How do you feel about using this method as opposed to pickling a model for use with Flask? I can see the obvious advantage of keeping all code in one place, but can you keep a notebook running for days or weeks?
Very interesting read!
I had no idea you published the data set! I recently published a 50k row crime dataset scraped from crimemap.police.gov.mn.
I will definitely be doing an analysis using this dataset!
Quick question, do you have access to other fields such as the comments or response by the agency/ministry it’s…
Yes my final model that is detailed in part 3 of the series used weather forecasts to predict PM2.5 pollution. It’s a bit tough though as the forecasts can change quite often.
Thanks for reading! Time series are quite useful because you don’t need outside data to make forecasts. However, they are also limited because they don’t incorporate many of the factors that impact the thing you are forecasting. I’ll try to answer your questions below: