1% Generated by roxygen2: do not edit by hand 2% Please edit documentation in R/xgb.plot.shap.R 3\name{xgb.shap.data} 4\alias{xgb.shap.data} 5\title{Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc. 6Internal utility function.} 7\usage{ 8xgb.shap.data( 9 data, 10 shap_contrib = NULL, 11 features = NULL, 12 top_n = 1, 13 model = NULL, 14 trees = NULL, 15 target_class = NULL, 16 approxcontrib = FALSE, 17 subsample = NULL, 18 max_observations = 1e+05 19) 20} 21\arguments{ 22\item{data}{data as a \code{matrix} or \code{dgCMatrix}.} 23 24\item{shap_contrib}{a matrix of SHAP contributions that was computed earlier for the above 25\code{data}. When it is NULL, it is computed internally using \code{model} and \code{data}.} 26 27\item{features}{a vector of either column indices or of feature names to plot. When it is NULL, 28feature importance is calculated, and \code{top_n} high ranked features are taken.} 29 30\item{top_n}{when \code{features} is NULL, top_n [1, 100] most important features in a model are taken.} 31 32\item{model}{an \code{xgb.Booster} model. It has to be provided when either \code{shap_contrib} 33or \code{features} is missing.} 34 35\item{trees}{passed to \code{\link{xgb.importance}} when \code{features = NULL}.} 36 37\item{target_class}{is only relevant for multiclass models. When it is set to a 0-based class index, 38only SHAP contributions for that specific class are used. 39If it is not set, SHAP importances are averaged over all classes.} 40 41\item{approxcontrib}{passed to \code{\link{predict.xgb.Booster}} when \code{shap_contrib = NULL}.} 42 43\item{subsample}{a random fraction of data points to use for plotting. When it is NULL, 44it is set so that up to 100K data points are used.} 45} 46\value{ 47A list containing: 'data', a matrix containing sample observations 48 and their feature values; 'shap_contrib', a matrix containing the SHAP contribution 49 values for these observations. 50} 51\description{ 52Prepare data for SHAP plots. To be used in xgb.plot.shap, xgb.plot.shap.summary, etc. 53Internal utility function. 54} 55\keyword{internal} 56