I completed the Google Cloud tutorial called Intro to Vertex Pipelines and I now want to adapt the completed Jupyter notebook for two things:
- Build and train a regression ML model instead of classification (used in the tutorial).
- I need to use my own dataset that is in a Google Cloud bucket.
I also went through other Google Cloud tutorials looking for code for a regression model using their pre-built components and Python packages but I have run into a variety of errors when attempting to just swap in my dataset for the tutorial's pre-made dataset.
My main question is where I need to put the location of my dataset and how I should format that information (Both tutorials I have gone through call their dataset in different ways).
For some context, I have about a year or two of coding experience with Python and have done a few, smaller projects similar to this one but am struggling with using Google's tools.