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

添加预测结果更新到记录表

Browse Source
This commit is contained in:
workpc 2024-12-30 14:00:16 +08:00
parent c9c456f750
commit 98e0178da0
8 changed files with 706 additions and 1690 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
aisenzhecode/液化石油气/日度价格预测_液化气最佳模型.pkl
View File

Binary file not shown.

1455
aisenzhecode/液化石油气/液化气价格预测ytj.ipynb
View File

File diff suppressed because it is too large Load Diff

BIN
aisenzhecode/液化石油气/液化气数据.xls
View File

Binary file not shown.

232
config_jingbo.py
View File

@ -197,52 +197,124 @@ ClassifyId = 1214
################################################################################################################ 变量定义--测试环境
# 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"
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://192.168.100.109:8080/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
}
}
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 = 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_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 = True # 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_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"
# upload_warning_url = "http://192.168.100.115:9090/dom-api/api/basicBuiness/crudeOilWarning/save"
# query_data_list_item_nos_url = "http://192.168.100.115:9090/dom-api/api/warehouse/dwDataItem/queryDataListItemNos"
# login_data = {
# "data": {
# "account": "api_test",
# # "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456
# "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
# "tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
# "account": "api-dev",
# "password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
# "tenantHashCode": "1eb24ab5a6af12e30daf78af276664f1",
# "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
# "ownerAccount":'rui.liu', #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
# "reportEmployeeCode":"U270018", # 报告人
# "reportDeptCode" :"D270001" ,# 报告部门
# # "reportDeptCode" :"000001" ,# 报告部门
# "productGroupCode":"RAW_MATERIAL" # 商品分类
# }
# }
@ -294,108 +366,6 @@ ClassifyId = 1214
# 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_warning_url = "http://192.168.100.115:9090/dom-api/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = "http://192.168.100.115:9090/dom-api/api/warehouse/dwDataItem/queryDataListItemNos"
login_data = {
"data": {
"account": "api-dev",
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=",
"tenantHashCode": "1eb24ab5a6af12e30daf78af276664f1",
"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
# 连接到数据库
db_mysql = MySQLDB(host=host, user=dbusername, password=password, database=dbname)
@ -448,12 +418,14 @@ settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}'
now = datetime.datetime.now().strftime('%Y-%m-%d') # 获取当前日期时间
reportname = f'Brent原油大模型预测--{now}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号
if end_time == '':
end_time = now
### 邮件配置
username='1321340118@qq.com'
passwd='wgczgyhtyyyyjghi'
# recv=['liurui_test@163.com','52585119@qq.com']
recv=['liurui_test@163.com']
recv=['liurui_test@163.com','jin.wang@chambroad.com']
# recv=['liurui_test@163.com']
title='reportname'
content='brent价格预测报告请看附件'
file=os.path.join(dataset,'reportname')

4
lib/dataread.py
View File

@ -140,12 +140,13 @@ def get_head_auth_report():
str: 如果登录成功，返回认证令牌；否则返回 None。
"""
logger.info("获取token中...")
logger.info(f'url:{login_pushreport_url},login_data:{login_data}')
# 发送 POST 请求到登录 URL，携带登录数据
login_res = requests.post(url=login_pushreport_url, json=login_data, timeout=(3, 30))
# 将响应内容转换为 JSON 格式
text = json.loads(login_res.text)
logger.info(f'token接口响应：{text}')
# 如果响应状态为成功
if text["status"]:
# 从响应数据中获取认证令牌
@ -1662,6 +1663,7 @@ def get_market_data(end_time,df):
logger.info('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)
logger.info(f"获取到的数据:{json_data}")
df3 = pd.DataFrame(json_data['data'])
# 按照dataItemNo 分组 得到多个dataframe ，最后根据dataDate merge 成一个dataframe
df2 = pd.DataFrame()

