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

New documentation rewording

Browse Source
This commit is contained in:
Michaël Benesty 2015-12-09 18:26:56 +01:00
parent f761432c11
commit b2e68b8dc7
6 changed files with 20 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
R-package/R/xgb.plot.deepness.R
View File

@ -69,7 +69,7 @@ get.paths.to.leaf <- function(dt.tree) {
#' @importFrom data.table setnames #' @importFrom data.table setnames
#' @importFrom data.table := #' @importFrom data.table :=
#' @importFrom magrittr %>% #' @importFrom magrittr %>%
#' @param model dump generated by the \code{xgb.train} function. Avoid the creation of a dump file. #' @param model dump generated by the \code{xgb.train} function.
#' #'
#' @return Two graphs showing the distribution of the model deepness. #' @return Two graphs showing the distribution of the model deepness.
#' #'
@ -86,7 +86,7 @@ get.paths.to.leaf <- function(dt.tree) {
#' #'
#' \itemize{ #' \itemize{
#' \item Count: number of leaf per level of deepness; #' \item Count: number of leaf per level of deepness;
#' \item Weighted cover: noramlized weighted cover per Leaf (weighted number of instances). #' \item Weighted cover: noramlized weighted cover per leaf (weighted number of instances).
#' } #' }
#' #'
#' This function is inspired by the blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html} #' This function is inspired by the blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html}

4
R-package/R/xgb.plot.multi.trees.R
View File

@ -10,8 +10,8 @@
#' @importFrom stringr str_detect #' @importFrom stringr str_detect
#' @importFrom stringr str_extract #' @importFrom stringr str_extract
#' #'
#' @param model dump generated by the \code{xgb.train} function. Avoid the creation of a dump file. #' @param model dump generated by the \code{xgb.train} function.
#' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}. #' @param feature_names names of each feature as a \code{character} vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.
#' @param features.keep number of features to keep in each position of the multi trees. #' @param features.keep number of features to keep in each position of the multi trees.
#' @param plot.width width in pixels of the graph to produce #' @param plot.width width in pixels of the graph to produce
#' @param plot.height height in pixels of the graph to produce #' @param plot.height height in pixels of the graph to produce

14
R-package/R/xgb.plot.tree.R
View File

@ -1,12 +1,11 @@
#' Plot a boosted tree model #' Plot a boosted tree model
#' #'
#' Read a tree model text dump. #' Read a tree model text dump and plot the model.
#' Plotting only works for boosted tree model (not linear model).
#' #'
#' @importFrom data.table data.table #' @importFrom data.table data.table
#' @importFrom data.table := #' @importFrom data.table :=
#' @importFrom magrittr %>% #' @importFrom magrittr %>%
#' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}. #' @param feature_names names of each feature as a \code{character} vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.
#' @param model generated by the \code{xgb.train} function. Avoid the creation of a dump file. #' @param model generated by the \code{xgb.train} function. Avoid the creation of a dump file.
#' @param n_first_tree limit the plot to the n first trees. If \code{NULL}, all trees of the model are plotted. Performance can be low for huge models. #' @param n_first_tree limit the plot to the n first trees. If \code{NULL}, all trees of the model are plotted. Performance can be low for huge models.
#' @param plot.width the width of the diagram in pixels. #' @param plot.width the width of the diagram in pixels.
@ -24,20 +23,15 @@
#' \item \code{gain}: metric the importance of the node in the model. #' \item \code{gain}: metric the importance of the node in the model.
#' } #' }
#' #'
#' Each branch finishes with a leaf. For each leaf, only the \code{cover} is indicated. #' The function uses \href{http://www.graphviz.org/}{GraphViz} library for that purpose.
#' It uses \href{http://www.graphviz.org/}{GraphViz} library for that purpose.
#' #'
#' @examples #' @examples
#' data(agaricus.train, package='xgboost') #' data(agaricus.train, package='xgboost')
#' #'
#' #Both dataset are list with two items, a sparse matrix and labels
#' #(labels = outcome column which will be learned).
#' #Each column of the sparse Matrix is a feature in one hot encoding format.
#'
#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2, #' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2,
#' eta = 1, nthread = 2, nround = 2,objective = "binary:logistic") #' eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#' #'
#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix. #' # agaricus.train$data@@Dimnames[[2]] represents the column names of the sparse matrix.
#' xgb.plot.tree(feature_names = agaricus.train$data@@Dimnames[[2]], model = bst) #' xgb.plot.tree(feature_names = agaricus.train$data@@Dimnames[[2]], model = bst)
#' #'
#' @export #' @export

