Hello! 
I’m currently doing the 2019 fast.ai course and I gotta say I’ve been enjoying it a lot so far! I also learn a lot by ‘doing’ first and learning the theory later so it’s nice to see a course structured in that way. Anyway, I’m at lesson 4 right now and I just got done with the tabular data section. Maybe I’m jumping the gun here but I wanted to try and apply what I’ve learned so far to the Housing Prices Kaggle dataset. I tried it out myself and I ran into some issues. First issue being that the accuracy I get is just completely terrible, like literally 1% so I’m sure I’m doing something wrong. Second issue is that when I try to create the databunch, I get an error where some columns get removed because it’s not in my validation set even though they’re from the same dataset and just being split. In any case, this is my code.
If someone can tell me where I’m going wrong and if there’s a different way I can do this I’d gladly appreciate it.
Thanks!