288
main_yongan.py Normal file
View File

@ -0,0 +1,288 @@
# 读取配置
from lib.dataread import *
from lib.tools import SendMail,exception_logger
from models.nerulforcastmodels import ex_Model,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting
import glob
import torch
torch.set_float32_matmul_precision("high")
def predict_main():
"""
主预测函数，用于从 ETA 获取数据、处理数据、训练模型并进行预测。
参数:
signature (BinanceAPI): Binance API 实例。
etadata (EtaReader): ETA 数据读取器实例。
is_eta (bool): 是否从 ETA 获取数据。
data_set (str): 数据集名称。
dataset (str): 数据集路径。
add_kdj (bool): 是否添加 KDJ 指标。
is_timefurture (bool): 是否添加时间衍生特征。
end_time (str): 结束时间。
is_edbnamelist (bool): 是否使用 EDB 名称列表。
edbnamelist (list): EDB 名称列表。
y (str): 预测目标列名。
sqlitedb (SQLiteDB): SQLite 数据库实例。
is_corr (bool): 是否进行相关性分析。
horizon (int): 预测时域。
input_size (int): 输入数据大小。
train_steps (int): 训练步数。
val_check_steps (int): 验证检查步数。
early_stop_patience_steps (int): 早停耐心步数。
is_debug (bool): 是否调试模式。
dataset (str): 数据集名称。
is_train (bool): 是否训练模型。
is_fivemodels (bool): 是否使用五个模型。
val_size (float): 验证集大小。
test_size (float): 测试集大小。
settings (dict): 模型设置。
now (str): 当前时间。
etadata (EtaReader): ETA 数据读取器实例。
modelsindex (list): 模型索引列表。
data (str): 数据类型。
is_eta (bool): 是否从 ETA 获取数据。
返回:
None
"""
# global end_time
# signature = BinanceAPI(APPID, SECRET)
# etadata = EtaReader(signature=signature,
# classifylisturl=classifylisturl,
# classifyidlisturl=classifyidlisturl,
# edbcodedataurl=edbcodedataurl,
# edbcodelist=edbcodelist,
# edbdatapushurl=edbdatapushurl,
# edbdeleteurl=edbdeleteurl,
# edbbusinessurl=edbbusinessurl
# )
# # 获取数据
# if is_eta:
# logger.info('从eta获取数据...')
# signature = BinanceAPI(APPID, SECRET)
# etadata = EtaReader(signature=signature,
# classifylisturl=classifylisturl,
# classifyidlisturl=classifyidlisturl,
# edbcodedataurl=edbcodedataurl,
# edbcodelist=edbcodelist,
# edbdatapushurl=edbdatapushurl,
# edbdeleteurl=edbdeleteurl,
# edbbusinessurl=edbbusinessurl,
# )
# df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set, dataset=dataset) # 原始数据，未处理
# if is_market:
# logger.info('从市场信息平台获取数据...')
# try:
# df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju)
# except :
# logger.info('从市场信息平台获取数据失败')
# # 保存到xlsx文件的sheet表
# with pd.ExcelWriter(os.path.join(dataset,data_set)) as file:
# df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False)
# df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# # 数据处理
# df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
# end_time=end_time)
# else:
# # 读取数据
# logger.info('读取本地数据：' + os.path.join(dataset, data_set))
# df,df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj,
# is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
# # 更改预测列名称
# df.rename(columns={y: 'y'}, inplace=True)
# if is_edbnamelist:
# df = df[edbnamelist]
# df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False)
# # 保存最新日期的y值到数据库
# # 取第一行数据存储到数据库中
# first_row = df[['ds', 'y']].tail(1)
# print(first_row['ds'].values[0])
# print(first_row['y'].values[0])
# # 判断y的类型是否为float
# if not isinstance(first_row['y'].values[0], float):
# logger.info(f'{end_time}预测目标数据为空，跳过')
# return None
# # 将最新真实值保存到数据库
# if not sqlitedb.check_table_exists('trueandpredict'):
# first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
# else:
# for row in first_row.itertuples(index=False):
# row_dict = row._asdict()
# row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S')
# check_query = sqlitedb.select_data('trueandpredict', where_condition=f"ds = '{row.ds}'")
# if len(check_query) > 0:
# set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()])
# sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
# continue
# sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys())
# # 更新accuracy表的y值
# if not sqlitedb.check_table_exists('accuracy'):
# pass
# else:
# update_y = sqlitedb.select_data('accuracy',where_condition="y is null")
# if len(update_y) > 0:
# logger.info('更新accuracy表的y值')
# # 找到update_y 中ds且df中的y的行
# update_y = update_y[update_y['ds']<=end_time]
# logger.info(f'要更新y的信息：{update_y}')
# try:
# for row in update_y.itertuples(index=False):
# row_dict = row._asdict()
# yy = df[df['ds']==row_dict['ds']]['y'].values[0]
# LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0]
# HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0]
# sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
# except Exception as e:
# logger.info(f'更新accuracy表的y值失败：{e}')
# import datetime
# # 判断当前日期是不是周一
# is_weekday = datetime.datetime.now().weekday() == 0
# if is_weekday:
# logger.info('今天是周一，更新预测模型')
# # 计算最近60天预测残差最低的模型名称
# model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60")
# # 删除空值率为40%以上的列
# if len(model_results) > 10:
# model_results = model_results.dropna(thresh=len(model_results)*0.6,axis=1)
# # 删除空行
# model_results = model_results.dropna()
# modelnames = model_results.columns.to_list()[2:]
# for col in model_results[modelnames].select_dtypes(include=['object']).columns:
# model_results[col] = model_results[col].astype(np.float32)
# # 计算每个预测值与真实值之间的偏差率
# for model in modelnames:
# model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y']
# # 获取每行对应的最小偏差率值
# min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
# # 获取每行对应的最小偏差率值对应的列名
# min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
# # 将列名索引转换为列名
# min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0])
# # 取出现次数最多的模型名称
# most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
# logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}")
# # 保存结果到数据库
# if not sqlitedb.check_table_exists('most_model'):
# sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT")
# sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
# try:
# if is_weekday:
# # if True:
# logger.info('今天是周一，发送特征预警')
# # 上传预警信息到数据库
# warning_data_df = df_zhibiaoliebiao.copy()
# warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']]
# # 重命名列名
# warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'})
# from sqlalchemy import create_engine
# import urllib
# global password
# if '@' in password:
# password = urllib.parse.quote_plus(password)
# engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
# warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S")
# warning_data_df['TENANT_CODE'] = 'T0004'
# # 插入数据之前查询表数据然后新增id列
# existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
# if not existing_data.empty:
# max_id = existing_data['ID'].astype(int).max()
# warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df))
# else:
# warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
# warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False)
# if is_update_warning_data:
# upload_warning_info(len(warning_data_df))
# except:
# logger.info('上传预警信息到数据库失败')
# if is_corr:
# df = corr_feature(df=df)
# df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
# logger.info(f"开始训练模型...")
# row, col = df.shape
# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
# ex_Model(df,
# horizon=horizon,
# input_size=input_size,
# train_steps=train_steps,
# val_check_steps=val_check_steps,
# early_stop_patience_steps=early_stop_patience_steps,
# is_debug=is_debug,
# dataset=dataset,
# is_train=is_train,
# is_fivemodels=is_fivemodels,
# val_size=val_size,
# test_size=test_size,
# settings=settings,
# now=now,
# etadata=etadata,
# modelsindex=modelsindex,
# data=data,
# is_eta=is_eta,
# end_time=end_time,
# )
# logger.info('模型训练完成')
# logger.info('训练数据绘图ing')
# model_results3 = model_losss(sqlitedb,end_time=end_time)
# logger.info('训练数据绘图end')
# 模型报告
logger.info('制作报告ing')
title = f'{settings}--{end_time}-预测报告' # 报告标题
reportname = f'Brent原油大模型预测--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号
brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
reportname=reportname,sqlitedb=sqlitedb),
logger.info('制作报告end')
logger.info('模型训练完成')
# # LSTM 单变量模型
# ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset)
# # lstm 多变量模型
# ex_Lstm_M(df,n_days=input_size,out_days=horizon,is_debug=is_debug,datasetpath=dataset)
# # GRU 模型
# # ex_GRU(df)
# 发送邮件
# m = SendMail(
# username=username,
# passwd=passwd,
# recv=recv,
# title=title,
# content=content,
# file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime),
# ssl=ssl,
# )
# m.send_mail()
if __name__ == '__main__':
global end_time
is_on = True
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期
for i_time in pd.date_range('2024-12-27', '2024-12-28', freq='B'):
end_time = i_time.strftime('%Y-%m-%d')
predict_main()

