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

[R-package] GPL2 dependency reduction and some fixes (#1401)

Browse Source 
* [R] do not remove zero coefficients from gblinear dump

* [R] switch from stringr to stringi

* fix #1399

* [R] separate ggplot backend, add base r graphics, cleanup, more plots, tests

* add missing include in amalgamation - fixes building R package in linux

* add forgotten file

* [R] fix DESCRIPTION

* [R] fix travis check issue and some cleanup
This commit is contained in:
Vadim Khotilovich
2016-07-27 02:05:04 -05:00
committed by Tong He
parent f6423056c0
commit d5c143367d
19 changed files with 548 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
R-package/R/xgb.model.dt.tree.R
View File

@@ -69,7 +69,7 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
text <- xgb.dump(model = model, with_stats = T)
}
position <- which(!is.na(str_match(text, "booster")))
position <- which(!is.na(stri_match_first_regex(text, "booster")))
add.tree.id <- function(x, i) paste(i, x, sep = "-")
@@ -82,16 +82,16 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
n_first_tree <- min(max(td$Tree), n_first_tree)
td <- td[Tree <= n_first_tree & !grepl('^booster', t)]
td[, Node := str_match(t, "(\\d+):")[,2] %>% as.numeric ]
td[, Node := stri_match_first_regex(t, "(\\d+):")[,2] %>% as.numeric ]
td[, ID := add.tree.id(Node, Tree)]
td[, isLeaf := !is.na(str_match(t, "leaf"))]
td[, isLeaf := !is.na(stri_match_first_regex(t, "leaf"))]
# parse branch lines
td[isLeaf==FALSE, c("Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover") := {
rx <- paste0("f(\\d+)<(", anynumber_regex, ")\\] yes=(\\d+),no=(\\d+),missing=(\\d+),",
"gain=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
# skip some indices with spurious capture groups from anynumber_regex
xtr <- str_match(t, rx)[, c(2,3,5,6,7,8,10)]
xtr <- stri_match_first_regex(t, rx)[, c(2,3,5,6,7,8,10)]
xtr[, 3:5] <- add.tree.id(xtr[, 3:5], Tree)
lapply(1:ncol(xtr), function(i) xtr[,i])
}]
@@ -102,7 +102,7 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
# parse leaf lines
td[isLeaf==TRUE, c("Feature", "Quality", "Cover") := {
rx <- paste0("leaf=(", anynumber_regex, "),cover=(", anynumber_regex, ")")
xtr <- str_match(t, rx)[, c(2,4)]
xtr <- stri_match_first_regex(t, rx)[, c(2,4)]
c("Leaf", lapply(1:ncol(xtr), function(i) xtr[,i]))
}]