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

some fixes for Travis #Rstat

Browse Source
This commit is contained in:
pommedeterresautee 2015-11-30 15:47:10 +01:00
parent c09c02300a
commit 730bd72056
9 changed files with 25 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
R-package/R/xgb.model.dt.tree.R
View File

@ -50,7 +50,7 @@
#' eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#'
#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix.
#' xgb.model.dt.tree(agaricus.train$data@@Dimnames[[2]], model = bst)
#' xgb.model.dt.tree(feature_names = agaricus.train$data@@Dimnames[[2]], model = bst)
#'
#' @export
xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL, n_first_tree = NULL){

2
R-package/R/xgb.plot.deepness.R
View File

@ -93,7 +93,7 @@ get.paths.to.leaf <- function(dt.tree) {
#' @examples
#' data(agaricus.train, package='xgboost')
#'
#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 15,
#' bst <- xgboost(data = agaricus.train$data, max.depth = 15,
#' eta = 1, nthread = 2, nround = 30, objective = "binary:logistic",
#' min_child_weight = 50)
#'

7
R-package/R/xgb.plot.multi.trees.R
View File

@ -11,6 +11,7 @@
#' @importFrom stringr str_extract
#'
#' @param model dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.
#' @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 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.height height in pixels of the graph to produce
@ -45,12 +46,12 @@
#' eta = 1, nthread = 2, nround = 30, objective = "binary:logistic",
#' min_child_weight = 50)
#'
#' p <- xgb.plot.multi.trees(model = bst, names = agaricus.train$data@Dimnames[[2]], 3)
#' p <- xgb.plot.multi.trees(model = bst, feature_names = agaricus.train$data@Dimnames[[2]], features.keep = 3)
#' print(p)
#'
#' @export
xgb.plot.multi.trees <- function(model, names, features.keep = 5, plot.width = NULL, plot.height = NULL){
tree.matrix <- xgb.model.dt.tree(names, model = model)
xgb.plot.multi.trees <- function(model, feature_names = NULL, features.keep = 5, plot.width = NULL, plot.height = NULL){
tree.matrix <- xgb.model.dt.tree(feature_names = feature_names, model = model)
# first number of the path represents the tree, then the following numbers are related to the path to follow
# root init

11
R-package/R/xgb.plot.tree.R
View File

@ -7,7 +7,6 @@
#' @importFrom data.table :=
#' @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 filename_dump the path to the text file storing the model. Model dump must include the gain per feature and per tree (parameter \code{with.stats = T} in function \code{xgb.dump}). Possible to provide a model directly (see \code{model} argument).
#' @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 plot.width the width of the diagram in pixels.
@ -40,12 +39,12 @@
#' eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#'
#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix.
#' xgb.plot.tree(agaricus.train$data@@Dimnames[[2]], model = bst)
#' xgb.plot.tree(feature_names = agaricus.train$data@@Dimnames[[2]], model = bst)
#'
#' @export
xgb.plot.tree <- function(feature_names = NULL, filename_dump = NULL, model = NULL, n_first_tree = NULL, plot.width = NULL, plot.height = NULL){
xgb.plot.tree <- function(feature_names = NULL, model = NULL, n_first_tree = NULL, plot.width = NULL, plot.height = NULL){
if (!class(model) %in% c("xgb.Booster", "NULL")) {
if (class(model) != "xgb.Booster") {
stop("model: Has to be an object of class xgb.Booster model generaged by the xgb.train function.")
}
@ -53,11 +52,7 @@ xgb.plot.tree <- function(feature_names = NULL, filename_dump = NULL, model = NU
stop("DiagrammeR package is required for xgb.plot.tree", call. = FALSE)
}
if(is.null(model)){
allTrees <- xgb.model.dt.tree(feature_names = feature_names, filename_dump = filename_dump, n_first_tree = n_first_tree)
} else {
allTrees <- xgb.model.dt.tree(feature_names = feature_names, model = model, n_first_tree = n_first_tree)
}
allTrees[, label:= paste0(Feature, "\nCover: ", Cover, "\nGain: ", Quality)]
allTrees[, shape:= "rectangle"][Feature == "Leaf", shape:= "oval"]

