105 lines
3.3 KiB
R
105 lines
3.3 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/xgb.plot.tree.R
|
|
\name{xgb.plot.tree}
|
|
\alias{xgb.plot.tree}
|
|
\title{Plot boosted trees}
|
|
\usage{
|
|
xgb.plot.tree(
|
|
feature_names = NULL,
|
|
model = NULL,
|
|
trees = NULL,
|
|
plot_width = NULL,
|
|
plot_height = NULL,
|
|
render = TRUE,
|
|
show_node_id = FALSE,
|
|
...
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{feature_names}{Character vector used to overwrite the feature names
|
|
of the model. The default (\code{NULL}) uses the original feature names.}
|
|
|
|
\item{model}{Object of class \code{xgb.Booster}.}
|
|
|
|
\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 = 0:2} for the first three trees).}
|
|
|
|
\item{plot_width, plot_height}{Width and height of the graph in pixels.
|
|
The values are passed to \code{\link[DiagrammeR:render_graph]{DiagrammeR::render_graph()}}.}
|
|
|
|
\item{render}{Should the graph be rendered or not? The default is \code{TRUE}.}
|
|
|
|
\item{show_node_id}{a logical flag for whether to show node id's in the graph.}
|
|
|
|
\item{...}{currently not used.}
|
|
}
|
|
\value{
|
|
The value depends on the \code{render} parameter:
|
|
\itemize{
|
|
\item If \code{render = TRUE} (default): Rendered graph object which is an htmlwidget of
|
|
class \code{grViz}. Similar to "ggplot" objects, it needs to be printed when not
|
|
running from the command line.
|
|
\item If \code{render = FALSE}: Graph object which is of DiagrammeR's class \code{dgr_graph}.
|
|
This could be useful if one wants to modify some of the graph attributes
|
|
before rendering the graph with \code{\link[DiagrammeR:render_graph]{DiagrammeR::render_graph()}}.
|
|
}
|
|
}
|
|
\description{
|
|
Read a tree model text dump and plot the model.
|
|
}
|
|
\details{
|
|
The content of each node is visualized like this:
|
|
\itemize{
|
|
\item \emph{Feature name}.
|
|
\item \emph{Cover:} The sum of second order gradients of training data.
|
|
For the squared loss, this simply corresponds to the number of instances in the node.
|
|
The deeper in the tree, the lower the value.
|
|
\item \emph{Gain} (for split nodes): Information gain metric of a split
|
|
(corresponds to the importance of the node in the model).
|
|
\item \emph{Value} (for leaves): Margin value that the leaf may contribute to the prediction.
|
|
}
|
|
|
|
The tree root nodes also indicate the tree index (0-based).
|
|
|
|
The "Yes" branches are marked by the "< split_value" label.
|
|
The branches also used for missing values are marked as bold
|
|
(as in "carrying extra capacity").
|
|
|
|
This function uses \href{https://www.graphviz.org/}{GraphViz} as DiagrammeR backend.
|
|
}
|
|
\examples{
|
|
data(agaricus.train, package = "xgboost")
|
|
|
|
bst <- xgboost(
|
|
data = agaricus.train$data,
|
|
label = agaricus.train$label,
|
|
max_depth = 3,
|
|
eta = 1,
|
|
nthread = 2,
|
|
nrounds = 2,
|
|
objective = "binary:logistic"
|
|
)
|
|
|
|
# plot all the trees
|
|
xgb.plot.tree(model = bst)
|
|
|
|
# plot only the first tree and display the node ID:
|
|
xgb.plot.tree(model = bst, trees = 0, show_node_id = TRUE)
|
|
|
|
\dontrun{
|
|
# Below is an example of how to save this plot to a file.
|
|
# Note that for export_graph() to work, the {DiagrammeRsvg}
|
|
# and {rsvg} packages must also be installed.
|
|
|
|
library(DiagrammeR)
|
|
|
|
gr <- xgb.plot.tree(model = bst, trees = 0:1, render = FALSE)
|
|
export_graph(gr, "tree.pdf", width = 1500, height = 1900)
|
|
export_graph(gr, "tree.png", width = 1500, height = 1900)
|
|
}
|
|
|
|
}
|