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

refactoring for perf

Browse Source
This commit is contained in:
El Potaeto 2015-01-07 17:09:56 +01:00
parent cce26756bf
commit e380e4facf
2 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
R-package/R/xgb.plot.tree.R
View File

@ -1,7 +1,7 @@
#' Plot a boosted tree model #' Plot a boosted tree model
#' #'
#' Read a xgboost model text dump. #' Read a xgboost model text dump.
#' Only works for boosted tree model (not linear model). #' Plotting only works for boosted tree model (not linear model).
#' #'
#' @importFrom data.table data.table #' @importFrom data.table data.table
#' @importFrom data.table set #' @importFrom data.table set
@ -33,7 +33,7 @@
#' \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 finished with a leaf. For each leaf, only the \code{cover} is indicated. #' Each branch finishes with a leaf. For each leaf, only the \code{cover} is indicated.
#' It uses Mermaid JS library for that purpose. #' It uses Mermaid JS library for that purpose.
#' #'
#' @examples #' @examples
@ -106,19 +106,18 @@ xgb.plot.tree <- function(feature_names = NULL, filename_dump = NULL, n_first_tr
coverLeaf <- extract(leaf, "cover=\\d*\\.*\\d*") coverLeaf <- extract(leaf, "cover=\\d*\\.*\\d*")
dt <- data.table(ID = c(idBranch, idLeaf), Feature = c(featureBranch, featureLeaf), Split = c(splitBranch, splitLeaf), Yes = c(yesBranch, yesLeaf), No = c(noBranch, noLeaf), Missing = c(missingBranch, missingLeaf), Quality = c(qualityBranch, qualityLeaf), Cover = c(coverBranch, coverLeaf))[order(ID)][,Tree:=i] dt <- data.table(ID = c(idBranch, idLeaf), Feature = c(featureBranch, featureLeaf), Split = c(splitBranch, splitLeaf), Yes = c(yesBranch, yesLeaf), No = c(noBranch, noLeaf), Missing = c(missingBranch, missingLeaf), Quality = c(qualityBranch, qualityLeaf), Cover = c(coverBranch, coverLeaf))[order(ID)][,Tree:=i]
set(dt, i = which(dt[,Feature]!= "Leaf"), j = "YesFeature", value = merge(copy(dt)[,ID:=Yes][, .(ID)], dt[,.(ID, Feature, Quality, Cover)], by = "ID")[,paste(Feature, "<br/>Cover: ", Cover, sep = "")])
set(dt, i = which(dt[,Feature]!= "Leaf"), j = "NoFeature", value = merge(copy(dt)[,ID:=No][, .(ID)], dt[,.(ID, Feature, Quality, Cover)], by = "ID")[,paste(Feature, "<br/>Cover: ", Cover, sep = "")])
dt[Feature!="Leaf" ,yesPath:= paste(ID,"(", Feature, "<br/>Cover: ", Cover, "<br/>Gain: ", Quality, ")-->|< ", Split, "|", Yes, ">", YesFeature, "]", sep = "")]
dt[Feature!="Leaf" ,noPath:= paste(ID,"(", Feature, ")-->|>= ", Split, "|", No, ">", NoFeature, "]", sep = "")]
#missingPath <- paste(dtBranch[,ID], "-->|Missing|", dtBranch[,Missing], sep = "")
allTrees <- rbindlist(list(allTrees, dt), use.names = T, fill = F) allTrees <- rbindlist(list(allTrees, dt), use.names = T, fill = F)
} }
set(allTrees, i = which(allTrees[,Feature]!= "Leaf"), j = "YesFeature", value = merge(copy(allTrees)[,ID:=Yes][, .(ID)], allTrees[,.(ID, Feature, Quality, Cover)], by = "ID")[,paste(Feature, "<br/>Cover: ", Cover, sep = "")])
set(allTrees, i = which(allTrees[,Feature]!= "Leaf"), j = "NoFeature", value = merge(copy(allTrees)[,ID:=No][, .(ID)], allTrees[,.(ID, Feature, Quality, Cover)], by = "ID")[,paste(Feature, "<br/>Cover: ", Cover, sep = "")])
allTrees[Feature!="Leaf" ,yesPath:= paste(ID,"(", Feature, "<br/>Cover: ", Cover, "<br/>Gain: ", Quality, ")-->|< ", Split, "|", Yes, ">", YesFeature, "]", sep = "")]
allTrees[Feature!="Leaf" ,noPath:= paste(ID,"(", Feature, ")-->|>= ", Split, "|", No, ">", NoFeature, "]", sep = "")]
if(is.null(styles)){ if(is.null(styles)){
styles <- "classDef greenNode fill:#A2EB86, stroke:#04C4AB, stroke-width:2px;classDef redNode fill:#FFA070, stroke:#FF5E5E, stroke-width:2px" styles <- "classDef greenNode fill:#A2EB86, stroke:#04C4AB, stroke-width:2px;classDef redNode fill:#FFA070, stroke:#FF5E5E, stroke-width:2px"
} }

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

@ -21,9 +21,10 @@ A \code{data.table} of the features used in the model with their average gain (a
} }
\description{ \description{
Read a xgboost model text dump. Read a xgboost model text dump.
Only works for boosted tree model (not linear model).
} }
\details{ \details{
Plotting only works for boosted tree model (not linear model).
The content of each node is organised that way: The content of each node is organised that way:
\itemize{ \itemize{
@ -32,7 +33,7 @@ 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 finished with a leaf. For each leaf, only the \code{cover} is indicated. Each branch finishes with a leaf. For each leaf, only the \code{cover} is indicated.
It uses Mermaid JS library for that purpose. It uses Mermaid JS library for that purpose.
} }
\examples{ \examples{