Closed onchiptech closed 1 month ago
I found this line in estimator.py time_features=time_features_from_frequency_str("S"),
Why time_features is 'S' always? Suppose, my input dataset is of frequency i"1D", will it get the correct time feature with S'?
https://github.com/time-series-foundation-models/lag-llama/blob/4ad82d9d5d6bff4e9dd9c36aa6eba4af7a4d4e07/lag_llama/gluon/estimator.py#L263
Regards, Surendra
I think "S" captures all frequencies of the date time.
I found this line in estimator.py time_features=time_features_from_frequency_str("S"),
Why time_features is 'S' always? Suppose, my input dataset is of frequency i"1D", will it get the correct time feature with S'?
https://github.com/time-series-foundation-models/lag-llama/blob/4ad82d9d5d6bff4e9dd9c36aa6eba4af7a4d4e07/lag_llama/gluon/estimator.py#L263
Regards, Surendra