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

Merge pull request #50 from tqchen/master

Browse Source 
pull master into unity
This commit is contained in:
Tianqi Chen 2014-08-27 19:19:48 -07:00
commit f9541efa01
28 changed files with 667 additions and 8763 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored
View File

@ -36,3 +36,7 @@ Debug
*test*
.Rhistory
*.dll
*i386
*x64
*dump
*save

4
R-package/DESCRIPTION
View File

@ -3,8 +3,8 @@ Type: Package
Title: R wrapper of xgboost
Version: 0.3-0
Date: 2014-08-23
Author: Tianqi Chen
Maintainer: Tianqi Chen <tianqi.tchen@gmail.com>
Author: Tianqi Chen, Tong He
Maintainer: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>
Description: xgboost
License: See LICENSE file
URL: https://github.com/tqchen/xgboost

19
R-package/NAMESPACE
View File

@ -2,17 +2,10 @@ importClassesFrom("Matrix", dgCMatrix, dgeMatrix)
export(xgboost)
export(xgb.DMatrix)
export(xgb.getinfo)
export(xgb.setinfo)
# exportClasses(xgb.Boost)
exportMethods(predict)
# export(xgb.Booster)
# export(xgb.train)
# export(xgb.save)
# export(xgb.predict)
# export(xgb.dump)
exportMethods(getinfo)
export(xgb.train)
export(xgb.save)
export(xgb.load)
export(xgb.dump)
export(xgb.DMatrix.save)

21
R-package/R/getinfo.xgb.DMatrix.R Normal file
View File

@ -0,0 +1,21 @@
setClass('xgb.DMatrix')
getinfo <- function(object, ...){
UseMethod("getinfo")
}
setMethod("getinfo", signature = "xgb.DMatrix",
definition = function(object, name) {
if (typeof(name) != "character") {
stop("xgb.getinfo: name must be character")
}
if (class(object) != "xgb.DMatrix") {
stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix")
}
if (name != "label" && name != "weight" && name != "base_margin") {
stop(paste("xgb.getinfo: unknown info name", name))
}
ret <- .Call("XGDMatrixGetInfo_R", object, name, PACKAGE = "xgboost")
return(ret)
})

13
R-package/R/predict.xgb.Booster.R Normal file
View File

@ -0,0 +1,13 @@
#' @export
setClass("xgb.Booster")
#' @export
setMethod("predict", signature = "xgb.Booster",
definition = function(object, newdata, outputmargin = FALSE) {
if (class(newdata) != "xgb.DMatrix") {
newdata <- xgb.DMatrix(newdata)
}
ret <- .Call("XGBoosterPredict_R", object, newdata, as.integer(outputmargin), PACKAGE = "xgboost")
return(ret)
})

16
R-package/R/predict.xgboost.R
View File

@ -1,16 +0,0 @@
#' @export
setClass("xgb.Booster")
#' @export
setMethod("predict",
signature = "xgb.Booster",
definition = function(object, newdata, outputmargin = FALSE)
{
if (class(newdata) != "xgb.DMatrix") {
newdata = xgb.DMatrix(newdata)
}
ret <- .Call("XGBoosterPredict_R", object, newdata,
as.integer(outputmargin), PACKAGE="xgboost")
return(ret)
})

