liurui/PriceForecast
Template
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

聚烯烃基础数据表更改

Browse Source
This commit is contained in:
workpc 2025-07-23 14:03:07 +08:00
parent 98836d7a4d
commit 497cd9f4ce
17 changed files with 860 additions and 594 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
aisenzhecode/沥青/定性模型数据项12-11.xlsx
View File

Binary file not shown.

4
aisenzhecode/沥青/沥青定性每日执行.py
View File

@ -950,14 +950,14 @@ def main(start_date=None, token=None, token_push=None):
date = start_date.strftime('%Y%m%d') date = start_date.strftime('%Y%m%d')
print(date) print(date)
logging.info("当前日期: %s", date) logging.info("当前日期: %s", date)
updateExcelData(date, token) # updateExcelData(date, token)
queryDataListItemNos(token=token) queryDataListItemNos(token=token)
update_e_value('定性模型数据项12-11.xlsx', 8, 1000) update_e_value('定性模型数据项12-11.xlsx', 8, 1000)
x = qualitativeModel() x = qualitativeModel()
if x is not None: if x is not None:
print('**************************************************预测结果：', x) print('**************************************************预测结果：', x)
logging.info("预测结果: %s", x) logging.info("预测结果: %s", x)
cur_time, cur_time2 = getNow(date) # cur_time, cur_time2 = getNow(date)
pushData(cur_time, x, token_push) pushData(cur_time, x, token_push)
logging.info("主函数执行完成") logging.info("主函数执行完成")
except Exception as e: except Exception as e:

346
config_jingbo.py
View File

@ -93,163 +93,24 @@ data = {
ClassifyId = 1214 ClassifyId = 1214
# 变量定义--线上环境 # # 变量定义--线上环境
server_host = '10.200.32.39' # server_host = '10.200.32.39'
login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login" # login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login"
upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave" # upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave"
upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save" # upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos" # query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos"
# 上传数据项值
push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
# 上传停更数据到市场信息平台
push_waring_data_value_list_url = f"http://{server_host}/jingbo-api/api/basicBuiness/crudeOilWarning/crudeSaveOrupdate"
# 获取预警数据中取消订阅指标ID
get_waring_data_value_list_url = f"http://{server_host}/jingbo-api/api/basicBuiness/crudeOilWarning/dataList"
login_data = {
"data": {
"account": "api_dev",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API"
},
"funcModule": "API",
"funcOperation": "获取token"
}
upload_data = {
"funcModule": '研究报告信息',
"funcOperation": '上传原油价格预测报告',
"data": {
"groupNo": '', # 用户组id
"ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
"reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST
"fileName": '', # 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": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
"reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
"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
}
]
}
push_waring_data_value_list_data = {
"data": {
"crudeOilWarningDtoList": [
{
"lastUpdateDate": "20240501",
"updateSuspensionCycle": 1,
"dataSource": "8",
"frequency": "1",
"indicatorName": "美元指数",
"indicatorId": "myzs001",
"warningDate": "2024-05-13"
}
],
"dataSource": "8"
},
"funcModule": "商品数据同步",
"funcOperation": "同步"
}
get_waring_data_value_list_data = {
"data": "8", "funcModule": "商品数据同步", "funcOperation": "同步"}
# 八大维度数据项编码
bdwd_items = {
'ciri': '原油大数据预测|FORECAST|PRICE|T',
'benzhou': '原油大数据预测|FORECAST|PRICE|W',
'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
}
# 生产环境数据库
host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
port = 3306
dbusername = 'jingbo'
password = 'shihua@123'
dbname = 'jingbo'
table_name = 'v_tbl_crude_oil_warning'
# # # 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 # # 上传数据项值
# push_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/dw/dataValue/pushDataValueList" # push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
# # 上传停更数据到市场信息平台 # # 上传停更数据到市场信息平台
# push_waring_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/crudeSaveOrupdate" # push_waring_data_value_list_url = f"http://{server_host}/jingbo-api/api/basicBuiness/crudeOilWarning/crudeSaveOrupdate"
# # 获取预警数据中取消订阅指标ID # # 获取预警数据中取消订阅指标ID
# get_waring_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/dataList" # get_waring_data_value_list_url = f"http://{server_host}/jingbo-api/api/basicBuiness/crudeOilWarning/dataList"
# login_data = { # login_data = {
# "data": { # "data": {
# "account": "api_test", # "account": "api_dev",
# # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 # "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
# "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
# "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", # "tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
# "terminal": "API" # "terminal": "API"
# }, # },
@ -257,25 +118,24 @@ table_name = 'v_tbl_crude_oil_warning'
# "funcOperation": "获取token" # "funcOperation": "获取token"
# } # }
# upload_data = { # upload_data = {
# "groupNo": '', # 用户组id
# "funcModule": '研究报告信息', # "funcModule": '研究报告信息',
# "funcOperation": '上传原油价格预测报告', # "funcOperation": '上传原油价格预测报告',
# "data": { # "data": {
# "ownerAccount": 'arui', # 报告所属用户账号 # "groupNo": '', # 用户组id
# "ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
# "reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST # "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 # "fileName": '', # 文件名称
# "fileBase64": '', # 文件内容base64 # "fileBase64": '', # 文件内容base64
# "categoryNo": 'yyjgycbg', # 研究报告分类编码 # "categoryNo": 'yyjgycbg', # 研究报告分类编码
# "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码 # "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码
# "reportEmployeeCode": "E40116", # 报告人 # "reportEmployeeCode": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
# "reportDeptCode": "D0044", # 报告部门 # "reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
# "productGroupCode": "RAW_MATERIAL" # 商品分类 # "productGroupCode": "RAW_MATERIAL" # 商品分类
# } # }
# } # }
# # 已弃用
# warning_data = { # warning_data = {
# "groupNo": '', # 用户组id # "groupNo": '', # 用户组id
# "funcModule": '原油特征停更预警', # "funcModule": '原油特征停更预警',
@ -297,6 +157,7 @@ table_name = 'v_tbl_crude_oil_warning'
# } # }
# } # }
# push_data_value_list_data = { # push_data_value_list_data = {
# "funcModule": "数据表信息列表", # "funcModule": "数据表信息列表",
# "funcOperation": "新增", # "funcOperation": "新增",
@ -319,6 +180,7 @@ table_name = 'v_tbl_crude_oil_warning'
# ] # ]
# } # }
# push_waring_data_value_list_data = { # push_waring_data_value_list_data = {
# "data": { # "data": {
# "crudeOilWarningDtoList": [ # "crudeOilWarningDtoList": [
@ -342,27 +204,165 @@ table_name = 'v_tbl_crude_oil_warning'
# get_waring_data_value_list_data = { # get_waring_data_value_list_data = {
# "data": "8", "funcModule": "商品数据同步", "funcOperation": "同步"} # "data": "8", "funcModule": "商品数据同步", "funcOperation": "同步"}
# # 八大维度数据项编码 # # 八大维度数据项编码
# bdwd_items = { # bdwd_items = {
# 'ciri': 'yyycbdwdcr', # 'ciri': '原油大数据预测|FORECAST|PRICE|T',
# 'benzhou': 'yyycbdwdbz', # 'benzhou': '原油大数据预测|FORECAST|PRICE|W',
# 'cizhou': 'yyycbdwdcz', # 'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
# 'gezhou': 'yyycbdwdgz', # 'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
# 'ciyue': 'yyycbdwdcy', # 'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
# 'cieryue': 'yyycbdwdcey', # 'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
# 'cisanyue': 'yyycbdwdcsy', # 'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
# 'cisiyue': 'yyycbdwdcsiy', # 'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
# } # }
# # 北京环境数据库 # # 生产环境数据库
# host = '192.168.101.27' # host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
# port = 3306 # port = 3306
# dbusername = 'root' # dbusername = 'jingbo'
# password = '123456' # password = 'shihua@123'
# dbname = 'jingbo_test' # dbname = 'jingbo'
# table_name = 'v_tbl_crude_oil_warning' # table_name = 'v_tbl_crude_oil_warning'
# # 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"
# 上传停更数据到市场信息平台
push_waring_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/crudeSaveOrupdate"
# 获取预警数据中取消订阅指标ID
get_waring_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/dataList"
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
}
}
# 已弃用
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
}
]
}
push_waring_data_value_list_data = {
"data": {
"crudeOilWarningDtoList": [
{
"lastUpdateDate": "20240501",
"updateSuspensionCycle": 1,
"dataSource": "8",
"frequency": "1",
"indicatorName": "美元指数",
"indicatorId": "myzs001",
"warningDate": "2024-05-13"
}
],
"dataSource": "8"
},
"funcModule": "商品数据同步",
"funcOperation": "同步"
}
get_waring_data_value_list_data = {
"data": "8", "funcModule": "商品数据同步", "funcOperation": "同步"}
# 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'
DEFAULT_CONFIG = { DEFAULT_CONFIG = {
'feature_factor_frequency': 'D', 'feature_factor_frequency': 'D',
'strategy_id': 1, 'strategy_id': 1,
@ -380,14 +380,14 @@ DEFAULT_CONFIG = {
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = True # 是否使用eta接口 is_eta = False # 是否使用eta接口
is_market = True # 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_market = True # 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_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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = False # 预测结果上传到eta
is_update_report = True # 是否上传报告 is_update_report = False # 是否上传报告
is_update_warning_data = True # 是否上传预警数据 is_update_warning_data = True # 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_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_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

