Data Processing
计算数值列的变异系数(CV),用于衡量相对变异性
用三种语言从你的代码中调用此工具。
curl -X POST 'https://api.elysiatools.com/zh/api/tools/coefficient-of-variation' \
-H 'Content-Type: application/json' \
-d '{"csvData":"在此输入您的CSV数据...\n\n示例:\n产品,销售额,销售数量,利润,价格\nA,1500.50,120,450.25,12.50\nB,2300.75,180,690.20,12.80\nC,890.25,95,267.15,9.35\nD,3200.00,210,960.50,15.25\nE,1750.80,155,525.30,11.30","selectedColumns":"逗号分隔的列名。留空则自动检测数值列。","hasHeader":true,"includeInterpretation":true,"outputFormat":"report"}'以 JSON 形式 POST 提交输入参数。文件类型参数需先单独上传。
POST https://api.elysiatools.com/zh/api/tools/coefficient-of-variation| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| csvData | textarea | 是 | — |
| selectedColumns | text | 否 | 指定要分析的列。如果留空,所有数值列将被自动检测和分析。 |
| hasHeader | checkbox | 否 | 将第一行作为列标题 |
| includeInterpretation | checkbox | 否 | 包含CV值的解释(低、中、高变异性) |
| outputFormat | select | 是 | — |
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-coefficient-of-variation": {
"name": "coefficient-of-variation",
"description": "计算数值列的变异系数(CV),用于衡量相对变异性",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=coefficient-of-variation",
"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": "coefficient-of-variation",
"arguments": {
"csvData": "在此输入您的CSV数据...\n\n示例:\n产品,销售额,销售数量,利润,价格\nA,1500.50,120,450.25,12.50\nB,2300.75,180,690.20,12.80\nC,890.25,95,267.15,9.35\nD,3200.00,210,960.50,15.25\nE,1750.80,155,525.30,11.30",
"selectedColumns": "逗号分隔的列名。留空则自动检测数值列。",
"hasHeader": true,
"includeInterpretation": true,
"outputFormat": "report"
}
}
}有问题或反馈?请联系 [email protected]
文本结果
{
"result": "Processed text content",
"error": "Error message (optional)",
"message": "Notification message (optional)",
"metadata": {
"key": "value"
}
}