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 6b87d61..2a88fb9 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 @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 12, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -303,7 +303,7 @@ " 复盘分析后发现2024-7月开始,开工率数据从0.28 变为了28 ,改为下面的判断规则\n", " '''\n", " if df1.loc[1,'70号沥青开工率'] / 100 > 0.3:\n", - " a = (df1.loc[1,'70号沥青开工率'] / 100 -0.2)*5/0.1\n", + " a = -(df1.loc[1,'70号沥青开工率'] / 100 -0.2)*5/0.1\n", " else :\n", " a = 0\n", " b = df1.loc[1,'资金因素']\n", 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 deleted file mode 100644 index 31df769..0000000 Binary files a/aisenzhecode/液化石油气/化工品价格预测准确率.xlsx and /dev/null differ diff --git a/aisenzhecode/液化石油气/液化气价格预测.py b/aisenzhecode/液化石油气/液化气价格预测.py index 384c57f..f4acfff 100644 --- a/aisenzhecode/液化石油气/液化气价格预测.py +++ b/aisenzhecode/液化石油气/液化气价格预测.py @@ -61,7 +61,8 @@ login_push_data = { "funcOperation": "获取token" } -read_file_path_name = "液化气数据.xls" +# read_file_path_name = "液化气数据.xls" +read_file_path_name = "液化气数据.xlsx" one_cols = [] two_cols = [] @@ -183,6 +184,88 @@ def upload_data_to_system(token_push, date): print('预测值:', data['data'][0]['dataValue']) +def getLogToken(): + login_res = requests.post(url=login_url, json=login_data, timeout=(3, 5)) + text = json.loads(login_res.text) + if text["status"]: + token = text["data"]["accessToken"] + else: + print("获取认证失败") + token = None + return token + + +def updateYesterdayExcelData(date='', token=None): + # 使用pandas读取Excel文件 + df = pd.read_excel(read_file_path_name, engine='openpyxl') + + # 获取第二行的数据作为列名 + one_cols = df.iloc[0, :].tolist() + + # 获取当前日期的前一天 + if date == '': + previous_date = (datetime.now() - timedelta(days=1) + ).strftime('%Y-%m-%d') + else: + # 字符串转日期 + previous_date = (datetime.strptime(date, "%Y-%m-%d") - + timedelta(days=1)).strftime('%Y-%m-%d') + + cur_time, cur_time2 = getNow(previous_date) + search_data = { + "data": { + "date": cur_time, + "dataItemNoList": one_cols[1:] + }, + "funcModule": "数据项", + "funcOperation": "查询" + } + headers = {"Authorization": token} + search_res = requests.post( + url=search_url, headers=headers, json=search_data, timeout=(3, 5)) + print('数据请求结果:') + print(search_res.text) + search_value = json.loads(search_res.text)["data"] + if search_value: + datas = search_value + else: + datas = None + + append_rows = [cur_time2] + dataItemNo_dataValue = {} + for data_value in datas: + if "dataValue" not in data_value: + print(data_value) + dataItemNo_dataValue[data_value["dataItemNo"]] = "" + else: + dataItemNo_dataValue[data_value["dataItemNo"] + ] = data_value["dataValue"] + for value in one_cols[1:]: + if value in dataItemNo_dataValue: + append_rows.append(dataItemNo_dataValue[value]) + else: + append_rows.append("") + + print('更新数据前') + print(df.tail(1)) + # 检查日期是否已存在于数据中 + if previous_date not in df['日期'].values: + # 将新的数据添加到DataFrame中 + new_row = pd.DataFrame([append_rows], columns=df.columns.tolist()) + df = pd.concat([df, new_row], ignore_index=True) + else: + # 更新现有数据 + print('日期存在,即将更新') + print('新数据', append_rows[1:]) + df.loc[df['日期'] == previous_date, + df.columns.tolist()[1:]] = append_rows[1:] + + print('更新数据后') + print(df.tail(1)) + # 使用pandas保存Excel文件 + df.to_excel("液化气数据.xls", index=False, engine='openpyxl') + + price_list = [] @@ -553,14 +636,12 @@ def save_xls_2(append_rows): start_date = datetime(2025, 3, 10) end_date = datetime(2025, 3, 20) +token = getLogToken() while start_date < end_date: - # 更新昨日数据 - start_1(start_date) - date = start_date.strftime('%Y%m%d') - # 获取当日数据,预测数据,并上传 - start(date) - # time.sleep(1) - start_date += timedelta(days=1) + date = start_date.strftime('%Y-%m-%d') + updateYesterdayExcelData(date, token=token) + # start(date) + # # time.sleep(1) + # start_1(start_date) + # start_date += timedelta(days=1) time.sleep(5) - -# print(price_list) diff --git a/aisenzhecode/液化石油气/液化气价格预测ytj.ipynb b/aisenzhecode/液化石油气/液化气价格预测ytj.ipynb index 1f487b0..b8c3e8b 100644 --- a/aisenzhecode/液化石油气/液化气价格预测ytj.ipynb +++ b/aisenzhecode/液化石油气/液化气价格预测ytj.ipynb @@ -2,9 +2,17 @@ "cells": [ { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": {}, "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "WARNING:tensorflow:From C:\\Users\\EDY\\AppData\\Roaming\\Python\\Python311\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n", + "\n" + ] + }, { "data": { "text/html": [ @@ -79,9 +87,6 @@ "import random\n", "import time\n", "\n", - "\n", - "\n", - "\n", "from plotly import __version__\n", "from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot\n", "\n", @@ -501,7 +506,70 @@ " pickle.dump(grid_search_XGB, file)\n", "\n", "\n", - " \n", + "def updateYesterdayExcelData(date='', token=None):\n", + " # 使用pandas读取Excel文件\n", + " df = pd.read_excel(read_file_path_name, engine='openpyxl')\n", + "\n", + " # 获取第二行的数据作为列名\n", + " one_cols = df.iloc[0,:].tolist()\n", + "\n", + " # 获取当前日期的前一天\n", + " if date == '':\n", + " previous_date = (datetime.now() - timedelta(days=1)).strftime('%Y-%m-%d')\n", + " else:\n", + " # 字符串转日期\n", + " previous_date = (datetime.strptime(date, \"%Y-%m-%d\")-timedelta(days=1)).strftime('%Y-%m-%d')\n", + " \n", + "\n", + " cur_time, cur_time2 = getNow(previous_date)\n", + " search_data = {\n", + " \"data\": {\n", + " \"date\": cur_time,\n", + " \"dataItemNoList\": one_cols[1:]\n", + " },\n", + " \"funcModule\": \"数据项\",\n", + " \"funcOperation\": \"查询\"\n", + " }\n", + " headers = {\"Authorization\": token}\n", + " search_res = requests.post(url=search_url, headers=headers, json=search_data, timeout=(3, 5))\n", + " search_value = json.loads(search_res.text)[\"data\"]\n", + " if search_value:\n", + " datas = search_value\n", + " else:\n", + " datas = None\n", + "\n", + " append_rows = [cur_time2]\n", + " dataItemNo_dataValue = {}\n", + " for data_value in datas:\n", + " if \"dataValue\" not in data_value:\n", + " print(data_value)\n", + " dataItemNo_dataValue[data_value[\"dataItemNo\"]] = \"\"\n", + " else:\n", + " dataItemNo_dataValue[data_value[\"dataItemNo\"]] = data_value[\"dataValue\"]\n", + " for value in one_cols[1:]:\n", + " if value in dataItemNo_dataValue:\n", + " append_rows.append(dataItemNo_dataValue[value])\n", + " else:\n", + " append_rows.append(\"\")\n", + "\n", + " print('更新数据前')\n", + " print(df.tail(1))\n", + " # 检查日期是否已存在于数据中\n", + " if previous_date not in df['日期'].values:\n", + " # 将新的数据添加到DataFrame中\n", + " new_row = pd.DataFrame([append_rows], columns=df.columns.tolist())\n", + " df = pd.concat([df, new_row], ignore_index=True)\n", + " else:\n", + " # 更新现有数据\n", + " print('日期存在,即将更新')\n", + " print('新数据',append_rows[1:])\n", + " df.loc[df['日期'] == previous_date, df.columns.tolist()[1:]] = append_rows[1:]\n", + "\n", + " print('更新数据后')\n", + " print(df.tail(1))\n", + " # 使用pandas保存Excel文件\n", + " df.to_excel(\"液化气数据.xls\", index=False, engine='openpyxl')\n", + "\n", "\n", "def read_xls_data_bak():\n", " global one_cols, two_cols\n", @@ -772,7 +840,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 1, "metadata": { "scrolled": true }, @@ -818,43 +886,32 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 2, "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "获取到的数据项ID['YHQMXBB|C01100008|STRIKE_PRICE', 'C01100008|CORTED_VALUE', 'C01100008|AUCTION_MAX_PRICE', 'C01100008|AMOUNT', 'ICE_CL0_LAST_YEDAY_PRICE', '100028046|LISTING_PRICE', 'C01100008|PLAN_SALE', '91370200163576944B|C01100008|STRIKE_PRICE', '9137078672073757X8|C01100008|STRIKE_PRICE', '91370500674526498A|C01100008|STRIKE_PRICE', '91370305773165341A|C01100008|STRIKE_PRICE', '91370521164880008P|C01100008|STRIKE_PRICE', '91370321164425136B|C01100008|STRIKE_PRICE', 'SD|GC|ZDW|LIST_PRICE', '370500|ISOBUTANE|LIST_PRICE', 'SD|YT|SG|LIST_PRICE', '91110000710926094P|C01100008|SUPPLY_MERE', '91110000710932515R|C01100008|SUPPLY_MERE', '91370500674526498A|C01100008|SUPPLY_MERE', '91370321164425136B|C01100008|SUPPLY_MERE', 'C01100008|OTHER|SUPPLY_MERE', 'SD|WJH|DEMANDS', 'C01100008|SUY_DED_DAP', 'C01100008|EFFECTIVE_STOCK', '912102117169477344|C01100008|STRIKE_PRICE', '91110304102767480H|C01100008|STRIKE_PRICE', '91130193670310403L|C01100008|STRIKE_PRICE', 'HD|LPG|IMPORT_PRICE', 'SD|WJH|SALES_PRICE']\n", - "获取的token: eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJzdWIiOiJhcGlfZGV2IiwidGgiOiI4YTQ1NzdkYmQ5MTk2NzU3NThkNTc5OTlhMWU4OTFmZSIsImx0IjoiYXBpIiwiaXNzIjoiIiwidG0iOiJQQyIsImV4cCI6MTc0MjMzMDEyMSwianRpIjoiMmI5ZmUzNTA5YjNmNGU4OTkzMjRiNzU1MzQ4ODlkNTQifQ.nezcKMQq4GnNoHKwvIOEe-1pK0Oz3LliiM8yYjOMG8c\n", - "补充20250228数据\n", - "数据项查询参数search_data:\n", - "{'data': {'date': '20250228', 'dataItemNoList': ['C01100008|CORTED_VALUE', 'C01100008|AUCTION_MAX_PRICE', 'C01100008|AMOUNT', 'ICE_CL0_LAST_YEDAY_PRICE', '100028046|LISTING_PRICE', 