You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The reason will be displayed to describe this comment to others. Learn more.
Hi @MayaSal - Sorry I didn't catch this before merging, but I realized that the origin/file date for this week should be 10-27-2024, with 11-03-2024 being the projection at horizon = 1. This is because the last available data point is 10-19. Projections for 10-27 (horizon = 0) aren't required, but if you could reformat so that 11-03 is horizon = 1 and rename the file, that would make things easier for figures/evaluation purposes. Hope this makes sense, thanks in advance! (You should still be able to submit despite it being past Tuesday for this)
The reason will be displayed to describe this comment to others. Learn more.
Hey,
Thank you for the clarification- We did notice that the last date was 10-19 and we actually ran the model with 6 horizons dropping the -1 for submission. Just for the future is there always expected to be the same time delay in data (IE should I set up my pipeline with the anticipation of forecasting for the previous Sunday?) . I will go ahead and rerun the model with 5 horizons and the appropriate data and resubmit.
Thanks for reaching out,
Maya
________________________________
From: Kimberlyn Roosa ***@***.***>
Sent: Wednesday, October 30, 2024 11:19 AM
To: HopkinsIDD/rsv-forecast-hub ***@***.***>
Cc: Mariah Victoria Salcedo ***@***.***>; Mention ***@***.***>
Subject: Re: [HopkinsIDD/rsv-forecast-hub] add 2024-11-03 INFLAenza (59f5be1)
[EXTERNAL SENDER - PROCEED CAUTIOUSLY]
Hi @MayaSal<https://github.com/MayaSal> - Sorry I didn't catch this before merging, but I realized that the origin/file date for this week should be 10-27-2024, with 11-03-2024 being the projection at horizon = 1. This is because the last available data point is 10-19. Projections for 10-27 (horizon = 0) aren't required, but if you could reformat so that 11-03 is horizon = 1 and rename the file, that would make things easier for figures/evaluation purposes. Hope this makes sense, thanks in advance! (You should still be able to submit despite it being past Tuesday for this)
—
Reply to this email directly, view it on GitHub<59f5be1#commitcomment-148555233>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AVIYM2E7QSXIX2MD6KGDBGTZ6D2JZAVCNFSM6AAAAABQ4LVOI2VHI2DSMVQWIX3LMV43OQ3PNVWWS5CDN5WW2ZLOOQ5TCNBYGU2TKMRTGM>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
59f5be1There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @MayaSal - Sorry I didn't catch this before merging, but I realized that the origin/file date for this week should be 10-27-2024, with 11-03-2024 being the projection at horizon = 1. This is because the last available data point is 10-19. Projections for 10-27 (horizon = 0) aren't required, but if you could reformat so that 11-03 is horizon = 1 and rename the file, that would make things easier for figures/evaluation purposes. Hope this makes sense, thanks in advance! (You should still be able to submit despite it being past Tuesday for this)
59f5be1There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
59f5be1There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sorry about the confusion! Yes - there will always be the same time delay in the data, so you can expect the origin_date to be the prior Sunday.