135
R-package/R/utils.R Normal file
View File

@ -0,0 +1,135 @@
# depends on matrix
.onLoad <- function(libname, pkgname) {
library.dynam("xgboost", pkgname, libname)
}
.onUnload <- function(libpath) {
library.dynam.unload("xgboost", libpath)
}
# set information into dmatrix, this mutate dmatrix
xgb.setinfo <- function(dmat, name, info) {
if (class(dmat) != "xgb.DMatrix") {
stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix")
}
if (name == "label") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
PACKAGE = "xgboost")
return(TRUE)
}
if (name == "weight") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
PACKAGE = "xgboost")
return(TRUE)
}
if (name == "base_margin") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
PACKAGE = "xgboost")
return(TRUE)
}
if (name == "group") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.integer(info),
PACKAGE = "xgboost")
return(TRUE)
}
stop(paste("xgb.setinfo: unknown info name", name))
return(FALSE)
}
# construct a Booster from cachelist
xgb.Booster <- function(params = list(), cachelist = list(), modelfile = NULL) {
if (typeof(cachelist) != "list") {
stop("xgb.Booster: only accepts list of DMatrix as cachelist")
}
for (dm in cachelist) {
if (class(dm) != "xgb.DMatrix") {
stop("xgb.Booster: only accepts list of DMatrix as cachelist")
}
}
handle <- .Call("XGBoosterCreate_R", cachelist, PACKAGE = "xgboost")
.Call("XGBoosterSetParam_R", handle, "seed", "0", PACKAGE = "xgboost")
if (length(params) != 0) {
for (i in 1:length(params)) {
p <- params[i]
.Call("XGBoosterSetParam_R", handle, names(p), as.character(p),
PACKAGE = "xgboost")
}
}
if (!is.null(modelfile)) {
if (typeof(modelfile) != "character") {
stop("xgb.Booster: modelfile must be character")
}
.Call("XGBoosterLoadModel_R", handle, modelfile, PACKAGE = "xgboost")
}
return(structure(handle, class = "xgb.Booster"))
}
# predict, depreciated
xgb.predict <- function(booster, dmat, outputmargin = FALSE) {
if (class(booster) != "xgb.Booster") {
stop("xgb.predict: first argument must be type xgb.Booster")
}
if (class(dmat) != "xgb.DMatrix") {
stop("xgb.predict: second argument must be type xgb.DMatrix")
}
ret <- .Call("XGBoosterPredict_R", booster, dmat, as.integer(outputmargin),
PACKAGE = "xgboost")
return(ret)
}
## ----the following are low level iteratively function, not needed if
## you do not want to use them ---------------------------------------
# iteratively update booster with dtrain
xgb.iter.update <- function(booster, dtrain, iter) {
if (class(booster) != "xgb.Booster") {
stop("xgb.iter.update: first argument must be type xgb.Booster")
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.iter.update: second argument must be type xgb.DMatrix")
}
.Call("XGBoosterUpdateOneIter_R", booster, as.integer(iter), dtrain,
PACKAGE = "xgboost")
return(TRUE)
}
# iteratively update booster with customized statistics
xgb.iter.boost <- function(booster, dtrain, gpair) {
if (class(booster) != "xgb.Booster") {
stop("xgb.iter.update: first argument must be type xgb.Booster")
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.iter.update: second argument must be type xgb.DMatrix")
}
.Call("XGBoosterBoostOneIter_R", booster, dtrain, gpair$grad, gpair$hess,
PACKAGE = "xgboost")
return(TRUE)
}
# iteratively evaluate one iteration
xgb.iter.eval <- function(booster, watchlist, iter) {
if (class(booster) != "xgb.Booster") {
stop("xgb.eval: first argument must be type xgb.Booster")
}
if (typeof(watchlist) != "list") {
stop("xgb.eval: only accepts list of DMatrix as watchlist")
}
for (w in watchlist) {
if (class(w) != "xgb.DMatrix") {
stop("xgb.eval: watch list can only contain xgb.DMatrix")
}
}
evnames <- list()
if (length(watchlist) != 0) {
for (i in 1:length(watchlist)) {
w <- watchlist[i]
if (length(names(w)) == 0) {
stop("xgb.eval: name tag must be presented for every elements in watchlist")
}
evnames <- append(evnames, names(w))
}
}
msg <- .Call("XGBoosterEvalOneIter_R", booster, as.integer(iter), watchlist,
evnames, PACKAGE = "xgboost")
return(msg)
}

26
R-package/R/xgb.DMatrix.R Normal file
View File

@ -0,0 +1,26 @@
# constructing DMatrix
xgb.DMatrix <- function(data, info = list(), missing = 0, ...) {
if (typeof(data) == "character") {
handle <- .Call("XGDMatrixCreateFromFile_R", data, as.integer(FALSE),
PACKAGE = "xgboost")
} else if (is.matrix(data)) {
handle <- .Call("XGDMatrixCreateFromMat_R", data, missing,
PACKAGE = "xgboost")
} else if (class(data) == "dgCMatrix") {
handle <- .Call("XGDMatrixCreateFromCSC_R", data@p, data@i, data@x,
PACKAGE = "xgboost")
} else {
stop(paste("xgb.DMatrix: does not support to construct from ",
typeof(data)))
}
dmat <- structure(handle, class = "xgb.DMatrix")
info <- append(info, list(...))
if (length(info) == 0)
return(dmat)
for (i in 1:length(info)) {
p <- info[i]
xgb.setinfo(dmat, names(p), p[[1]])
}
return(dmat)
}

13
R-package/R/xgb.DMatrix.save.R Normal file
View File

@ -0,0 +1,13 @@
# save model or DMatrix to file
xgb.DMatrix.save <- function(handle, fname) {
if (typeof(fname) != "character") {
stop("xgb.save: fname must be character")
}
if (class(handle) == "xgb.DMatrix") {
.Call("XGDMatrixSaveBinary_R", handle, fname, as.integer(FALSE),
PACKAGE = "xgboost")
return(TRUE)
}
stop("xgb.save: the input must be either xgb.DMatrix or xgb.Booster")
return(FALSE)
}