288
config_jingbo_yuedu.py
View File

@ -172,131 +172,19 @@ data = {
ClassifyId = 1214 ClassifyId = 1214
# 变量定义--线上环境 # # 变量定义--线上环境
server_host = '10.200.32.39' # server_host = '10.200.32.39'
login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login" # login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login"
upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave" # upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave"
upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save" # upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos" # query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos"
# 上传数据项值
push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
login_data = {
"data": {
"account": "api_dev",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API"
},
"funcModule": "API",
"funcOperation": "获取token"
}
upload_data = {
"funcModule": '研究报告信息',
"funcOperation": '上传原油价格预测报告',
"data": {
"groupNo": '', # 用户组id
"ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
"reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST
"fileName": '', # 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": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
"reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
"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': '原油大数据预测|FORECAST|PRICE|T',
'benzhou': '原油大数据预测|FORECAST|PRICE|W',
'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
}
# 报告中八大维度数据项重命名
columnsrename = {
'原油大数据预测|FORECAST|PRICE|T': '次日', '原油大数据预测|FORECAST|PRICE|W': '本周',
'原油大数据预测|FORECAST|PRICE|W_1': '次周', '原油大数据预测|FORECAST|PRICE|W_2': '隔周',
'原油大数据预测|FORECAST|PRICE|M_1': '次月', '原油大数据预测|FORECAST|PRICE|M_2': '次二月',
'原油大数据预测|FORECAST|PRICE|M_3': '次三月', '原油大数据预测|FORECAST|PRICE|M_4': '次四月'
}
# 生产环境数据库
host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
port = 3306
dbusername = 'jingbo'
password = 'shihua@123'
dbname = 'jingbo'
table_name = 'v_tbl_crude_oil_warning'
# # 变量定义--测试环境
# server_host = '192.168.100.53:8080' # 内网
# # server_host = '183.242.74.28' # 外网
# login_pushreport_url = f"http://{server_host}/jingbo-dev/api/server/login"
# upload_url = f"http://{server_host}/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave"
# upload_warning_url = f"http://{server_host}/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
# query_data_list_item_nos_url = f"http://{server_host}/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos"
# # 上传数据项值 # # 上传数据项值
# push_data_value_list_url = f"http://{server_host}/jingbo-dev/api/dw/dataValue/pushDataValueList" # push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
# login_data = { # login_data = {
# "data": { # "data": {
# "account": "api_test", # "account": "api_dev",
# # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 # "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
# "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
# "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", # "tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
# "terminal": "API" # "terminal": "API"
# }, # },
@ -304,24 +192,24 @@ table_name = 'v_tbl_crude_oil_warning'
# "funcOperation": "获取token" # "funcOperation": "获取token"
# } # }
# upload_data = { # upload_data = {
# "groupNo": '', # 用户组id
# "funcModule": '研究报告信息', # "funcModule": '研究报告信息',
# "funcOperation": '上传原油价格预测报告', # "funcOperation": '上传原油价格预测报告',
# "data": { # "data": {
# "ownerAccount": 'arui', # 报告所属用户账号 # "groupNo": '', # 用户组id
# "ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
# "reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST # "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 # "fileName": '', # 文件名称
# "fileBase64": '', # 文件内容base64 # "fileBase64": '', # 文件内容base64
# "categoryNo": 'yyjgycbg', # 研究报告分类编码 # "categoryNo": 'yyjgycbg', # 研究报告分类编码
# "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码 # "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码
# "reportEmployeeCode": "E40116", # 报告人 # "reportEmployeeCode": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
# "reportDeptCode": "D0044", # 报告部门 # "reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
# "productGroupCode": "RAW_MATERIAL" # 商品分类 # "productGroupCode": "RAW_MATERIAL" # 商品分类
# } # }
# } # }
# warning_data = { # warning_data = {
# "groupNo": '', # 用户组id # "groupNo": '', # 用户组id
# "funcModule": '原油特征停更预警', # "funcModule": '原油特征停更预警',
@ -343,6 +231,7 @@ table_name = 'v_tbl_crude_oil_warning'
# } # }
# } # }
# push_data_value_list_data = { # push_data_value_list_data = {
# "funcModule": "数据表信息列表", # "funcModule": "数据表信息列表",
# "funcOperation": "新增", # "funcOperation": "新增",
@ -366,27 +255,138 @@ table_name = 'v_tbl_crude_oil_warning'
# } # }
# # 八大维度数据项编码 # # 八大维度数据项编码
# bdwd_items = { # bdwd_items = {
# 'ciri': 'yyycbdwdcr', # 'ciri': '原油大数据预测|FORECAST|PRICE|T',
# 'benzhou': 'yyycbdwdbz', # 'benzhou': '原油大数据预测|FORECAST|PRICE|W',
# 'cizhou': 'yyycbdwdcz', # 'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
# 'gezhou': 'yyycbdwdgz', # 'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
# 'ciyue': 'yyycbdwdcy', # 'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
# 'cieryue': 'yyycbdwdcey', # 'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
# 'cisanyue': 'yyycbdwdcsy', # 'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
# 'cisiyue': 'yyycbdwdcsiy', # 'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
# } # }
# # 报告中八大维度数据项重命名 # # 报告中八大维度数据项重命名
# columnsrename = {'yyycbdwdbz': '本周', 'yyycbdwdcey': '次二月', 'yyycbdwdcr': '次日', 'yyycbdwdcsiy': '次四月', # columnsrename = {
# 'yyycbdwdcsy': '次三月', 'yyycbdwdcy': '次月', 'yyycbdwdcz': '次周', 'yyycbdwdgz': '隔周', } # '原油大数据预测|FORECAST|PRICE|T': '次日', '原油大数据预测|FORECAST|PRICE|W': '本周',
# # 北京环境数据库 # '原油大数据预测|FORECAST|PRICE|W_1': '次周', '原油大数据预测|FORECAST|PRICE|W_2': '隔周',
# host = '192.168.101.27' # '原油大数据预测|FORECAST|PRICE|M_1': '次月', '原油大数据预测|FORECAST|PRICE|M_2': '次二月',
# '原油大数据预测|FORECAST|PRICE|M_3': '次三月', '原油大数据预测|FORECAST|PRICE|M_4': '次四月'
# }
# # 生产环境数据库
# host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
# port = 3306 # port = 3306
# dbusername = 'root' # dbusername = 'jingbo'
# password = '123456' # password = 'shihua@123'
# dbname = 'jingbo_test' # dbname = 'jingbo'
# table_name = 'v_tbl_crude_oil_warning' # table_name = 'v_tbl_crude_oil_warning'
# 变量定义--测试环境
server_host = '192.168.100.53:8080' # 内网
# server_host = '183.242.74.28' # 外网
login_pushreport_url = f"http://{server_host}/jingbo-dev/api/server/login"
upload_url = f"http://{server_host}/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave"
upload_warning_url = f"http://{server_host}/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos"
# 上传数据项值
push_data_value_list_url = f"http://{server_host}/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',
}
# 报告中八大维度数据项重命名
columnsrename = {'yyycbdwdbz': '本周', 'yyycbdwdcey': '次二月', 'yyycbdwdcr': '次日', 'yyycbdwdcsiy': '次四月',
'yyycbdwdcsy': '次三月', 'yyycbdwdcy': '次月', 'yyycbdwdcz': '次周', 'yyycbdwdgz': '隔周', }
# 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'
DEFAULT_CONFIG = { DEFAULT_CONFIG = {
'feature_factor_frequency': 'D', 'feature_factor_frequency': 'D',
'strategy_id': 1, 'strategy_id': 1,
@ -404,14 +404,14 @@ DEFAULT_CONFIG = {
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = True # 是否使用eta接口 is_eta = False # 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_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_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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = True # 预测结果上传到eta
is_update_report = True # 是否上传报告 is_update_report = False # 是否上传报告
is_update_warning_data = False # 是否上传预警数据 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_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_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

