add api for data clean && sensor_placement

influxdb_api.py

@@ -3513,6 +3513,129 @@ def delete_data(delete_date: str, bucket: str) -> None:
 
     delete_api: DeleteApi = client.delete_api()
     delete_api.delete(start=start_time, stop=stop_time, predicate=predicate, bucket=bucket)
+
+    #2025/08/18 从文件导入scada数据，xkl
+def import_data_from_file(file_path: str, bucket: str = "SCADA_data") -> None:
+    """
+    从指定的CSV文件导入数据到InfluxDB的指定bucket中。
+    :param file_path: CSV文件的路径
+    :param bucket: 数据存储的 bucket 名称，默认值为 "SCADA_data"
+    :return:
+    """
+    client = get_new_client()
+    if not client.ping():
+        print("{} -- Failed to connect to InfluxDB.".format(datetime.now().strftime('%Y-%m-%d %H:%M:%S')))
+
+    #清空指定bucket的数据
+    # delete_api = DeleteApi(client)
+    # start = "1970-01-01T00:00:00Z"
+    # stop = "2100-01-01T00:00:00Z"
+    # delete_api.delete(start, stop, '', bucket="SCADA_data", org="TJWATERORG")
+
+    df = pd.read_csv(file_path)
+    write_api = client.write_api(write_options=SYNCHRONOUS)
+    points_to_write = []
+    for _, row in df.iterrows():
+        scada_id = row['ScadaId']
+        value = row['Value']
+        time_str = row['Time']
+        date_str = str(time_str)[:10]  # 取前10位作为日期
+        try:
+            raw_value = float(value)
+        except (ValueError, TypeError):
+            raw_value = 0.0
+        point = Point("SCADA") \
+            .tag("date", date_str) \
+            .tag("description", None) \
+            .tag("device_ID", scada_id) \
+            .field("monitored_value", raw_value) \
+            .field("datacleaning_value", 0.0) \
+            .field("simulation_value", 0.0) \
+            .time(time_str, write_precision='s')
+        points_to_write.append(point)
+    # 批量写入数据
+    batch_size = 500
+    for i in range(0, len(points_to_write), batch_size):
+        batch = points_to_write[i:i+batch_size]
+        write_api.write(bucket=bucket, record=batch)
+    print(f"Data imported from {file_path} to bucket {bucket} successfully.")
+    print(f"Total points written: {len(points_to_write)}")
+    write_api.close()
+    client.close()
+
+#2025/08/28 从多列格式文件导入SCADA数据，xkl
+def import_multicolumn_data_from_file(file_path: str,  raw: bool = True, bucket: str = "SCADA_data") -> None:
+    """
+    从指定的多列格式CSV文件导入数据到InfluxDB的指定bucket中。
+    :param file_path: CSV文件的路径
+    :param bucket: 数据存储的 bucket 名称，默认值为 "SCADA_data"
+    :return:
+    """
+    client = get_new_client()
+    write_api = client.write_api(write_options=SYNCHRONOUS)
+    points_to_write = []
+    if not client.ping():
+        print("{} -- Failed to connect to InfluxDB.".format(datetime.now().strftime('%Y/%m/%d %H:%M')))
+    def convert_to_iso(timestr):
+        # 假设原格式为 '2025/8/3 0:00'
+        dt = datetime.strptime(timestr, '%Y-%m-%d %H:%M:%S')
+        return dt.isoformat()
+
+    with open(file_path, encoding='utf-8') as f:
+        reader = csv.reader(f)
+        header = next(reader)
+        device_ids = header[1:]  # 第一列是time，后面是device_ID
+        if raw:
+            for row in reader:
+                time_str = row[0]
+                iso_time = convert_to_iso(time_str)
+                for idx, value in enumerate(row[1:]):
+                    try:
+                        raw_value = float(value)
+                    except (ValueError, TypeError):
+                        raw_value = 0.0
+                    scada_id = device_ids[idx]
+                    # 如果是原始数据，直接使用Value列
+                    point = Point("SCADA") \
+                        .tag("date", iso_time.split('T')[0]) \
+                        .tag("description", None) \
+                        .tag("device_ID", scada_id) \
+                        .field("monitored_value", raw_value) \
+                        .field("datacleaning_value", 0.0) \
+                        .field("simulation_value", 0.0) \
+                        .time(iso_time, WritePrecision.S)
+                    points_to_write.append(point)
+        else:
+            for row in reader:
+                time_str = row[0]
+                iso_time = convert_to_iso(time_str)
+                # 如果不是原始数据，直接使用datacleaning_value列               
+                for idx, value in enumerate(row[1:]):
+                    scada_id = device_ids[idx]
+                    try:
+                        datacleaning_value = float(value)
+                    except (ValueError, TypeError):
+                        datacleaning_value = 0.0
+                    # 如果是清洗数据，直接使用datacleaning_value列
+                    point = Point("SCADA") \
+                        .tag("date", iso_time.split('T')[0]) \
+                        .tag("description", "None") \
+                        .tag("device_ID", scada_id) \
+                        .field("monitored_value",  0.0) \
+                        .field("datacleaning_value",datacleaning_value) \
+                        .field("simulation_value", 0.0) \
+                        .time(iso_time, WritePrecision.S)
+                    points_to_write.append(point)
+        # 批量写入数据
+        batch_size = 1000
+        for i in range(0, len(points_to_write), batch_size):
+            batch = points_to_write[i:i+batch_size]
+            write_api.write(bucket=bucket, record=batch)
+        print(f"Data imported from {file_path} to bucket {bucket} successfully.")
+        print(f"Total points written: {len(points_to_write)}")
+        write_api.close()
+    client.close()
+
     
 
 # 示例调用
@@ -3652,5 +3775,25 @@ if __name__ == "__main__":
     #                                                     end_time='2024-03-26T23:59:00+08:00')
     # print(result)
 
+    #示例：import_data_from_file
+    #import_data_from_file(file_path='data/Flow_Timedata.csv', bucket='SCADA_data')
 
+    #     # 示例：query_all_records_by_type_date
+    #result = query_all__records_by_type__date(type='node', query_date='2025-08-04')
+
+    #示例：query_all_records_by_date_hour
+    #result = query_all_records_by_date_hour(query_date='2025-08-04', query_hour=1)
+
+    #示例：import_multicolumn_data_from_file
+    #import_multicolumn_data_from_file(file_path='data/selected_Flow_Timedata2025_new_format_cleaned.csv', raw=False, bucket='SCADA_data')
+    
+    # client = InfluxDBClient(url="http://localhost:8086", token=token, org=org_name)
+    # delete_api = client.delete_api()
+
+    # start = "2025-08-02T00:00:00Z"  # 要删除的起始时间
+    # stop = "2025-08-11T00:00:00Z"   # 结束时间（可设为未来）
+    # predicate = '_measurement="SCADA"'  # 指定 measurement
+
+    # delete_api.delete(start, stop, predicate, bucket="SCADA_data", org=org_name)
+    # client.close()