In this part of the project I'm going to create a fact model in dbt. Yikes is that hard. First of all, I had to remember a lot of things that I hadn't written down. Fortunately I had the repo from class. I was able to look up the files that I had made before. I copied the directories to my repo and made some changes, then tried to fix the dates on my files to be a genuine timestamp. I went around and around and finally found one error, which was that I said my project name was data-engineering-2024, when in fact it was data-engineering-2024-411821. It didn't help that the error log file said "expected ) but found ;" Once I made that change, I could build my model, and it worked. I still haven't built the full model, but the one where I limit to 100 lines works. I verified it on BigQuery and the timestamp was a genuine timestamp.
Then I added a few directories to .gitignore. That's when the problems started. I tried over and over to commit my changes, but I got an absurd error that said I had to type "git push --set-upstream origin cmcrawford2-patch-1" and some other useless advice. I went back and forth with ChatGPT about this, but finally I went to Google and typed dbt won't let me commit files to GitHub repository. This led me to dbt documentation, where I found out that there was a special secret handshake that I had to do when I changed .gitignore. It consisted of approximately 12 steps, including resetting the IDE twice, deleting the unwanted folders, etc. I followed the instructions and was able to push my changes and merge the commit on my GitHub repo. Tomorrow I'll make some more changes to the fact model, and then I can finally see what I have.
Top comments (0)