PriceForecast/config_juxiting.py

320 lines
11 KiB
Python
Raw Normal View History

2024-11-01 16:38:21 +08:00
import logging
import os
import logging.handlers
import datetime
from lib.tools import MySQLDB, SQLiteHandler
2024-11-01 16:38:21 +08:00
# eta 接口token
APPID = "XNLDvxZHHugj7wJ7"
SECRET = "iSeU4s6cKKBVbt94htVY1p0sqUMqb2xa"
# eta 接口url
sourcelisturl = 'http://10.189.2.78:8108/v1/edb/source/list'
2024-11-01 16:38:21 +08:00
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']
2024-11-01 16:38:21 +08:00
# 临时写死用指定的列,与上面的edbcode对应后面更改
edbnamelist = [
'ds', 'y',
2024-11-01 16:38:21 +08:00
'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'
]
2024-11-01 16:38:21 +08:00
edbcodenamedict = {
'ID01385938': 'PP拉丝1102K市场价青州国家能源宁煤',
'ID01384463': 'PP拉丝L5E89出厂价华北第二区域内蒙古久泰新材料',
'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',
2024-11-01 16:38:21 +08:00
}
# 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'
}
2025-02-11 16:31:52 +08:00
2025-02-13 11:25:03 +08:00
2024-11-01 16:38:21 +08:00
# 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": "",
2024-11-01 16:38:21 +08:00
"Frequency": "日度",
"SourceName": f"价格预测",
"Remark": 'ddd',
"DataList": [
{
"Date": "2024-05-02",
"Value": 333444
}
]
}
2024-11-01 16:38:21 +08:00
# eta 分类
# level3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
# ParentId ":1214,",就是原油下所有的数据。
ClassifyId = 1161
2024-11-01 16:38:21 +08:00
# 变量定义--测试环境
2025-02-11 16:31:52 +08:00
server_host = '192.168.100.53'
2024-11-01 16:38:21 +08:00
2025-02-11 16:31:52 +08:00
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"
2025-02-11 08:53:51 +08:00
login_data = {
"data": {
"account": "api_test",
2025-02-11 16:31:52 +08:00
# "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
2025-02-11 08:53:51 +08:00
"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": "000127",
"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
}
2025-02-11 08:53:51 +08:00
}
2025-02-11 16:31:52 +08:00
warning_data = {
"funcModule": '原油特征停更预警',
"funcOperation": '原油特征停更预警',
"data": {
"groupNo": "000127",
'WARNING_TYPE_NAME': '特征数据停更预警',
'WARNING_CONTENT': '',
'WARNING_DATE': ''
}
2025-02-11 16:31:52 +08:00
}
query_data_list_item_nos_data = {
"funcModule": "数据项",
"funcOperation": "查询",
2025-02-11 16:31:52 +08:00
"data": {
"dateStart": "20200101",
"dateEnd": "20241231",
"dataItemNoList": ["Brentzdj", "Brentzgj"] # 数据项编码,代表 brent最低价和最高价
2025-02-11 16:31:52 +08:00
}
}
# 北京环境数据库
host = '192.168.101.27'
port = 3306
dbusername = 'root'
2025-02-11 16:31:52 +08:00
password = '123456'
dbname = 'jingbo_test'
table_name = 'v_tbl_crude_oil_warning'
2024-11-01 16:38:21 +08:00
# 开关
2025-03-11 10:10:20 +08:00
is_train = True # 是否训练
2025-03-11 11:25:43 +08:00
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
2025-03-11 10:10:20 +08:00
is_update_report = False # 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
2024-11-01 16:38:21 +08:00
2025-02-11 09:46:34 +08:00
# 连接到数据库
db_mysql = MySQLDB(host=host, user=dbusername,
password=password, database=dbname)
2025-02-11 16:31:52 +08:00
db_mysql.connect()
print("数据库连接成功", host, dbname, dbusername)
2025-02-11 09:46:34 +08:00
2024-11-01 16:38:21 +08:00
# 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
2024-11-01 16:38:21 +08:00
if add_kdj and is_edbnamelist:
edbnamelist = edbnamelist+['K', 'D', 'J']
2025-02-11 16:31:52 +08:00
# 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',
'PP拉丝L5E89出厂价华北第二区域内蒙古久泰新材料',
'PP拉丝L5E89出厂价河北、鲁北大唐内蒙多伦',
'PP拉丝HP550J市场价青岛金能化学'
]
2024-11-14 17:26:17 +08:00
offsite = 80
offsite_col = ['PP拉丝HP550J市场价青岛金能化学']
horizon = 5 # 预测的步长
2024-11-01 16:38:21 +08:00
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
2024-11-01 16:38:21 +08:00
val_check_steps = 30 # 评估频率
early_stop_patience_steps = 5 # 早停的耐心步数
2024-11-01 16:38:21 +08:00
# --- 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
2024-11-01 16:38:21 +08:00
# 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
2025-02-11 16:31:52 +08:00
# 计算准确率
weight_dict = [0.4, 0.15, 0.1, 0.1, 0.25] # 权重
2024-11-01 16:38:21 +08:00
# 文件
data_set = 'PP指标数据.xlsx' # 数据集文件
dataset = 'juxitingdataset' # 数据集文件夹
2024-11-01 16:38:21 +08:00
# 数据库名称
db_name = os.path.join(dataset, 'jbsh_juxiting.db')
sqlitedb = SQLiteHandler(db_name)
2025-02-11 09:46:34 +08:00
sqlitedb.connect()
2024-11-01 16:38:21 +08:00
settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}'
2024-11-01 16:38:21 +08:00
# 获取日期时间
2025-02-11 16:31:52 +08:00
# 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
2025-02-11 16:31:52 +08:00
if end_time == '':
end_time = now
# 邮件配置
username = '1321340118@qq.com'
passwd = 'wgczgyhtyyyyjghi'
2025-02-11 16:31:52 +08:00
# recv=['liurui_test@163.com','52585119@qq.com']
recv = ['liurui_test@163.com']
2025-02-11 16:31:52 +08:00
# recv=['liurui_test@163.com']
title = 'reportname'
content = y+'预测报告请看附件'
file = os.path.join(dataset, 'reportname')
2024-11-01 16:38:21 +08:00
# 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
2024-11-01 16:38:21 +08:00
# 日志配置
2024-11-01 16:38:21 +08:00
# 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(
2025-03-11 10:10:20 +08:00
'%(asctime)s - %(name)s - %(levelname)s - %(message)s', datefmt='%Y-%m-%d %H:%M:%S'))
2024-11-01 16:38:21 +08:00
# 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)
2025-02-11 16:31:52 +08:00
# logger.info('当前配置:'+settings)