222
R-package/R/xgb.Utils.R
View File

@ -1,222 +0,0 @@
# depends on matrix
.onLoad <- function(libname, pkgname) {
library.dynam("xgboost", pkgname, libname);
}
.onUnload <- function(libpath) {
library.dynam.unload("xgboost", libpath);
}
# constructing DMatrix
xgb.DMatrix <- function(data, info=list(), missing=0.0) {
if (typeof(data) == "character") {
handle <- .Call("XGDMatrixCreateFromFile_R", data, as.integer(FALSE), PACKAGE="xgboost")
} else if(is.matrix(data)) {
handle <- .Call("XGDMatrixCreateFromMat_R", data, missing, PACKAGE="xgboost")
} else if(class(data) == "dgCMatrix") {
handle <- .Call("XGDMatrixCreateFromCSC_R", data@p, data@i, data@x, PACKAGE="xgboost")
} else {
stop(paste("xgb.DMatrix: does not support to construct from ", typeof(data)))
}
dmat <- structure(handle, class="xgb.DMatrix")
if (length(info) != 0) {
for (i in 1:length(info)) {
p <- info[i]
xgb.setinfo(dmat, names(p), p[[1]])
}
}
return(dmat)
}
# get information from dmatrix
xgb.getinfo <- function(dmat, name) {
if (typeof(name) != "character") {
stop("xgb.getinfo: name must be character")
}
if (class(dmat) != "xgb.DMatrix") {
stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix");
}
if (name != "label" &&
name != "weight" &&
name != "base_margin" ) {
stop(paste("xgb.getinfo: unknown info name", name))
}
ret <- .Call("XGDMatrixGetInfo_R", dmat, name, PACKAGE="xgboost")
return(ret)
}
# set information into dmatrix, this mutate dmatrix
xgb.setinfo <- function(dmat, name, info) {
if (class(dmat) != "xgb.DMatrix") {
stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix");
}
if (name == "label") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), PACKAGE="xgboost")
return(TRUE)
}
if (name == "weight") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), PACKAGE="xgboost")
return(TRUE)
}
if (name == "base_margin") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), PACKAGE="xgboost")
return(TRUE)
}
if (name == "group") {
.Call("XGDMatrixSetInfo_R", dmat, name, as.integer(info), PACKAGE="xgboost")
return(TRUE)
}
stop(pase("xgb.setinfo: unknown info name", name))
return(FALSE)
}
# construct a Booster from cachelist
xgb.Booster <- function(params = list(), cachelist = list(), modelfile = NULL) {
if (typeof(cachelist) != "list") {
stop("xgb.Booster: only accepts list of DMatrix as cachelist")
}
for (dm in cachelist) {
if (class(dm) != "xgb.DMatrix") {
stop("xgb.Booster: only accepts list of DMatrix as cachelist")
}
}
handle <- .Call("XGBoosterCreate_R", cachelist, PACKAGE="xgboost")
.Call("XGBoosterSetParam_R", handle, "seed", "0", PACKAGE="xgboost")
if (length(params) != 0) {
for (i in 1:length(params)) {
p <- params[i]
.Call("XGBoosterSetParam_R", handle, names(p), as.character(p), PACKAGE="xgboost")
}
}
if (!is.null(modelfile)) {
if (typeof(modelfile) != "character"){
stop("xgb.Booster: modelfile must be character");
}
.Call("XGBoosterLoadModel_R", handle, modelfile, PACKAGE="xgboost")
}
return(structure(handle, class="xgb.Booster"))
}
# train a model using given parameters
xgb.train <- function(params, dtrain, nrounds=10, watchlist=list(), obj=NULL, feval=NULL) {
if (typeof(params) != "list") {
stop("xgb.train: first argument params must be list");
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.train: second argument dtrain must be xgb.DMatrix");
}
bst <- xgb.Booster(params, append(watchlist,dtrain))
for (i in 1:nrounds) {
if (is.null(obj)) {
succ <- xgb.iter.update(bst, dtrain, i-1)
} else {
pred <- xgb.predict(bst, dtrain)
gpair <- obj(pred, dtrain)
succ <- xgb.iter.boost(bst, dtrain, gpair)
}
if (length(watchlist) != 0) {
if (is.null(feval)) {
msg <- xgb.iter.eval(bst, watchlist, i-1)
cat(msg); cat("\n")
} else {
cat("["); cat(i); cat("]");
for (j in 1:length(watchlist)) {
w <- watchlist[j]
if (length(names(w)) == 0) {
stop("xgb.eval: name tag must be presented for every elements in watchlist")
}
ret <- feval(xgb.predict(bst, w[[1]]), w[[1]])
cat("\t"); cat(names(w)); cat("-"); cat(ret$metric);
cat(":"); cat(ret$value)
}
cat("\n")
}
}
}
return(bst)
}
# save model or DMatrix to file
xgb.save <- function(handle, fname) {
if (typeof(fname) != "character") {
stop("xgb.save: fname must be character")
}
if (class(handle) == "xgb.Booster") {
.Call("XGBoosterSaveModel_R", handle, fname, PACKAGE="xgboost")
return(TRUE)
}
if (class(handle) == "xgb.DMatrix") {
.Call("XGDMatrixSaveBinary_R", handle, fname, as.integer(FALSE), PACKAGE="xgboost")
return(TRUE)
}
stop("xgb.save: the input must be either xgb.DMatrix or xgb.Booster")
return(FALSE)
}
# predict
xgb.predict <- function(booster, dmat, outputmargin = FALSE) {
if (class(booster) != "xgb.Booster") {
stop("xgb.predict: first argument must be type xgb.Booster")
}
if (class(dmat) != "xgb.DMatrix") {
stop("xgb.predict: second argument must be type xgb.DMatrix")
}
ret <- .Call("XGBoosterPredict_R", booster, dmat, as.integer(outputmargin), PACKAGE="xgboost")
return(ret)
}
# dump model
xgb.dump <- function(booster, fname, fmap = "") {
if (class(booster) != "xgb.Booster") {
stop("xgb.dump: first argument must be type xgb.Booster")
}
if (typeof(fname) != "character"){
stop("xgb.dump: second argument must be type character")
}
.Call("XGBoosterDumpModel_R", booster, fname, fmap, PACKAGE="xgboost")
return(TRUE)
}
##--------------------------------------
# the following are low level iteratively function, not needed
# if you do not want to use them
#---------------------------------------
# iteratively update booster with dtrain
xgb.iter.update <- function(booster, dtrain, iter) {
if (class(booster) != "xgb.Booster") {
stop("xgb.iter.update: first argument must be type xgb.Booster")
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.iter.update: second argument must be type xgb.DMatrix")
}
.Call("XGBoosterUpdateOneIter_R", booster, as.integer(iter), dtrain, PACKAGE="xgboost")
return(TRUE)
}
# iteratively update booster with customized statistics
xgb.iter.boost <- function(booster, dtrain, gpair) {
if (class(booster) != "xgb.Booster") {
stop("xgb.iter.update: first argument must be type xgb.Booster")
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.iter.update: second argument must be type xgb.DMatrix")
}
.Call("XGBoosterBoostOneIter_R", booster, dtrain, gpair$grad, gpair$hess, PACKAGE="xgboost")
return(TRUE)
}
# iteratively evaluate one iteration
xgb.iter.eval <- function(booster, watchlist, iter) {
if (class(booster) != "xgb.Booster") {
stop("xgb.eval: first argument must be type xgb.Booster")
}
if (typeof(watchlist) != "list") {
stop("xgb.eval: only accepts list of DMatrix as watchlist")
}
for (w in watchlist) {
if (class(w) != "xgb.DMatrix") {
stop("xgb.eval: watch list can only contain xgb.DMatrix")
}
}
evnames <- list()
if (length(watchlist) != 0) {
for (i in 1:length(watchlist)) {
w <- watchlist[i]
if (length(names(w)) == 0) {
stop("xgb.eval: name tag must be presented for every elements in watchlist")
}
evnames <- append(evnames, names(w))
}
}
msg <- .Call("XGBoosterEvalOneIter_R", booster, as.integer(iter), watchlist, evnames, PACKAGE="xgboost")
return(msg)
}