390
main_yuanyou.py
View File

@ -48,203 +48,203 @@ def predict_main():
返回:
None
"""
# global end_time
# signature = BinanceAPI(APPID, SECRET)
# etadata = EtaReader(signature=signature,
# classifylisturl=classifylisturl,
# classifyidlisturl=classifyidlisturl,
# edbcodedataurl=edbcodedataurl,
# edbcodelist=edbcodelist,
# edbdatapushurl=edbdatapushurl,
# edbdeleteurl=edbdeleteurl,
# edbbusinessurl=edbbusinessurl
# )
# # 获取数据
# if is_eta:
# logger.info('从eta获取数据...')
# signature = BinanceAPI(APPID, SECRET)
# etadata = EtaReader(signature=signature,
# classifylisturl=classifylisturl,
# classifyidlisturl=classifyidlisturl,
# edbcodedataurl=edbcodedataurl,
# edbcodelist=edbcodelist,
# edbdatapushurl=edbdatapushurl,
# edbdeleteurl=edbdeleteurl,
# edbbusinessurl=edbbusinessurl,
# )
# df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set, dataset=dataset) # 原始数据，未处理
global end_time
signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl
)
# 获取数据
if is_eta:
logger.info('从eta获取数据...')
signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl,
)
df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set, dataset=dataset) # 原始数据，未处理
# if is_market:
# logger.info('从市场信息平台获取数据...')
# try:
# df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju)
# except :
# logger.info('从市场信息平台获取数据失败')
if is_market:
logger.info('从市场信息平台获取数据...')
try:
df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju)
except :
logger.info('从市场信息平台获取数据失败')
# # 保存到xlsx文件的sheet表
# with pd.ExcelWriter(os.path.join(dataset,data_set)) as file:
# df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False)
# df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# 保存到xlsx文件的sheet表
with pd.ExcelWriter(os.path.join(dataset,data_set)) as file:
df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False)
df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# # 数据处理
# df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
# end_time=end_time)
# 数据处理
df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
end_time=end_time)
# else:
# # 读取数据
# logger.info('读取本地数据：' + os.path.join(dataset, data_set))
# df,df_zhibiaoliebiao = getdata(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
else:
# 读取数据
logger.info('读取本地数据：' + os.path.join(dataset, data_set))
df,df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj,
is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
# # 更改预测列名称
# df.rename(columns={y: 'y'}, inplace=True)
# 更改预测列名称
df.rename(columns={y: 'y'}, inplace=True)
# if is_edbnamelist:
# df = df[edbnamelist]
# df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False)
# # 保存最新日期的y值到数据库
# # 取第一行数据存储到数据库中
# first_row = df[['ds', 'y']].tail(1)
# print(first_row['ds'].values[0])
# print(first_row['y'].values[0])
# # 判断y的类型是否为float
# if not isinstance(first_row['y'].values[0], float):
# logger.info(f'{end_time}预测目标数据为空，跳过')
# return None
if is_edbnamelist:
df = df[edbnamelist]
df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False)
# 保存最新日期的y值到数据库
# 取第一行数据存储到数据库中
first_row = df[['ds', 'y']].tail(1)
print(first_row['ds'].values[0])
print(first_row['y'].values[0])
# 判断y的类型是否为float
if not isinstance(first_row['y'].values[0], float):
logger.info(f'{end_time}预测目标数据为空，跳过')
return None
# # 将最新真实值保存到数据库
# if not sqlitedb.check_table_exists('trueandpredict'):
# first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
# else:
# for row in first_row.itertuples(index=False):
# row_dict = row._asdict()
# row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S')
# check_query = sqlitedb.select_data('trueandpredict', where_condition=f"ds = '{row.ds}'")
# if len(check_query) > 0:
# set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()])
# sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
# continue
# sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys())
# 将最新真实值保存到数据库
if not sqlitedb.check_table_exists('trueandpredict'):
first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
else:
for row in first_row.itertuples(index=False):
row_dict = row._asdict()
row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S')
check_query = sqlitedb.select_data('trueandpredict', where_condition=f"ds = '{row.ds}'")
if len(check_query) > 0:
set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()])
sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
continue
sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys())
# # 更新accuracy表的y值
# if not sqlitedb.check_table_exists('accuracy'):
# pass
# else:
# update_y = sqlitedb.select_data('accuracy',where_condition="y is null")
# if len(update_y) > 0:
# logger.info('更新accuracy表的y值')
# # 找到update_y 中ds且df中的y的行
# update_y = update_y[update_y['ds']<=end_time]
# logger.info(f'要更新y的信息：{update_y}')
# try:
# for row in update_y.itertuples(index=False):
# row_dict = row._asdict()
# yy = df[df['ds']==row_dict['ds']]['y'].values[0]
# LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0]
# HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0]
# sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
# except Exception as e:
# logger.info(f'更新accuracy表的y值失败：{e}')
# 更新accuracy表的y值
if not sqlitedb.check_table_exists('accuracy'):
pass
else:
update_y = sqlitedb.select_data('accuracy',where_condition="y is null")
if len(update_y) > 0:
logger.info('更新accuracy表的y值')
# 找到update_y 中ds且df中的y的行
update_y = update_y[update_y['ds']<=end_time]
logger.info(f'要更新y的信息：{update_y}')
try:
for row in update_y.itertuples(index=False):
row_dict = row._asdict()
yy = df[df['ds']==row_dict['ds']]['y'].values[0]
LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0]
HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0]
sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
except Exception as e:
logger.info(f'更新accuracy表的y值失败：{e}')
# import datetime
# # 判断当前日期是不是周一
# is_weekday = datetime.datetime.now().weekday() == 0
# if is_weekday:
# logger.info('今天是周一，更新预测模型')
# # 计算最近60天预测残差最低的模型名称
# model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60")
# # 删除空值率为40%以上的列
# if len(model_results) > 10:
# model_results = model_results.dropna(thresh=len(model_results)*0.6,axis=1)
# # 删除空行
# model_results = model_results.dropna()
# modelnames = model_results.columns.to_list()[2:]
# for col in model_results[modelnames].select_dtypes(include=['object']).columns:
# model_results[col] = model_results[col].astype(np.float32)
# # 计算每个预测值与真实值之间的偏差率
# for model in modelnames:
# model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y']
# # 获取每行对应的最小偏差率值
# min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
# # 获取每行对应的最小偏差率值对应的列名
# min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
# # 将列名索引转换为列名
# min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0])
# # 取出现次数最多的模型名称
# most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
# logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}")
# # 保存结果到数据库
# if not sqlitedb.check_table_exists('most_model'):
# sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT")
# sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
import datetime
# 判断当前日期是不是周一
is_weekday = datetime.datetime.now().weekday() == 0
if is_weekday:
logger.info('今天是周一，更新预测模型')
# 计算最近60天预测残差最低的模型名称
model_results = sqlitedb.select_data('trueandpredict', order_by="ds DESC", limit="60")
# 删除空值率为90%以上的列
if len(model_results) > 10:
model_results = model_results.dropna(thresh=len(model_results)*0.1,axis=1)
# 删除空行
model_results = model_results.dropna()
modelnames = model_results.columns.to_list()[2:-1]
for col in model_results[modelnames].select_dtypes(include=['object']).columns:
model_results[col] = model_results[col].astype(np.float32)
# 计算每个预测值与真实值之间的偏差率
for model in modelnames:
model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y']
# 获取每行对应的最小偏差率值
min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
# 获取每行对应的最小偏差率值对应的列名
min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
# 将列名索引转换为列名
min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0])
# 取出现次数最多的模型名称
most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}")
# 保存结果到数据库
if not sqlitedb.check_table_exists('most_model'):
sqlitedb.create_table('most_model', columns="ds datetime, most_common_model TEXT")
sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
# try:
# if is_weekday:
# # if True:
# logger.info('今天是周一，发送特征预警')
# # 上传预警信息到数据库
# warning_data_df = df_zhibiaoliebiao.copy()
# warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']]
# # 重命名列名
# warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'})
# from sqlalchemy import create_engine
# import urllib
# global password
# if '@' in password:
# password = urllib.parse.quote_plus(password)
try:
