失败: ${failCount}/${results.length}`, failCount > 0 ? 'red' : 'green');
|
||||
|
||||
log('\n📋 详细结果:', 'cyan');
|
||||
results.forEach((r, i) => {
|
||||
const icon = r.success ? '✅' : '❌';
|
||||
log(` ${icon} 场景${i + 1}: ${r.scenario}`, r.success ? 'green' : 'red');
|
||||
});
|
||||
|
||||
// Step 4: 测试导出功能
|
||||
log('\n📥 测试导出功能...', 'cyan');
|
||||
try {
|
||||
const exportResponse = await fetch(`${API_BASE}/sessions/${sessionId}/export`);
|
||||
if (exportResponse.ok) {
|
||||
const buffer = await exportResponse.arrayBuffer();
|
||||
const exportPath = path.join(__dirname, 'test-output', `export_${Date.now()}.xlsx`);
|
||||
|
||||
// 确保目录存在
|
||||
const dir = path.dirname(exportPath);
|
||||
if (!fs.existsSync(dir)) {
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
}
|
||||
|
||||
fs.writeFileSync(exportPath, Buffer.from(buffer));
|
||||
log(`✅ 导出成功: ${exportPath} (${(buffer.byteLength / 1024).toFixed(2)}KB)`, 'green');
|
||||
} else {
|
||||
log(`❌ 导出失败: HTTP ${exportResponse.status}`, 'red');
|
||||
}
|
||||
} catch (error) {
|
||||
log(`❌ 导出异常: ${error.message}`, 'red');
|
||||
}
|
||||
|
||||
log('\n' + '='.repeat(80), 'bright');
|
||||
log('🎉 测试完成！', 'bright');
|
||||
log('='.repeat(80) + '\n', 'bright');
|
||||
}
|
||||
|
||||
// ==================== 执行测试 ====================
|
||||
|
||||
runAdvancedTests().catch(error => {
|
||||
log(`\n❌ 测试异常: ${error.message}`, 'red');
|
||||
console.error(error);
|
||||
process.exit(1);
|
||||
});
|
||||
|
||||
|
||||
Reference in New Issue
Block a user