SQLAlchemy is arguably the most powerful and ubiquitous ORM framework for Python.
At Oursky, we have been using SQLAlchemy for quite a period of time and appreciated the flexibility and elegance it provides over the Data Mapper abstraction. No doubt, it works very well for modern web applications but what about long-running background jobs? Would the abstraction get in your ways? (tl;dr: yes, but we still prefer it)
Here are some hands-on experiences from us.
We built a popular iOS application with a song recommendation system at the backend. The system suggests a top list for 20 popular songs.
Previously our editors hand-picked popular songs by download count and gather a new playlist as a recommendation to users. Now, we want to automate this process and generate the playlist weekly.