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

添加雍安环境配置

Browse Source
This commit is contained in:
workpc 2024-12-27 18:46:01 +08:00
parent 19f76e6b83
commit c9c456f750
5 changed files with 311 additions and 261 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Timed_task.bat
View File

@ -1,4 +0,0 @@
@echo on
d:
cd code/PricePredict/
C:/Users/Hello/.conda/envs/predict-py397/python.exe main.py

65
Untitled.ipynb
View File

@ -1,65 +0,0 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"id": "b3cde8ea",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'ovx index': '原油波动率', 'dxy curncy': '美元指数', 'C2403128043': 'Brent连1合约价格拟合残差/美元指数', 'C2403150124': 'Brent连1合约价格拟合残差/Brent 连2-连3', 'DOESCRUD Index': '美国商业原油库存', 'FVHCM1 INDEX': '美国取暖油裂解C1', 'doedtprd index': '美国成品油表需', 'CFFDQMMN INDEX': 'WTI管理资金净多持仓', 'C2403083739': 'WTI基金多空持仓比', 'C2404167878': 'WTI基金净持仓COT指标（代码运算）', 'lmcads03 lme comdty': 'LME铜价', 'GC1 COMB Comdty': '黄金连1合约', 'C2404167855': '金油比'}\n"
]
}
],
"source": [
"data = \"\"\"\n",
"ovx index 原油波动率\n",
"dxy curncy 美元指数\n",
"C2403128043 Brent连1合约价格拟合残差/美元指数\n",
"C2403150124 Brent连1合约价格拟合残差/Brent 连2-连3\n",
"DOESCRUD Index 美国商业原油库存\n",
"FVHCM1 INDEX 美国取暖油裂解C1\n",
"doedtprd index 美国成品油表需\n",
"CFFDQMMN INDEX WTI管理资金净多持仓\n",
"C2403083739 WTI基金多空持仓比\n",
"C2404167878 WTI基金净持仓COT指标（代码运算）\n",
"lmcads03 lme comdty LME铜价\n",
"GC1 COMB Comdty 黄金连1合约\n",
"C2404167855 金油比\n",
"\"\"\"\n",
"\n",
"result_dict = {}\n",
"lines = data.strip().split('\\n')\n",
"for line in lines:\n",
" key, value = line.strip().split(' ')\n",
" result_dict[key] = value\n",
"\n",
"print(result_dict)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

139
config_jingbo.py
View File

@ -197,24 +197,142 @@ ClassifyId = 1214
################################################################################################################ 变量定义--测试环境 ################################################################################################################ 变量定义--测试环境
login_pushreport_url = "http://192.168.100.53:8080/jingbo-dev/api/server/login" # login_pushreport_url = "http://192.168.100.53:8080/jingbo-dev/api/server/login"
upload_url = "http://192.168.100.53:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" # upload_url = "http://192.168.100.53:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave"
# # upload_url = "http://192.168.100.109:8080/jingbo/api/analysis/reportInfo/researchUploadReportSave" # zhaoqiwei
# upload_warning_url = "http://192.168.100.53:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
# query_data_list_item_nos_url = "http://192.168.100.53:8080/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
# # }
# # }
# 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":'1', #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
# }
# }
# # 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 = False # 是否调试
# 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_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
################################################################################################################ 变量定义--雍安测试环境
login_pushreport_url = "http://192.168.100.115:9090/dom-api/api/server/login"
upload_url = "http://192.168.100.115:9090/dom-api/api/analysis/reportInfo/researchUploadReportSave"
# upload_url = "http://192.168.100.109:8080/jingbo/api/analysis/reportInfo/researchUploadReportSave" # zhaoqiwei # upload_url = "http://192.168.100.109:8080/jingbo/api/analysis/reportInfo/researchUploadReportSave" # zhaoqiwei
upload_warning_url = "http://192.168.100.53:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" upload_warning_url = "http://192.168.100.115:9090/dom-api/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = "http://192.168.100.53:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" query_data_list_item_nos_url = "http://192.168.100.115:9090/dom-api/api/warehouse/dwDataItem/queryDataListItemNos"
login_data = { login_data = {
"data": { "data": {
"account": "api_test", "account": "api-dev",
# "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456 "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456 "tenantHashCode": "1eb24ab5a6af12e30daf78af276664f1",
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API" "terminal": "API"
}, },
"funcModule": "API", "funcModule": "API",
"funcOperation": "获取token" "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
# }
# }
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',
@ -224,13 +342,14 @@ upload_data = {
"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": '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 "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":'1', #分析报告分类编码
"reportEmployeeCode":"E40116", # 报告人 "reportEmployeeCode":"E40116", # 报告人
"reportDeptCode" :"D0044" ,# 报告部门 "reportDeptCode" :"D0044" ,# 报告部门
"productGroupCode":"RAW_MATERIAL" # 商品分类 "productGroupCode":"RAW_MATERIAL" # 商品分类
} }
} }
warning_data = { warning_data = {
"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',
@ -271,7 +390,7 @@ 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 = False # 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 = False # 是否上传预警数据 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_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

