xgb.importance
Importance of features in a model.
Creates a data.table of feature importances in a model.
Usage
xgb.importance(
feature_names = NULL,
model = NULL,
trees = NULL,
data = NULL,
label = NULL,
target = NULL
)Arguments
- feature_names
character vector of feature names. If the model already contains feature names, those would be used when
feature_names=NULL(default value). Non-nullfeature_namescould be provided to override those in the model.- model
object of class
xgb.Booster.- trees
(only for the gbtree booster) an integer vector of tree indices that should be included into the importance calculation. If set to
NULL, all trees of the model are parsed. It could be useful, e.g., in multiclass classification to get feature importances for each class separately. IMPORTANT: the tree index in xgboost models is zero-based (e.g., usetrees = 0:4for first 5 trees).- data
deprecated.
- label
deprecated.
- target
deprecated.
Details
This function works for both linear and tree models.
For linear models, the importance is the absolute magnitude of linear coefficients. For that reason, in order to obtain a meaningful ranking by importance for a linear model, the features need to be on the same scale (which you also would want to do when using either L1 or L2 regularization).
Value
For a tree model, a data.table with the following columns:
Featuresnames of the features used in the model;Gainrepresents fractional contribution of each feature to the model based on the total gain of this feature's splits. Higher percentage means a more important predictive feature.Covermetric of the number of observation related to this feature;Frequencypercentage representing the relative number of times a feature have been used in trees.
A linear model's importance data.table has the following columns:
Featuresnames of the features used in the model;Weightthe linear coefficient of this feature;Class(only for multiclass models) class label.
If feature_names is not provided and model doesn't have feature_names,
index of the features will be used instead. Because the index is extracted from the model dump
(based on C++ code), it starts at 0 (as in C/C++ or Python) instead of 1 (usual in R).
Examples
# NOT RUN {
# binomial classification using gbtree:
data(agaricus.train, package='xgboost')
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
xgb.importance(model = bst)
# binomial classification using gblinear:
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, booster = "gblinear",
eta = 0.3, nthread = 1, nrounds = 20, objective = "binary:logistic")
xgb.importance(model = bst)
# multiclass classification using gbtree:
nclass <- 3
nrounds <- 10
mbst <- xgboost(data = as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1,
max_depth = 3, eta = 0.2, nthread = 2, nrounds = nrounds,
objective = "multi:softprob", num_class = nclass)
# all classes clumped together:
xgb.importance(model = mbst)
# inspect importances separately for each class:
xgb.importance(model = mbst, trees = seq(from=0, by=nclass, length.out=nrounds))
xgb.importance(model = mbst, trees = seq(from=1, by=nclass, length.out=nrounds))
xgb.importance(model = mbst, trees = seq(from=2, by=nclass, length.out=nrounds))
# multiclass classification using gblinear:
mbst <- xgboost(data = scale(as.matrix(iris[, -5])), label = as.numeric(iris$Species) - 1,
booster = "gblinear", eta = 0.2, nthread = 1, nrounds = 15,
objective = "multi:softprob", num_class = nclass)
xgb.importance(model = mbst)
# }