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

fix namespace and desc

Browse Source
This commit is contained in:
unknown 2015-07-24 11:58:02 -07:00
parent 141f9ebf4b
commit 198c5bb55e
5 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
R-package/.Rbuildignore
View File

@ -3,3 +3,4 @@
\.dll$ \.dll$
^.*\.Rproj$ ^.*\.Rproj$
^\.Rproj\.user$ ^\.Rproj\.user$
README.md

2
R-package/DESCRIPTION
View File

@ -5,7 +5,7 @@ Version: 0.4-0
Date: 2015-05-11 Date: 2015-05-11
Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>, Michael Benesty <michael@benesty.fr> Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>, Michael Benesty <michael@benesty.fr>
Maintainer: Tong He <hetong007@gmail.com> Maintainer: Tong He <hetong007@gmail.com>
Description: Xgboost is short for eXtreme Gradient Boosting, which is an Description: eXtreme Gradient Boosting, which is an
efficient and scalable implementation of gradient boosting framework. efficient and scalable implementation of gradient boosting framework.
This package is an R wrapper of xgboost. The package includes efficient This package is an R wrapper of xgboost. The package includes efficient
linear model solver and tree learning algorithms. The package can automatically linear model solver and tree learning algorithms. The package can automatically

4
R-package/R/utils.R
View File

@ -288,7 +288,7 @@ xgb.cv.aggcv <- function(res, showsd = TRUE) {
} }
ret <- paste(ret, sprintf("%f", mean(stats)), sep="") ret <- paste(ret, sprintf("%f", mean(stats)), sep="")
if (showsd) { if (showsd) {
ret <- paste(ret, sprintf("+%f", sd(stats)), sep="") ret <- paste(ret, sprintf("+%f", stats::sd(stats)), sep="")
} }
} }
return (ret) return (ret)
@ -313,7 +313,7 @@ xgb.createFolds <- function(y, k = 10)
if(cuts < 2) cuts <- 2 if(cuts < 2) cuts <- 2
if(cuts > 5) cuts <- 5 if(cuts > 5) cuts <- 5
y <- cut(y, y <- cut(y,
unique(quantile(y, probs = seq(0, 1, length = cuts))), unique(stats::quantile(y, probs = seq(0, 1, length = cuts))),
include.lowest = TRUE) include.lowest = TRUE)
} }

2
R-package/R/xgb.cv.R
View File

@ -240,7 +240,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
else colnames <- colnamesMean else colnames <- colnamesMean
type <- rep(x = "numeric", times = length(colnames)) type <- rep(x = "numeric", times = length(colnames))
dt <- read.table(text = "", colClasses = type, col.names = colnames) %>% as.data.table dt <- utils::read.table(text = "", colClasses = type, col.names = colnames) %>% as.data.table
split <- str_split(string = history, pattern = "\t") split <- str_split(string = history, pattern = "\t")
for(line in split) dt <- line[2:length(line)] %>% str_extract_all(pattern = "\\d*\\.+\\d*") %>% unlist %>% as.numeric %>% as.list %>% {rbindlist(list(dt, .), use.names = F, fill = F)} for(line in split) dt <- line[2:length(line)] %>% str_extract_all(pattern = "\\d*\\.+\\d*") %>% unlist %>% as.numeric %>% as.list %>% {rbindlist(list(dt, .), use.names = F, fill = F)}

4
R-package/R/xgb.plot.importance.R
View File

@ -33,7 +33,7 @@ xgb.plot.importance <- function(importance_matrix = NULL, numberOfClusters = c(1
if (!"data.table" %in% class(importance_matrix)) { if (!"data.table" %in% class(importance_matrix)) {
stop("importance_matrix: Should be a data.table.") stop("importance_matrix: Should be a data.table.")
} }
if (!require(ggplot2, quietly = TRUE)) { if (!requireNamespace(ggplot2, quietly = TRUE)) {
stop("ggplot2 package is required for plotting the importance", call. = FALSE) stop("ggplot2 package is required for plotting the importance", call. = FALSE)
} }
if (!requireNamespace("Ckmeans.1d.dp", quietly = TRUE)) { if (!requireNamespace("Ckmeans.1d.dp", quietly = TRUE)) {
@ -46,7 +46,7 @@ xgb.plot.importance <- function(importance_matrix = NULL, numberOfClusters = c(1
clusters <- suppressWarnings(Ckmeans.1d.dp::Ckmeans.1d.dp(importance_matrix[,Gain], numberOfClusters)) clusters <- suppressWarnings(Ckmeans.1d.dp::Ckmeans.1d.dp(importance_matrix[,Gain], numberOfClusters))
importance_matrix[,"Cluster":=clusters$cluster %>% as.character] importance_matrix[,"Cluster":=clusters$cluster %>% as.character]
plot <- ggplot(importance_matrix, aes(x=reorder(Feature, Gain), y = Gain, width= 0.05), environment = environment())+ geom_bar(aes(fill=Cluster), stat="identity", position="identity") + coord_flip() + xlab("Features") + ylab("Gain") + ggtitle("Feature importance") + theme(plot.title = element_text(lineheight=.9, face="bold"), panel.grid.major.y = element_blank() ) plot <- ggplot(importance_matrix, aes(x=stats::reorder(Feature, Gain), y = Gain, width= 0.05), environment = environment())+ geom_bar(aes(fill=Cluster), stat="identity", position="identity") + coord_flip() + xlab("Features") + ylab("Gain") + ggtitle("Feature importance") + theme(plot.title = element_text(lineheight=.9, face="bold"), panel.grid.major.y = element_blank() )
return(plot) return(plot)
} }