This message was deleted Nixtla Community #general

Join Slack

This message was deleted.

# general

Slackbot

12/22/2022, 5:22 PM

This message was deleted.

Darius Marginean

12/22/2022, 5:24 PM

Copy code

fcst = MLForecast( 
                 models=models, 
                 freq='W-MON',
                 differences=data['differences']
                )

Darius Marginean

12/22/2022, 5:26 PM

Copy code

models = [lgb.LGBMRegressor()]
fcst = MLForecast( 
                 models=models, 
                 freq='W-MON',
                 differences=[]
                )

Max (Nixtla)

12/22/2022, 5:39 PM

@José Morales, this one is for you.

José Morales

12/22/2022, 6:13 PM

Do you mean using the empty list as differences?

Darius Marginean

12/22/2022, 6:14 PM

@José Morales yes

Darius Marginean

12/22/2022, 6:14 PM

I ve noticed that if I left the differences as an empty list the predicted values are the same

José Morales

12/22/2022, 6:18 PM

The differences argument is there to specify sequential differences to apply to the series, e.g. [1,12] first subtracts the previous value and then the 12th. If you don't pass anything or pass the empty list it won't take any. What are you trying to accomplish?

Darius Marginean

12/23/2022, 10:13 AM

We are working on a weekly timeseries dataset, and didn't quite know what that argument did. We've seen that if we set

differences = [52]

the output of the predictions wasn't the same on the whole horizon. We've set

differenences = [52]

as a suggestion from @fede (nixtla) (they/them) in a previous thread to capture the yearly trend & seasonalities.

Darius Marginean

12/23/2022, 10:14 AM

Mostly I was wondering if there's something else we should do to our data (in case we don't want to use differences) to not predict the same values for the whole horizon

José Morales

12/28/2022, 2:35 AM

Maybe a straight line is the best prediction. What does your data look like?

Open in Slack

Previous Next