search

erdogant / hgboost

hgboost is a python package for hyper-parameter optimization for xgboost, catboost or lightboost using cross-validation, and evaluating the results on an independent validation set. hgboost can be applied for classification and regression tasks.
http://erdogant.github.io/hgboost
Other
57 stars 17 forks source link

hgb.plot command returns seaborn regplot error #13

Closed ninjit closed 1 year ago

ninjit commented 1 year ago

From the example classification notebook: Screen Shot 2022-10-04 at 14 42 22

Maybe tmpdf is a list or dictionary that seaborn is complaining about?

erdogant commented 1 year ago

Found it and fixed it! The order of the input parameters were changed for regplot so no now I explicitly define them. Update with:

pip install -U hgboost

Version should be >= 1.1.3

ninjit commented 1 year ago

Confirmed, thanks!

It also fixed some of the blank plots I was getting through hgb.plot_params There was no associated error message there, so I wasn't sure what was missing, but I now see scatter plots of each hyperparameter vs iteration #