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

fix

Browse Source
This commit is contained in:
El Potaeto 2015-02-19 00:16:50 +01:00
parent d982f2746c
commit 815789bed6
1 changed files with 11 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
R-package/R/xgb.importance.R
View File

@ -95,28 +95,26 @@ xgb.importance <- function(feature_names = NULL, filename_dump = NULL, model = N
result <- treeDump(feature_names, text = text, keepDetail = !is.null(data)) result <- treeDump(feature_names, text = text, keepDetail = !is.null(data))
# Co-occurence computation # Co-occurence computation
if(!is.null(data) & !is.null(label) & nrow(result) > 0) { if(!is.null(data) & !is.null(label) & nrow(result) > 0) {
# Apply split
a <- data[, result[,Feature],drop=FALSE] < as.numeric(result[,Split])
# Take care of missing column # Take care of missing column
b <- data[, result[No == Missing,Feature],drop=FALSE] != 0 a <- data[, result[MissingNo == T,Feature], drop=FALSE] != 0
# Do nothing if missing should be included in Yes # Bind the two Matrix and reorder columns
c <- data[, result[No != Missing,Feature],drop=FALSE] c <- data[, result[MissingNo == F,Feature], drop=FALSE] %>% cBind(a,.) %>% .[,result[,Feature]]
# Bind the two previous Matrix and reorder columns rm(a)
d <- cBind(b,c) %>% .[,result[,Feature]] # Apply split
d <- data[, result[,Feature], drop=FALSE] < as.numeric(result[,Split])
apply(a & d, 2, . %>% target %>% sum) -> vec apply(c & d, 2, . %>% target %>% sum) -> vec
result <- result[, "RealCover":= as.numeric(vec), with = F][, "RealCover %" := RealCover / sum(label)][,`:=`(No = NULL, Missing = NULL)] result <- result[, "RealCover":= as.numeric(vec), with = F][, "RealCover %" := RealCover / sum(label)][,MissingNo:=NULL]
} }
} }
result result
} }
treeDump <- function(feature_names, text, keepDetail){ treeDump <- function(feature_names, text, keepDetail){
if(keepDetail) groupBy <- c("Feature", "Split", "No", "Missing") else groupBy <- "Feature" if(keepDetail) groupBy <- c("Feature", "Split", "MissingNo") else groupBy <- "Feature"
result <- xgb.model.dt.tree(feature_names = feature_names, text = text)[Feature!="Leaf",.(Gain = sum(Quality), Cover = sum(Cover), Frequence = .N), by = groupBy, with = T][,`:=`(Gain = Gain/sum(Gain), Cover = Cover/sum(Cover), Frequence = Frequence/sum(Frequence))][order(Gain, decreasing = T)] result <- xgb.model.dt.tree(feature_names = feature_names, text = text)[,"MissingNo":= Missing == No ][Feature!="Leaf",.(Gain = sum(Quality), Cover = sum(Cover), Frequence = .N), by = groupBy, with = T][,`:=`(Gain = Gain/sum(Gain), Cover = Cover/sum(Cover), Frequence = Frequence/sum(Frequence))][order(Gain, decreasing = T)]
result result
} }