Replies: 1 comment 2 replies
-
Thanks for pointing this out. Looks like it grabbing data from the wrong year. I'll have a PR for this soon. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Looks like there might be an issue with the way get_data and create_games are populating the sqlite db.
For instance, I'll clone the repo and run both scripts to pull in any missing data up until the completion of yesterday's games. I'm looking at games on Jan 9th 2023:
The Lakers are listed as being home to Memphis
Toronto is listed as being home to New Orleans
Here's the problem though..
Memphis was home to San Antonio on Jan 9 and Toronto didn't even play. New Orleans was in Washington.
I've had a look at the scripts I mentioned above and don't quite see where things are going off the rails but if the dates and teams are being pulled incorrectly, this obviously has bearing in pulling in the wrong stats, which are used in the model, which would in turn give the wrong projections as far as I understand.
Beta Was this translation helpful? Give feedback.
All reactions