diff --git a/aisenzhecode/沥青/沥青定性模型每日推送-ytj.ipynb b/aisenzhecode/沥青/沥青定性模型每日推送-ytj.ipynb index 2a88fb9..a9754b4 100644 --- a/aisenzhecode/沥青/沥青定性模型每日推送-ytj.ipynb +++ b/aisenzhecode/沥青/沥青定性模型每日推送-ytj.ipynb @@ -18,10 +18,22 @@ "import numpy as np\n", "# 变量定义\n", "login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n", - "search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\"\n", + "# query_data_list_item_nos_url\n", + "search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\" #jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos\n", "upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n", "\n", "\n", + "query_data_list_item_nos_data = {\n", + " \"funcModule\": \"数据项\",\n", + " \"funcOperation\": \"查询\",\n", + " \"data\": {\n", + " \"dateStart\": \"20200101\",\n", + " \"dateEnd\": \"20241231\",\n", + " \"dataItemNoList\": [\"Brentzdj\", \"Brentzgj\"] # 数据项编码,代表 brent最低价和最高价\n", + " }\n", + "}\n", + "\n", + "\n", "login_data = {\n", " \"data\": {\n", " \"account\": \"api_dev\",\n", @@ -844,7 +856,7 @@ " # headers1 = {\"Authorization\": token_push}\n", " # res = requests.post(url=upload_url, headers=headers1, json=data1, timeout=(3, 5))\n", " \n", - " \n", + "\n", "\n", "\n", "\n", @@ -960,8 +972,6 @@ " # 保存新的xls文件\n", " new_workbook.save(\"定性模型数据项12-11.xlsx\")\n", "\n", - "\n", - "\n", "\n" ] }, diff --git a/aisenzhecode/沥青/沥青定量价格预测每日推送-ytj.ipynb b/aisenzhecode/沥青/沥青定量价格预测每日推送-ytj.ipynb index a6e4b52..51725e9 100644 --- a/aisenzhecode/沥青/沥青定量价格预测每日推送-ytj.ipynb +++ b/aisenzhecode/沥青/沥青定量价格预测每日推送-ytj.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": {}, "outputs": [ { @@ -11,23 +11,23 @@ " \n", + " \n", " " ] }, "metadata": {}, "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\h5218\\AppData\\Local\\Temp\\ipykernel_25428\\1736143337.py:811: DeprecationWarning:\n", + "\n", + "The truth value of an empty array is ambiguous. Returning False, but in future this will result in an error. Use `array.size > 0` to check that an array is not empty.\n", + "\n" + ] } ], "source": [ @@ -35,11 +35,14 @@ "import json\n", "import xlrd\n", "import xlwt\n", - "from datetime import datetime\n", + "import datetime\n", "import time\n", + "import pandas as pd\n", + "\n", "# 变量定义\n", "login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n", "search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\"\n", + "queryDataListItemNos_url = \"http://10.200.32.39/jingbo-api//api/warehouse/dwDataItem/queryDataListItemNos\"\n", "\n", "login_push_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n", "upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n", @@ -756,9 +759,133 @@ " new_workbook.save(\"沥青数据项.xls\")\n", "\n", "\n", + "\n", + "\n", + "\n", + "def get_queryDataListItemNos_value(token, url, dataItemNoList, dateStart, dateEnd):\n", + "\n", + " search_data = {\n", + " \"funcModule\": \"数据项\",\n", + " \"funcOperation\": \"查询\",\n", + " \"data\": {\n", + " \"dateStart\": dateStart,\n", + " \"dateEnd\": dateEnd,\n", + " \"dataItemNoList\": dataItemNoList # 数据项编码,代表 brent最低价和最高价\n", + " }\n", + " }\n", + "\n", + " headers = {\"Authorization\": token}\n", + " search_res = requests.post(url=url, headers=headers, json=search_data, timeout=(3, 5))\n", + " search_value = json.loads(search_res.text)[\"data\"]\n", + " if search_value:\n", + " return search_value\n", + " else:\n", + " return None\n", + "\n", + "\n", + "\n", + "def save_queryDataListItemNos_xls(data_df,dataItemNoList):\n", + "\n", + " current_year_month = datetime.datetime.now().strftime('%Y-%m')\n", + " grouped = data_df.groupby(\"dataDate\")\n", + "\n", + " # 打开xls文件\n", + " workbook = xlrd.open_workbook('沥青数据项.xls')\n", + "\n", + " # 获取所有sheet的个数\n", + " sheet_count = len(workbook.sheet_names())\n", + "\n", + " # 获取所有sheet的名称\n", + " sheet_names = workbook.sheet_names()\n", + "\n", + " new_workbook = xlwt.Workbook()\n", + " for i in range(sheet_count):\n", + " # 获取当前sheet\n", + " sheet = workbook.sheet_by_index(i)\n", + "\n", + " # 获取sheet的行数和列数\n", + " row_count = sheet.nrows\n", + " col_count = sheet.ncols\n", + " # 获取原有数据\n", + " data = []\n", + " for row in range(row_count):\n", + " row_data = []\n", + " for col in range(col_count):\n", + " row_data.append(sheet.cell_value(row, col))\n", + " data.append(row_data)\n", + "\n", + " # 创建xlwt的Workbook对象\n", + " # 创建sheet\n", + " new_sheet = new_workbook.add_sheet(sheet_names[i])\n", + "\n", + "\n", + " current_year_month_row = 0\n", + " # 将原有的数据写入新的sheet\n", + " for row in range(row_count):\n", + " for col in range(col_count):\n", + " col0 = data[row][0]\n", + " # print(\"col0\",col0[:7])\n", + " if col0[:7] == current_year_month:\n", + " current_year_month_row += 1\n", + " break\n", + " new_sheet.write(row, col, data[row][col])\n", + "\n", + "\n", + " # print(\"current_year_month_row\",current_year_month_row)\n", + " if i == 0:\n", + " rowFlag = 0\n", + " # 查看每组数据\n", + " for date, group in grouped:\n", + " new_sheet.write(row_count + rowFlag - current_year_month_row, 0, date)\n", + " for j in range(len(dataItemNoList)):\n", + " dataItemNo = dataItemNoList[j]\n", + "\n", + " # for dataItemNo in dataItemNoList:\n", + " if group[group[\"dataItemNo\"] == dataItemNo][\"dataValue\"].values:\n", + "\n", + " new_sheet.write(row_count + rowFlag - current_year_month_row, j + 1, group[group[\"dataItemNo\"] == dataItemNo][\"dataValue\"].values[0])\n", + "\n", + " rowFlag += 1\n", + "\n", + "\n", + " # 保存新的xls文件\n", + " new_workbook.save(\"沥青数据项.xls\")\n", + "\n", + "\n", + "\n", + "\n", + "def queryDataListItemNos():\n", + " df = pd.read_excel('沥青数据项.xls')\n", + " dataItemNoList = df.iloc[0].tolist()[1:]\n", + "\n", + " token = get_head_auth()\n", + " if not token:\n", + " return\n", + "\n", + " # 获取当前日期\n", + " current_date = datetime.datetime.now()\n", + "\n", + " # 获取当月1日\n", + " first_day_of_month = current_date.replace(day=1)\n", + "\n", + " # 格式化为 YYYYMMDD 格式\n", + " dateEnd = current_date.strftime('%Y%m%d')\n", + " dateStart = first_day_of_month.strftime('%Y%m%d')\n", + "\n", + " search_value = get_queryDataListItemNos_value(token, queryDataListItemNos_url, dataItemNoList, dateStart, dateEnd)\n", + "\n", + "\n", + " data_df = pd.DataFrame(search_value)\n", + "\n", + " data_df[\"dataDate\"] = pd.to_datetime(data_df[\"dataDate\"])\n", + " data_df[\"dataDate\"] = data_df[\"dataDate\"].dt.strftime('%Y-%m-%d')\n", + " save_queryDataListItemNos_xls(data_df,dataItemNoList)\n", + "\n", + "\n", "if __name__ == \"__main__\":\n", " pass\n", " # 需要单独运行放开\n", + "\n", "# start()\n", "\n", " # 每天定时12点运行\n", @@ -767,9 +894,17 @@ " # current_time = time.strftime(\"%H:%M:%S\", time.localtime())\n", " # current_time_1 = time.strftime(\"%H:%M:%S\", time.localtime())\n", "\n", + " # 获取当月的数据写入到指定文件\n", + " # queryDataListItemNos()\n", + "\n", " # # 判断当前时间是否为执行任务的时间点\n", " # if current_time == \"12:00:00\":\n", " # print(\"执行定时任务\")\n", + "\n", + " # 这个函数，获取当天数据，\n", + " # 预测训练，\n", + " # 预测结果上传\n", + "\n", " # start()\n", "\n", " # # 休眠1秒钟，避免过多占用CPU资源\n", @@ -777,6 +912,8 @@ " \n", " # elif current_time_1 == \"20:00:00\":\n", " # print(\"更新数据\")\n", + "\n", + " # 这个函数，获取当天数据，保存\n", " # start_1()\n", " # time.sleep(1)\n", "\n", @@ -2270,7 +2407,7 @@ ], "metadata": { "kernelspec": { - "display_name": "base", + "display_name": "Python 3", "language": "python", "name": "python3" }, @@ -2284,7 +2421,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.7" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/aisenzhecode/沥青/沥青数据项.xls b/aisenzhecode/沥青/沥青数据项.xls index ce5117c..384c605 100644 Binary files a/aisenzhecode/沥青/沥青数据项.xls and b/aisenzhecode/沥青/沥青数据项.xls differ diff --git a/aisenzhecode/液化石油气/化工品价格预测准确率.xlsx b/aisenzhecode/液化石油气/化工品价格预测准确率.xlsx new file mode 100644 index 0000000..31df769 Binary files /dev/null and b/aisenzhecode/液化石油气/化工品价格预测准确率.xlsx differ diff --git a/config_shiyoujiao.py b/config_shiyoujiao.py new file mode 100644 index 0000000..c6a6a5d --- /dev/null +++ b/config_shiyoujiao.py @@ -0,0 +1,320 @@ +import logging +import os +import logging.handlers +import datetime +from lib.tools import MySQLDB,SQLiteHandler + + +# eta 接口token +APPID = "XNLDvxZHHugj7wJ7" +SECRET = "iSeU4s6cKKBVbt94htVY1p0sqUMqb2xa" + +# eta 接口url +sourcelisturl = 'http://10.189.2.78:8108/v1/edb/source/list' +classifylisturl = 'http://10.189.2.78:8108/v1/edb/classify/list?ClassifyType=' +uniquecodedataurl = 'http://10.189.2.78:8108/v1/edb/data?UniqueCode=4991c37becba464609b409909fe4d992&StartDate=2024-02-01' +classifyidlisturl = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId=' +edbcodedataurl = 'http://10.189.2.78:8108/v1/edb/data?EdbCode=' +edbdatapushurl = 'http://10.189.2.78:8108/v1/edb/push' +edbdeleteurl = 'http://10.189.2.78:8108/v1/edb/business/edb/del' +edbbusinessurl = 'http://10.189.2.78:8108/v1/edb/business/data/del' +edbcodelist = ['ID01385938','lmcads03 lme comdty', +'GC1 COMB Comdty', +'C2404171822', +'dxy curncy', +'S5443199 ', +'S5479800', +'S5443108', +'H7358586', +'LC3FM1 INDEX', +'CNY REGN Curncy', +'s0105897', +'M0067419', +'M0066351', +'S0266372', +'S0266438', +'S0266506', +'ID01384463'] + +# 临时写死用指定的列,与上面的edbcode对应，后面更改 +edbnamelist = [ + 'ds','y', + 'LME铜价', + '黄金连1合约', + 'Brent-WTI', + '美元指数', + '甲醇鲁南价格', + '甲醇太仓港口价格', + '山东丙烯主流价', + '丙烷（山东）', + 'FEI丙烷 M1', + '在岸人民币汇率', + '南华工业品指数', + 'PVC期货主力', + 'PE期货收盘价', +'PP连续-1月', +'PP连续-5月', +'PP连续-9月', +'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）' + ] + +edbcodenamedict = { +'ID01385938':'PP：拉丝：1102K：市场价：青州：国家能源宁煤（日）', +'ID01384463':'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', +'lmcads03 lme comdty':'LME铜价', +'GC1 COMB Comdty':'黄金连1合约', +'C2404171822':'Brent-WTI', +'dxy curncy':'美元指数', +'S5443199 ':'甲醇鲁南价格', +'S5479800':'甲醇太仓港口价格', +'S5443108':'山东丙烯主流价', +'H7358586':'丙烷（山东）', +'LC3FM1 INDEX':'FEI丙烷 M1', +'CNY REGN Curncy':'在岸人民币汇率', +'s0105897':'南华工业品指数', +'M0067419':'PVC期货主力', +'M0066351':'PE期货收盘价', +'S0266372':'PP连续-1月', +'S0266438':'PP连续-5月', +'S0266506':'PP连续-9月', + +} + +# eta自有数据指标编码 +modelsindex = { + 'NHITS': 'SELF0000077', + 'Informer':'SELF0000078', + 'LSTM':'SELF0000079', + 'iTransformer':'SELF0000080', + 'TSMixer':'SELF0000081', + 'TSMixerx':'SELF0000082', + 'PatchTST':'SELF0000083', + 'RNN':'SELF0000084', + 'GRU':'SELF0000085', + 'TCN':'SELF0000086', + 'BiTCN':'SELF0000087', + 'DilatedRNN':'SELF0000088', + 'MLP':'SELF0000089', + 'DLinear':'SELF0000090', + 'NLinear':'SELF0000091', + 'TFT':'SELF0000092', + 'FEDformer':'SELF0000093', + 'StemGNN':'SELF0000094', + 'MLPMultivariate':'SELF0000095', + 'TiDE':'SELF0000096', + 'DeepNPTS':'SELF0000097' + } + + + +# eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据 +data = { + "IndexCode": "", + "IndexName": "价格预测模型", + "Unit": "无", + "Frequency": "日度", + "SourceName": f"价格预测", + "Remark": 'ddd', + "DataList": [ + { + "Date": "2024-05-02", + "Value": 333444 + } + ] + } + +# eta 分类 +# level：3才可以获取到数据，所以需要人工把能源化工下所有的level3级都找到 + # url = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId=1214' + #ParentId ":1160, 能源化工 + # ClassifyId ":1214,原油 3912 石油焦 + #ParentId ":1214,"，就是原油下所有的数据。 +ClassifyId = 3707 + + + +############################################################################################################### 变量定义--测试环境 +server_host = '192.168.100.53' + +login_pushreport_url = f"http://{server_host}:8080/jingbo-dev/api/server/login" +upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" +upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" +query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" + +login_data = { + "data": { + "account": "api_test", + # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 + "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456 + "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", + "terminal": "API" + }, + "funcModule": "API", + "funcOperation": "获取token" +} + +upload_data = { + "funcModule":'研究报告信息', + "funcOperation":'上传聚烯烃PP价格预测报告', + "data":{ + "groupNo":'000128', # 用户组编号 + "ownerAccount":'arui', #报告所属用户账号 + "reportType":'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST + "fileName": '2000-40-5-50--100-原油指标数据.xlsx-Brent活跃合约--2024-09-06-15-01-29-预测报告.pdf', #文件名称 + "fileBase64": '' ,#文件内容base64 + "categoryNo":'yyjgycbg', # 研究报告分类编码 + "smartBusinessClassCode":'JXTJGYCBG', #分析报告分类编码 + "reportEmployeeCode":"E40116", # 报告人 + "reportDeptCode" :"D0044" ,# 报告部门 + "productGroupCode":"RAW_MATERIAL" # 商品分类 + } +} + + +warning_data = { + "groupNo":'000128', # 用户组编号 + "funcModule":'原油特征停更预警', + "funcOperation":'原油特征停更预警', + "data":{ + 'WARNING_TYPE_NAME':'特征数据停更预警', + 'WARNING_CONTENT':'', + 'WARNING_DATE':'' + } +} + +query_data_list_item_nos_data = { + "funcModule": "数据项", + "funcOperation": "查询", + "data": { + "dateStart":"20200101", + "dateEnd":"20241231", + "dataItemNoList":["Brentzdj","Brentzgj"] # 数据项编码,代表 brent最低价和最高价 + } +} + + +# 北京环境数据库 +host = '192.168.101.27' +port = 3306 +dbusername ='root' +password = '123456' +dbname = 'jingbo_test' +table_name = 'v_tbl_crude_oil_warning' + + +### 开关 +is_train = False # 是否训练 +is_debug = True # 是否调试 +is_eta = True # 是否使用eta接口 +is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 +is_timefurture = True # 是否使用时间特征 +is_fivemodels = False # 是否使用之前保存的最佳的5个模型 +is_edbcode = False # 特征使用edbcoding列表中的 +is_edbnamelist = False # 自定义特征，对应上面的edbnamelist +is_update_eta = False # 预测结果上传到eta +is_update_report = True # 是否上传报告 +is_update_warning_data = False # 是否上传预警数据 +is_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征 +is_del_tow_month = True # 是否删除两个月不更新的特征 + + + +# 连接到数据库 +db_mysql = MySQLDB(host=host, user=dbusername, password=password, database=dbname) +db_mysql.connect() +print("数据库连接成功",host,dbname,dbusername) + + +# 数据截取日期 +start_year = 2020 # 数据开始年份 +end_time = '' # 数据截取日期 +freq = 'B' # 时间频率，"D": 天 "W": 周"M": 月"Q": 季度"A": 年 "H": 小时 "T": 分钟 "S": 秒 "B": 工作日 +delweekenday = True if freq == 'B' else False # 是否删除周末数据 +is_corr = False # 特征是否参与滞后领先提升相关系数 +add_kdj = False # 是否添加kdj指标 +if add_kdj and is_edbnamelist: + edbnamelist = edbnamelist+['K','D','J'] + +### 模型参数 +y = 'AVG-金能大唐久泰青州' +avg_cols = [ + 'PP：拉丝：1102K：出厂价：青州：国家能源宁煤（日）', + 'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', + 'PP：拉丝：L5E89：出厂价：河北、鲁北：大唐内蒙多伦（日）', + 'PP：拉丝：HP550J：市场价：青岛：金能化学（日）' +] +offsite = 80 +offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）'] +horizon =5 # 预测的步长 +input_size = 40 # 输入序列长度 +train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数 +val_check_steps = 30 # 评估频率 +early_stop_patience_steps = 5 # 早停的耐心步数 +# --- 交叉验证用的参数 +test_size = 200 # 测试集大小，定义100，后面使用的时候重新赋值 +val_size = test_size # 验证集大小,同测试集大小 + +### 特征筛选用到的参数 +k = 100 # 特征筛选数量，如果是0或者值比特征数量大，代表全部特征 +corr_threshold = 0.6 # 相关性大于0.6的特征 +rote = 0.06 # 绘图上下界阈值 + +### 计算准确率 +weight_dict = [0.4,0.15,0.1,0.1,0.25] # 权重 + + +### 文件 +data_set = '石油焦指标数据.xlsx' # 数据集文件 +dataset = 'shiyoujiaodataset' # 数据集文件夹 + +# 数据库名称 +db_name = os.path.join(dataset,'jbsh_juxiting.db') +sqlitedb = SQLiteHandler(db_name) +sqlitedb.connect() + +settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}' +# 获取日期时间 +# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') # 获取当前日期时间 +now = datetime.datetime.now().strftime('%Y-%m-%d') # 获取当前日期时间 +reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 +reportname = reportname.replace(':', '-') # 替换冒号 +if end_time == '': + end_time = now +### 邮件配置 +username='1321340118@qq.com' +passwd='wgczgyhtyyyyjghi' +# recv=['liurui_test@163.com','52585119@qq.com'] +recv=['liurui_test@163.com'] +# recv=['liurui_test@163.com'] +title='reportname' +content=y+'预测报告请看附件' +file=os.path.join(dataset,'reportname') +# file=os.path.join(dataset,'14-7-50--100-原油指标数据.xlsx-Brent连1合约价格--20240731175936-预测报告.pdf') +ssl=True + + +### 日志配置 + +# 创建日志目录（如果不存在） +log_dir = 'logs' +if not os.path.exists(log_dir): + os.makedirs(log_dir) + +# 配置日志记录器 +logger = logging.getLogger('my_logger') +logger.setLevel(logging.INFO) + +# 配置文件处理器，将日志记录到文件 +file_handler = logging.handlers.RotatingFileHandler(os.path.join(log_dir, 'pricepredict.log'), maxBytes=1024 * 1024, backupCount=5) +file_handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')) + +# 配置控制台处理器，将日志打印到控制台 +console_handler = logging.StreamHandler() +console_handler.setFormatter(logging.Formatter('%(message)s')) + +# 将处理器添加到日志记录器 +logger.addHandler(file_handler) +logger.addHandler(console_handler) + +# logger.info('当前配置：'+settings) + diff --git a/config_shiyoujiao_lvyong.py b/config_shiyoujiao_lvyong.py index bb3b82d..fe0329b 100644 --- a/config_shiyoujiao_lvyong.py +++ b/config_shiyoujiao_lvyong.py @@ -295,7 +295,7 @@ bdwd_items = { # 京博测试环境 host = 'rm-2zehj3r1n60ttz9x5ko.mysql.rds.aliyuncs.com' port = 3306 -dbusername ='jingbo' +dbusername = 'jingbo' password = 'shihua@123' dbname = 'jingbo-test' @@ -338,7 +338,7 @@ if add_kdj and is_edbnamelist: edbnamelist = edbnamelist+['K', 'D', 'J'] # 模型参数 -y = '煅烧焦山东高硫(高端S < 3.5，普货)(元/吨)' +y = '煅烧焦华东中硫(高端S < 3.0，钒 < 400)(元/吨)' avg_cols = [ ] diff --git a/config_shiyoujiao_puhuo.py b/config_shiyoujiao_puhuo.py index e271eb1..75c0661 100644 --- a/config_shiyoujiao_puhuo.py +++ b/config_shiyoujiao_puhuo.py @@ -18,93 +18,140 @@ edbcodedataurl = 'http://10.189.2.78:8108/v1/edb/data?EdbCode=' edbdatapushurl = 'http://10.189.2.78:8108/v1/edb/push' edbdeleteurl = 'http://10.189.2.78:8108/v1/edb/business/edb/del' edbbusinessurl = 'http://10.189.2.78:8108/v1/edb/business/data/del' -edbcodelist = ['ID01385938', 'lmcads03 lme comdty', - 'GC1 COMB Comdty', - 'C2404171822', - 'dxy curncy', - 'S5443199 ', - 'S5479800', - 'S5443108', - 'H7358586', - 'LC3FM1 INDEX', - 'CNY REGN Curncy', - 's0105897', - 'M0067419', - 'M0066351', - 'S0266372', - 'S0266438', - 'S0266506', - 'ID01384463'] - -# 临时写死用指定的列,与上面的edbcode对应，后面更改 -edbnamelist = [ - 'ds', 'y', - 'LME铜价', - '黄金连1合约', - 'Brent-WTI', - '美元指数', - '甲醇鲁南价格', - '甲醇太仓港口价格', - '山东丙烯主流价', - '丙烷（山东）', - 'FEI丙烷 M1', - '在岸人民币汇率', - '南华工业品指数', - 'PVC期货主力', - 'PE期货收盘价', - 'PP连续-1月', - 'PP连续-5月', - 'PP连续-9月', - 'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）' -] edbcodenamedict = { - 'ID01385938': 'PP：拉丝：1102K：市场价：青州：国家能源宁煤（日）', - 'ID01384463': 'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', - 'lmcads03 lme comdty': 'LME铜价', - 'GC1 COMB Comdty': '黄金连1合约', - 'C2404171822': 