Ethan Rosenthal

Hi, I'm not sure if you can use `skits` for this, but my recommendation would be to create a column in your feature matrix for each possible feature and time-offset...

The `link_mat` comes from the middle line of this equation (from my [blog post](https://www.ethanrosenthal.com/2018/12/06/spacecutter-ordinal-regression/) on this)  Adjacent cutpoints have to be subtracted from each other. The `AscenscionCallback` gets [called](https://github.com/EthanRosenthal/spacecutter/blob/master/spacecutter/callbacks.py#L40)...

Sorry I can't really help debug -- it could have something to do with the library or be something else. Perhaps you can try training as a regular regression model...

I don't really have enough information to help you debug this. All I can say is that there should be one fewer cutpoint than the number of classes that you're...

Yup, you're totally right. I should fix that...

Is there anything I can do to help complete this PR?

@vene Sounds good - I'm happy to take a look and see if I can improve the performance.

Hmm I should add some more `poetry`-specific explanation. I don't usually use `poetry` to manage my virtual environments; I only use it for installing dependencies. Regardless, you shouldn't need to...

Hey, sorry, that implicit fork is super old and out of date. I would recommend trying to install the main version of implicit. I think that implicit now has a...

Weird, I have not run into this before. I honestly have no idea what's going on. I believe that `contruct-dataset` first downloads a single large zip file from Kaggle into...