PriceForecast/main_juxiting.py

303 lines
14 KiB
Python
Raw Normal View History

# 读取配置
from lib.dataread import *
2025-02-11 16:31:52 +08:00
from lib.tools import SendMail,exception_logger
2025-02-13 13:30:08 +08:00
from models.nerulforcastmodels import ex_Model_Juxiting,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting
import glob
import torch
torch.set_float32_matmul_precision("high")
2025-02-11 16:31:52 +08:00
def predict_main():
2025-02-11 16:31:52 +08:00
"""
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,
2025-02-11 16:31:52 +08:00
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,
2025-02-11 16:31:52 +08:00
edbbusinessurl=edbbusinessurl,
)
2025-02-11 16:31:52 +08:00
df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_pp_data(data_set=data_set, dataset=dataset) # 原始数据,未处理
2025-02-11 16:31:52 +08:00
if is_market:
logger.info('从市场信息平台获取数据...')
try:
# 如果是测试环境最高价最低价取excel文档
if server_host == '192.168.100.53':
logger.info('从excel文档获取最高价最低价')
df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju)
else:
logger.info('从市场信息平台获取数据')
df_zhibiaoshuju = get_market_data(end_time,df_zhibiaoshuju)
except :
logger.info('最高最低价拼接失败')
# 保存到xlsx文件的sheet表
with pd.ExcelWriter(os.path.join(dataset,data_set)) as file:
df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False)
df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# 数据处理
2025-02-11 16:31:52 +08:00
df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
end_time=end_time)
else:
2025-02-11 16:31:52 +08:00
# 读取数据
logger.info('读取本地数据:' + os.path.join(dataset, data_set))
df,df_zhibiaoliebiao = getdata_juxiting(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj,
is_timefurture=is_timefurture, end_time=end_time) # 原始数据,未处理
# 更改预测列名称
2025-02-11 16:31:52 +08:00
df.rename(columns={y: 'y'}, inplace=True)
if is_edbnamelist:
2025-02-11 16:31:52 +08:00
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
2025-02-11 16:31:52 +08:00
first_row = df[['ds', 'y']].tail(1)
# 判断y的类型是否为float
if not isinstance(first_row['y'].values[0], float):
logger.info(f'{end_time}预测目标数据为空,跳过')
return None
# 将最新真实值保存到数据库
if not sqlitedb.check_table_exists('trueandpredict'):
2025-02-11 16:31:52 +08:00
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')
2025-02-11 16:31:52 +08:00
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()])
2025-02-11 16:31:52 +08:00
sqlitedb.update_data('trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
continue
2025-02-11 16:31:52 +08:00
sqlitedb.insert_data('trueandpredict', tuple(row_dict.values()), columns=row_dict.keys())
# 更新accuracy表的y值
if not sqlitedb.check_table_exists('accuracy'):
pass
else:
update_y = sqlitedb.select_data('accuracy',where_condition="y is null")
if len(update_y) > 0:
logger.info('更新accuracy表的y值')
# 找到update_y 中ds且df中的y的行
update_y = update_y[update_y['ds']<=end_time]
logger.info(f'要更新y的信息{update_y}')
# try:
for row in update_y.itertuples(index=False):
try:
row_dict = row._asdict()
yy = df[df['ds']==row_dict['ds']]['y'].values[0]
LOW = df[df['ds']==row_dict['ds']]['Brentzdj'].values[0]
HIGH = df[df['ds']==row_dict['ds']]['Brentzgj'].values[0]
sqlitedb.update_data('accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
except:
logger.info(f'更新accuracy表的y值失败{row_dict}')
# except Exception as e:
# logger.info(f'更新accuracy表的y值失败{e}')
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')
2025-02-11 16:31:52 +08:00
# 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()
2025-02-11 16:31:52 +08:00
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()
2025-02-11 16:31:52 +08:00
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'):
2025-02-11 16:31:52 +08:00
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)
2025-02-11 16:31:52 +08:00
# 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))
2025-02-11 16:31:52 +08:00
if is_update_warning_data:
upload_warning_info(10)
2025-02-11 16:31:52 +08:00
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...")
2025-02-11 16:31:52 +08:00
row, col = df.shape
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
# ex_Model_Juxiting(df,
# horizon=horizon,
# input_size=input_size,
# train_steps=train_steps,
# val_check_steps=val_check_steps,
# early_stop_patience_steps=early_stop_patience_steps,
# is_debug=is_debug,
# dataset=dataset,
# is_train=is_train,
# is_fivemodels=is_fivemodels,
# val_size=val_size,
# test_size=test_size,
# settings=settings,
# now=now,
# etadata=etadata,
# modelsindex=modelsindex,
# data=data,
# is_eta=is_eta,
# end_time=end_time,
# )
logger.info('模型训练完成')
2025-02-11 16:31:52 +08:00
logger.info('训练数据绘图ing')
model_results3 = model_losss_juxiting(sqlitedb)
logger.info('训练数据绘图end')
2025-02-11 16:31:52 +08:00
# 模型报告
logger.info('制作报告ing')
2025-02-11 16:31:52 +08:00
title = f'{settings}--{end_time}-预测报告' # 报告标题
reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号
2024-11-14 17:26:17 +08:00
pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
2025-02-11 16:31:52 +08:00
reportname=reportname,sqlitedb=sqlitedb),
logger.info('制作报告end')
logger.info('模型训练完成')
2025-02-11 16:31:52 +08:00
# # 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,
)
2025-02-11 16:31:52 +08:00
# m.send_mail()
if __name__ == '__main__':
2025-02-11 16:31:52 +08:00
# 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('2025-1-20', '2025-2-6', freq='B'):
# end_time = i_time.strftime('%Y-%m-%d')
# try:
# predict_main()
# except:
# pass
predict_main()