Andrew Stanton comments

Results 20 comments of


                                            Andrew Stanton

Thanks for the report and good question; I don't remember off the top of my head. Let me take a look at it tonight.

Interesting. This might be due to us using an older version of scikit-learn. Can you run `pip freeze` and say which version you're using?

OK. I'll see if I can put out a patch tonight; stay tuned.

@RiyaDhameliyal76 did that solve the problem? I'm unfortunately on linux so can't test this problem.

I need a bit more to go on. Can I get your system info, gcc version, and full stack trace?

My hunch is you ran out of memory on your machine. How big is the training dataset and how much memory is in the machine? How many features in the...

Thanks for the find; good ol' Numpy.. I'll make a note in the README that labels need to be JSON serializable.

Valid question! I've updated the README with a sample data format and how it can be run. Let me know if this answers your question!

I'll try it out today; on first blush the changes seem reasonable. It's also clearly time to drop python2 support.

Here's the paper that goes into details around the methods: https://yashoteja.github.io/papers/PfastreXML.pdf