Why does XGBoost only support binary classification

Question

I have noticed that the implementations for XGBoost both in Python and R support only binary classification of a categorical target variable.

• I have implemented both Random Forest and Extremely Randomised Trees for my classification problem

Why can I not use this method to classify targets coming from multiple categories?

Are there adjustments that can be made to my multiclass dataset in order to use XGBoost?

Answer 1

It does support multi class classification. Below is the code:

param = {
    'max_depth': 3,  # the maximum depth of each tree
    'eta': 0.3,  # the training step for each iteration
    'silent': 1,  # logging mode - quiet
    'objective': 'multi:softprob',  # error evaluation for multiclass training
    'num_class': 3}  # the number of classes that exist in this dataset

You can use num_class as parameter in Python for Multi Class Classification.