358
main_yuanyou.py
View File

@ -48,203 +48,203 @@ def predict_main():
返回: 返回:
None None
""" """
global end_time # global end_time
signature = BinanceAPI(APPID, SECRET) # signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature, # etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl, # classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl, # classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl, # edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist, # edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl, # edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl, # edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl # edbbusinessurl=edbbusinessurl
) # )
# 获取数据 # # 获取数据
if is_eta: # if is_eta:
logger.info('从eta获取数据...') # logger.info('从eta获取数据...')
signature = BinanceAPI(APPID, SECRET) # signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature, # etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl, # classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl, # classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl, # edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist, # edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl, # edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl, # edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl, # edbbusinessurl=edbbusinessurl,
) # )
df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set, dataset=dataset) # 原始数据，未处理 # df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set, dataset=dataset) # 原始数据，未处理
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:
df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju) # df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju)
except : # except :
logger.info('从市场信息平台获取数据失败') # logger.info('从市场信息平台获取数据失败')
# 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:
df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) # 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) # df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# 数据处理 # # 数据处理
df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, # df = datachuli(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: # else:
# 读取数据 # # 读取数据
logger.info('读取本地数据：' + os.path.join(dataset, data_set)) # 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, # 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 # is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
# 更改预测列名称 # # 更改预测列名称
df.rename(columns={y: 'y'}, inplace=True) # df.rename(columns={y: 'y'}, inplace=True)
if is_edbnamelist: # if is_edbnamelist:
df = df[edbnamelist] # df = df[edbnamelist]
df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False) # 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 # # 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 # # 取第一行数据存储到数据库中
first_row = df[['ds', 'y']].tail(1) # first_row = df[['ds', 'y']].tail(1)
print(first_row['ds'].values[0]) # print(first_row['ds'].values[0])
print(first_row['y'].values[0]) # print(first_row['y'].values[0])
# 判断y的类型是否为float # # 判断y的类型是否为float
if not isinstance(first_row['y'].values[0], 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') # logger.info(f'{end_time}预测目标数据为空，跳过')
return None # return None
# 将最新真实值保存到数据库 # # 将最新真实值保存到数据库
if not sqlitedb.check_table_exists('trueandpredict'): # if not sqlitedb.check_table_exists('trueandpredict'):
first_row.to_sql('trueandpredict', sqlitedb.connection, index=False) # first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
else: # else:
for row in first_row.itertuples(index=False): # for row in first_row.itertuples(index=False):
row_dict = row._asdict() # row_dict = row._asdict()
row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') # 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: # if len(check_query) > 0:
set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()]) # 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}'") # sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
continue # 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 # # 更新accuracy表的y值
if not sqlitedb.check_table_exists('accuracy'): # if not sqlitedb.check_table_exists('accuracy'):
pass # pass
else: # 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: # if len(update_y) > 0:
logger.info('更新accuracy表的y值') # logger.info('更新accuracy表的y值')
# 找到update_y 中ds且df中的y的行 # # 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}') # logger.info(f'要更新y的信息：{update_y}')
try: # try:
for row in update_y.itertuples(index=False): # for row in update_y.itertuples(index=False):
row_dict = row._asdict() # row_dict = row._asdict()
yy = df[df['ds']==row_dict['ds']]['y'].values[0] # yy = df[df['ds']==row_dict['ds']]['y'].values[0]
LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0] # LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0]
HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].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']}'") # sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
except Exception as e: # except Exception as e:
logger.info(f'更新accuracy表的y值失败：{e}') # logger.info(f'更新accuracy表的y值失败：{e}')
import datetime # import datetime
# 判断当前日期是不是周一 # # 判断当前日期是不是周一
is_weekday = datetime.datetime.now().weekday() == 0 # is_weekday = datetime.datetime.now().weekday() == 0
if is_weekday: # if is_weekday:
logger.info('今天是周一，更新预测模型') # 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 # # 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40%以上的列 # # 删除空值率为40%以上的列
if len(model_results) > 10: # if len(model_results) > 10:
model_results = model_results.dropna(thresh=len(model_results)*0.6,axis=1) # model_results = model_results.dropna(thresh=len(model_results)*0.6,axis=1)
# 删除空行 # # 删除空行
model_results = model_results.dropna() # model_results = model_results.dropna()
modelnames = model_results.columns.to_list()[2:] # modelnames = model_results.columns.to_list()[2:]
for col in model_results[modelnames].select_dtypes(include=['object']).columns: # for col in model_results[modelnames].select_dtypes(include=['object']).columns:
model_results[col] = model_results[col].astype(np.float32) # 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 # # 计算每个预测值与真实值之间的偏差率
for model in modelnames: # 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 # # 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 # # 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 # # 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 # # 取出现次数最多的模型名称
most_common_model = min_abs_error_rate_column_name.value_counts().idxmax() # 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}") # 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 # # 保存结果到数据库
if not sqlitedb.check_table_exists('most_model'): # if not sqlitedb.check_table_exists('most_model'):
sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT") # 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.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
try: # try:
if is_weekday: # if is_weekday:
# if True: # # if True:
logger.info('今天是周一，发送特征预警') # logger.info('今天是周一，发送特征预警')
# 上传预警信息到数据库 # # 上传预警信息到数据库
warning_data_df = df_zhibiaoliebiao.copy() # 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 # # 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 # from sqlalchemy import create_engine
import urllib # import urllib
global password # global password
if '@' in password: # if '@' in password:
password = urllib.parse.quote_plus(password) # password = urllib.parse.quote_plus(password)
engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') # 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['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S")
warning_data_df['TENANT_CODE'] = 'T0004' # warning_data_df['TENANT_CODE'] = 'T0004'
# 插入数据之前查询表数据然后新增id列 # # 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) # existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
if not existing_data.empty: # if not existing_data.empty:
max_id = existing_data['ID'].astype(int).max() # 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: # else:
warning_data_df['ID'] = range(1, 1 + len(warning_data_df)) # 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: # if is_update_warning_data:
upload_warning_info(len(warning_data_df)) # upload_warning_info(len(warning_data_df))
except: # except:
logger.info('上传预警信息到数据库失败') # logger.info('上传预警信息到数据库失败')
if is_corr: # if is_corr:
df = corr_feature(df=df) # 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 # 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...") # logger.info(f"开始训练模型...")
row, col = df.shape # row, col = df.shape
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') # now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
ex_Model(df, # ex_Model(df,
horizon=horizon, # horizon=horizon,
input_size=input_size, # input_size=input_size,
train_steps=train_steps, # train_steps=train_steps,
val_check_steps=val_check_steps, # val_check_steps=val_check_steps,
early_stop_patience_steps=early_stop_patience_steps, # early_stop_patience_steps=early_stop_patience_steps,
is_debug=is_debug, # is_debug=is_debug,
dataset=dataset, # dataset=dataset,
is_train=is_train, # is_train=is_train,
is_fivemodels=is_fivemodels, # is_fivemodels=is_fivemodels,
val_size=val_size, # val_size=val_size,
test_size=test_size, # test_size=test_size,
settings=settings, # settings=settings,
now=now, # now=now,
etadata=etadata, # etadata=etadata,
modelsindex=modelsindex, # modelsindex=modelsindex,
data=data, # data=data,
is_eta=is_eta, # is_eta=is_eta,
end_time=end_time, # end_time=end_time,
) # )
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(sqlitedb,end_time=end_time) # model_results3 = model_losss(sqlitedb,end_time=end_time)
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')