270
config_jingbo_zhoudu.py
View File

@ -119,125 +119,19 @@ data = {
ClassifyId = 1214 ClassifyId = 1214
# 变量定义--线上环境 # # 变量定义--线上环境
server_host = '10.200.32.39' # server_host = '10.200.32.39'
login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login" # login_pushreport_url = "http://10.200.32.39/jingbo-api/api/server/login"
upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave" # upload_url = "http://10.200.32.39/jingbo-api/api/analysis/reportInfo/researchUploadReportSave"
upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save" # upload_warning_url = "http://10.200.32.39/jingbo-api/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos" # query_data_list_item_nos_url = f"http://{server_host}/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos"
# 上传数据项值
push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
login_data = {
"data": {
"account": "api_dev",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API"
},
"funcModule": "API",
"funcOperation": "获取token"
}
upload_data = {
"funcModule": '研究报告信息',
"funcOperation": '上传原油价格预测报告',
"data": {
"groupNo": '', # 用户组id
"ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
"reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST
"fileName": '', # 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": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
"reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
"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': '原油大数据预测|FORECAST|PRICE|T',
'benzhou': '原油大数据预测|FORECAST|PRICE|W',
'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
}
# 生产环境数据库
host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
port = 3306
dbusername = 'jingbo'
password = 'shihua@123'
dbname = 'jingbo'
table_name = 'v_tbl_crude_oil_warning'
# # # 变量定义--测试环境
# server_host = '192.168.100.53:8080' # 内网
# # server_host = '183.242.74.28' # 外网
# login_pushreport_url = f"http://{server_host}/jingbo-dev/api/server/login"
# upload_url = f"http://{server_host}/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave"
# upload_warning_url = f"http://{server_host}/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
# query_data_list_item_nos_url = f"http://{server_host}/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos"
# # 上传数据项值 # # 上传数据项值
# push_data_value_list_url = f"http://{server_host}/jingbo-dev/api/dw/dataValue/pushDataValueList" # push_data_value_list_url = f"http://{server_host}/jingbo-api/api/dw/dataValue/pushDataValueList"
# login_data = { # login_data = {
# "data": { # "data": {
# "account": "api_test", # "account": "api_dev",
# # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 # "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
# "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
# "tenantHashCode": "8a4577dbd919675758d57999a1e891fe", # "tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
# "terminal": "API" # "terminal": "API"
# }, # },
@ -245,24 +139,26 @@ table_name = 'v_tbl_crude_oil_warning'
# "funcOperation": "获取token" # "funcOperation": "获取token"
# } # }
# upload_data = { # upload_data = {
# "funcModule": '研究报告信息', # "funcModule": '研究报告信息',
# "funcOperation": '上传原油价格预测报告', # "funcOperation": '上传原油价格预测报告',
# "data": { # "data": {
# "ownerAccount": 'arui', # 报告所属用户账号 # "groupNo": '', # 用户组id
# "ownerAccount": '27663', # 报告所属用户账号 27663 - 刘小朋
# "reportType": 'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST # "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 # "fileName": '', # 文件名称
# "fileBase64": '', # 文件内容base64 # "fileBase64": '', # 文件内容base64
# "categoryNo": 'yyjgycbg', # 研究报告分类编码 # "categoryNo": 'yyjgycbg', # 研究报告分类编码
# "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码 # "smartBusinessClassCode": 'YCJGYCBG', # 分析报告分类编码
# "reportEmployeeCode": "E40116", # 报告人 # "reportEmployeeCode": "E40482", # 报告人 E40482 - 管理员 0000027663 - 刘小朋
# "reportDeptCode": "D0044", # 报告部门 # "reportDeptCode": "002000621000", # 报告部门 - 002000621000 SH期货研究部
# "productGroupCode": "RAW_MATERIAL" # 商品分类 # "productGroupCode": "RAW_MATERIAL" # 商品分类
# } # }
# } # }
# warning_data = { # warning_data = {
# "groupNo": '', # 用户组id
# "funcModule": '原油特征停更预警', # "funcModule": '原油特征停更预警',
# "funcOperation": '原油特征停更预警', # "funcOperation": '原油特征停更预警',
# "data": { # "data": {
@ -282,6 +178,7 @@ table_name = 'v_tbl_crude_oil_warning'
# } # }
# } # }
# push_data_value_list_data = { # push_data_value_list_data = {
# "funcModule": "数据表信息列表", # "funcModule": "数据表信息列表",
# "funcOperation": "新增", # "funcOperation": "新增",
@ -305,26 +202,129 @@ table_name = 'v_tbl_crude_oil_warning'
# } # }
# # 八大维度数据项编码 # # 八大维度数据项编码
# bdwd_items = { # bdwd_items = {
# 'ciri': 'yyycbdwdcr', # 'ciri': '原油大数据预测|FORECAST|PRICE|T',
# 'benzhou': 'yyycbdwdbz', # 'benzhou': '原油大数据预测|FORECAST|PRICE|W',
# 'cizhou': 'yyycbdwdcz', # 'cizhou': '原油大数据预测|FORECAST|PRICE|W_1',
# 'gezhou': 'yyycbdwdgz', # 'gezhou': '原油大数据预测|FORECAST|PRICE|W_2',
# 'ciyue': 'yyycbdwdcy', # 'ciyue': '原油大数据预测|FORECAST|PRICE|M_1',
# 'cieryue': 'yyycbdwdcey', # 'cieryue': '原油大数据预测|FORECAST|PRICE|M_2',
# 'cisanyue': 'yyycbdwdcsy', # 'cisanyue': '原油大数据预测|FORECAST|PRICE|M_3',
# 'cisiyue': 'yyycbdwdcsiy', # 'cisiyue': '原油大数据预测|FORECAST|PRICE|M_4',
# } # }
# # 北京环境数据库 # # 生产环境数据库
# host = '192.168.101.27' # host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
# port = 3306 # port = 3306
# dbusername = 'root' # dbusername = 'jingbo'
# password = '123456' # password = 'shihua@123'
# dbname = 'jingbo_test' # dbname = 'jingbo'
# table_name = 'v_tbl_crude_oil_warning' # table_name = 'v_tbl_crude_oil_warning'
# # 变量定义--测试环境
server_host = '192.168.100.53:8080' # 内网
