Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[R] xgb.importance: fix for multiclass gblinear, new 'trees' parameter (#2388)

Browse Source
This commit is contained in:
Vadim Khotilovich
2017-06-07 13:13:21 -05:00
committed by GitHub
parent 2ae56ca84f
commit c82276386d
4 changed files with 120 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
R-package/man/xgb.importance.Rd
View File

@@ -4,8 +4,8 @@
\alias{xgb.importance}
\title{Importance of features in a model.}
\usage{
xgb.importance(feature_names = NULL, model = NULL, data = NULL,
label = NULL, target = NULL)
xgb.importance(feature_names = NULL, model = NULL, trees = NULL,
data = NULL, label = NULL, target = NULL)
}
\arguments{
\item{feature_names}{character vector of feature names. If the model already
@@ -14,6 +14,12 @@ Non-null \code{feature_names} could be provided to override those in the model.}
\item{model}{object of class \code{xgb.Booster}.}
\item{trees}{(only for the gbtree booster) an integer vector of tree indices that should be included
into the importance calculation. If set to \code{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., use \code{trees = 0:4} for first 5 trees).}
\item{data}{deprecated.}
\item{label}{deprecated.}
@@ -32,13 +38,14 @@ For a tree model, a \code{data.table} with the following columns:
a feature have been used in trees.
}
A linear model's importance \code{data.table} has only two columns:
A linear model's importance \code{data.table} has the following columns:
\itemize{
\item \code{Features} names of the features used in the model;
\item \code{Weight} the linear coefficient of this feature.
\item \code{Weight} the linear coefficient of this feature;
\item \code{Class} (only for multiclass models) class label.
}
If you don't provide or \code{model} doesn't have \code{feature_names},
If \code{feature_names} is not provided and \code{model} doesn't have \code{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).
}
@@ -55,11 +62,34 @@ L1 or L2 regularization).
}
\examples{
# 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")
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)
}