04141525

post_processing/cdq_coe_gen.py

@@ -4,7 +4,159 @@
 # @Time      :2025/3/28 16:20
 # @Author    :David
 # @Company: shenyang JY
- 
- 
+import os, requests, json
+import pandas as pd
+import numpy as np
+from common.database_dml_koi import get_data_from_mongo
+from pymongo import MongoClient
+from flask import Flask,request,jsonify
+from datetime import datetime
+from common.logs import Log
+logger = Log('post-processing').logger
+current_path = os.path.dirname(__file__)
+API_URL = "http://ds2:18080/accuracyAndBiasByJSON"
+
+
+def iterate_coe(pre_data, point, col_power, col_pre):
+    """
+    更新16个点系数
+    """
+    coe = {}
+    T = 'T' + str(point + 1)
+    best_acc, best_score1, best_coe_m, best_coe_n = 0, 0, 0, 0
+    best_score, best_acc1, best_score_m, best_score_n = 999, 0, 0, 0
+    req_his_fix = prepare_request_body(pre_data, col_power, 'his_fix')
+    req_dq = prepare_request_body(pre_data, col_power, col_pre)
+
+    his_fix_acc, his_fix_score = calculate_acc(API_URL, req_his_fix)
+    dq_acc, dq_score = calculate_acc(API_URL, req_dq)
+    for i in range(5, 210):
+        for j in range(5, 210):
+            pre_data["new"] = round(i / 170 * pre_data[col_pre] + j / 170 * pre_data['his_fix'], 3)
+            req_new = prepare_request_body(pre_data, col_power, 'new')
+            acc, acc_score = calculate_acc(API_URL, req_new)
+
+            if acc > best_acc:
+                best_acc = acc
+                best_score1 = acc_score
+                best_coe_m = i / 170
+                best_coe_n = j / 170
+            if acc_score < best_score:
+                best_score = acc_score
+                best_acc1 = acc
+                best_score_m = i / 170
+                best_score_n = j / 170
+
+    pre_data["coe-acc"] = round(best_coe_m * pre_data[col_pre] + best_coe_n * pre_data['his_fix'], 3)
+    pre_data["coe-ass"] = round(best_score_m * pre_data[col_pre] + best_score_n * pre_data['his_fix'], 3)
+    logger.info(
+        "1.过去{} - {}的短期的准确率：{:.4f}，自动确认系数后，{} 超短期的准确率：{:.4f}，历史功率：{:.4f}".format(
+            pre_data['C_TIME'][0], pre_data['C_TIME'].iloc[-1], dq_acc, T, best_acc, his_fix_acc))
+    logger.info(
+        "2.过去{} - {}的短期的考核分：{:.4f}，自动确认系数后，{} 超短期的考核分：{:.4f}，历史功率：{:.4f}".format(
+            pre_data['C_TIME'][0], pre_data['C_TIME'].iloc[-1], dq_score, T, best_score1, his_fix_score))
+    logger.info(
+        "3.过去{} - {}的短期的准确率：{:.4f}，自动确认系数后，{} 超短期的准确率：{:.4f}，历史功率：{:.4f}".format(
+            pre_data['C_TIME'][0], pre_data['C_TIME'].iloc[-1], dq_acc, T, best_acc1, his_fix_acc))
+    logger.info(
+        "4.过去{} - {}的短期的考核分：{:.4f}，自动确认系数后，{} 超短期的考核分：{:.4f}，历史功率：{:.4f}".format(
+            pre_data['C_TIME'][0], pre_data['C_TIME'].iloc[-1], dq_score, T, best_score, his_fix_score))
+
+    coe[T]['score_m'] = round(best_score_m, 3)
+    coe[T]['score_n'] = round(best_score_n, 3)
+    coe[T]['acc_m'] = round(best_coe_m, 3)
+    coe[T]['acc_n'] = round(best_coe_n, 3)
+    logger.info("系数轮询后，最终调整的系数为：{}".format(coe))
+
+def prepare_request_body(df, col_power, col_pre):
+    """
+    准备请求体，动态保留MongoDB中的所有字段
+    """
+    # 转换时间格式为字符串
