石油焦普货日度预测配置
This commit is contained in:
workpc
parent
deab1ec0bb
commit
f8fa931067
@ -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"
|
||||
]
|
||||
},
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -11,23 +11,23 @@
|
||||
" <script type=\"text/javascript\">\n",
|
||||
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
|
||||
" if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
|
||||
" if (typeof require !== 'undefined') {\n",
|
||||
" require.undef(\"plotly\");\n",
|
||||
" requirejs.config({\n",
|
||||
" paths: {\n",
|
||||
" 'plotly': ['https://cdn.plot.ly/plotly-2.12.1.min']\n",
|
||||
" }\n",
|
||||
" });\n",
|
||||
" require(['plotly'], function(Plotly) {\n",
|
||||
" window._Plotly = Plotly;\n",
|
||||
" });\n",
|
||||
" }\n",
|
||||
" </script>\n",
|
||||
" <script type=\"module\">import \"https://cdn.plot.ly/plotly-3.0.1.min\"</script>\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,
|
||||
|
||||
Binary file not shown.
BIN
aisenzhecode/液化石油气/化工品价格预测准确率.xlsx
Normal file
BIN
aisenzhecode/液化石油气/化工品价格预测准确率.xlsx
Normal file
Binary file not shown.
320
config_shiyoujiao.py
Normal file
320
config_shiyoujiao.py
Normal file
@ -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)
|
||||
|
||||
@ -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 = [
|
||||
|
||||
]
|
||||
|
||||
@ -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
|
||||
|
||||
301
main_shiyoujiao.py
Normal file
301
main_shiyoujiao.py
Normal file
@ -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()
|
||||
@ -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()
|
||||
|
||||
Loading…
Reference in New Issue
Block a user