Hi, I refer to the code template in the example to train my own data using the timeGAN model, and it worked perfectly. Thanks for the hard working that makes it easy for us to use the TimeGAN model.
But I have encountered one problem, I don't know how to save the generated data.
Because at the begining, there is a parameter seq_len = 24 # Timesteps . The original shape of my csv file is (3000, 7), column: date, T1, T2, ... , T6. After begining, the shape became (2976, 24, 6), when i use .to_csv, the shape didn't match.
I know the shape change is from shift sampling every 24 lines, how can I aggregate the generated data in the original shape (3000,7), column: date, T1, T2, ... , T6, and save it as csv file?
Hi, I refer to the code template in the example to train my own data using the timeGAN model, and it worked perfectly. Thanks for the hard working that makes it easy for us to use the TimeGAN model.
But I have encountered one problem, I don't know how to save the generated data.
Because at the begining, there is a parameter seq_len = 24 # Timesteps . The original shape of my csv file is (3000, 7), column: date, T1, T2, ... , T6. After begining, the shape became (2976, 24, 6), when i use .to_csv, the shape didn't match.
I know the shape change is from shift sampling every 24 lines, how can I aggregate the generated data in the original shape (3000,7), column: date, T1, T2, ... , T6, and save it as csv file?