+    if 'dateTime' in df.columns and isinstance(df['dateTime'].iloc[0], datetime):
+        df['dateTime'] = df['dateTime'].dt.strftime('%Y-%m-%d %H:%M:%S')
+
+    # 排除不需要的字段（如果有）
+    exclude_fields = ['_id']  # 通常排除MongoDB的默认_id字段
+
+    # 获取所有字段名（排除不需要的字段）
+    available_fields = [col for col in df.columns if col not in exclude_fields]
+
+    # 转换为记录列表（保留所有字段）
+    data = df[available_fields].to_dict('records')
+
+    # 构造请求体（固定部分+动态数据部分）
+    request_body = {
+        "stationCode": "J00600",
+        "realPowerColumn": col_power,
+        "ablePowerColumn": col_power,
+        "predictPowerColumn": col_pre,
+        "inStalledCapacityName": 153,
+        "computTypeEnum": "E2",
+        "computMeasEnum": "E2",
+        "openCapacityName": 153,
+        "onGridEnergy": 0,
+        "price": 0,
+        "fault": -99,
+        "colTime": "dateTime",  #时间列名（可选，要与上面'dateTime一致'）
+        # "computPowersEnum": "E4"  # 计算功率类型（可选）
+        "data": data  # MongoDB数据
+    }
+
+    return request_body
+
+def calculate_acc(api_url, request_body):
+    """
+    调用API接口
+    """
+    headers = {
+        'Content-Type': 'application/json',
+        'Accept': 'application/json'
+    }
+    try:
+        response = requests.post(
+            api_url,
+            data=json.dumps(request_body, ensure_ascii=False),
+            headers=headers
+        )
+        result = response.json()
+        if result['status'] == 200:
+            acc = np.average([res['accuracy'] for res in result])
+            ass = np.average([res['accuracyAssessment'] for res in result])
+            return acc, ass
+        else:
+            logger.info(f"失败：{result['status']},{result['error']}")
+    except requests.exceptions.RequestException as e:
+        print(f"API调用失败: {e}")
+        return None
+
+def history_error(data, col_power, col_pre):
+    data['error'] =  data[col_power] - data[col_pre]
+    data['error'] = data['error'].round(2)
+    data.reset_index(drop=True, inplace=True)
+    # 用前面5个点的平均error，和象心力相加
+    numbers = len(data) - 5
+    datas = [data.iloc[x: x+5, :].reset_index(drop=True) for x in range(0, numbers)]
+    data_error = [np.mean(d.iloc[0:5, -1]) for d in datas]
+    pad_data_error = np.pad(data_error, (5, 0), mode='constant', constant_values=0)
+    data['his_fix'] = data[col_pre] + pad_data_error
+    data = data.iloc[5:, :].reset_index(drop=True)
+    data.loc[data[col_pre] <= 0, ['his_fix']] = 0
+    data['dateTime'] = pd.to_datetime(data['dateTime'])
+    data = data.loc[:, ['dateTime', col_power, col_pre, 'his_fix']]
+    # data.to_csv('J01080原始数据.csv', index=False)
+    return data
+
+
 if __name__ == "__main__":
-    run_code = 0
+    args = {
+        'mongodb_database': 'ldw_ftp',
+        'mongodb_read_table': 'j00600',
+        # 'timeBegin': '2025-01-01 00:00:00',
+        # 'timeEnd': '2025-01-03 23:45:00'
+    }
+    data = get_data_from_mongo(args).sort_values(by='dateTime', ascending=True)
+    pre_data = history_error(data, col_power='realPower', col_pre='dq')
+    for point in range(0, 16, 1):
+        iterate_coe(pre_data, point, 'realPower', 'dq')
+    run_code = 0