'C01100008|PLAN_SALE', '91370200163576944B|C01100008|STRIKE_PRICE', '9137078672073757X8|C01100008|STRIKE_PRICE', '91370500674526498A|C01100008|STRIKE_PRICE', '91370305773165341A|C01100008|STRIKE_PRICE', '91370521164880008P|C01100008|STRIKE_PRICE', '91370321164425136B|C01100008|STRIKE_PRICE', 'SD|GC|ZDW|LIST_PRICE', '370500|ISOBUTANE|LIST_PRICE', 'SD|YT|SG|LIST_PRICE', '91110000710926094P|C01100008|SUPPLY_MERE', '91110000710932515R|C01100008|SUPPLY_MERE', '91370500674526498A|C01100008|SUPPLY_MERE', '91370321164425136B|C01100008|SUPPLY_MERE', 'C01100008|OTHER|SUPPLY_MERE', 'SD|WJH|DEMANDS', 'C01100008|SUY_DED_DAP', 'C01100008|EFFECTIVE_STOCK', '912102117169477344|C01100008|STRIKE_PRICE', '91110304102767480H|C01100008|STRIKE_PRICE', '91130193670310403L|C01100008|STRIKE_PRICE', 'HD|LPG|IMPORT_PRICE', 'SD|WJH|SALES_PRICE']}, 'funcModule': '数据项', 'funcOperation': '查询'}\n", - "数据项查询结果search_res:\n", - "{\"confirmFlg\":false,\"data\":[{\"dataDate\":\"20250228\",\"dataItemNo\":\"100028046|LISTING_PRICE\",\"dataValue\":8441.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"370500|ISOBUTANE|LIST_PRICE\",\"dataValue\":5380.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91110000710926094P|C01100008|SUPPLY_MERE\",\"dataValue\":1300.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91110000710932515R|C01100008|SUPPLY_MERE\"},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91110304102767480H|C01100008|STRIKE_PRICE\",\"dataValue\":5150.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91130193670310403L|C01100008|STRIKE_PRICE\",\"dataValue\":5150.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"912102117169477344|C01100008|STRIKE_PRICE\",\"dataValue\":4670.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370200163576944B|C01100008|STRIKE_PRICE\",\"dataValue\":5300.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370305773165341A|C01100008|STRIKE_PRICE\",\"dataValue\":5600.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370321164425136B|C01100008|STRIKE_PRICE\",\"dataValue\":5500.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370321164425136B|C01100008|SUPPLY_MERE\",\"dataValue\":200.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370500674526498A|C01100008|STRIKE_PRICE\",\"dataValue\":5488.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370500674526498A|C01100008|SUPPLY_MERE\",\"dataValue\":175.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"91370521164880008P|C01100008|STRIKE_PRICE\",\"dataValue\":5455.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|AMOUNT\",\"dataValue\":342.72000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|AUCTION_MAX_PRICE\",\"dataValue\":5500.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|CORTED_VALUE\",\"dataValue\":5500.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|EFFECTIVE_STOCK\",\"dataValue\":-550.20000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|OTHER|SUPPLY_MERE\",\"dataValue\":5000.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|PLAN_SALE\",\"dataValue\":500.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"C01100008|SUY_DED_DAP\",\"dataValue\":-50.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"HD|LPG|IMPORT_PRICE\",\"dataValue\":5400.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"ICE_CL0_LAST_YEDAY_PRICE\",\"dataValue\":73.35000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"SD|GC|ZDW|LIST_PRICE\",\"dataValue\":5250.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"SD|WJH|DEMANDS\",\"dataValue\":8500.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"SD|WJH|SALES_PRICE\",\"dataValue\":8400.00000000},{\"dataDate\":\"20250228\",\"dataItemNo\":\"SD|YT|SG|LIST_PRICE\",\"dataValue\":6050.00000000}],\"status\":true}\n", - "数据项查询结果: [{'dataDate': '20250228', 'dataItemNo': '100028046|LISTING_PRICE', 'dataValue': 8441.0}, {'dataDate': '20250228', 'dataItemNo': '370500|ISOBUTANE|LIST_PRICE', 'dataValue': 5380.0}, {'dataDate': '20250228', 'dataItemNo': '91110000710926094P|C01100008|SUPPLY_MERE', 'dataValue': 1300.0}, {'dataDate': '20250228', 'dataItemNo': '91110000710932515R|C01100008|SUPPLY_MERE'}, {'dataDate': '20250228', 'dataItemNo': '91110304102767480H|C01100008|STRIKE_PRICE', 'dataValue': 5150.0}, {'dataDate': '20250228', 'dataItemNo': '91130193670310403L|C01100008|STRIKE_PRICE', 'dataValue': 5150.0}, {'dataDate': '20250228', 