4
R-package/man/xgb.plot.deepness.Rd
View File

@ -7,7 +7,7 @@
xgb.plot.deepness(model = NULL) xgb.plot.deepness(model = NULL)
} }
\arguments{ \arguments{
\item{model}{dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.} \item{model}{dump generated by the \code{xgb.train} function.}
} }
\value{ \value{
Two graphs showing the distribution of the model deepness. Two graphs showing the distribution of the model deepness.
@ -28,7 +28,7 @@ The graph is made of two parts:
\itemize{ \itemize{
\item Count: number of leaf per level of deepness; \item Count: number of leaf per level of deepness;
\item Weighted cover: noramlized weighted cover per Leaf (weighted number of instances). \item Weighted cover: noramlized weighted cover per leaf (weighted number of instances).
} }
This function is inspired by the blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html} This function is inspired by the blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html}

4
R-package/man/xgb.plot.multi.trees.Rd
View File

@ -8,9 +8,9 @@ xgb.plot.multi.trees(model, feature_names = NULL, features.keep = 5,
plot.width = NULL, plot.height = NULL) plot.width = NULL, plot.height = NULL)
} }
\arguments{ \arguments{
\item{model}{dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.} \item{model}{dump generated by the \code{xgb.train} function.}
\item{feature_names}{names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.} \item{feature_names}{names of each feature as a \code{character} vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.}
\item{features.keep}{number of features to keep in each position of the multi trees.} \item{features.keep}{number of features to keep in each position of the multi trees.}

14
R-package/man/xgb.plot.tree.Rd
View File

@ -8,7 +8,7 @@ xgb.plot.tree(feature_names = NULL, model = NULL, n_first_tree = NULL,
plot.width = NULL, plot.height = NULL) plot.width = NULL, plot.height = NULL)
} }
\arguments{ \arguments{
\item{feature_names}{names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.} \item{feature_names}{names of each feature as a \code{character} vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.}
\item{model}{generated by the \code{xgb.train} function. Avoid the creation of a dump file.} \item{model}{generated by the \code{xgb.train} function. Avoid the creation of a dump file.}
@ -22,8 +22,7 @@ xgb.plot.tree(feature_names = NULL, model = NULL, n_first_tree = NULL,
A \code{DiagrammeR} of the model. A \code{DiagrammeR} of the model.
} }
\description{ \description{
Read a tree model text dump. Read a tree model text dump and plot the model.
Plotting only works for boosted tree model (not linear model).
} }
\details{ \details{
The content of each node is organised that way: The content of each node is organised that way:
@ -34,20 +33,15 @@ The content of each node is organised that way:
\item \code{gain}: metric the importance of the node in the model. \item \code{gain}: metric the importance of the node in the model.
} }
Each branch finishes with a leaf. For each leaf, only the \code{cover} is indicated. The function uses \href{http://www.graphviz.org/}{GraphViz} library for that purpose.
It uses \href{http://www.graphviz.org/}{GraphViz} library for that purpose.
} }
\examples{ \examples{
data(agaricus.train, package='xgboost') data(agaricus.train, package='xgboost')
#Both dataset are list with two items, a sparse matrix and labels
#(labels = outcome column which will be learned).
#Each column of the sparse Matrix is a feature in one hot encoding format.
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2, bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2,
eta = 1, nthread = 2, nround = 2,objective = "binary:logistic") eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#agaricus.test$data@Dimnames[[2]] represents the column names of the sparse matrix. # agaricus.train$data@Dimnames[[2]] represents the column names of the sparse matrix.
xgb.plot.tree(feature_names = agaricus.train$data@Dimnames[[2]], model = bst) xgb.plot.tree(feature_names = agaricus.train$data@Dimnames[[2]], model = bst)
} }