npc_gzip

npc_gzip copied to clipboard

Let the example adapt to any compression algorithm (that conforms to spec) by importing the module under an exception handler. Example using zstd, which is not found in the original...

congruency

Train - test leakage

4

Hi, I looked into the OOD results and many examples in the test sets seem to be in the train set. E.g. DengueFilipino has the same train and test set....

YannDubs

Hi, How I can save and load the trained model for prediction, without re-train it.? Thanks

pribadihcr

Is there a way to multi thread this in python 3.9 so that It runs faster?

sakgoyal

Discussion on future work

2

Hi there! First of all, I appreciate the team for putting in the work for this research paper. I would like to preface this by saying that my comments here...

jamestiotio

added examples for the other two compressor types. eventually i want to add support for other compressors that don't come stock with python

CaltropHungerton

Bias term using NCD?

4

Hey! I've been playing around with this method and I've noticed something interesting. When calculating the NCD you use ```python ncd = (Cx1x2 - min(Cx1, Cx2)) / max(Cx1,Cx2) ``` And...

Maimonator

Problem with accuracy calculation?

25

https://github.com/bazingagin/npc_gzip/blob/a46991564161023bba3b1267e0e74c69dab8f8eb/experiments.py#L116 It appears that in the `calc_acc` method it marks a sample correct if ANY of the labels with the same `most_count` have the correct label. For `k=2` (I think...

kts

How to directly input text for prediction？

4

gggdroa

Accuracy issue

4

 I tested Filipino and AG_NEWS datasets, but I couldn’t achieve the accuracy mentioned in your paper. I’m not sure where I went wrong.

lx-zg