Because you need data, trained models, etc.
Because data scientists aren't typically product people or software engineers with UX in mind.
Because ML packages are brittle and tied to specific hardware configurations.
Because the ML world is evolving rapidly. It's quick, dirty, and messy.
View these as stepping stones for research and product development.
(I created https://vo.codes using a lot of these, fwiw, in an attempt to make it easy.)
They would have to release a great many different ones or alternatively bundle all libraries with it.
I once saw a comparison with LibreOffice that showed that the the package Debian itself provided was 20% of the size of the package LibreOffice provided targeting Debian, — which would not receive the same benefits of security bugfixes to libraries, but of course also not the same problems that often arise on Debian when they arrogantly patch libraries they barely understand and create their own unique security problems.