新增 SCADA 设备清洗 API；新增调试配置文件

main.py

@@ -4080,6 +4080,107 @@ async def fastapi_pressure_sensor_placement(
         raise HTTPException(status_code=500, detail=f"执行失败: {str(e)}")
 
 
+# 新增 SCADA 设备清洗接口
+@app.post("/scadadevicedatacleaning/")
+async def fastapi_scada_device_data_cleaning(
+    network: str = Query(...),
+    ids_list: List[str] = Query(...),
+    start_time: str = Query(...),
+    end_time: str = Query(...),
+    user_name: str = Query(...),
+) -> str:
+    import pandas as pd  # 假设可以使用 pandas 处理表格数据
+
+    item = {
+        "network": network,
+        "ids": ids_list,
+        "start_time": start_time,
+        "end_time": end_time,
+        "user_name": user_name,
+    }
+    query_ids_list = item["ids"][0].split(",")
+    # 先调用 query_SCADA_data_by_device_ID_and_timerange 获取原始数据
+    scada_data = influxdb_api.query_SCADA_data_by_device_ID_and_timerange(
+        query_ids_list=query_ids_list,
+        start_time=item["start_time"],
+        end_time=item["end_time"],
+    )
+
+    # 获取对应管网的所有 SCADA 设备信息
+    scada_device_info = influxdb_api.query_pg_scada_info(item["network"])
+    # 将列表转换为字典，以 device_id 为键
+    scada_device_info_dict = {info["id"]: info for info in scada_device_info}
+
+    # 按设备类型分组设备
+    type_groups = {}
+    for device_id in query_ids_list:
+        device_info = scada_device_info_dict.get(device_id, {})
+        device_type = device_info.get("type", "unknown")
+        if device_type not in type_groups:
+            type_groups[device_type] = []
+        type_groups[device_type].append(device_id)
+
+    # 批量处理每种类型的设备
+    for device_type, device_ids in type_groups.items():
+        if device_type not in ["pressure", "pipe_flow"]:
+            continue  # 跳过未知类型
+
+        # 过滤该类型的设备数据
+        type_scada_data = {
+            device_id: scada_data[device_id]
+            for device_id in device_ids
+            if device_id in scada_data
+        }
+
+        if not type_scada_data:
+            continue
+
+        # 假设所有设备的时间点相同，提取 time 列表
+        time_list = [record["time"] for record in next(iter(type_scada_data.values()))]
+
+        # 创建 DataFrame，第一列是 time，然后是每个设备的 value 列
+        df = pd.DataFrame({"time": time_list})
+        for device_id in device_ids:
+            if device_id in type_scada_data:
+                values = [record["value"] for record in type_scada_data[device_id]]
+                df[device_id] = values
+
+        # 移除 time 列，准备输入给清洗方法（清洗方法期望 value 表格）
+        value_df = df.drop(columns=["time"])
+
+        # 调用清洗方法
+        if device_type == "pressure":
+            cleaned_value_df = api_ex.Pdataclean.clean_pressure_data_dict_km(value_df)
+        elif device_type == "pipe_flow":
+            cleaned_value_df = api_ex.Fdataclean.clean_flow_data_dict(value_df)
+
+            # 添加 time 列到首列
+        cleaned_value_df = pd.DataFrame(cleaned_value_df)
+        # 只选择以 '_cleaned' 结尾的清洗数据列
+        cleaned_columns = [
+            col for col in cleaned_value_df.columns if col.endswith("_cleaned")
+        ]
+        cleaned_value_df = cleaned_value_df[cleaned_columns]
+        # 重命名列,移除 '_cleaned' 后缀
+        cleaned_value_df = cleaned_value_df.rename(
+            columns={
+                col: col.replace("_cleaned", "") for col in cleaned_value_df.columns
+            }
+        )
+        cleaned_df = pd.concat([df["time"], cleaned_value_df], axis=1)
+
+        # 调试输出,确认列名
+        print(f"清洗后的列名: {cleaned_df.columns.tolist()}")
+
+        # 将清洗后的数据写回数据库
+        influxdb_api.import_multicolumn_data_from_dict(
+            data_dict=cleaned_df.to_dict("list"),  # 转换为 {column_name: [values]} 格式
+            raw=False,
+        )
+
+    return "success"
+
+
 class Item(BaseModel):
     str_info: str
     dict_info: Optional[dict] = None