Pavan Ramkumar

A couple of issues: - The assertion introduced in this [commit](https://github.com/glm-tools/pyglmnet/commit/0d3c3aed25bb320783e25bdfc88ee2c67b541fc9#diff-19c4b2f295f0c831b8250caa4bbfbba5) which tests that at least one group must be all zeros seems not guaranteed to pass. In practice I've...

In `test_glmcv()` we need to test both a dense (L2 like) and a sparse (L1 like) regime with different values of `alpha`.

See here: https://github.com/openjournals/brief-ideas/issues/132

We should look into more standard structuring of the repo tree: https://blog.ionelmc.ro/2014/05/25/python-packaging/#the-structure And modern testing automation: https://tox.readthedocs.io/en/latest/

enable warm restarts for partial models

3

potentially create a separate function called `init_params()` which can initialize the model betas while creating the new object. suggested by @pnlawlor

cc @teonbrooks Look at the table here: http://blog.shakirm.com/2015/01/a-statistical-view-of-deep-learning-i-recursive-glms/ Ask me if you have questions!

Example of object detection in docs

2

It would be great to have a simple example of object detection in the documentation so I can reproduce it. I currently tried to use the `detect` method, but I'm...