https://github.com/nixtla logo
#neural-forecast
Title
# neural-forecast
f

Farzad E

08/31/2023, 8:50 PM
I am trying to apply NHiTS to some new data I have but I get an error of
Out of bounds nanosecond timestamp: 2385-12-31 00:00:00
when I do nf.predict(futr_df=df_test). But my df_test only has 364 days in it with dates going from 2022-01-03 to 2023-01-01. There is no date even close to 2385! Also, the 'ds' column is properly converted to datetime type. It's weird. I am thinking that 2385 might be coming from adding a date to the last point in an input batch? I'm not sure. There is a line in the error stack pointing to core.py line 109 dates=np.tile(last_date_f(last_dates[0], len(dataset)). Has anyone seen this type of error before?
c

Cristian (Nixtla)

09/01/2023, 3:04 AM
Hi @Farzad E! It has been a while, hopefully everything was running smoothly 🙂. The dates are created based on the frequency you specified when you instantiated the
nf
object. Based on the value
2385-12-31
it seems you are using a frequency of
Y
or
A
, instead of day (
D
)
❤️ 1
f

Farzad E

09/01/2023, 2:14 PM
@Cristian (Nixtla) yeah I know. Have been busy with other things. Back to forecasting again 🙂. You are absolutely right. I found my dumb mistake after I learned how to make VSCode debugger step into the neuralforecast scripts while executing and saw the frequency was not right inside of
_future_dates
function of the core module. Thanks for the quick reply. Hope all is well with you and the team.
3 Views