'Brent-WTI', - 'dxy curncy': '美元指数', - 'S5443199 ': '甲醇鲁南价格', - 'S5479800': '甲醇太仓港口价格', - 'S5443108': '山东丙烯主流价', - 'H7358586': '丙烷（山东）', - 'LC3FM1 INDEX': 'FEI丙烷 M1', - 'CNY REGN Curncy': '在岸人民币汇率', - 's0105897': '南华工业品指数', - 'M0067419': 'PVC期货主力', - 'M0066351': 'PE期货收盘价', - 'S0266372': 'PP连续-1月', - 'S0266438': 'PP连续-5月', - 'S0266506': 'PP连续-9月', - + 'C2403287411': '华北高硫焦与等热值动力煤价格对比', + 'C2403282801': '华东高硫焦与等热值动力煤价格对比', + 'ID00150321': '石油焦：2 # A：市场低端价：山东（日）', + 'ID00150329': '石油焦：2 # A：市场主流价：山东（日）', + 'ID00150325': '石油焦：2 # A：市场高端价：山东（日）', + 'ID00150333': '石油焦：2 # B：市场低端价：山东（日）', + 'ID00150357': '石油焦：2 # B：市场主流价：山东（日）', + 'ID00150345': '石油焦：2 # B：市场高端价：山东（日）', + 'ID01101276': '高硫焦：4B：出厂价：山东：青岛炼化（日）', + 'ID00150417': '石油焦：高硫焦：市场低端价：华北地区（日）', + 'ID00150425': '石油焦：高硫焦：市场低端价：华南地区（日）', + 'ID00150437': '石油焦：高硫焦：市场高端价：华北地区（日）', + 'ID00150441': '石油焦：高硫焦：市场高端价：华东地区（日）', + 'ID00150445': '石油焦：高硫焦：市场高端价：华南地区（日）', + 'ID00150449': '石油焦：高硫焦：市场高端价：西北地区（日）', + 'ID00150453': '石油焦：高硫焦：市场高端价：西南地区（日）', + 'ID01300358': '石油焦：3 # C：市场低端价：山东（日）', + 'ID01300357': '石油焦：3 # C：市场高端价：山东（日）', + 'ID00150377': '石油焦：3 # ：市场主流价：华中地区（日）', + 'ID01387678': '煅烧焦：中硫：3 % S：市场价：华中地区（日）', + 'ID01387656': '煅烧焦：中硫：3 % S：市场价：山东（日）', + 'ID00150381': '石油焦：3 # A：市场低端价：山东（日）', + 'ID00150397': '石油焦：3 # B：市场低端价：山东（日）', + 'ID00150405': '石油焦：3 # B：市场高端价：山东（日）', + 'ID00150429': '石油焦：高硫焦：市场低端价：西北地区（日）', + 'ID00150433': '石油焦：高硫焦：市场低端价：西南地区（日）', + 'ID00150457': '石油焦：高硫焦：市场主流价：华北地区（日）', + 'ID00150461': '石油焦：高硫焦：市场主流价：华东地区（日）', + 'ID00150465': '石油焦：高硫焦：市场主流价：华南地区（日）', + 'ID00150469': '石油焦：高硫焦：市场主流价：西北地区（日）', + 'ID00150473': '石油焦：高硫焦：市场主流价：西南地区（日）', + 'B3e90b34e4b9e7a6ea3': '石油焦市场均价(元/吨)', + 'B8a0ab5357569c385a9': '石油焦海绵焦市场均价(元/吨)', + 'B8a920b59fe7effd116': '石油焦4 # -5#市场均价(元/吨)', + 'B81e66c7dc542809035': '石油焦海绵焦华东高硫焦（低端）(元/吨)（百川）', + 'B6fc631d20e277ce496': '石油焦海绵焦华东高硫焦（高端）(元/吨)（百川）', + 'Be9ed3ebd44ad291a3c': '石油焦海绵焦华南高硫焦（低端）(元/吨)（百川）', + 'B347350473783e640dc': '石油焦海绵焦华南高硫焦（高端）(元/吨)（百川）', + 'B7acab268ac4a419f77': '煅烧焦华北中硫(低端S < 3.0，普货)(元/吨)', + 'Beecfb2678481997f68': '煅烧焦山东中硫(高端S < 3.0，普货)(元/吨)', + 'B4bc4d186dc0f7d6d96': '煅烧焦华中中硫(高端S < 3.0，普货)(元/吨)', + 'B46cc7d0a90155b5bfd': '煅烧焦山东高硫(高端S < 3.5，普货)(元/吨)', + 'B4501068048575cd6f1': '煅烧焦西北高硫(S < 4.0，普货)(元/吨)', + 'Bfccb234f4c4e047314': '煅烧焦中硫普货市场均价(硫 < 3.0 %)(元/吨)', + 'B1133e458cc493d7728': '煅烧焦高硫普货市场均价(元/吨)（百川）', + 'B185a597decfc71915a': '预焙阳极山东低端(元/吨)（百川）', + 'B16b98ff5f959dfdcad': '负极材料市场参考价(元/吨)（百川）', + 'B7ce1371e09479bee56': '人造石墨负极材料中端(元/吨)', + 'Bab0904b23e968a3068': '天然石墨负极材料中端(元/吨)', + 'B180e67aaa174414553': '中间相碳微球负极材料高端(元/吨)', + 'B41c03de42ea84d5c2f': '中间相碳微球负极材料中端(元/吨)', + 'B5c3b60680b7bbd92af': '负极材料石墨化国内低端价(元/吨)', + 'B1bcde6130de031bd42': '山西 改质沥青(元/吨)', + 'Bb9f4a1f6dd32b4ad8a': '山东 改质沥青(元/吨)', + 'C2411261557491549': '石油焦市场均价(元/吨)/4DMA', + 'C2411271143174617': '石油焦市场均价(元/吨)/9DMA', + 'RE00010074': '煅烧焦：中硫焦：生产毛利：山东（周）', + 'B9d1acaf80383683da3': '石油焦总产量（周）(吨)', + 'Bdaa719a38936c8dd76': '石油焦开工率（周）(% )', + 'B9459d549a332b200e7': '石油焦行业总库存（周）(吨)', + 'Bce6e098b9518370cff': '石油焦工厂库存（周）(吨)', + 'B577ce2809772779710': '石油焦市场库存（周）(吨)', + 'B5d8c564c62f3e6b77f': '石油焦成本（周）(吨)', + 'B43baa98bcaa06c11a5': '石油焦利润（周）(吨)', + 'Bdd0c1361d94081211c': '煅烧石油焦总产量（周）(吨)', + 'B65315111fa28951b1e': '煅烧石油焦开工率（周）(% )', + 'B2aff5f2632a20027d0': '煅烧石油焦行业总库存（周）(吨)', + 'B29fbd31128cd71b212': '煅烧石油焦工厂库存（周）(吨)', + 'B7a88313a89d1261c53': '煅烧石油焦成本（周）(吨)', + 'Bd4fa36b4decec0aafa': '煅烧石油焦利润（周）(吨)', + 'B9bd80eac7df81ffbd4': '预焙阳极总产量（周）(吨)', + 'B27074786605f4660d2': '预焙阳极开工率（周）(% )', + 'Bdc2a5985ecb56b6a0c': '预焙阳极行业总库存（周）(吨)', + 'Bce8511f899e487e5b6': '预焙阳极工厂库存（周）(吨)', + 'B13ec89105bd866a2bd': '预焙阳极成本（周）(吨)', + 'B66c3abcfa15a2e611c': '预焙阳极利润（周）(吨)', + 'Ba3bcf63e6e846cd3f8': '负极材料总产量（周）(吨)', + 'B10b8f4c702b72f4ee4': '负极材料开工率（周）(% )', + 'Bc25e82dd595c5f92fc': '负极材料行业总库存（周）(吨)', + 'B0a14d1936a5e072f25': '负极材料工厂库存（周）(吨)', + 'Ba9d192464b78194a48': '负极材料成本（周）(吨)', + 'B15d62d9f48ccfa5984': '负极材料利润（周）(吨)', + 'B7478e77ca116386afd': '针状焦总产量（周）(吨)', + 'Bbe316d65258a4d47f4': '针状焦行业总库存（周）(吨)', + 'Bf036a360a5eecb591d': '针状焦工厂库存（周）(吨)', + 'Bc43a790c62aa57fc9d': '针状焦成本（周）(吨)', + 'B23ebedbb88ff412952': '针状焦利润（周）(吨)', + 'C2403286685': '黄骅港动力煤等热值', + 'C2403285171': '黄骅等热值动力煤', + 'C2403287884': '中硫石油焦煅烧利润', + 'W000294': '国内主要港口石油焦出货量（隆重）', + 'W000293': '日照港库存（隆重）', + 'W000292': '港口总库存（隆重）', + 'W000283': '主营石油焦产量（隆重）', + 'W000282': '地炼石油焦产量（隆重）', + 'W000281': '中国石油焦产量（隆重）', + 'W000280': '主营石油焦开工负荷率（隆重）', + 'W000279': '地炼石油焦开工负荷率（隆重）', } -# eta自有数据指标编码 + +edbcodelist = edbcodenamedict.keys() +# 临时写死用指定的列,与上面的edbcode对应，后面更改 +edbnamelist = ['ds', 'y']+[edbcodenamedict[edbcodename] + for edbcodename in edbcodelist] + +# eta自有数据指标编码，石油焦铝用还没新增，暂且留空 modelsindex = { - 'NHITS': 'SELF0000077', - 'Informer': 'SELF0000078', - 'LSTM': 'SELF0000079', - 'iTransformer': 'SELF0000080', - 'TSMixer': 'SELF0000081', - 'TSMixerx': 'SELF0000082', - 'PatchTST': 'SELF0000083', - 'RNN': 'SELF0000084', - 'GRU': 'SELF0000085', - 'TCN': 'SELF0000086', - 'BiTCN': 'SELF0000087', - 'DilatedRNN': 'SELF0000088', - 'MLP': 'SELF0000089', - 'DLinear': 'SELF0000090', - 'NLinear': 'SELF0000091', - 'TFT': 'SELF0000092', - 'FEDformer': 'SELF0000093', - 'StemGNN': 'SELF0000094', - 'MLPMultivariate': 'SELF0000095', - 'TiDE': 'SELF0000096', - 'DeepNPTS': 'SELF0000097' } +# 百川数据指标编码 +baichuanidnamedict = { + '1588348470396480901': '石油焦滨州-友泰', + '1588348470396480903': '石油焦东营-海科瑞林', + '1588348470396480911': '石油焦东营-亚通', + '1588348470396480888': '石油焦沧州-鑫海', + '1588348470396480888': '江苏鑫海', + '1588348470396480917': '石油焦东营-万通', + '1588348470396480925': '石油焦东营-齐润', + '1588348470396481084': '石油焦东营-尚能4 # ', + '1588348470396480930': '石油焦潍坊-寿光鲁清', + '1588348470396480929': '石油焦滨州-鑫岳', + '1588348470396480650': '煅烧石油焦东营-启德-1', + '1588348470396481053': '煅烧石油焦东营-启德-2', + '1588348470396480645': '煅烧石油焦东营-山东汇宇-1', + '1588348470396481049': '煅烧石油焦东营-山东汇宇-2', + '1588348470396481098': '煅烧石油焦东营-山东汇宇-3', + '1588348470396481108': '煅烧石油焦东营-山东汇宇-4' +} + + +# baichuanidnamedict = {'1588348470396475286': 'test1', '1666': 'test2'} # 北京环境测试用 # eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据 data = { @@ -132,12 +179,17 @@ ClassifyId = 3707 # 变量定义--测试环境 -server_host = '192.168.100.53' - +server_host = '192.168.100.53' # 内网 +# server_host = '183.242.74.28' # 外网 login_pushreport_url = f"http://{server_host}:8080/jingbo-dev/api/server/login" +# 上传报告 upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" +# 停更预警 upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" +# 查询数据项编码 query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" +# 上传数据项值 +push_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/dw/dataValue/pushDataValueList" login_data = { "data": { @@ -152,16 +204,16 @@ login_data = { } upload_data = { + "groupNo": '', # 用户组id "funcModule": '研究报告信息', - "funcOperation": '上传聚烯烃PP价格预测报告', + "funcOperation": '上传原油价格预测报告', "data": { - "groupNo": '000128', # 用户组编号 "ownerAccount": 'arui', # 报告所属用户账号 "reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST "fileName": '2000-40-5-50--100-原油指标数据.xlsx-Brent活跃合约--2024-09-06-15-01-29-预测报告.pdf', # 文件名称 "fileBase64": '', # 文件内容base64 "categoryNo": 'yyjgycbg', # 研究报告分类编码 - "smartBusinessClassCode": 'JXTJGYCBG', # 分析报告分类编码 + "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码 "reportEmployeeCode": "E40116", # 报告人 "reportDeptCode": "D0044", # 报告部门 "productGroupCode": "RAW_MATERIAL" # 商品分类 @@ -170,7 +222,7 @@ upload_data = { warning_data = { - "groupNo": '000128', # 用户组编号 + "groupNo": '', # 用户组id "funcModule": '原油特征停更预警', "funcOperation": '原油特征停更预警', "data": { @@ -190,19 +242,60 @@ query_data_list_item_nos_data = { } } +push_data_value_list_data = { + "funcModule": "数据表信息列表", + "funcOperation": "新增", + "data": [ + {"dataItemNo": "91230600716676129", + "dataDate": "20230113", + "dataStatus": "add", + "dataValue": 100.11 + }, + {"dataItemNo": "91230600716676129P|ETHYL_BEN|CAPACITY", + "dataDate": "20230113", + "dataStatus": "add", + "dataValue": 100.55 + }, + {"dataItemNo": "91230600716676129P|ETHYL_BEN|CAPACITY", + "dataDate": "20230113", + "dataStatus": "add", + "dataValue": 100.55 + } + ] +} +# 八大维度数据项编码 +bdwd_items = { + 'ciri': 'syjphycbdwdcr', + 'benzhou': 'syjphycbdwdbz', + 'cizhou': 'syjlyycbdwdcz', + 'gezhou': 'syjlyycbdwdgz', + 'ciyue': 'syjlyycbdwdcy', + 'cieryue': 'syjlyycbdwdcey', + 'cisanyue': 'syjlyycbdwdcsy', + 'cisiyue': 'syjlyycbdwdcsiy', +} # 北京环境数据库 -host = '192.168.101.27' +# host = '192.168.101.27' +# port = 3306 +# dbusername = 'root' +# password = '123456' +# dbname = 'jingbo_test' + +# 京博测试环境 +host = 'rm-2zehj3r1n60ttz9x5ko.mysql.rds.aliyuncs.com' port = 3306 -dbusername = 'root' -password = '123456' -dbname = 'jingbo_test' +dbusername = 'jingbo' +password = 'shihua@123' +dbname = 'jingbo-test' + + table_name = 'v_tbl_crude_oil_warning' baichuan_table_name = 'V_TBL_BAICHUAN_YINGFU_VALUE' # select BAICHUAN_ID, DATA_DATE, DATA_VALUE from V_TBL_BAICHUAN_YINGFU_VALUE where BAICHUAN_ID in ('1588348470396475286', '1666') # 开关 -is_train = False # 是否训练 -is_debug = True # 是否调试 +is_train = True # 是否训练 +is_debug = False # 是否调试 is_eta = True # 是否使用eta接口 is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 is_timefurture = True # 是否使用时间特征 @@ -212,6 +305,7 @@ is_edbnamelist = False # 自定义特征，对应上面的edbnamelist is_update_eta = False # 预测结果上传到eta is_update_report = True # 是否上传报告 is_update_warning_data = False # 是否上传预警数据 +is_update_predict_value = True # 是否上传预测值到市场信息平台 is_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征 is_del_tow_month = True # 是否删除两个月不更新的特征 @@ -234,15 +328,12 @@ if add_kdj and is_edbnamelist: edbnamelist = edbnamelist+['K', 'D', 'J'] # 模型参数 -y = 'AVG-金能大唐久泰青州' +y = '煅烧焦山东高硫(高端S < 3.5，普货)(元/吨)' avg_cols = [ - 'PP：拉丝：1102K：出厂价：青州：国家能源宁煤（日）', - 'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）', - 'PP：拉丝：L5E89：出厂价：河北、鲁北：大唐内蒙多伦（日）', - 'PP：拉丝：HP550J：市场价：青岛：金能化学（日）' + ] offsite = 80 -offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）'] +offsite_col = [] horizon = 5 # 预测的步长 input_size = 40 # 输入序列长度 train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数 @@ -262,19 +353,19 @@ weight_dict = [0.4, 0.15, 0.1, 0.1, 0.25] # 权重 # 文件 -data_set = '石油焦指标数据.xlsx' # 数据集文件 -dataset = 'shiyoujiaodataset' # 数据集文件夹 +data_set = '石油焦铝用指标数据.xlsx' # 数据集文件 +dataset = 'shiyoujiaolvyongdataset' # 数据集文件夹 # 数据库名称 -db_name = os.path.join(dataset, 'jbsh_juxiting.db') +db_name = os.path.join(dataset, 'jbsh_shiyoujiao_lvyong.db') sqlitedb = SQLiteHandler(db_name) sqlitedb.connect() -settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}' +settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}' # 获取日期时间 # now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') # 获取当前日期时间 now = datetime.datetime.now().strftime('%Y-%m-%d') # 获取当前日期时间 -reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 +reportname = f'石油焦铝用大模型日度预测报告--{end_time}.pdf' # 报告文件名 reportname = reportname.replace(':', '-') # 替换冒号 if end_time == '': end_time = now diff --git a/main_shiyoujiao.py b/main_shiyoujiao.py new file mode 100644 index 0000000..c706c9f --- /dev/null +++ b/main_shiyoujiao.py @@ -0,0 +1,301 @@ +# 读取配置 +from lib.dataread import * +from lib.tools import SendMail,exception_logger +from models.nerulforcastmodels import ex_Model_Juxiting,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting + +import glob +import torch +torch.set_float32_matmul_precision("high") + + + +def predict_main(): + """ + 主预测函数，用于从 ETA 获取数据、处理数据、训练模型并进行预测。 + + 参数: + signature (BinanceAPI): Binance API 实例。 + etadata (EtaReader): ETA 数据读取器实例。 + is_eta (bool): 是否从 ETA 获取数据。 + data_set (str): 数据集名称。 + dataset (str): 数据集路径。 + add_kdj (bool): 是否添加 KDJ 指标。 + is_timefurture (bool): 是否添加时间衍生特征。 + end_time (str): 结束时间。 + is_edbnamelist (bool): 是否使用 EDB 名称列表。 + edbnamelist (list): EDB 名称列表。 + y (str): 预测目标列名。 + sqlitedb (SQLiteDB): SQLite 数据库实例。 + is_corr (bool): 是否进行相关性分析。 + horizon (int): 预测时域。 + input_size (int): 输入数据大小。 + train_steps (int): 训练步数。 + val_check_steps (int): 验证检查步数。 + early_stop_patience_steps (int): 早停耐心步数。 + is_debug (bool): 是否调试模式。 + dataset (str): 数据集名称。 + is_train (bool): 是否训练模型。 + is_fivemodels (bool): 是否使用五个模型。 + val_size (float): 验证集大小。 + test_size (float): 测试集大小。 + settings (dict): 模型设置。 + now (str): 当前时间。 + etadata (EtaReader): ETA 数据读取器实例。 + modelsindex (list): 模型索引列表。 + data (str): 数据类型。 + is_eta (bool): 是否从 ETA 获取数据。 + + 返回: + None + """ + global end_time + signature = BinanceAPI(APPID, SECRET) + etadata = EtaReader(signature=signature, + classifylisturl=classifylisturl, + classifyidlisturl=classifyidlisturl, + edbcodedataurl=edbcodedataurl, + edbcodelist=edbcodelist, + edbdatapushurl=edbdatapushurl, + edbdeleteurl=edbdeleteurl, + edbbusinessurl=edbbusinessurl + ) + # 获取数据 + if is_eta: + logger.info('从eta获取数据...') + signature = BinanceAPI(APPID, SECRET) + etadata = EtaReader(signature=signature, + classifylisturl=classifylisturl, + classifyidlisturl=classifyidlisturl, + edbcodedataurl=edbcodedataurl, + edbcodelist=edbcodelist, + edbdatapushurl=edbdatapushurl, + edbdeleteurl=edbdeleteurl, + edbbusinessurl=edbbusinessurl, + ) + df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_data(data_set=data_set, dataset=dataset) # 原始数据，未处理 + + if is_market: + logger.info('从市场信息平台获取数据...') + try: + # 如果是测试环境，最高价最低价取excel文档 + if server_host == '192.168.100.53': + logger.info('从excel文档获取最高价最低价') + df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju) + else: + logger.info('从市场信息平台获取数据') + df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju) + + except : + logger.info('最高最低价拼接失败') + + # 保存到xlsx文件的sheet表 + with pd.ExcelWriter(os.path.join(dataset,data_set)) as file: + df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) + df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) + + + # 数据处理 + df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, + end_time=end_time) + + else: + # 读取数据 + logger.info('读取本地数据：' + os.path.join(dataset, data_set)) + df,df_zhibiaoliebiao = getdata_juxiting(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, + is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 + + # 更改预测列名称 + df.rename(columns={y: 'y'}, inplace=True) + + if is_edbnamelist: + df = df[edbnamelist] + df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False) + # 保存最新日期的y值到数据库 + # 取第一行数据存储到数据库中 + first_row = df[['ds', 'y']].tail(1) + # 判断y的类型是否为float + if not isinstance(first_row['y'].values[0], float): + logger.info(f'{end_time}预测目标数据为空，跳过') + return None + + # 将最新真实值保存到数据库 + if not sqlitedb.check_table_exists('trueandpredict'): + first_row.to_sql('trueandpredict', sqlitedb.connection, index=False) + else: + for row in first_row.itertuples(index=False): + row_dict = row._asdict() + row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') + check_query = sqlitedb.select_data('trueandpredict', where_condition=f"ds = '{row.ds}'") + if len(check_query) > 0: + set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()]) + sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'") + continue + sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys()) + + # 更新accuracy表的y值 + if not sqlitedb.check_table_exists('accuracy'): + pass + else: + update_y = sqlitedb.select_data('accuracy',where_condition="y is null") + if len(update_y) > 0: + logger.info('更新accuracy表的y值') + # 找到update_y 中ds且df中的y的行 + update_y = update_y[update_y['ds']<=end_time] + logger.info(f'要更新y的信息：{update_y}') + # try: + for row in update_y.itertuples(index=False): + try: + row_dict = row._asdict() + yy = df[df['ds']==row_dict['ds']]['y'].values[0] + LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0] + HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0] + sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'") + except: + logger.info(f'更新accuracy表的y值失败：{row_dict}') + # except Exception as e: + # logger.info(f'更新accuracy表的y值失败：{e}') + + import datetime + # 判断当前日期是不是周一 + is_weekday = datetime.datetime.now().weekday() == 0 + if is_weekday: + logger.info('今天是周一，更新预测模型') + # 计算最近60天预测残差最低的模型名称 + model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60") + # 删除空值率为90%以上的列 + if len(model_results) > 10: + model_results = model_results.dropna(thresh=len(model_results)*0.1,axis=1) + # 删除空行 + model_results = model_results.dropna() + modelnames = model_results.columns.to_list()[2:-1] + for col in model_results[modelnames].select_dtypes(include=['object']).columns: + model_results[col] = model_results[col].astype(np.float32) + # 计算每个预测值与真实值之间的偏差率 + for model in modelnames: + model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y'] + # 获取每行对应的最小偏差率值 + min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1) + # 获取每行对应的最小偏差率值对应的列名 + min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1) + # 将列名索引转换为列名 + min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0]) + # 取出现次数最多的模型名称 + most_common_model = min_abs_error_rate_column_name.value_counts().idxmax() + logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}") + # 保存结果到数据库 + if not sqlitedb.check_table_exists('most_model'): + sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT") + sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',)) + + try: + if is_weekday: + # if True: + logger.info('今天是周一，发送特征预警') + # 上传预警信息到数据库 + warning_data_df = df_zhibiaoliebiao.copy() + warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']] + # 重命名列名 + warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'}) + from sqlalchemy import create_engine + import urllib + global password + if '@' in password: + password = urllib.parse.quote_plus(password) + + engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') + warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S") + warning_data_df['TENANT_CODE'] = 'T0004' + # 插入数据之前查询表数据然后新增id列 + existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine) + if not existing_data.empty: + max_id = existing_data['ID'].astype(int).max() + warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df)) + else: + warning_data_df['ID'] = range(1, 1 + len(warning_data_df)) + warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False) + if is_update_warning_data: + upload_warning_info(len(warning_data_df)) + except: + logger.info('上传预警信息到数据库失败') + + if is_corr: + df = corr_feature(df=df) + + df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用 + logger.info(f"开始训练模型...") + row, col = df.shape + + now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') + ex_Model_Juxiting(df, + horizon=horizon, + input_size=input_size, + train_steps=train_steps, + val_check_steps=val_check_steps, + early_stop_patience_steps=early_stop_patience_steps, + is_debug=is_debug, + dataset=dataset, + is_train=is_train, + is_fivemodels=is_fivemodels, + val_size=val_size, + test_size=test_size, + settings=settings, + now=now, + etadata=etadata, + modelsindex=modelsindex, + data=data, + is_eta=is_eta, + end_time=end_time, + ) + + + logger.info('模型训练完成') + + logger.info('训练数据绘图ing') + model_results3 = model_losss_juxiting(sqlitedb) + logger.info('训练数据绘图end') + + # 模型报告 + logger.info('制作报告ing') + title = f'{settings}--{end_time}-预测报告' # 报告标题 + reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 + reportname = reportname.replace(':', '-') # 替换冒号 + pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, + reportname=reportname,sqlitedb=sqlitedb), + + logger.info('制作报告end') + logger.info('模型训练完成') + + # # LSTM 单变量模型 + # ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset) + + # # lstm 多变量模型 + # ex_Lstm_M(df,n_days=input_size,out_days=horizon,is_debug=is_debug,datasetpath=dataset) + + # # GRU 模型 + # # ex_GRU(df) + + # 发送邮件 + m = SendMail( + username=username, + passwd=passwd, + recv=recv, + title=title, + content=content, + file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), + ssl=ssl, + ) + # m.send_mail() + + +if __name__ == '__main__': + # global end_time + # is_on = True + # # 遍历2024-11-25 到 2024-12-3 之间的工作日日期 + # for i_time in pd.date_range('2025-1-20', '2025-2-6', freq='B'): + # end_time = i_time.strftime('%Y-%m-%d') + # try: + # predict_main() + # except: + # pass + + predict_main() \ No newline at end of file diff --git a/main_shiyoujiao_puhuo.py b/main_shiyoujiao_puhuo.py index 2d94e58..b54cfc5 100644 --- a/main_shiyoujiao_puhuo.py +++ b/main_shiyoujiao_puhuo.py @@ -1,9 +1,9 @@ # 读取配置 from lib.dataread import * -from config_shiyoujiao_puhuo import * +from config_shiyoujiao_lvyong import * from lib.tools import SendMail, exception_logger -from models.nerulforcastmodels import ex_Model, model_losss_juxiting, tansuanli_export_pdf, pp_export_pdf +from models.nerulforcastmodels import ex_Model, model_losss, shiyoujiao_lvyong_export_pdf import datetime import torch torch.set_float32_matmul_precision("high") @@ -13,14 +13,12 @@ global_config.update({ 'logger': logger, 'dataset': dataset, 'y': y, - 'offsite_col': offsite_col, - 'avg_cols': avg_cols, - 'offsite': offsite, - 'edbcodenamedict': edbcodenamedict, 'is_debug': is_debug, 'is_train': is_train, 'is_fivemodels': is_fivemodels, 'settings': settings, + 'weight_dict': weight_dict, + 'baichuanidnamedict': baichuanidnamedict, # 模型参数 @@ -33,6 +31,8 @@ global_config.update({ 'test_size': test_size, 'modelsindex': modelsindex, 'rote': rote, + 'bdwd_items': bdwd_items, + 'baichuanidnamedict': baichuanidnamedict, # 特征工程开关 'is_del_corr': is_del_corr, @@ -40,6 +40,7 @@ global_config.update({ 'is_eta': is_eta, 'is_update_eta': is_update_eta, 'is_fivemodels': is_fivemodels, + 'is_update_predict_value': is_update_predict_value, 'early_stop_patience_steps': early_stop_patience_steps, # 时间参数 @@ -58,6 +59,10 @@ global_config.update({ 'query_data_list_item_nos_url': query_data_list_item_nos_url, 'query_data_list_item_nos_data': query_data_list_item_nos_data, + # 上传数据项 + 'push_data_value_list_url': push_data_value_list_url, + 'push_data_value_list_data': push_data_value_list_data, + # eta 配置 'APPID': APPID, 'SECRET': SECRET, @@ -69,14 +74,71 @@ global_config.update({ 'edbdatapushurl': edbdatapushurl, 'edbdeleteurl': edbdeleteurl, 'edbbusinessurl': edbbusinessurl, + 'edbcodenamedict': edbcodenamedict, 'ClassifyId': ClassifyId, 'classifylisturl': classifylisturl, # 数据库配置 'sqlitedb': sqlitedb, + 'db_mysql': db_mysql, + 'baichuan_table_name': baichuan_table_name, }) +def push_market_value(): + logger.info('发送预测结果到市场信息平台') + # 读取预测数据和模型评估数据 + predict_file_path = os.path.join(config.dataset, 'predict.csv') + model_eval_file_path = os.path.join(config.dataset, 'model_evaluation.csv') + try: + predictdata_df = pd.read_csv(predict_file_path) + top_models_df = pd.read_csv(model_eval_file_path) + except FileNotFoundError as e: + logger.error(f"文件未找到: {e}") + return + + predictdata = predictdata_df.copy() + + # 取模型前十 + top_models = top_models_df['模型(Model)'].head(10).tolist() + + # 计算前十模型的均值 + predictdata_df['top_models_mean'] = predictdata_df[top_models].mean(axis=1) + + # 打印日期和前十模型均值 + print(predictdata_df[['ds', 'top_models_mean']]) + + # 准备要推送的数据 + first_mean = predictdata_df['top_models_mean'].iloc[0] + last_mean = predictdata_df['top_models_mean'].iloc[-1] + # 保留两位小数 + first_mean = round(first_mean, 2) + last_mean = round(last_mean, 2) + + predictdata = [ + { + "dataItemNo": global_config['bdwd_items']['ciri'], + "dataDate": global_config['end_time'].replace('-', ''), + "dataStatus": "add", + "dataValue": first_mean + }, + { + "dataItemNo": global_config['bdwd_items']['benzhou'], + "dataDate": global_config['end_time'].replace('-', ''), + "dataStatus": "add", + "dataValue": last_mean + } + ] + + print(predictdata) + + # 推送数据到市场信息平台 + try: + push_market_data(predictdata) + except Exception as e: + logger.error(f"推送数据失败: {e}") + + def predict_main(): """ 主预测函数，用于从 ETA 获取数据、处理数据、训练模型并进行预测。 @@ -116,31 +178,23 @@ def predict_main(): 返回: None """ - global end_time - signature = BinanceAPI(APPID, SECRET) - etadata = EtaReader(signature=signature, - classifylisturl=classifylisturl, - classifyidlisturl=classifyidlisturl, - edbcodedataurl=edbcodedataurl, - edbcodelist=edbcodelist, - edbdatapushurl=edbdatapushurl, - edbdeleteurl=edbdeleteurl, - edbbusinessurl=edbbusinessurl - ) + + end_time = global_config['end_time'] # 获取数据 if is_eta: logger.info('从eta获取数据...') signature = BinanceAPI(APPID, SECRET) etadata = EtaReader(signature=signature, - classifylisturl=classifylisturl, - classifyidlisturl=classifyidlisturl, - edbcodedataurl=edbcodedataurl, - edbcodelist=edbcodelist, - edbdatapushurl=edbdatapushurl, - edbdeleteurl=edbdeleteurl, - edbbusinessurl=edbbusinessurl, + classifylisturl=global_config['classifylisturl'], + classifyidlisturl=global_config['classifyidlisturl'], + edbcodedataurl=global_config['edbcodedataurl'], + edbcodelist=global_config['edbcodelist'], + edbdatapushurl=global_config['edbdatapushurl'], + edbdeleteurl=global_config['edbdeleteurl'], + edbbusinessurl=global_config['edbbusinessurl'], + classifyId=global_config['ClassifyId'], ) - df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_data( + df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_lvyong_data( data_set=data_set, dataset=dataset) # 原始数据，未处理 if is_market: @@ -158,20 +212,33 @@ def predict_main(): except: logger.info('最高最低价拼接失败') + if len(global_config['baichuanidnamedict']) > 0: + logger.info('从市场数据库获取百川数据...') + baichuandf = get_baichuan_data(global_config['baichuanidnamedict']) + df_zhibiaoshuju = pd.merge( + df_zhibiaoshuju, baichuandf, on='date', how='outer') + # 指标列表添加百川数据 + df_baichuanliebiao = pd.DataFrame( + global_config['baichuanidnamedict'].items(), columns=['指标id', '指标名称']) + df_baichuanliebiao['指标分类'] = '石油焦对标炼厂价格' + df_baichuanliebiao['频度'] = '其他' + df_zhibiaoliebiao = pd.concat( + [df_zhibiaoliebiao, df_baichuanliebiao], axis=0) + # 保存到xlsx文件的sheet表 with pd.ExcelWriter(os.path.join(dataset, data_set)) as file: df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) # 数据处理 - df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, - end_time=end_time) + df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, + end_time=end_time) else: # 读取数据 logger.info('读取本地数据：' + os.path.join(dataset, data_set)) - df, df_zhibiaoliebiao = getdata_juxiting(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, - is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 + df, df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, + is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 # 更改预测列名称 df.rename(columns={y: 'y'}, inplace=True) @@ -193,7 +260,18 @@ def predict_main(): else: for row in first_row.itertuples(index=False): row_dict = row._asdict() - row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') + config.logger.info(f'要保存的真实值：{row_dict}') + # 判断ds是否为字符串类型,如果不是则转换为字符串类型 + if isinstance(row_dict['ds'], (pd.Timestamp, datetime.datetime)): + row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') + elif not isinstance(row_dict['ds'], str): + try: + row_dict['ds'] = pd.to_datetime( + row_dict['ds']).strftime('%Y-%m-%d') + except: + logger.warning(f"无法解析的时间格式: {row_dict['ds']}") + # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') + # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') check_query = sqlitedb.select_data( 'trueandpredict', where_condition=f"ds = '{row.ds}'") if len(check_query) > 0: @@ -230,7 +308,6 @@ def predict_main(): # except Exception as e: # logger.info(f'更新accuracy表的y值失败：{e}') - import datetime # 判断当前日期是不是周一 is_weekday = datetime.datetime.now().weekday() == 0 if is_weekday: @@ -315,76 +392,64 @@ def predict_main(): row, col = df.shape now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') - ex_Model_Juxiting(df, - horizon=horizon, - input_size=input_size, - train_steps=train_steps, - val_check_steps=val_check_steps, - early_stop_patience_steps=early_stop_patience_steps, - is_debug=is_debug, - dataset=dataset, - is_train=is_train, - is_fivemodels=is_fivemodels, - val_size=val_size, - test_size=test_size, - settings=settings, - now=now, - etadata=etadata, - modelsindex=modelsindex, - data=data, - is_eta=is_eta, - end_time=end_time, - ) + ex_Model(df, + horizon=global_config['horizon'], + input_size=global_config['input_size'], + train_steps=global_config['train_steps'], + val_check_steps=global_config['val_check_steps'], + early_stop_patience_steps=global_config['early_stop_patience_steps'], + is_debug=global_config['is_debug'], + dataset=global_config['dataset'], + is_train=global_config['is_train'], + is_fivemodels=global_config['is_fivemodels'], + val_size=global_config['val_size'], + test_size=global_config['test_size'], + settings=global_config['settings'], + now=now, + etadata=global_config['etadata'], + modelsindex=global_config['modelsindex'], + data=data, + is_eta=global_config['is_eta'], + end_time=global_config['end_time'], + ) logger.info('模型训练完成') logger.info('训练数据绘图ing') - model_results3 = model_losss_juxiting(sqlitedb) + model_results3 = model_losss(sqlitedb, end_time=end_time) logger.info('训练数据绘图end') # 模型报告 logger.info('制作报告ing') title = f'{settings}--{end_time}-预测报告' # 报告标题 - reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名 + reportname = f'石油焦铝用大模型日度预测--{end_time}.pdf' # 报告文件名 reportname = reportname.replace(':', '-') # 替换冒号 - pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, - reportname=reportname, sqlitedb=sqlitedb), + shiyoujiao_lvyong_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, + reportname=reportname, sqlitedb=sqlitedb), logger.info('制作报告end') logger.info('模型训练完成') - # # LSTM 单变量模型 - # ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset) - - # # lstm 多变量模型 - # ex_Lstm_M(df,n_days=input_size,out_days=horizon,is_debug=is_debug,datasetpath=dataset) - - # # GRU 模型 - # # ex_GRU(df) + push_market_value() # 发送邮件 - m = SendMail( - username=username, - passwd=passwd, - recv=recv, - title=title, - content=content, - file=max(glob.glob(os.path.join(dataset, '*.pdf')), - key=os.path.getctime), - ssl=ssl, - ) + # m = SendMail( + # username=username, + # passwd=passwd, + # recv=recv, + # title=title, + # content=content, + # file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), + # ssl=ssl, + # ) # m.send_mail() if __name__ == '__main__': # global end_time - # is_on = True # # 遍历2024-11-25 到 2024-12-3 之间的工作日日期 - # for i_time in pd.date_range('2025-1-20', '2025-2-6', freq='B'): + # for i_time in pd.date_range('2024-12-1', '2025-2-26', freq='W'): # end_time = i_time.strftime('%Y-%m-%d') - # try: - # predict_main() - # except: - # pass + # predict_main() predict_main()