xgboost

Do not use saveRDS or save for long-term archival of models. Instead, use xgb.save or xgb.save.raw.

Test part from Mushroom Data Set

Training part from Mushroom Data Set

Callback closures for booster training.

Callback closure for returning cross-validation based predictions.

Callback closure to activate the early stopping.

Callback closure for logging the evaluation history

Callback closure for collecting the model coefficients history of a gblinear booster during its training.

Callback closure for printing the result of evaluation

Callback closure for resetting the booster's parameters at each iteration.

Callback closure for saving a model file.

Dimensions of xgb.DMatrix

Handling of column names of xgb.DMatrix

Get information of an xgb.DMatrix object

Scale feature value to have mean 0, standard deviation 1

Predict method for eXtreme Gradient Boosting model

Combine and melt feature values and SHAP contributions for sample observations.

Print xgb.Booster

Print xgb.DMatrix

Print xgb.cv result

Set information of an xgb.DMatrix object

Get a new DMatrix containing the specified rows of original xgb.DMatrix object

Restore missing parts of an incomplete xgb.Booster object.

Construct xgb.DMatrix object

Save xgb.DMatrix object to binary file

Accessors for serializable attributes of a model.

Accessors for model parameters as JSON string.

Create new features from a previously learned model

Cross Validation

Dump an xgboost model in text format.

Extract gblinear coefficients history.

Importance of features in a model.

Load xgboost model from binary file

Load serialised xgboost model from R's raw vector

Parse a boosted tree model text dump

Accessors for model parameters.

Plot model trees deepness

Plot feature importance as a bar graph

Project all trees on one tree and plot it

SHAP contribution dependency plots

SHAP contribution dependency summary plot

Plot a boosted tree model

Save xgboost model to binary file

Save xgboost model to R's raw vector, user can call xgb.load.raw to load the model back from raw vector

Serialize the booster instance into R's raw vector. The serialization method differs from xgb.save.raw as the latter one saves only the model but not parameters. This serialization format is not stable across different xgboost versions.

Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc. Internal utility function.

eXtreme Gradient Boosting Training

Load the instance back from xgb.serialize

Set and get global configuration

Deprecation notices.