c:\laragon\www\LPG\.venv\Scripts\python.exe : WARNING: All log messages before 
absl::InitializeLog() is called are written to STDERR
At line:1 char:1
+ c:\laragon\www\LPG\.venv\Scripts\python.exe c:\laragon\www\LPG\ai_scr ...
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : NotSpecified: (WARNING: All lo...itten to STDERR:Strin 
   g) [], RemoteException
    + FullyQualifiedErrorId : NativeCommandError
 
I0000 00:00:1773436638.982568   14416 port.cc:153] oneDNN custom operations are on. 
You may see slightly different numerical results due to floating-point round-off 
errors from different computation orders. To turn them off, set the environment 
variable `TF_ENABLE_ONEDNN_OPTS=0`.
WARNING: All log messages before absl::InitializeLog() is called are written to 
STDERR
I0000 00:00:1773436640.741093   14416 port.cc:153] oneDNN custom operations are on. 
You may see slightly different numerical results due to floating-point round-off 
errors from different computation orders. To turn them off, set the environment 
variable `TF_ENABLE_ONEDNN_OPTS=0`.
c:\laragon\www\LPG\ai_scripts\forecast_lstm.py:33: UserWarning: pandas only supports 
SQLAlchemy connectable (engine/connection) or database string URI or sqlite3 DBAPI2 
connection. Other DBAPI2 objects are not tested. Please consider using SQLAlchemy.
  df = pd.read_sql(query, connection)
1. Mengambil data transaksi dari MySQL...
Data kosong atau belum cukup untuk training LSTM (Butuh minimal 14 hari data historis).