shankarpandala / lazypredict

Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning
MIT License
2.76k stars 317 forks source link

Remove "QuantileRegressor" from Supervised.py to avoid system hanging #401

Open IslamAAli opened 1 year ago

IslamAAli commented 1 year ago

Removing "QuantileRegressor" which is the cause of the system to hang at 64% or 74%. Tested on multiple size datasets and it solves the problem

KayO-GH commented 1 year ago

This is a simple but very useful PR. @shankarpandala I think you should look into this. It solves a problem many of us are facing. Personally, I manually remove that regressor before using LazyPredict, otherwise, it stalls right after using the Poisson Regressor.

I used the code below to get it running without this fix, but the fix would certainly help a great deal, unless there's some other consideration I do not know of:

import sklearn
from lazypredict import Supervised

Supervised.removed_regressors.append("QuantileRegressor")
Supervised.REGRESSORS.remove(('QuantileRegressor', sklearn.linear_model._quantile.QuantileRegressor))
LazyRegressor = Supervised.LazyRegressor

Then use the LazyRegressor as usual.

IslamAAli commented 4 months ago

Let's rename the PR such it reflects the suggested change...

Changed the title of the MR as suggested.