# server_host = '183.242.74.28' # 外网
login_pushreport_url = f"http://{server_host}/jingbo-dev/api/server/login"
upload_url = f"http://{server_host}/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave"
upload_warning_url = f"http://{server_host}/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos"
# 上传数据项值
push_data_value_list_url = f"http://{server_host}/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 = {
"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 = {
"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'
DEFAULT_CONFIG = { DEFAULT_CONFIG = {
'feature_factor_frequency': 'D', 'feature_factor_frequency': 'D',
'strategy_id': 1, 'strategy_id': 1,
@ -342,14 +342,14 @@ DEFAULT_CONFIG = {
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = True # 是否使用eta接口 is_eta = False # 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_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_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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = True # 预测结果上传到eta
is_update_report = True # 是否上传报告 is_update_report = False # 是否上传报告
is_update_warning_data = False # 是否上传预警数据 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_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_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

4
config_juxiting.py
View File

@ -432,8 +432,8 @@ 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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = False # 预测结果上传到eta
is_update_report = False # 是否上传报告 is_update_report = True # 是否上传报告
is_update_warning_data = True # 是否上传预警数据 is_update_warning_data = True # 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_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_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

41
config_juxiting_yuedu.py
View File

@ -1,3 +1,4 @@
from decimal import Decimal
import logging import logging
import os import os
import logging.handlers import logging.handlers
@ -416,18 +417,32 @@ password = '123456'
dbname = 'jingbo_test' dbname = 'jingbo_test'
table_name = 'v_tbl_crude_oil_warning' table_name = 'v_tbl_crude_oil_warning'
DEFAULT_CONFIG = {
'feature_factor_frequency': 'D',
'strategy_id': 2,
'model_evaluation_id': 1,
'tenant_code': '',
'version_num': Decimal(1),
'delete_flag': '0',
'create_user': 'admin',
'create_date': datetime.datetime.now(),
'update_user': 'admin',
'update_date': datetime.datetime.now(),
'oil_code': 'PP',
'oil_name': 'PP期货',
}
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = True # 是否使用eta接口 is_eta = False # 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_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_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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = True # 预测结果上传到eta
is_update_report = True # 是否上传报告 is_update_report = False # 是否上传报告
is_update_warning_data = False # 是否上传预警数据 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_update_predict_value = True # 是否上传预测值到市场信息平台
is_del_corr = 0 # 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_corr = 0 # 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
@ -452,16 +467,20 @@ add_kdj = False # 是否添加kdj指标
if add_kdj and is_edbnamelist: if add_kdj and is_edbnamelist:
edbnamelist = edbnamelist+['K', 'D', 'J'] edbnamelist = edbnamelist+['K', 'D', 'J']
# 模型参数 # 模型参数
y = 'AVG-金能大唐久泰青州' # y = 'AVG-金能大唐久泰青州'
avg_cols = [ # avg_cols = [
'PP：拉丝：1102K：出厂价：青州：国家能源宁煤（日）', # '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：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：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）' # 'PP：拉丝：HP550J：市场价：青岛：金能化学（日）'
] # ]
offsite = 80 # offsite = 80
offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）'] # offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）']
y = 'MAIN_CONFT_SETTLE_PRICE'
horizon = 4 # 预测的步长 horizon = 4 # 预测的步长
input_size = 16 # 输入序列长度 input_size = 16 # 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 train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数

10
config_juxiting_zhoudu.py
View File

@ -450,15 +450,15 @@ DEFAULT_CONFIG = {
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = False # 是否使用eta接口 is_eta = True # 是否使用eta接口
is_market = True # 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_market = True # 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_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_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_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_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = True # 预测结果上传到eta is_update_eta = False # 预测结果上传到eta
is_update_report = False # 是否上传报告 is_update_report = True # 是否上传报告
is_update_warning_data = True # 是否上传预警数据 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_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_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 is_del_tow_month = True # 是否删除两个月不更新的特征
@ -475,7 +475,7 @@ print("数据库连接成功", host, dbname, dbusername)
# 数据截取日期 # 数据截取日期
start_year = 2015 # 数据开始年份 start_year = 2015 # 数据开始年份
end_time = '' # 数据截取日期 end_time = '' # 数据截取日期
freq = 'WW' # 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 "WW" 自定义周 freq = 'W' # 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 "WW" 自定义周
delweekenday = True if freq == 'B' else False # 是否删除周末数据 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 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 add_kdj = False # 是否添加kdj指标

