5a2dcd1c33
* [R] Provide better guidance for persisting XGBoost model * Update saving_model.rst * Add a paragraph about xgb.serialize()
84 lines
3.4 KiB
R
84 lines
3.4 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 a boosted tree model text dump}
|
|
\usage{
|
|
xgb.model.dt.tree(
|
|
feature_names = NULL,
|
|
model = NULL,
|
|
text = NULL,
|
|
trees = NULL,
|
|
use_int_id = FALSE,
|
|
...
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{feature_names}{character vector of feature names. If the model already
|
|
contains feature names, those would be used when \code{feature_names=NULL} (default value).
|
|
Non-null \code{feature_names} could be provided to override those in the model.}
|
|
|
|
\item{model}{object of class \code{xgb.Booster}}
|
|
|
|
\item{text}{\code{character} vector previously generated by the \code{xgb.dump}
|
|
function (where parameter \code{with_stats = TRUE} should have been set).
|
|
\code{text} takes precedence over \code{model}.}
|
|
|
|
\item{trees}{an integer vector of tree indices that should be parsed.
|
|
If set to \code{NULL}, all trees of the model are parsed.
|
|
It could be useful, e.g., in multiclass classification to get only
|
|
the trees of one certain class. IMPORTANT: the tree index in xgboost models
|
|
is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).}
|
|
|
|
\item{use_int_id}{a logical flag indicating whether nodes in columns "Yes", "No", "Missing" should be
|
|
represented as integers (when FALSE) or as "Tree-Node" character strings (when FALSE).}
|
|
|
|
\item{...}{currently not used.}
|
|
}
|
|
\value{
|
|
A \code{data.table} with detailed information about model trees' nodes.
|
|
|
|
The columns of the \code{data.table} are:
|
|
|
|
\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, it's a feature id or name (when available);
|
|
for a leaf note, 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 branch value is missing
|
|
\item \code{Quality}: either the split gain (change in loss) or the leaf value
|
|
\item \code{Cover}: metric related to the number of observation 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')
|
|
|
|
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max_depth = 2,
|
|
eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
|
|
|
|
(dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
|
|
|
|
# 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(model = 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)]
|
|
|
|
}
|