Hi everyone, I have a question regarding the training data requirements for TimeGPT. With the following line of code: timegpt_fcst_df = nixtla_client.forecast(df=df, h=96, freq='15min', id_col='unique_id', time_col='ds', target_col='y') I get the following error:

ValueError: Series contain missing or duplicate timestamps, or the timestamps do not match the provided frequency.
Please make sure that all series have a single observation from the first to the last timestamp and that the provided frequency matches the timestamps'.
You can refer to <https://docs.nixtla.io/docs/tutorials-missing_values> for an end to end example.

My training data (df) is structured as follows: I have three columns unique_id, ds and y. The time series of one unique_id are always 288 rows long and the next time series starts one hour after the previous one. So there are the same timestamps several times but with different unique_ids. According to the documentation, this should work, right? Unfortunately I don't understand why I am getting this error in my setup.

Hello! Maybe you have some missing values. You can see here how to handle that.

I checked that already, there are no missing values in any column ...

I mean, are you sure that there are no gaps? If you run the function

fill_gaps

in the link I sent before, does the number of rows stay the same?

okay my fault, I only checked for NaNs and not for missing timestamps ... thank you Marco!