xgboost on data set with both categorical and numerical data

[Monira_Mahmoud]

I am working on diabetes data set with 35 attributes some are categorical like race, age groups drug dosages up down steady and no and some are numerical like time in hospital and admission id. and i would like to apply xgboost which is as I know works on numerical data only could you help with an example workflow with xgboost?

[ScottF]

Hi @Monira_Mahmoud -

You can use XGboost for both classification and regression. The KNIME Hub has you covered:

Workflows: XGboost – KNIME Hub

In particular you might start with this relatively simple classification workflow:

Forest Cover Type Classification with XGBoost – nemad

[mlauber71]

@Monira_Mahmoud you could take a look at this example also including xgboost

Decision tree learner seems to be overfitting

@akhtarameen the Decision tree of @aworker does a wonderful job. I wanted to see what else is possible so I took it up a notch. H2O.ai and XGBoost are able to do an even slighly better job with more correct classification (on the test set). [image] Admitteldly H2O.ai would add a further level of complication since it would use an ensemble of models to predict the outcome. If you data would differ over time very complicated models might also be less robust than a tree model. But from my expe…

[Daniel_Weikert]

I have not checked in KNIME but if XGB really only support numerical data (I would actually assume otherwise) you need to encode your categorical features (one to many node does one hot encoding)
br