12
lib/dataread.py
View File

@ -516,7 +516,8 @@ def featureAnalysis(df, dataset, y):
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
# 选择特征和标签列 # 选择特征和标签列
X = df.drop(['ds', 'y'], axis=1) # 特征集，排除时间戳和标签列 X = df.drop(['ds', 'y'], axis=1) # 特征集，排除时间戳和标签列
yy = df['y'] # 标签集 yy = df['y'] # 标签集
# 标签集自相关函数分析 # 标签集自相关函数分析
from statsmodels.graphics.tsaplots import plot_acf from statsmodels.graphics.tsaplots import plot_acf
@ -2439,6 +2440,15 @@ def get_high_low_data(df):
df = pd.merge(df, df1, how='left', on='date') df = pd.merge(df, df1, how='left', on='date')
return df return df
def get_shujuxiang_data(df):
# 读取excel 从第五行开始
df1 = pd.read_excel(os.path.join(config.dataset, '数据项下载.xls'), header=5, names=[
'numid', 'date', 'MAIN_CONFT_SETTLE_PRICE'])
df1['MAIN_CONFT_SETTLE_PRICE'] = df1['MAIN_CONFT_SETTLE_PRICE'].str.replace(',', '').astype(float)
# 合并数据
df = pd.merge(df, df1, how='left', on='date')
return df
def get_waring_data(): def get_waring_data():
'''获取取消订阅的指标数据''' '''获取取消订阅的指标数据'''

68
main_juxiting.py
View File

@ -191,7 +191,7 @@ def sql_inset_predict(global_config):
] ]
insert_query = f""" insert_query = f"""
INSERT INTO v_tbl_predict_prediction_results ( INSERT INTO v_tbl_predict_pp_prediction_results (
feature_factor_frequency, strategy_id, oil_code, oil_name, data_date, feature_factor_frequency, strategy_id, oil_code, oil_name, data_date,
market_price, day_price, week_price, second_week_price, next_week_price, market_price, day_price, week_price, second_week_price, next_week_price,
next_month_price, next_february_price, next_march_price, next_april_price, next_month_price, next_february_price, next_march_price, next_april_price,
@ -300,18 +300,17 @@ def predict_main():
if is_market: if is_market:
logger.info('从市场信息平台获取数据...') logger.info('从市场信息平台获取数据...')
try: # try:
# 如果是测试环境，最高价最低价取excel文档 # 如果是测试环境，最高价最低价取excel文档
if server_host == '192.168.100.53': if server_host == '192.168.100.53':
logger.info('从excel文档获取市场信息平台指标') logger.info('从excel文档获取市场信息平台指标')
df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju) df_zhibiaoshuju = get_shujuxiang_data(df_zhibiaoshuju)
else: else:
logger.info('从市场信息平台获取数据') logger.info('从市场信息平台获取数据')
df_zhibiaoshuju = get_market_data( df_zhibiaoshuju = get_market_data(
end_time, df_zhibiaoshuju) end_time, df_zhibiaoshuju)
# except:
except: # logger.info('市场信息平台数据项-eta数据项 拼接失败')
logger.info('市场信息平台数据项-eta数据项 拼接失败')
# 保存到xlsx文件的sheet表 # 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:
@ -503,21 +502,20 @@ def predict_main():
logger.info('模型训练完成') logger.info('模型训练完成')
logger.info('训练数据绘图ing') # logger.info('训练数据绘图ing')
model_results3 = model_losss_juxiting( # model_results3 = model_losss_juxiting(
sqlitedb, end_time=global_config['end_time'], is_fivemodels=global_config['is_fivemodels']) # sqlitedb, end_time=global_config['end_time'], is_fivemodels=global_config['is_fivemodels'])
logger.info('训练数据绘图end') # logger.info('训练数据绘图end')
# # 模型报告 # # # 模型报告
logger.info('制作报告ing') # logger.info('制作报告ing')
title = f'{settings}--{end_time}-预测报告' # 报告标题 # title = f'{settings}--{end_time}-预测报告' # 报告标题
reportname = f'聚烯烃PP大模型日度预测--{end_time}.pdf' # 报告文件名 # reportname = f'聚烯烃PP大模型日度预测--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号 # reportname = reportname.replace(':', '-') # 替换冒号
pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, # pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time,
reportname=reportname, sqlitedb=sqlitedb), # reportname=reportname, sqlitedb=sqlitedb),
logger.info('制作报告end') # logger.info('制作报告end')
logger.info('模型训练完成')
push_market_value() push_market_value()
sql_inset_predict(global_config) sql_inset_predict(global_config)
@ -547,15 +545,17 @@ def predict_main():
if __name__ == '__main__': if __name__ == '__main__':
# global end_time # global end_time
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期 # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
# for i_time in pd.date_range('2025-4-14', '2025-4-15', freq='B'): for i_time in pd.date_range('2025-6-2', '2025-7-23', freq='B'):
# try: try:
# global_config['end_time'] = i_time.strftime('%Y-%m-%d') global_config['end_time'] = i_time.strftime('%Y-%m-%d')
# predict_main() global_config['db_mysql'].connect()
# except Exception as e: predict_main()
# logger.info(f'预测失败：{e}') except Exception as e:
# continue logger.info(f'预测失败：{e}')
continue
# predict_main()
predict_main()
# push_market_value() # push_market_value()
# sql_inset_predict(global_config) # sql_inset_predict(global_config)

