原油周度配置

This commit is contained in:
jingboyitiji 2025-02-12 11:20:26 +08:00
parent 7b39b67842
commit c428e9d993
3 changed files with 23 additions and 23 deletions

View File

@ -216,7 +216,7 @@ data_set = '原油指标数据.xlsx' # 数据集文件
dataset = 'yuanyouzhoududataset' # 数据集文件夹
# 数据库名称
db_name = os.path.join(dataset,'jbsh_yuanyou.db')
db_name = os.path.join(dataset,'jbsh_yuanyou_zhoudu.db')
sqlitedb = SQLiteHandler(db_name)
sqlitedb.connect()

View File

@ -254,16 +254,16 @@ def predict_main():
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),
# # 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')
# 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)
@ -288,11 +288,11 @@ def predict_main():
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('2025-1-20', '2025-2-6', freq='B'):
# end_time = i_time.strftime('%Y-%m-%d')
# predict_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('2024-10-8', '2025-2-12', freq='B'):
end_time = i_time.strftime('%Y-%m-%d')
predict_main()
predict_main()
# predict_main()

View File

@ -188,9 +188,9 @@ def ex_Model(df,horizon,input_size,train_steps,val_check_steps,early_stop_patien
logger.info('读取模型:'+ filename)
nf = load(filename)
# # 测试集预测
nf_test_preds = nf.cross_validation(df=df_test, val_size=val_size, test_size=test_size, n_windows=None)
# 测试集预测结果保存
nf_test_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False)
# nf_test_preds = nf.cross_validation(df=df_test, val_size=val_size, test_size=test_size, n_windows=None)
# # 测试集预测结果保存
# nf_test_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False)
df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce')
@ -257,7 +257,7 @@ def model_losss_yongan(sqlitedb,end_time,table_name_prefix):
# 然后筛选出那些 cutoff 等于 max_cutoff 的行,这样就得到了每个分组中 cutoff 最大的行,并保留了其他列
df_combined = df_combined[df_combined['CREAT_DATE'] == df_combined['max_cutoff']]
# 删除模型生成的cutoff列
df_combined.drop(columns=['CREAT_DATE', 'max_cutoff','created_dt','min_within_quantile','max_within_quantile','id','min_price','max_price','LOW_PRICE','HIGH_PRICE','mean'], inplace=True)
df_combined.drop(columns=['CREAT_DATE', 'max_cutoff','created_dt','min_within_quantile','max_within_quantile','id','min_price','max_price','LOW_PRICE','HIGH_PRICE','mean'])
# 获取模型名称
modelnames = df_combined.columns.to_list()[1:]
if 'y' in modelnames:
@ -657,14 +657,14 @@ def model_losss(sqlitedb,end_time):
df_combined.dropna(inplace=True)
logger.info(df_combined.shape)
# 其他列转为数值类型
df_combined = df_combined.astype({col: 'float32' for col in df_combined.columns if col not in ['CREAT_DATE','ds','created_dt'] })
df_combined = df_combined.astype({col: 'float32' for col in df_combined.columns if col not in ['CREAT_DATE','ds','created_dt','cutoff'] })
# 使用 groupby 和 transform 结合 lambda 函数来获取每个分组中 cutoff 的最小值,并创建一个新的列来存储这个最大值
df_combined['max_cutoff'] = df_combined.groupby('ds')['CREAT_DATE'].transform('max')
# 然后筛选出那些 cutoff 等于 max_cutoff 的行,这样就得到了每个分组中 cutoff 最大的行,并保留了其他列
df_combined = df_combined[df_combined['CREAT_DATE'] == df_combined['max_cutoff']]
# 删除模型生成的cutoff列
df_combined.drop(columns=['CREAT_DATE', 'max_cutoff','created_dt','min_within_quantile','max_within_quantile','id','min_price','max_price','LOW_PRICE','HIGH_PRICE','mean'], inplace=True)
df_combined.drop(columns=['CREAT_DATE', 'max_cutoff','created_dt','min_within_quantile','max_within_quantile','id','min_price','max_price','LOW_PRICE','HIGH_PRICE','mean'], inplace=True,errors='ignore')
# 获取模型名称
modelnames = df_combined.columns.to_list()[1:]
if 'y' in modelnames: