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

聚烯烃日度预测调试

Browse Source
This commit is contained in:
jingboyitiji 2025-03-28 13:54:14 +08:00
parent 27960c9083
commit 1e75070ca3
2 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
lib/dataread.py
View File

@ -977,21 +977,21 @@ def datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, datecol='date', end_t
two_months_ago = current_date - timedelta(days=40) two_months_ago = current_date - timedelta(days=40)
# 检查两月不更新的特征 # 检查两月不更新的特征
def check_column(col_name): # def check_column(col_name):
if 'ds' in col_name or 'y' in col_name: # if 'ds' in col_name or 'y' in col_name:
return False # return False
df_check_column = df[['ds', col_name]] # df_check_column = df[['ds', col_name]]
df_check_column = df_check_column.dropna() # df_check_column = df_check_column.dropna()
if len(df_check_column) == 0: # if len(df_check_column) == 0:
return True # return True
if df_check_column[(df_check_column['ds'] >= two_months_ago)].groupby(col_name).ngroups < 2: # if df_check_column[(df_check_column['ds'] >= two_months_ago)].groupby(col_name).ngroups < 2:
return True # return True
corresponding_date = df_check_column.iloc[-1]['ds'] # corresponding_date = df_check_column.iloc[-1]['ds']
return corresponding_date < two_months_ago # return corresponding_date < two_months_ago
columns_to_drop = df.columns[df.columns.map(check_column)].tolist() # columns_to_drop = df.columns[df.columns.map(check_column)].tolist()
df = df.drop(columns=columns_to_drop) # df = df.drop(columns=columns_to_drop)
config.logger.info(f'删除两月不更新特征后数据量：{df.shape}') # config.logger.info(f'删除两月不更新特征后数据量：{df.shape}')
# 删除预测列空值的行 # 删除预测列空值的行
df = df.dropna(subset=['y']) df = df.dropna(subset=['y'])

2
main_juxiting.py
View File

@ -388,7 +388,7 @@ 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('2025-2-1', '2025-3-18', freq='B'): for i_time in pd.date_range('2025-2-10', '2025-3-18', 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() predict_main()