Data Analysis
从 CSV 或 JSON 时间序列数据中预测未来数期，并在一份报告中查看趋势、季节项和残差分解
用三种语言从你的代码中调用此工具。
# 1) Upload each file first → returns { filePath }
curl -X POST 'https://api.elysiatools.com/upload/time-series-forecast-seasonality-analyzer' \
-F 'file=@/path/to/dataFile.ext'
# 2) Call the tool with the returned filePath values
curl -X POST 'https://api.elysiatools.com/zh/api/tools/time-series-forecast-seasonality-analyzer' \
-F 'seriesInput=timestamp,value
2026-01-01,120
2026-01-02,128
2026-01-03,132
2026-01-04,125
2026-01-05,140
2026-01-06,148
2026-01-07,145
2026-01-08,126
2026-01-09,133
2026-01-10,138' \
-F 'dataFile=/path/to/file.ext' \
-F 'timestampColumn=timestamp' \
-F 'valueColumn=value' \
-F 'model=arima' \
-F 'forecastPeriods=8' \
-F 'seasonLength=7' \
-F 'confidenceLevel=0.95' \
-F 'exportFormat=json'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/time-series-forecast-seasonality-analyzer| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| seriesInput | textarea | 否 | — |
| dataFile | file需先上传 | 否 | — |
| timestampColumn | text | 是 | — |
| valueColumn | text | 是 | — |
| model | select | 否 | — |
| forecastPeriods | number | 否 | — |
| seasonLength | number | 否 | — |
| confidenceLevel | select | 否 | — |
| exportFormat | select | 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-time-series-forecast-seasonality-analyzer": {
"name": "time-series-forecast-seasonality-analyzer",
"description": "从 CSV 或 JSON 时间序列数据中预测未来数期，并在一份报告中查看趋势、季节项和残差分解",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=time-series-forecast-seasonality-analyzer",
"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": "time-series-forecast-seasonality-analyzer",
"arguments": {
"seriesInput": "timestamp,value\n2026-01-01,120\n2026-01-02,128\n2026-01-03,132\n2026-01-04,125\n2026-01-05,140\n2026-01-06,148\n2026-01-07,145\n2026-01-08,126\n2026-01-09,133\n2026-01-10,138",
"dataFile": "https://example.com/file.ext",
"timestampColumn": "timestamp",
"valueColumn": "value",
"model": "arima",
"forecastPeriods": 8,
"seasonLength": 7,
"confidenceLevel": "0.95",
"exportFormat": "json"
}
}
}有问题或反馈？请联系 [email protected]