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

refactoring of validation to improve source code readability.

Browse Source
This commit is contained in:
El Potaeto 2014-12-28 11:18:26 +01:00
parent 151285300b
commit 2154a160a3
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
R-package/R/xgb.importance.R
View File

@ -41,14 +41,14 @@ treeDump <- function(feature_names, text){
m <- regexec("\\[f.*\\]", line)
p <- regmatches(line, m)
if (length(p[[1]]) > 0) {
splits <- as.numeric(strsplit(sub("\\]", "", sub("\\[f", "", p[[1]])), "<")[[1]])
splits <- sub("\\]", "", sub("\\[f", "", p[[1]])) %>% strsplit("<")[[1]] %>% as.numeric
result <- c(result, feature_names[splits[1]+ 1])
}
}
#1. Reduce, 2. %, 3. remove temp col, 4. reorder - bigger top
#1. Reduce, 2. %, 3. reorder - bigger top, 4. remove temp col
data.table(Feature = result)[,.N, by = Feature][, Weight:= N /sum(N)][order(-rank(Weight))][,-2,with=F]
}
linearDump <- function(feature_names, text){
which(text == "weight:") %>% {a=.+1;text[a:length(text)]} %>% as.numeric %>% data.table(Feature = feature_names, Weight = .)
which(text == "weight:") %>% {a=.+1; text[a:length(text)]} %>% as.numeric %>% data.table(Feature = feature_names, Weight = .)
}