122
main_juxiting_yuedu.py
View File

@ -2,8 +2,8 @@
from lib.dataread import * from lib.dataread import *
from config_juxiting_yuedu import * from config_juxiting_yuedu import *
from lib.tools import SendMail, exception_logger from lib.tools import SendMail, convert_df_to_pydantic, exception_logger, get_modelsname
from models.nerulforcastmodels import ex_Model, model_losss_juxiting, tansuanli_export_pdf, pp_export_pdf from models.nerulforcastmodels import ex_Model, model_losss_juxiting, pp_export_pdf
import datetime import datetime
import torch import torch
torch.set_float32_matmul_precision("high") torch.set_float32_matmul_precision("high")
@ -13,9 +13,9 @@ global_config.update({
'logger': logger, 'logger': logger,
'dataset': dataset, 'dataset': dataset,
'y': y, 'y': y,
'offsite_col': offsite_col, # 'offsite_col': offsite_col,
'avg_cols': avg_cols, # 'avg_cols': avg_cols,
'offsite': offsite, # 'offsite': offsite,
'edbcodenamedict': edbcodenamedict, 'edbcodenamedict': edbcodenamedict,
'is_debug': is_debug, 'is_debug': is_debug,
'is_train': is_train, 'is_train': is_train,
@ -23,6 +23,7 @@ global_config.update({
'is_update_report': is_update_report, 'is_update_report': is_update_report,
'settings': settings, 'settings': settings,
'bdwdname': bdwdname, 'bdwdname': bdwdname,
'columnsrename': columnsrename,
# 模型参数 # 模型参数
@ -84,7 +85,8 @@ global_config.update({
# 数据库配置 # 数据库配置
'sqlitedb': sqlitedb, 'sqlitedb': sqlitedb,
'is_bdwd': is_bdwd, 'is_bdwd': is_bdwd,
'columnsrename':columnsrename, 'db_mysql': db_mysql,
'DEFAULT_CONFIG': DEFAULT_CONFIG,
}) })
@ -160,6 +162,97 @@ def push_market_value():
logger.error(f"推送数据失败: {e}") logger.error(f"推送数据失败: {e}")
def sql_inset_predict(global_config):
df = pd.read_csv(os.path.join(config.dataset, 'predict.csv'))
df['created_dt'] = pd.to_datetime(df['created_dt'])
df['ds'] = pd.to_datetime(df['ds'])
# 获取次月预测结果
next_month_price_df = df[df['ds'] == df['ds'].min()]
# 获取次二月预测结果
next_february_price_df = df.iloc[[1]]
# 获取次三月预测结果
next_march_price_df = df.iloc[[2]]
# 获取次四月预测结果
next_april_price_df = df[df['ds'] == df['ds'].max()]
wd = ['next_month_price', 'next_february_price',
'next_march_price', 'next_april_price']
model_name_list, model_id_name_dict = get_modelsname(df, global_config)
PRICE_COLUMNS = [
'day_price', 'week_price', 'second_week_price', 'next_week_price',
'next_month_price', 'next_february_price', 'next_march_price', 'next_april_price'
]
params_list = []
for df, price_type in zip([next_month_price_df, next_february_price_df, next_march_price_df, next_april_price_df], wd):
update_columns = [
"feature_factor_frequency = VALUES(feature_factor_frequency)",
"oil_code = VALUES(oil_code)",
"oil_name = VALUES(oil_name)",
"data_date = VALUES(data_date)",
"market_price = VALUES(market_price)",
f"{price_type} = VALUES({price_type})",
"model_evaluation_id = VALUES(model_evaluation_id)",
"tenant_code = VALUES(tenant_code)",
"version_num = VALUES(version_num)",
"delete_flag = VALUES(delete_flag)",
"update_user = VALUES(update_user)",
"update_date = VALUES(update_date)"
]
insert_query = f"""
INSERT INTO v_tbl_predict_pp_prediction_results (
feature_factor_frequency, strategy_id, oil_code, oil_name, data_date,
market_price, day_price, week_price, second_week_price, next_week_price,
next_month_price, next_february_price, next_march_price, next_april_price,
model_evaluation_id, model_id, tenant_code, version_num, delete_flag,
create_user, create_date, update_user, update_date
) VALUES (
%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s
)
ON DUPLICATE KEY UPDATE
{', '.join(update_columns)}
"""
next_day_df = df[['ds', 'created_dt'] + model_name_list]
pydantic_results = convert_df_to_pydantic(
next_day_df, model_id_name_dict, global_config)
if pydantic_results:
for result in pydantic_results:
price_values = [None] * len(PRICE_COLUMNS)
price_index = PRICE_COLUMNS.index(price_type)
price_values[price_index] = next_day_df[model_id_name_dict[result.model_id]].values[0]
params = (
result.feature_factor_frequency,
result.strategy_id,
result.oil_code,
result.oil_name,
next_day_df['created_dt'].values[0],
result.market_price,
*price_values,
result.model_evaluation_id,
result.model_id,
result.tenant_code,
1,
'0',
result.create_user,
result.create_date,
result.update_user,
result.update_date
)
params_list.append(params)
affected_rows = config.db_mysql.execute_batch_insert(
insert_query, params_list)
config.logger.info(f"成功插入或更新 {affected_rows} 条记录")
config.db_mysql.close()
def predict_main(): 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。 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。
@ -392,15 +485,16 @@ def predict_main():
# push_market_value() # push_market_value()
# # 模型报告 # # 模型报告
logger.info('制作报告ing') # logger.info('制作报告ing')
title = f'{settings}--{end_time}-预测报告' # 报告标题 # title = f'{settings}--{end_time}-预测报告' # 报告标题
reportname = f'聚烯烃PP大模型月度预测--{end_time}.pdf' # 报告文件名 # reportname = f'聚烯烃PP大模型月度预测--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号 # reportname = reportname.replace(':', '-') # 替换冒号
pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, # pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time,
reportname=reportname, sqlitedb=sqlitedb), # reportname=reportname, sqlitedb=sqlitedb),
logger.info('制作报告end') # logger.info('制作报告end')
logger.info('模型训练完成') # logger.info('模型训练完成')
sql_inset_predict(global_config)
# # LSTM 单变量模型 # # LSTM 单变量模型
# ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset) # ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset)