if is_weekday:
# if True:
logger.info('今天是周一，发送特征预警')
# 上传预警信息到数据库
warning_data_df = df_zhibiaoliebiao.copy()
warning_data_df = warning_data_df[warning_data_df['停更周期']> 3 ][['指标名称', '指标id', '频度','更新周期','指标来源','最后更新时间','停更周期']]
# 重命名列名
warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'})
from sqlalchemy import create_engine
import urllib
global password
if '@' in password:
password = urllib.parse.quote_plus(password)
# engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
# warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S")
# warning_data_df['TENANT_CODE'] = 'T0004'
# # 插入数据之前查询表数据然后新增id列
# existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
# if not existing_data.empty:
# max_id = existing_data['ID'].astype(int).max()
# warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df))
# else:
# warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
# warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False)
# if is_update_warning_data:
# upload_warning_info(len(warning_data_df))
# except:
# logger.info('上传预警信息到数据库失败')
engine = create_engine(f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
warning_data_df['WARNING_DATE'] = datetime.date.today().strftime("%Y-%m-%d %H:%M:%S")
warning_data_df['TENANT_CODE'] = 'T0004'
# 插入数据之前查询表数据然后新增id列
existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
if not existing_data.empty:
max_id = existing_data['ID'].astype(int).max()
warning_data_df['ID'] = range(max_id + 1, max_id + 1 + len(warning_data_df))
else:
warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
warning_data_df.to_sql(table_name, con=engine, if_exists='append', index=False)
if is_update_warning_data:
upload_warning_info(len(warning_data_df))
except:
logger.info('上传预警信息到数据库失败')
# if is_corr:
# df = corr_feature(df=df)
if is_corr:
df = corr_feature(df=df)
# df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
# logger.info(f"开始训练模型...")
# row, col = df.shape
df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
logger.info(f"开始训练模型...")
row, col = df.shape
# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
# ex_Model(df,
# horizon=horizon,
# input_size=input_size,
# train_steps=train_steps,
# val_check_steps=val_check_steps,
# early_stop_patience_steps=early_stop_patience_steps,
# is_debug=is_debug,
# dataset=dataset,
# is_train=is_train,
# is_fivemodels=is_fivemodels,
# val_size=val_size,
# test_size=test_size,
# settings=settings,
# now=now,
# etadata=etadata,
# modelsindex=modelsindex,
# data=data,
# is_eta=is_eta,
# end_time=end_time,
# )
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
ex_Model(df,
horizon=horizon,
input_size=input_size,
train_steps=train_steps,
val_check_steps=val_check_steps,
early_stop_patience_steps=early_stop_patience_steps,
is_debug=is_debug,
dataset=dataset,
is_train=is_train,
is_fivemodels=is_fivemodels,
val_size=val_size,
test_size=test_size,
settings=settings,
now=now,
etadata=etadata,
modelsindex=modelsindex,
data=data,
is_eta=is_eta,
end_time=end_time,
)
# logger.info('模型训练完成')
logger.info('模型训练完成')
# logger.info('训练数据绘图ing')
# model_results3 = model_losss(sqlitedb,end_time=end_time)
# logger.info('训练数据绘图end')
logger.info('训练数据绘图ing')
model_results3 = model_losss(sqlitedb,end_time=end_time)
logger.info('训练数据绘图end')
# 模型报告
logger.info('制作报告ing')
@ -267,22 +267,24 @@ def predict_main():
# # ex_GRU(df)
# 发送邮件
# m = SendMail(
# username=username,
# passwd=passwd,
# recv=recv,
# title=title,
# content=content,
# file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime),
# ssl=ssl,
# )
# m.send_mail()
m = SendMail(
username=username,
passwd=passwd,
recv=recv,
title=title,
content=content,
file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime),
ssl=ssl,
)
m.send_mail()
if __name__ == '__main__':
global end_time
is_on = True
# 遍历2024-11-25 到 2024-12-3 之间的工作日日期
for i_time in pd.date_range('2024-12-27', '2024-12-28', freq='B'):
end_time = i_time.strftime('%Y-%m-%d')
# global end_time
# is_on = True
# # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
# for i_time in pd.date_range('2024-12-27', '2024-12-28', freq='B'):
# end_time = i_time.strftime('%Y-%m-%d')
# predict_main()
predict_main()