'dataItemNo': '912102117169477344|C01100008|STRIKE_PRICE', 'dataValue': 4670.0}, {'dataDate': '20250228', 'dataItemNo': '91370200163576944B|C01100008|STRIKE_PRICE', 'dataValue': 5300.0}, {'dataDate': '20250228', 'dataItemNo': '91370305773165341A|C01100008|STRIKE_PRICE', 'dataValue': 5600.0}, {'dataDate': '20250228', 'dataItemNo': '91370321164425136B|C01100008|STRIKE_PRICE', 'dataValue': 5500.0}, {'dataDate': '20250228', 'dataItemNo': '91370321164425136B|C01100008|SUPPLY_MERE', 'dataValue': 200.0}, {'dataDate': '20250228', 'dataItemNo': '91370500674526498A|C01100008|STRIKE_PRICE', 'dataValue': 5488.0}, {'dataDate': '20250228', 'dataItemNo': '91370500674526498A|C01100008|SUPPLY_MERE', 'dataValue': 175.0}, {'dataDate': '20250228', 'dataItemNo': '91370521164880008P|C01100008|STRIKE_PRICE', 'dataValue': 5455.0}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|AMOUNT', 'dataValue': 342.72}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|AUCTION_MAX_PRICE', 'dataValue': 5500.0}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|CORTED_VALUE', 'dataValue': 5500.0}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|EFFECTIVE_STOCK', 'dataValue': -550.2}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|OTHER|SUPPLY_MERE', 'dataValue': 5000.0}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|PLAN_SALE', 'dataValue': 500.0}, {'dataDate': '20250228', 'dataItemNo': 'C01100008|SUY_DED_DAP', 'dataValue': -50.0}, {'dataDate': '20250228', 'dataItemNo': 'HD|LPG|IMPORT_PRICE', 'dataValue': 5400.0}, {'dataDate': '20250228', 'dataItemNo': 'ICE_CL0_LAST_YEDAY_PRICE', 'dataValue': 73.35}, {'dataDate': '20250228', 'dataItemNo': 'SD|GC|ZDW|LIST_PRICE', 'dataValue': 5250.0}, {'dataDate': '20250228', 'dataItemNo': 'SD|WJH|DEMANDS', 'dataValue': 8500.0}, {'dataDate': '20250228', 'dataItemNo': 'SD|WJH|SALES_PRICE', 'dataValue': 8400.0}, {'dataDate': '20250228', 'dataItemNo': 'SD|YT|SG|LIST_PRICE', 'dataValue': 6050.0}]\n", - "{'dataDate': '20250228', 'dataItemNo': '91110000710932515R|C01100008|SUPPLY_MERE'}\n", - "添加的行: ['20250228', '', 5500.0, 5500.0, 342.72, 73.35, 8441.0, 500.0, 5300.0, '', 5488.0, 5600.0, 5455.0, 5500.0, 5250.0, 5380.0, 6050.0, 1300.0, '', 175.0, 200.0, 5000.0, 8500.0, -50.0, -550.2, 4670.0, 5150.0, 5150.0, 5400.0, 8400.0]\n", - "Index(['Date', 'Price', '修正价', '竞拍最高价', '液化石油气|发货量', '昨日布伦特价格', '昨日92#汽油价格',\n", - " '计划出货量', '青岛石化', '中化工-昌邑', '海科瑞林', '鑫泰石化|液化石油气|成交价', '垦利价格', '汇丰价格',\n", - " '正丁烷', '异丁烷价格', '顺酐', '中石化供应量', '中化工供应量', '海科供应量', '汇丰供应量', '京博和其他供应量',\n", - " '烷基化需求量', '昨日烷基化价差', '我司库存', '东北-大连石化', '华北-燕山石化', '华北-石家庄炼化',\n", - " '昨日原料气价格', '烷基化油销售价格'],\n", - " dtype='object')\n", - "保存数据时发生错误: 'Date'\n" + "ename": "NameError", + "evalue": "name 'datetime' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m start_date \u001b[38;5;241m=\u001b[39m datetime(\u001b[38;5;241m2025\u001b[39m, \u001b[38;5;241m3\u001b[39m, \u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m 2\u001b[0m end_date \u001b[38;5;241m=\u001b[39m datetime(\u001b[38;5;241m2025\u001b[39m, \u001b[38;5;241m3\u001b[39m, \u001b[38;5;241m12\u001b[39m)\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m start_date \u001b[38;5;241m<\u001b[39m end_date:\n", + "\u001b[1;31mNameError\u001b[0m: name 'datetime' is not defined" ] } ], "source": [ "start_date = datetime(2025, 3, 1)\n", - "end_date = datetime(2025, 3, 2)\n", + "end_date = datetime(2025, 3, 12)\n", "\n", "while start_date < end_date:\n", " date = start_date.strftime('%Y%m%d')\n", + " updateYesterdayExcelData(date)\n", " # start(date)\n", - " # time.sleep(1)\n", - " start_1(start_date)\n", - " start_date += timedelta(days=1)\n", + " # # time.sleep(1)\n", + " # start_1(start_date)\n", + " # start_date += timedelta(days=1)\n", " time.sleep(5)\n", "\n", "# print(price_list)" diff --git a/aisenzhecode/液化石油气/液化气数据.xlsx b/aisenzhecode/液化石油气/液化气数据.xlsx new file mode 100644 index 0000000..0652c5c Binary files /dev/null and b/aisenzhecode/液化石油气/液化气数据.xlsx differ diff --git a/config_shiyoujiao.py b/config_shiyoujiao.py deleted file mode 100644 index c6a6a5d..0000000 --- a/config_shiyoujiao.py +++ /dev/null @@ -1,320 +0,0 @@ -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 new file mode 100644 index 0000000..895a9b7 --- /dev/null +++ b/config_shiyoujiao_lvyong.py @@ -0,0 +1,408 @@ +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' + +edbcodenamedict = { + 'C2403283369': '预赔阳极加工利润(高端)', + 'C2403285560': '预培阳极加工利润(低端)', + 'C2403288616': '低硫石油焦煅烧利润', + 'S6949656': '平均价:氧化铝:一级:全国', + 'S5807052': '氧化铝:一级:贵阳', + 'S5443355': '市场价:煤沥青:河北地区', + 'S5443357': '市场价:煤沥青:山西地区', + '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)', + 'ID00150273': '石油焦:1 # :市场低端价:东北地区(日)', + 'ID00150281': '石油焦:1 # :市场主流价:东北地区(日)', + 'ID00150277': '石油焦:1 # :市场高端价:东北地区(日)', + 'ID00150289': '石油焦:2 # :市场低端价:华东地区(日)', + 'ID00150285': '石油焦:2 # :市场低端价:西北地区(日)', + 'ID00150313': '石油焦:2 # :市场主流价:华东地区(日)', + 'ID00150309': '石油焦:2 # :市场主流价:西北地区(日)', + 'ID00150301': '石油焦:2 # :市场高端价:华东地区(日)', + 'ID00150297': '石油焦:2 # :市场高端价:西北地区(日)', + '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)', + 'ID00150337': '石油焦:2 # B:市场低端价:华南地区(日)', + 'ID00150341': '石油焦:2 # B:市场低端价:华中地区(日)', + 'ID00150361': '石油焦:2 # B:市场主流价:华南地区(日)', + 'ID00150365': '石油焦:2 # B:市场主流价:华中地区(日)', + 'ID00150349': '石油焦:2 # B:市场高端价:华南地区(日)', + 'ID00150353': '石油焦:2 # B:市场高端价:华中地区(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)', + 'ID00150369': '石油焦:3 # :市场低端价:华中地区(日)', + 'ID00150373': '石油焦:3 # :市场高端价:华中地区(日)', + 'ID00150385': '石油焦:3 # A:市场高端价:山东(日)', + 'ID00150393': '石油焦:3 # B:市场低端价:华东地区(日)', + 'ID00150409': '石油焦:3 # B:市场主流价:华东地区(日)', + 'ID00150401': '石油焦:3 # B:市场高端价:华东地区(日)', + 'ID00146589': '海绵焦:4 # :出厂价:华中地区:洛阳石化(日)', + 'ID01242846': '石油焦:4 # B:挂牌价:华北地区:中石化燕山(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)', + 'ID01387643': '煅烧焦:低硫:0.5 % S:市场价:东北地区(日)', + 'ID01387646': '煅烧焦:低硫:3.5 % S:市场价:东北地区(日)', + 'ID01387660': '煅烧焦:中硫:3 % S,400V: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)', + 'ID00146545': '海绵焦:3B:出厂价:山东:山东东明(日)', + 'B3e90b34e4b9e7a6ea3': '石油焦市场均价(元/吨)', + 'B6b5c53b270a3af12ac': '石油焦1 # 市场均价(元/吨)', + 'B10721189a11c209a20': '石油焦2 # 市场均价(元/吨)', + 'B6accfa9d2bf4735a50': '石油焦3 # 市场均价(元/吨)', + 'B8a0ab5357569c385a9': '石油焦海绵焦市场均价(元/吨)', + 'B19dcf45e22fbfd3e43': '石油焦海绵焦东北1 # A焦(低端)(元/吨)(百川)', + 'B5832a62d1e0fba50b6': '石油焦海绵焦东北1 # A焦(高端)(元/吨)(百川)', + 'B1de4fba026d4609cc7': '石油焦海绵焦东北1 # B焦(低端)(元/吨)(百川)', + 'B38f89180736172490d': '石油焦海绵焦东北1 # B焦(高端)(元/吨)(百川)', + 'B4f847871674c3d77f2': '石油焦海绵焦山东地炼1 # -3#焦(低端)(元/吨)', + 'B1aefb8a64a5200adbd': '石油焦海绵焦山东地炼1 # -3#焦(高端)(元/吨)', + 'B1df7d0afbfedfb628a': '煅烧焦东北低硫(高端S < 0.5)(元/吨)', + 'B5f8f9859635876da28': '煅烧焦东北低硫(低端S < 0.5)(元/吨)', + 'B2342a8c5a39fa00348': '煅烧焦华北中硫(高端S < 3.0,钒 < 400)(元/吨)', + 'B051f27900397c6a35f': '煅烧焦山东中硫(高端S < 3.0,钒 < 400)(元/吨)', + 'Be2a8050a48e86cae1f': '煅烧焦华东中硫(高端S < 3.0,钒 < 400)(元/吨)', + 'B4a1811938f85065f6a': '煅烧焦华中中硫(高端S < 3.0,钒 < 400)(元/吨)', + 'Bc197d4834ef7fb98ec': '煅烧焦华东高硫(高端S < 3.5,钒 < 400)(元/吨)', + 'B62be5dbdb8c6454530': '煅烧焦低硫参考价格(元/吨)(百川)', + 'Bdd813140bffc4edfa6': '煅烧焦中硫微量市场均价(元/吨)(百川)', + 'B185a597decfc71915a': '预焙阳极山东低端(元/吨)(百川)', + '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', + 'ID01387649': '煅烧焦:中硫:3 % S,350V:市场价:华东地区(日)', + 'ID01387655': '煅烧焦:中硫:3 % S,350V:市场价:山东(日)', + 'RE00010076': '煅烧焦:低硫:生产毛利:东北地区(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)', + 'Bf7efe3200f9abc0453': '电解铝开工率(周)( % )', + 'Be193166f347267b1a7': '电解铝行业总库存(周)(吨)', + 'Baa744fc97769353175': '电解铝工厂库存(周)(吨)', + 'Bf9654603913cfc5282': '电解铝市场库存(周)(吨)', + 'Bef1535c96da0d70fbc': '电解铝利润(周)(吨)', + 'B7d1d0b24316d49cbdc': '煤沥青总产量(周)(吨)', + 'B4303fb002ea1c214da': '煤沥青开工率(周)( % )', + 'Be9a470c97e9efe660c': '煤沥青行业总库存(周)(吨)', + 'B50d4d87f6b78bca587': '煤沥青工厂库存(周)(吨)', + 'B46cc7d0a90155b5bfd': '煅烧焦山东高硫(高端S < 3.5,普货)(元/吨)' +} + +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 = { +} + +# 百川数据指标编码 +baicangidnamedict = { + '1588348470396480000': '石油焦滨州-友泰', + '1588348470396480000.00': '石油焦东营-海科瑞林', + '1588348470396480000.00': '石油焦东营-华联2', + '1588348470396480000.00': '石油焦东营-华联3', + '1588348470396480000.00': '石油焦东营-联合', + '1588348470396480000.00': '石油焦东营-联合3', + '1588348470396480915': '石油焦淄博-汇丰', + '1588348470396480888': '石油焦沧州-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', +} + + +# 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' # 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": { + "account": "api_test", + # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 + "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456 + "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", + "terminal": "API" + }, + "funcModule": "API", + "funcOperation": "获取token" +} + +upload_data = { + "groupNo": '', # 用户组id + "funcModule": '研究报告信息', + "funcOperation": '上传原油价格预测报告', + "data": { + "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": '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 + } +} + + +warning_data = { + "groupNo": '', # 用户组id + "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 + } +} + +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': 'yyycbdwdcr', + # 'benzhou': 'yyycbdwdbz', + # 'cizhou': 'yyycbdwdcz', + # 'gezhou': 'yyycbdwdgz', + # 'ciyue': 'yyycbdwdcy', + # 'cieryue': 'yyycbdwdcey', + # 'cisanyue': 'yyycbdwdcsy', + # 'cisiyue': 'yyycbdwdcsiy', +} + +# 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' +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 = 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 +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_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 + + +# 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 = 'B46cc7d0a90155b5bfd' +avg_cols = [ + +] +offsite = 80 +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 +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_shiyoujiao_lvyong.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'石油焦铝用大模型预测报告--{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_puhuo.py b/config_shiyoujiao_puhuo.py new file mode 100644 index 0000000..e271eb1 --- /dev/null +++ b/config_shiyoujiao_puhuo.py @@ -0,0 +1,319 @@ +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' +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_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/lib/dataread.py b/lib/dataread.py index 8895ff4..84b85cf 100644 --- a/lib/dataread.py +++ b/lib/dataread.py @@ -797,14 +797,14 @@ def datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, datecol='date', end_time='', y if config.is_del_tow_month: current_date = datetime.datetime.now() two_months_ago = current_date - timedelta(days=180) - config.logger.info(f'删除两月不更新特征前数据量:{df.shape}') + config.logger.info(f'删除半年不更新特征前数据量:{df.shape}') columns_to_drop = [] for clo in df.columns: if check_column(df, clo, two_months_ago): columns_to_drop.append(clo) df = df.drop(columns=columns_to_drop) - config.logger.info(f'删除两月不更新特征后数据量:{df.shape}') + config.logger.info(f'删除半年不更新特征后数据量:{df.shape}') # 衍生时间特征 if is_timefurture: @@ -1604,6 +1604,7 @@ class EtaReader(): f'Error: {response.status_code}, {response.text}') # 主动抛出异常 raise Exception(f'Error: {response.status_code}, {response.text}') + # 原油数据获取 def get_eta_api_yuanyou_data(self, data_set, dataset=''): ''' @@ -1790,6 +1791,7 @@ class EtaReader(): df_zhibiaoshuju = df1.copy() df_zhibiaoliebiao = df.copy() return df_zhibiaoshuju, df_zhibiaoliebiao + # 聚烯烃PP数据获取 def get_eta_api_pp_data(self, data_set, dataset=''): today = datetime.date.today().strftime("%Y-%m-%d") @@ -2012,6 +2014,71 @@ class EtaReader(): # 主动抛出异常 raise Exception(f'Error: {response.status_code}, {response.text}') + # 石油焦铝用数据获取 + def get_eta_api_shiyoujiao_lvyong_data(self, data_set, dataset=''): + today = datetime.date.today().strftime("%Y-%m-%d") + + # 定义你的headers,这里可以包含多个参数 + self.headers = { + 'nonce': self.signature.nonce, # 例如,一个认证令牌 + # 自定义的header参数 + 'timestamp': str(self.signature.timestamp), + 'appid': self.signature.APPID, # 另一个自定义的header参数 + 'signature': self.signature.signature + } + + # 从列表数据中获取指标名称,判断指标名称频度是否为日 ,如果是,则获取UniqueCode,然后获取指标数据,保存到xlat文件中的sheet表。 + + ''' + df = sheetname 指标列表,存储 指标分类-指标名称-指标id-频度 + df1 = sheetname 指标数据 ,存储 时间-指标名称1-指标名称2... + + ''' + + # 构建新的DataFrame df df1 + df = pd.DataFrame(columns=['指标分类', '指标名称', '指标id', '频度']) + df1 = pd.DataFrame(columns=['DataTime']) + + # 外网环境无法访问,请确认是否为内网环境 + try: + # 发送GET请求 获取指标分类列表 + response = requests.get(self.classifylisturl, headers=self.headers) + except requests.exceptions.RequestException as e: + raise Exception(f"请求失败,请确认是否为内网环境: {e}", "\033[0m") + # 找到列表中不在指标列中的指标id,保存成新的list + new_list = [ + item for item in self.edbcodelist if item not in df['指标id'].tolist()] + config.logger.info(new_list) + # 遍历new_list,获取指标数据,保存到df1 + for item in new_list: + config.logger.info(item) + # 将item 加入到 df['指标id']中 + try: + itemname = config.edbcodenamedict[item] + except: + itemname = item + + df1 = self.edbcodegetdata(df1, item, itemname) + df = pd.concat([df, pd.DataFrame( + {'指标分类': '其他', '指标名称': itemname, '指标id': item, '频度': '其他'}, index=[0])]) + + # 按时间排序 + df1.sort_values('DataTime', inplace=True, ascending=False) + df1.rename(columns={'DataTime': 