Nick Crews

Throwing in my 2 cents here in case anyone feels like moving this forward, I like how [spacy](https://spacy.io/usage) handles downloading/installing their pre-trained models.

FYI, a modern maintained version of this is https://github.com/carltonnorthern/nicknames

OK, it looks like there isn't any solution that I am looking for. I misunderstood the semantics of what a pyarrow dictionary array was. Perhaps if this gets added to...

@cosmicBboy MANY months later 🤣 , but how's that PR look?

Re treating as multinomial classification, in section 4.5 of [this survey](https://doi.org/10.48550/arXiv.2010.11075) they mention that [Entity Resolution Using Convolutional Neural Net](https://doi.org/10.1016/j.procs.2016.09.306) treats linking records as a classification problem. I didn't dive...

[splink](https://github.com/moj-analytical-services/splink) seems to somehow guess which records are matches using some sort of [unsupervised Expectation Maximisation algorithm](https://moj-analytical-services.github.io/splink/demos/03_Estimating_model_parameters.html) (that it does not explain very well and I couldn't find a good...

I haven't used it, but I imagine that [pytest-memray](https://github.com/bloomberg/pytest-memray) might be a good alternative, instead of profiling memory directly in this pytest extension. This appears to be a tricky task,...

I'm interested in this too. Any help appreciated.

FYI it looks like #35 was only merged to the [feature/support-relaxedjs](https://github.com/orzih/mkdocs-with-pdf/tree/feature/support-relaxedjs) branch, not main, so that's why it's not visible. It would be great if it could be ported to...

EDIT: actually this won't work because it won't include the trained data `python -m pip install "usaddress @ git+https://github.com/tirkarthi/usaddress.git@70accf06879c099bb0d7259be7c98c613b98e8d0"`