87 lines
3.2 KiB
R
87 lines
3.2 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/xgb.model.dt.tree.R
|
|
\name{xgb.model.dt.tree}
|
|
\alias{xgb.model.dt.tree}
|
|
\title{Parse model text dump}
|
|
\usage{
|
|
xgb.model.dt.tree(
|
|
model = NULL,
|
|
text = NULL,
|
|
trees = NULL,
|
|
use_int_id = FALSE,
|
|
...
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{model}{Object of class \code{xgb.Booster}. If it contains feature names (they can
|
|
be set through \code{\link[=setinfo]{setinfo()}}), they will be used in the output from this function.}
|
|
|
|
\item{text}{Character vector previously generated by the function \code{\link[=xgb.dump]{xgb.dump()}}
|
|
(called with parameter \code{with_stats = TRUE}). \code{text} takes precedence over \code{model}.}
|
|
|
|
\item{trees}{An integer vector of tree indices that should be used. The default
|
|
(\code{NULL}) uses all trees. Useful, e.g., in multiclass classification to get only
|
|
the trees of one class. \emph{Important}: the tree index in XGBoost models
|
|
is zero-based (e.g., use \code{trees = 0:4} for the first five trees).}
|
|
|
|
\item{use_int_id}{A logical flag indicating whether nodes in columns "Yes", "No", and
|
|
"Missing" should be represented as integers (when \code{TRUE}) or as "Tree-Node"
|
|
character strings (when \code{FALSE}, default).}
|
|
|
|
\item{...}{Currently not used.}
|
|
}
|
|
\value{
|
|
A \code{data.table} with detailed information about tree nodes. It has the following columns:
|
|
\itemize{
|
|
\item \code{Tree}: integer ID of a tree in a model (zero-based index).
|
|
\item \code{Node}: integer ID of a node in a tree (zero-based index).
|
|
\item \code{ID}: character identifier of a node in a model (only when \code{use_int_id = FALSE}).
|
|
\item \code{Feature}: for a branch node, a feature ID or name (when available);
|
|
for a leaf node, it simply labels it as \code{"Leaf"}.
|
|
\item \code{Split}: location of the split for a branch node (split condition is always "less than").
|
|
\item \code{Yes}: ID of the next node when the split condition is met.
|
|
\item \code{No}: ID of the next node when the split condition is not met.
|
|
\item \code{Missing}: ID of the next node when the branch value is missing.
|
|
\item \code{Gain}: either the split gain (change in loss) or the leaf value.
|
|
\item \code{Cover}: metric related to the number of observations either seen by a split
|
|
or collected by a leaf during training.
|
|
}
|
|
|
|
When \code{use_int_id = FALSE}, columns "Yes", "No", and "Missing" point to model-wide node identifiers
|
|
in the "ID" column. When \code{use_int_id = TRUE}, those columns point to node identifiers from
|
|
the corresponding trees in the "Node" column.
|
|
}
|
|
\description{
|
|
Parse a boosted tree model text dump into a \code{data.table} structure.
|
|
}
|
|
\examples{
|
|
# Basic use:
|
|
|
|
data(agaricus.train, package = "xgboost")
|
|
## Keep the number of threads to 1 for examples
|
|
nthread <- 1
|
|
data.table::setDTthreads(nthread)
|
|
|
|
bst <- xgb.train(
|
|
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
|
|
max_depth = 2,
|
|
eta = 1,
|
|
nthread = nthread,
|
|
nrounds = 2,
|
|
objective = "binary:logistic"
|
|
)
|
|
|
|
# This bst model already has feature_names stored with it, so those would be used when
|
|
# feature_names is not set:
|
|
dt <- xgb.model.dt.tree(bst)
|
|
|
|
# How to match feature names of splits that are following a current 'Yes' branch:
|
|
merge(
|
|
dt,
|
|
dt[, .(ID, Y.Feature = Feature)], by.x = "Yes", by.y = "ID", all.x = TRUE
|
|
)[
|
|
order(Tree, Node)
|
|
]
|
|
|
|
}
|