Analyze the agaricus dataset using extreme gradient boosting. This dataset is supplied

with the xgboost package and is already divided into training and test subsets. The

training and test data is in sparse matrix format $($class dgCMatrix with $6$ slots$)$ while the

labels $($i$.$e$.$ responses$)$ are numeric vectors. You will have to decide whether to use this

data in sparse or dense format when you call xgboost. Label is binary and represents

whether a mushroom is safe to eat, or not, given characteristics of the mushrooms $($i$.$e$.,$

the predictors$).$ Tune your model in the training phase to yield best performance. Then

test your trained model using the test data. Show the predictive performance using tabular

and graphical representations. $(20$ points$)$