61
main_juxiting_zhoudu.py
View File

@ -158,12 +158,12 @@ def sql_inset_predict(global_config):
df = pd.read_csv(os.path.join(config.dataset, 'predict.csv')) df = pd.read_csv(os.path.join(config.dataset, 'predict.csv'))
df['created_dt'] = pd.to_datetime(df['created_dt']) df['created_dt'] = pd.to_datetime(df['created_dt'])
df['ds'] = pd.to_datetime(df['ds']) df['ds'] = pd.to_datetime(df['ds'])
# 获取次日预测结果 # 获取次周预测结果
next_day_df = df[df['ds'] == df['ds'].min()] second_week_price_df = df[df['ds'] == df['ds'].min()]
# 获取本周预测结果 # 获取隔周周预测结果
this_week_df = df[df['ds'] == df['ds'].max()] next_week_price_df = df[df['ds'] == df['ds'].max()]
wd = ['day_price', 'week_price'] wd = ['second_week_price', 'next_week_price']
model_name_list, model_id_name_dict = get_modelsname(df, global_config) model_name_list, model_id_name_dict = get_modelsname(df, global_config)
PRICE_COLUMNS = [ PRICE_COLUMNS = [
@ -172,7 +172,7 @@ def sql_inset_predict(global_config):
] ]
params_list = [] params_list = []
for df, price_type in zip([next_day_df, this_week_df], wd): for df, price_type in zip([second_week_price_df, next_week_price_df], wd):
update_columns = [ update_columns = [
"feature_factor_frequency = VALUES(feature_factor_frequency)", "feature_factor_frequency = VALUES(feature_factor_frequency)",
@ -190,7 +190,7 @@ def sql_inset_predict(global_config):
] ]
insert_query = f""" insert_query = f"""
INSERT INTO v_tbl_predict_prediction_results ( INSERT INTO v_tbl_predict_pp_prediction_results (
feature_factor_frequency, strategy_id, oil_code, oil_name, data_date, feature_factor_frequency, strategy_id, oil_code, oil_name, data_date,
market_price, day_price, week_price, second_week_price, next_week_price, market_price, day_price, week_price, second_week_price, next_week_price,
next_month_price, next_february_price, next_march_price, next_april_price, next_month_price, next_february_price, next_march_price, next_april_price,
@ -238,7 +238,6 @@ def sql_inset_predict(global_config):
config.logger.info(f"成功插入或更新 {affected_rows} 条记录") config.logger.info(f"成功插入或更新 {affected_rows} 条记录")
config.db_mysql.close() config.db_mysql.close()
def predict_main(): 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。 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。
@ -303,7 +302,7 @@ def predict_main():
# 如果是测试环境，最高价最低价取excel文档 # 如果是测试环境，最高价最低价取excel文档
if server_host == '192.168.100.53': if server_host == '192.168.100.53':
logger.info('从excel文档获取市场信息平台指标') logger.info('从excel文档获取市场信息平台指标')
df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju) df_zhibiaoshuju = get_shujuxiang_data(df_zhibiaoshuju)
else: else:
logger.info('从市场信息平台获取数据') logger.info('从市场信息平台获取数据')
df_zhibiaoshuju = get_market_data( df_zhibiaoshuju = get_market_data(
@ -318,7 +317,7 @@ def predict_main():
df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# 数据处理 # 数据处理
df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, df = zhoududatachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
end_time=end_time) end_time=end_time)
else: else:
@ -465,21 +464,20 @@ def predict_main():
logger.info('模型训练完成') logger.info('模型训练完成')
logger.info('训练数据绘图ing') # logger.info('训练数据绘图ing')
model_results3 = model_losss_juxiting( # model_results3 = model_losss_juxiting(
sqlitedb, end_time=global_config['end_time'], is_fivemodels=global_config['is_fivemodels']) # sqlitedb, end_time=global_config['end_time'], is_fivemodels=global_config['is_fivemodels'])
logger.info('训练数据绘图end') # logger.info('训练数据绘图end')
# # 模型报告 # # # 模型报告
logger.info('制作报告ing') # logger.info('制作报告ing')
title = f'{settings}--{end_time}-预测报告' # 报告标题 # title = f'{settings}--{end_time}-预测报告' # 报告标题
reportname = f'聚烯烃PP大模型周度预测--{end_time}.pdf' # 报告文件名 # reportname = f'聚烯烃PP大模型周度预测--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号 # reportname = reportname.replace(':', '-') # 替换冒号
pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, # pp_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time,
reportname=reportname, sqlitedb=sqlitedb), # reportname=reportname, sqlitedb=sqlitedb),
logger.info('制作报告end') # logger.info('制作报告end')
logger.info('模型训练完成')
push_market_value() push_market_value()
sql_inset_predict(global_config) sql_inset_predict(global_config)
@ -509,15 +507,16 @@ def predict_main():
if __name__ == '__main__': if __name__ == '__main__':
# global end_time # global end_time
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期 # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
# for i_time in pd.date_range('2025-4-14', '2025-4-15', freq='B'): for i_time in pd.date_range('2025-7-18', '2025-7-23', freq='B'):
# try: try:
# global_config['end_time'] = i_time.strftime('%Y-%m-%d') global_config['end_time'] = i_time.strftime('%Y-%m-%d')
# predict_main() global_config['db_mysql'].connect()
# except Exception as e: predict_main()
# logger.info(f'预测失败：{e}') except Exception as e:
# continue logger.info(f'预测失败：{e}')
continue
# predict_main() # predict_main()
# push_market_value() # push_market_value()
sql_inset_predict(global_config) # sql_inset_predict(global_config)

4
main_yuanyou.py
View File

@ -580,8 +580,8 @@ def predict_main():
if __name__ == '__main__': if __name__ == '__main__':
# global end_time # global end_time
# # 遍历2024-11-25 到 2024-12-3 之间的工作日日期 # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
# for i_time in pd.date_range('2025-6-19', '2025-6-28', freq='B'): # for i_time in pd.date_range('2024-9-12', '2024-10-7', freq='B'):
# global_config['end_time'] = i_time.strftime('%Y-%m-%d') # global_config['end_time'] = i_time.strftime('%Y-%m-%d')
# global_config['db_mysql'].connect() # global_config['db_mysql'].connect()
# predict_main() # predict_main()

2
main_yuanyou_yuedu.py
View File

@ -590,7 +590,7 @@ def predict_main():
if __name__ == '__main__': if __name__ == '__main__':
# global end_time # global end_time
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期 # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
for i_time in pd.date_range('2025-6-4', '2025-6-30', freq='B'): for i_time in pd.date_range('2025-3-17', '2025-3-31', freq='B'):
global_config['end_time'] = i_time.strftime('%Y-%m-%d') global_config['end_time'] = i_time.strftime('%Y-%m-%d')
global_config['db_mysql'].connect() global_config['db_mysql'].connect()
predict_main() predict_main()

2
main_yuanyou_zhoudu.py
View File

@ -492,7 +492,7 @@ def predict_main():
if __name__ == '__main__': if __name__ == '__main__':
# global end_time # global end_time
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期 # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
for i_time in pd.date_range('2025-6-23', '2025-6-30', freq='B'): for i_time in pd.date_range('2025-3-5', '2025-3-18', freq='B'):
global_config['end_time'] = i_time.strftime('%Y-%m-%d') global_config['end_time'] = i_time.strftime('%Y-%m-%d')
global_config['db_mysql'].connect() global_config['db_mysql'].connect()
predict_main() predict_main()