'date'}, inplace=True) + # df1.dropna(inplace=True) + # 去掉大于今天日期的行 + df1 = df1[df1['date'] <= datetime.datetime.now().strftime('%Y-%m-%d')] + config.logger.info(df1.head()) + # config.logger.info(f'{df1.head()}') + # 保存到xlsx文件的sheet表 + with pd.ExcelWriter(os.path.join(dataset, data_set)) as file: + df1.to_excel(file, sheet_name='指标数据', index=False) + df.to_excel(file, sheet_name='指标列表', index=False) + + df_zhibiaoshuju = df1.copy() + df_zhibiaoliebiao = df.copy() + return df_zhibiaoshuju, df_zhibiaoliebiao + def get_market_data(end_time, df): """ diff --git a/main_juxiting.py b/main_juxiting.py index 9126724..2b878e3 100644 --- a/main_juxiting.py +++ b/main_juxiting.py @@ -340,7 +340,8 @@ def predict_main(): logger.info('模型训练完成') logger.info('训练数据绘图ing') - model_results3 = model_losss_juxiting(sqlitedb, end_time=global_config['end_time'],is_fivemodels=global_config['is_fivemodels']) + model_results3 = model_losss_juxiting( + sqlitedb, end_time=global_config['end_time'], is_fivemodels=global_config['is_fivemodels']) logger.info('训练数据绘图end') # # 模型报告 diff --git a/main_shiyoujiao_lvyong.py b/main_shiyoujiao_lvyong.py new file mode 100644 index 0000000..63bb087 --- /dev/null +++ b/main_shiyoujiao_lvyong.py @@ -0,0 +1,445 @@ +# 读取配置 + +from lib.dataread import * +from config_shiyoujiao_lvyong import * +from lib.tools import SendMail, exception_logger +from models.nerulforcastmodels import ex_Model, model_losss, model_losss_juxiting, brent_export_pdf, tansuanli_export_pdf, pp_export_pdf, model_losss_juxiting +import datetime +import torch +torch.set_float32_matmul_precision("high") + +global_config.update({ + # 核心参数 + 'logger': logger, + 'dataset': dataset, + 'y': y, + 'is_debug': is_debug, + 'is_train': is_train, + 'is_fivemodels': is_fivemodels, + 'settings': settings, + 'weight_dict': weight_dict, + + + # 模型参数 + 'data_set': data_set, + 'input_size': input_size, + 'horizon': horizon, + 'train_steps': train_steps, + 'val_check_steps': val_check_steps, + 'val_size': val_size, + 'test_size': test_size, + 'modelsindex': modelsindex, + 'rote': rote, + 'bdwd_items': bdwd_items, + + # 特征工程开关 + 'is_del_corr': is_del_corr, + 'is_del_tow_month': is_del_tow_month, + '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 + 'start_year': start_year, + 'end_time': end_time or datetime.datetime.now().strftime("%Y-%m-%d"), + 'freq': freq, # 保持列表结构 + + # 接口配置 + 'login_pushreport_url': login_pushreport_url, + 'login_data': login_data, + 'upload_url': upload_url, + 'upload_warning_url': upload_warning_url, + 'warning_data': warning_data, + + # 查询接口 + '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, + 'etadata': data, + 'edbcodelist': edbcodelist, + 'ClassifyId': ClassifyId, + 'edbcodedataurl': edbcodedataurl, + 'classifyidlisturl': classifyidlisturl, + 'edbdatapushurl': edbdatapushurl, + 'edbdeleteurl': edbdeleteurl, + 'edbbusinessurl': edbbusinessurl, + 'ClassifyId': ClassifyId, + 'classifylisturl': classifylisturl, + + # 数据库配置 + 'sqlitedb': sqlitedb, +}) + + +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。 + + 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 + """ + 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=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_lvyong_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(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(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() + 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: + 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}') + + # 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(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(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'Brent原油大模型日度预测--{end_time}.pdf' # 报告文件名 + reportname = reportname.replace(':', '-') # 替换冒号 + brent_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') + + push_market_value() + + # # 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 + # # 遍历2024-11-25 到 2024-12-3 之间的工作日日期 + # for i_time in pd.date_range('2024-12-1', '2025-2-26', freq='W'): + # end_time = i_time.strftime('%Y-%m-%d') + # predict_main() + + predict_main() diff --git a/main_shiyoujiao.py b/main_shiyoujiao_puhuo.py similarity index 57% rename from main_shiyoujiao.py rename to main_shiyoujiao_puhuo.py index c706c9f..2d94e58 100644 --- a/main_shiyoujiao.py +++ b/main_shiyoujiao_puhuo.py @@ -1,12 +1,80 @@ # 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 +from lib.dataread import * +from config_shiyoujiao_puhuo import * +from lib.tools import SendMail, exception_logger +from models.nerulforcastmodels import ex_Model, model_losss_juxiting, tansuanli_export_pdf, pp_export_pdf +import datetime import torch torch.set_float32_matmul_precision("high") +global_config.update({ + # 核心参数 + '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, + + + # 模型参数 + 'data_set': data_set, + 'input_size': input_size, + 'horizon': horizon, + 'train_steps': train_steps, + 'val_check_steps': val_check_steps, + 'val_size': val_size, + 'test_size': test_size, + 'modelsindex': modelsindex, + 'rote': rote, + + # 特征工程开关 + 'is_del_corr': is_del_corr, + 'is_del_tow_month': is_del_tow_month, + 'is_eta': is_eta, + 'is_update_eta': is_update_eta, + 'is_fivemodels': is_fivemodels, + 'early_stop_patience_steps': early_stop_patience_steps, + + # 时间参数 + 'start_year': start_year, + 'end_time': end_time or datetime.datetime.now().strftime("%Y-%m-%d"), + 'freq': freq, # 保持列表结构 + + # 接口配置 + 'login_pushreport_url': login_pushreport_url, + 'login_data': login_data, + 'upload_url': upload_url, + 'upload_warning_url': upload_warning_url, + 'warning_data': warning_data, + + # 查询接口 + 'query_data_list_item_nos_url': query_data_list_item_nos_url, + 'query_data_list_item_nos_data': query_data_list_item_nos_data, + + # eta 配置 + 'APPID': APPID, + 'SECRET': SECRET, + 'etadata': data, + 'edbcodelist': edbcodelist, + 'ClassifyId': ClassifyId, + 'edbcodedataurl': edbcodedataurl, + 'classifyidlisturl': classifyidlisturl, + 'edbdatapushurl': edbdatapushurl, + 'edbdeleteurl': edbdeleteurl, + 'edbbusinessurl': edbbusinessurl, + 'ClassifyId': ClassifyId, + 'classifylisturl': classifylisturl, + + # 数据库配置 + 'sqlitedb': sqlitedb, +}) def predict_main(): @@ -72,7 +140,8 @@ def predict_main(): 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 + 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...') @@ -83,26 +152,26 @@ def predict_main(): 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 : + 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: + 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) + 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_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) @@ -125,31 +194,37 @@ def predict_main(): 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}'") + 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}'") + 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()) + 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") + 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] + 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']}'") + 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: @@ -161,10 +236,12 @@ def predict_main(): 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") + 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) + 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] @@ -172,47 +249,59 @@ def predict_main(): 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'] + 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) + 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) + 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]) + 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',)) + 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: + # 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']] + 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'}) + 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' + 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)) + 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) + 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: @@ -227,50 +316,49 @@ def predict_main(): 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, - ) - + 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), + 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) @@ -281,10 +369,11 @@ def predict_main(): recv=recv, title=title, content=content, - file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), + file=max(glob.glob(os.path.join(dataset, '*.pdf')), + key=os.path.getctime), ssl=ssl, ) - # m.send_mail() + # m.send_mail() if __name__ == '__main__': @@ -298,4 +387,4 @@ if __name__ == '__main__': # except: # pass - predict_main() \ No newline at end of file + predict_main()