Data Analysis
Friedman 与 Iman-Davenport 检验(精确 p 值)、平均排名、Nemenyi 临界差与经典 CD 图(含无显著差异 clique),另可叠加对对照模型的 Bonferroni-Dunn。
用三种语言从你的代码中调用此工具。
curl -X POST 'http://127.0.0.1:3003/zh/api/tools/nemenyi-critical-difference-friedman-rank-plotter' \
-H 'Content-Type: application/json' \
-d '{"matrix":"dataset, AdaBoost, SVM, kNN, C4.5\nd1, 0.95, 0.83, 0.76, 0.69\nd2, 0.96, 0.77, 0.84, 0.70\nd3, 0.94, 0.82, 0.75, 0.68\nd4, 0.95, 0.76, 0.83, 0.69\nd5, 0.96, 0.84, 0.77, 0.70\nd6, 0.94, 0.75, 0.82, 0.68\nd7, 0.95, 0.83, 0.76, 0.69\nd8, 0.96, 0.77, 0.84, 0.70\nd9, 0.94, 0.82, 0.75, 0.68\nd10, 0.95, 0.76, 0.83, 0.69\nd11, 0.96, 0.84, 0.77, 0.70\nd12, 0.94, 0.75, 0.82, 0.68","direction":"higher","alpha":"0.05","posthoc":"nemenyi","control":"exact column name of the baseline model"}'以 JSON 形式 POST 提交输入参数。文件类型参数需先单独上传。
POST http://127.0.0.1:3003/zh/api/tools/nemenyi-critical-difference-friedman-rank-plotter| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| matrix | textarea | 是 | — |
| direction | select | 是 | — |
| alpha | select | 是 | — |
| posthoc | select | 是 | — |
| control | text | 否 | — |
HTML 结果
{
"result": "<div>Processed HTML content</div>",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}将此工具加入你的 Model Context Protocol 服务,让 AI 智能体可以列出并调用它。
将以下内容加入你的 MCP 客户端配置:
{
"mcpServers": {
"elysiatools-nemenyi-critical-difference-friedman-rank-plotter": {
"name": "nemenyi-critical-difference-friedman-rank-plotter",
"description": "Friedman 与 Iman-Davenport 检验(精确 p 值)、平均排名、Nemenyi 临界差与经典 CD 图(含无显著差异 clique),另可叠加对对照模型的 Bonferroni-Dunn。",
"baseUrl": "http://127.0.0.1:3003/mcp/sse?toolId=nemenyi-critical-difference-friedman-rank-plotter",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}连接到 SSE 端点后,列出已开放的工具:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}通过工具 id 调用,参数由其参数表构建:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "nemenyi-critical-difference-friedman-rank-plotter",
"arguments": {
"matrix": "dataset, AdaBoost, SVM, kNN, C4.5\nd1, 0.95, 0.83, 0.76, 0.69\nd2, 0.96, 0.77, 0.84, 0.70\nd3, 0.94, 0.82, 0.75, 0.68\nd4, 0.95, 0.76, 0.83, 0.69\nd5, 0.96, 0.84, 0.77, 0.70\nd6, 0.94, 0.75, 0.82, 0.68\nd7, 0.95, 0.83, 0.76, 0.69\nd8, 0.96, 0.77, 0.84, 0.70\nd9, 0.94, 0.82, 0.75, 0.68\nd10, 0.95, 0.76, 0.83, 0.69\nd11, 0.96, 0.84, 0.77, 0.70\nd12, 0.94, 0.75, 0.82, 0.68",
"direction": "higher",
"alpha": "0.05",
"posthoc": "nemenyi",
"control": "exact column name of the baseline model"
}
}
}有问题或反馈?请联系 [email protected]