80
models/nerulforcastmodels.py
View File

@ -165,8 +165,8 @@ def ex_Model(df, horizon, input_size, train_steps, val_check_steps, early_stop_p
# VanillaTransformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了 # VanillaTransformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了
# Autoformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了 # Autoformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了
# NBEATS(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), NBEATS(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ),
# NBEATSx (h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard',activation='ReLU', ), //报错 # NBEATSx(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard',activation='ReLU', ), //报错
# HINT(h=horizon), # HINT(h=horizon),
] ]
@ -439,12 +439,12 @@ def ex_Model_Juxiting(df, horizon, input_size, train_steps, val_check_steps, ear
config.dataset, '*.joblib')), key=os.path.getctime) config.dataset, '*.joblib')), key=os.path.getctime)
config.logger.info('读取模型：' + filename) config.logger.info('读取模型：' + filename)
nf = load(filename) nf = load(filename)
# 测试集预测 # # 测试集预测
nf_test_preds = nf.cross_validation( # nf_test_preds = nf.cross_validation(
df=df_test, val_size=val_size, test_size=test_size, n_windows=None) # df=df_test, val_size=val_size, test_size=test_size, n_windows=None)
# 测试集预测结果保存 # # 测试集预测结果保存
nf_test_preds.to_csv(os.path.join( # nf_test_preds.to_csv(os.path.join(
config.dataset, "cross_validation.csv"), index=False) # config.dataset, "cross_validation.csv"), index=False)
df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce') df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce')
@ -2344,38 +2344,42 @@ def brent_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, in
# 去掉created_dt 列 # 去掉created_dt 列
df4 = df4.drop(columns=['created_dt']) df4 = df4.drop(columns=['created_dt'])
# 计算模型偏差率 # 计算模型偏差率
# 计算各列对于y列的差值百分比 try:
df3 = pd.DataFrame() # 存储偏差率 # 计算各列对于y列的差值百分比
df3 = pd.DataFrame() # 存储偏差率
# 删除有null的行 # 删除有null的行
df4 = df4.dropna() df4 = df4.dropna()
df3['ds'] = df4['ds'] df3['ds'] = df4['ds']
for col in fivemodels_list: for col in fivemodels_list:
df3[col] = round(abs(df4[col] - df4['y']) / df4['y'] * 100, 2) df3[col] = round(abs(df4[col] - df4['y']) / df4['y'] * 100, 2)
# 找出决定系数前五的偏差率 # 找出决定系数前五的偏差率
df3 = df3[['ds']+fivemodels_list.tolist()][-inputsize:] df3 = df3[['ds']+fivemodels_list.tolist()][-inputsize:]
# 找出上一预测区间的时间 # 找出上一预测区间的时间
stime = df3['ds'].iloc[0] stime = df3['ds'].iloc[0]
etime = df3['ds'].iloc[-1] etime = df3['ds'].iloc[-1]
# 添加偏差率表格 # 添加偏差率表格
fivemodels = '、'.join(eval_df['模型(Model)'].values[:5]) # 字符串形式，后面写入字符串使用 fivemodels = '、'.join(eval_df['模型(Model)'].values[:5]) # 字符串形式，后面写入字符串使用
content.append(Graphs.draw_text( content.append(Graphs.draw_text(
f'预测使用了{num_models}个模型进行训练，使用评估结果MAE前五的模型分别是 {fivemodels} ，模型上一预测区间 {stime} -- {etime}的偏差率(%)分别是：')) f'预测使用了{num_models}个模型进行训练，使用评估结果MAE前五的模型分别是 {fivemodels} ，模型上一预测区间 {stime} -- {etime}的偏差率(%)分别是：'))
# # 添加偏差率表格 # # 添加偏差率表格
df3 = df3.T df3 = df3.T
df3 = df3.reset_index() df3 = df3.reset_index()
data = df3.values.tolist() data = df3.values.tolist()
col_width = 500/len(df3.columns) col_width = 500/len(df3.columns)
content.append(Graphs.draw_table(col_width, *data)) content.append(Graphs.draw_table(col_width, *data))
content.append(Graphs.draw_little_title('上一周预测准确率：')) content.append(Graphs.draw_little_title('上一周预测准确率：'))
df4 = sqlitedb.select_data('accuracy_rote', order_by='结束日期 desc', limit=1) df4 = sqlitedb.select_data('accuracy_rote', order_by='结束日期 desc', limit=1)
df4 = df4.T df4 = df4.T
df4 = df4.reset_index() df4 = df4.reset_index()
df4 = df4.T df4 = df4.T
data = df4.values.tolist() data = df4.values.tolist()
col_width = 500/len(df4.columns) col_width = 500/len(df4.columns)
content.append(Graphs.draw_table(col_width, *data)) content.append(Graphs.draw_table(col_width, *data))
except:
content.append(Graphs.draw_text('暂无'))
config.logger.info('偏差率计算错误，跳过')
content.append(Graphs.draw_little_title('三、预测过程解析：')) content.append(Graphs.draw_little_title('三、预测过程解析：'))
# 特征、模型、参数配置 # 特征、模型、参数配置

140
test/demo.py Normal file
View File

@ -0,0 +1,140 @@
import requests
import json
def get_cptcha():
url = 'https://marketinfo.jbshihua.com/jingbo-api/captcha'
res = requests.get(url)
res = json.loads(res.text)
res = res["data"]["img"]
imgurl = 'data:image/jpeg;base64,/' + res
res = requests.get(imgurl)
with open('cptcha.png', 'wb') as f:
f.write(res.content)
def main() -> dict:
login_url = "http://marketinfo.jbshihua.com/jingbo-api/api/server/login"
login_data = {
"data": {
"account": "api_dev",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API"
},
"funcModule": "API",
"funcOperation": "获取token"
}
query_data_list_item_nos_url = f"http://marketinfo.jbshihua.com/jingbo-api/api/warehouse/dwDataItem/queryDataListItemNos"
query_data_list_item_nos_data = {
"funcModule": "数据项",
"funcOperation": "查询",
"data": {
"dateStart": "20200101",
"dateEnd": "20241231",
"dataItemNoList": ["Brentjsj"] # 数据项编码,代表 brent结算价
}
}
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"]
print('获取到的token', token)
headers = {"Authorization": token}
print('获取数据中...')
items_res = requests.post(url=query_data_list_item_nos_url, headers=headers,
json=query_data_list_item_nos_data, timeout=(3, 35))
json_data = json.loads(items_res.text)
print(json_data)
return text
return {
"result": token,
}
class AuthHandler:
def __init__(self):
# 初始化登录表单数据
self.loginForm = {
'captchaToken': '',
'src': ''
}
self.loading = False
def loadCaptcha(self):
"""加载验证码图片"""
try:
self.loading = True
# 发送 POST 请求获取验证码
response = requests.post(
url="https://marketinfo.jbshihua.com/jingbo-api/captcha",
json={}, # 发送空 JSON 数据体
timeout=10 # 设置超时时间为 10 秒
)
# 检查响应状态码
response.raise_for_status()
# 处理响应数据
data = response.json()
if data:
self.loginForm['captchaToken'] = data.get('token', '')
self.loginForm['src'] = "data:image/jpeg;base64," + \
data.get('img', '')
# 保存图片
with open('cptcha.png', 'wb') as f:
f.write(res.content)
except requests.exceptions.RequestException as e:
print(f"请求出错: {e}")
finally:
self.loading = False
def main2() -> dict:
import requests
import json
login_url = "http://marketinfo.jbshihua.com/jingbo-api/api/server/login"
login_data = {
"data": {
"account": "admin",
"password": "OWZlYjcyNDAwZDRkYjEwZjE1ZjA0MTIwNDAwOGI5NjI=",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "PC"
},
"funcModule": "登录页面",
"funcOperation": "登录"
}
login_res = requests.post(
url=login_url, json=login_data, timeout=(3, 5))
text = json.loads(login_res.text)
print(text)
if text["status"]:
token = text["data"]["accessToken"]
return {
"accessToken": token,
}
return {
"accessToken": "",
}
# 使用示例
if __name__ == "__main__":
# auth = AuthHandler()
# auth.loadCaptcha()
# # 打印获取到的验证码信息
# print(f"验证码 Token: {auth.loginForm['captchaToken']}")
# print(f"验证码图片: {auth.loginForm['src']}...") # 只显示前50个字符
# main2()
main()