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

Merge pull request #225 from chrissly31415/master

Browse Source 
Fixing parsing of model dump text file in R
This commit is contained in:
Tianqi Chen 2015-04-09 09:53:38 -07:00
commit 0ea28c35c4
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
R-package/R/xgb.model.dt.tree.R
View File

@ -95,7 +95,8 @@ xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model
addTreeId <- function(x, i) paste(i,x,sep = "-")
allTrees <- data.table()
anynumber_regex<-"[-+]?[0-9]*\\.?[0-9]+([eE][-+]?[0-9]+)?"
for(i in 1:n_round){
tree <- text[(position[i]+1):(position[i+1]-1)]
@ -115,7 +116,7 @@ xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model
featureBranch <- feature_names[featureBranch + 1]
}
featureLeaf <- rep("Leaf", length(leaf))
splitBranch <- str_extract(branch, "<\\d*\\.*\\d*\\]") %>% str_replace("<", "") %>% str_replace("\\]", "")
splitBranch <- str_extract(branch, paste0("<",anynumber_regex,"\\]")) %>% str_replace("<", "") %>% str_replace("\\]", "")
splitLeaf <- rep(NA, length(leaf))
yesBranch <- extract(branch, "yes=\\d*") %>% addTreeId(treeID)
yesLeaf <- rep(NA, length(leaf))
@ -123,8 +124,8 @@ xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model
noLeaf <- rep(NA, length(leaf))
missingBranch <- extract(branch, "missing=\\d+") %>% addTreeId(treeID)
missingLeaf <- rep(NA, length(leaf))
qualityBranch <- extract(branch, "gain=\\d*\\.*\\d*")
qualityLeaf <- extract(leaf, "leaf=\\-*\\d*\\.*\\d*")
qualityBranch <- extract(branch, paste0("gain=",anynumber_regex))
qualityLeaf <- extract(leaf, paste0("leaf=",anynumber_regex))
coverBranch <- extract(branch, "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:=treeID]