25
models/nerulforcastmodels.py
View File

@ -317,6 +317,28 @@ def model_losss(sqlitedb,end_time):
except ValueError :
df_predict['ds'] = pd.to_datetime(df_predict['ds'],format=r'%Y/%m/%d')
def first_row_to_database(df):
# # 取第一行数据存储到数据库中
first_row = df.head(1)
first_row['ds'] = first_row['ds'].dt.strftime('%Y-%m-%d 00:00:00')
# 将预测结果保存到数据库
if not sqlitedb.check_table_exists('trueandpredict'):
first_row.to_sql('trueandpredict',sqlitedb.connection,index=False)
else:
for col in first_row.columns:
sqlitedb.add_column_if_not_exists('trueandpredict',col,'TEXT')
for row in first_row.itertuples(index=False):
row_dict = row._asdict()
columns=row_dict.keys()
check_query = sqlitedb.select_data('trueandpredict',where_condition = f"ds = '{row.ds}'")
if len(check_query) > 0:
set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()])
sqlitedb.update_data('trueandpredict',set_clause,where_condition = f"ds = '{row.ds}'")
continue
sqlitedb.insert_data('trueandpredict',tuple(row_dict.values()),columns=columns)
first_row_to_database(df_predict)
df_combined3 = pd.concat([df_combined3, df_predict]).reset_index(drop=True)
# 计算每个模型与最佳模型的绝对误差比例，根据设置的阈值rote筛选预测值显示最大最小值
@ -1018,6 +1040,7 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu
df4 = sqlitedb.select_data('accuracy_rote',order_by='结束日期 desc',limit=1)
df4 = df4.T
df4 = df4.reset_index()
df4 = df4.T
data = df4.values.tolist()
col_width = 500/len(df4.columns)
content.append(Graphs.draw_table(col_width,*data))
@ -1133,7 +1156,7 @@ def brent_export_pdf(num_indicators=475,num_models=21, num_dayindicator=202,inpu
eval_df = eval_df.T
# df重置索引
eval_df = eval_df.reset_index()
# eval_df = eval_df.T
eval_df = eval_df.T
# # 添加表格
data = eval_df.values.tolist()
col_width = 500/len(eval_df.columns)