2
R-package/man/xgb.model.dt.tree.Rd
View File

@ -52,7 +52,7 @@ bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#agaricus.test$data@Dimnames[[2]] represents the column names of the sparse matrix.
xgb.model.dt.tree(agaricus.train$data@Dimnames[[2]], model = bst)
xgb.model.dt.tree(feature_names = agaricus.train$data@Dimnames[[2]], model = bst)
}

2
R-package/man/xgb.plot.deepness.Rd
View File

@ -35,7 +35,7 @@ This function is inspired by this blog post \url{http://aysent.github.io/2015/11
\examples{
data(agaricus.train, package='xgboost')
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 15,
bst <- xgboost(data = agaricus.train$data, max.depth = 15,
eta = 1, nthread = 2, nround = 30, objective = "binary:logistic",
min_child_weight = 50)

8
R-package/man/xgb.plot.multi.trees.Rd
View File

@ -4,12 +4,14 @@
\alias{xgb.plot.multi.trees}
\title{Project all trees on one tree and plot it}
\usage{
xgb.plot.multi.trees(model, names, features.keep = 5, plot.width = NULL,
plot.height = NULL)
xgb.plot.multi.trees(model, feature_names = NULL, features.keep = 5,
plot.width = NULL, plot.height = NULL)
}
\arguments{
\item{model}{dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.}
\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{features.keep}{number of features to keep in each position of the multi trees.}
\item{plot.width}{width in pixels of the graph to produce}
@ -49,7 +51,7 @@ bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.dep
eta = 1, nthread = 2, nround = 30, objective = "binary:logistic",
min_child_weight = 50)
p <- xgb.plot.multi.trees(model = bst, names = agaricus.train$data@Dimnames[[2]], 3)
p <- xgb.plot.multi.trees(model = bst, feature_names = agaricus.train$data@Dimnames[[2]], features.keep = 3)
print(p)
}

8
R-package/man/xgb.plot.tree.Rd
View File

@ -4,14 +4,12 @@
\alias{xgb.plot.tree}
\title{Plot a boosted tree model}
\usage{
xgb.plot.tree(feature_names = NULL, filename_dump = NULL, model = NULL,
n_first_tree = NULL, plot.width = NULL, plot.height = NULL)
xgb.plot.tree(feature_names = NULL, model = NULL, n_first_tree = NULL,
plot.width = NULL, plot.height = NULL)
}
\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{filename_dump}{the path to the text file storing the model. Model dump must include the gain per feature and per tree (parameter \code{with.stats = T} in function \code{xgb.dump}). Possible to provide a model directly (see \code{model} argument).}
\item{model}{generated by the \code{xgb.train} function. Avoid the creation of a dump file.}
\item{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.}
@ -51,7 +49,7 @@ bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#agaricus.test$data@Dimnames[[2]] represents the column names of the sparse matrix.
xgb.plot.tree(agaricus.train$data@Dimnames[[2]], model = bst)
xgb.plot.tree(feature_names = agaricus.train$data@Dimnames[[2]], model = bst)
}

6
R-package/tests/testthat/test_helpers.R
View File

@ -23,13 +23,13 @@ test_that("xgb.dump works", {
})
test_that("xgb.importance works", {
importance <- xgb.importance(sparse_matrix@Dimnames[[2]], model = bst)
importance <- xgb.importance(feature_names = sparse_matrix@Dimnames[[2]], model = bst)
expect_equal(dim(importance), c(7, 4))
expect_equal(colnames(importance), c("Feature", "Gain", "Cover", "Frequency"))
})
test_that("xgb.plot.tree works", {
xgb.plot.tree(names = agaricus.train$data@Dimnames[[2]], model = bst)
xgb.plot.tree(feature_names = agaricus.train$data@Dimnames[[2]], model = bst)
})
test_that("xgb.plot.deepness works", {
@ -37,5 +37,5 @@ test_that("xgb.plot.deepness works", {
})
test_that("xgb.plot.multi.trees works", {
xgb.plot.multi.trees(model = bst, names = agaricus.train$data@Dimnames[[2]], 3)
xgb.plot.multi.trees(model = bst, feature_names = agaricus.train$data@Dimnames[[2]], 3)
})