Is it safe to use scikit-learn == 1.1.1 ?

First I'd like to thank you for sharing your code!

I run Apple m1 chipset and needed to update requirements. txt to list scikit-learn == 1.1.1 instead of 0.22.

I tested on https://github.com/solana-labs/whitepaper.git which is a very small repo.

Here are the results:

1) git/BoDeGiC/venv39/lib/python3.9/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 0.22 when using version 1.1.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to: https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations

2) output:

               messages  patterns  dispersion prediction

author
Anonymous 16 2.0 -0.000 Bot Greg Fitzgerald 13 12.0 0.104 Bot jang 19 8.0 0.144 Bot Anatoly Yakovenko 100 24.0 0.066 Human Eric Williams 24 15.0 0.035 Human Jangsa 14 11.0 0.057 Human Michael Vines 28 24.0 0.031 Human Andre2112 1 NaN Unknown Andreas Heiberg 1 NaN Unknown Casey Rodarmor 2 NaN Unknown Celien Nanson 2 NaN Unknown Franck Verrot 1 NaN Unknown Grimes 5 NaN Unknown Jackson Sandland 3 NaN Unknown anatoly yakovenko 3 NaN Unknown cornholington 2 NaN Unknown jeamick 1 NaN Unknown

Of all names there must be only one bot: Anonymous. Everybody else is human.

mehdigolzadeh / BoDeGiC

Is it safe to use scikit-learn == 1.1.1 ? #2