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

add limit number of trees option

Browse Source
This commit is contained in:
El Potaeto 2015-01-06 13:59:29 +01:00
parent a6c588f90d
commit 94d070da60
2 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
R-package/R/xgb.plot.tree.R
View File

@ -17,6 +17,7 @@
#' @importFrom DiagrammeR DiagrammeR #' @importFrom DiagrammeR DiagrammeR
#' @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 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 (\code{with.stats = T} in function \code{xgb.dump}). #' @param filename_dump the path to the text file storing the model. Model dump must include the gain per feature and per tree (\code{with.stats = T} in function \code{xgb.dump}).
#' @param n_first_tree limit the plot to the n first trees.
#' #'
#' @return A \code{data.table} of the features used in the model with their average gain (and their weight for boosted tree model) in the model. #' @return A \code{data.table} of the features used in the model with their average gain (and their weight for boosted tree model) in the model.
#' #'
@ -41,25 +42,30 @@
#' xgb.plot.tree(agaricus.train$data@@Dimnames[[2]], 'xgb.model.dump') #' xgb.plot.tree(agaricus.train$data@@Dimnames[[2]], 'xgb.model.dump')
#' #'
#' @export #' @export
xgb.plot.tree <- function(feature_names = NULL, filename_dump = NULL){ xgb.plot.tree <- function(feature_names = NULL, filename_dump = NULL, n_first_tree = NULL){
if (!class(feature_names) %in% c("character", "NULL")) { if (!class(feature_names) %in% c("character", "NULL")) {
stop("feature_names: Has to be a vector of character or NULL if the model dump already contains feature name. Look at this function documentation to see where to get feature names.") stop("feature_names: Has to be a vector of character or NULL if the model dump already contains feature name. Look at this function documentation to see where to get feature names.")
} }
if (class(filename_dump) != "character" & file.exists(filename_dump)) { if (class(filename_dump) != "character" || !file.exists(filename_dump)) {
stop("filename_dump: Has to be a path to the model dump file.") stop("filename_dump: Has to be a path to the model dump file.")
} }
if (!class(n_first_tree) %in% c("numeric", "NULL") | length(n_first_tree) > 1) {
stop("n_first_tree: Has to be a numeric vector of size 1.")
}
text <- readLines(filename_dump) %>% str_trim(side = "both") text <- readLines(filename_dump) %>% str_trim(side = "both")
position <- str_match(text, "booster") %>% is.na %>% not %>% which %>% c(length(text)+1) position <- str_match(text, "booster") %>% is.na %>% not %>% which %>% c(length(text)+1)
extract <- function(x, pattern) str_extract(x, pattern) %>% str_split("=") %>% lapply(function(x) x[2] %>% as.numeric) %>% unlist extract <- function(x, pattern) str_extract(x, pattern) %>% str_split("=") %>% lapply(function(x) x[2] %>% as.numeric) %>% unlist
n_round <- min(length(position) - 1, n_first_tree)
addTreeId <- function(x, i) paste(i,x,sep = "-") addTreeId <- function(x, i) paste(i,x,sep = "-")
allTrees <- data.table() allTrees <- data.table()
for(i in 1:(length(position)-1)){ for(i in 1:n_round){
tree <- text[(position[i]+1):(position[i+1]-1)] tree <- text[(position[i]+1):(position[i+1]-1)]

5
R-package/man/xgb.plot.tree.Rd
View File

@ -4,12 +4,15 @@
\alias{xgb.plot.tree} \alias{xgb.plot.tree}
\title{Plot a boosted tree model} \title{Plot a boosted tree model}
\usage{ \usage{
xgb.plot.tree(feature_names = NULL, filename_dump = NULL) xgb.plot.tree(feature_names = NULL, filename_dump = NULL,
n_first_tree = 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 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 (\code{with.stats = T} in function \code{xgb.dump}).} \item{filename_dump}{the path to the text file storing the model. Model dump must include the gain per feature and per tree (\code{with.stats = T} in function \code{xgb.dump}).}
\item{n_first_tree}{limit the plot to the n first trees.}
} }
\value{ \value{
A \code{data.table} of the features used in the model with their average gain (and their weight for boosted tree model) in the model. A \code{data.table} of the features used in the model with their average gain (and their weight for boosted tree model) in the model.