Mostly I am interested in the exercise to show how a real ML project can reach production.
Usually everyone is interested in the central part of this pipeline but it seems the other elements are the one more time consuming. So I analyzed the pipelined stated by miguelfzafra and changed accordingly to my taste.
The project consists of the following steps:
- Dataset Creation
- Exploratory Data Analysis
- Feature Engineering
- Model Training
- News Scraping
- App Creation
- Annex - Installation
- Annex - Deployment
- Report
- App Creation v2 (*I created a new version of the application after submitting the project.)
NB - Project started -> 2020/04/25