6
models/nerulforcastmodels.py
View File

@ -945,14 +945,14 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu
content.append(Graphs.draw_img(os.path.join(dataset,'历史价格-预测值.png'))) content.append(Graphs.draw_img(os.path.join(dataset,'历史价格-预测值.png')))
# 波动率画图逻辑 # 波动率画图逻辑
content.append(Graphs.draw_text('图示说明：')) content.append(Graphs.draw_text('图示说明：'))
content.append(Graphs.draw_text(' 确定波动率置信区间：设置残差置信阈值，以每周最佳模型为基准，选取在置信区间的预测值作为置信区间;')) content.append(Graphs.draw_text(' 确定置信区间：设置残差置信阈值，以每周最佳模型为基准，选取在置信区间的预测值作为置信区间;'))
# 添加历史走势及预测价格的走势图片 # 添加历史走势及预测价格的走势图片
content.append(Graphs.draw_img(os.path.join(dataset,'历史价格-预测值1.png'))) content.append(Graphs.draw_img(os.path.join(dataset,'历史价格-预测值1.png')))
content.append(Graphs.draw_text('图示说明：')) content.append(Graphs.draw_text('图示说明：'))
content.append(Graphs.draw_text(' 确定波动率置信区间：使用模型评估指标MAE得到前十个模型，取平均值上下1.5作为价格波动置信区间;')) content.append(Graphs.draw_text(' 确定置信区间：使用模型评估指标MAE得到前十个模型，取平均值上下1.5作为价格波动置信区间;'))
# 取df中y列为空的行 # 取df中y列为空的行
import pandas as pd import pandas as pd