11
R-package/R/xgb.dump.R Normal file
View File

@ -0,0 +1,11 @@
# dump model
xgb.dump <- function(booster, fname, fmap = "") {
if (class(booster) != "xgb.Booster") {
stop("xgb.dump: first argument must be type xgb.Booster")
}
if (typeof(fname) != "character") {
stop("xgb.dump: second argument must be type character")
}
.Call("XGBoosterDumpModel_R", booster, fname, fmap, PACKAGE = "xgboost")
return(TRUE)
}

5
R-package/R/xgb.load.R Normal file
View File

@ -0,0 +1,5 @@
xgb.load <- function(modelfile) {
if (is.null(modelfile))
stop("xgb.load: modelfile cannot be NULL")
xgb.Booster(modelfile = modelfile)
}

12
R-package/R/xgb.save.R Normal file
View File

@ -0,0 +1,12 @@
# save model or DMatrix to file
xgb.save <- function(handle, fname) {
if (typeof(fname) != "character") {
stop("xgb.save: fname must be character")
}
if (class(handle) == "xgb.Booster") {
.Call("XGBoosterSaveModel_R", handle, fname, PACKAGE = "xgboost")
return(TRUE)
}
stop("xgb.save: the input must be either xgb.DMatrix or xgb.Booster")
return(FALSE)
}

47
R-package/R/xgb.train.R Normal file
View File

@ -0,0 +1,47 @@
# train a model using given parameters
xgb.train <- function(params=list(), dtrain, nrounds = 10, watchlist = list(),
obj = NULL, feval = NULL, ...) {
if (typeof(params) != "list") {
stop("xgb.train: first argument params must be list")
}
if (class(dtrain) != "xgb.DMatrix") {
stop("xgb.train: second argument dtrain must be xgb.DMatrix")
}
params = append(params, list(...))
bst <- xgb.Booster(params, append(watchlist, dtrain))
for (i in 1:nrounds) {
if (is.null(obj)) {
succ <- xgb.iter.update(bst, dtrain, i - 1)
} else {
pred <- xgb.predict(bst, dtrain)
gpair <- obj(pred, dtrain)
succ <- xgb.iter.boost(bst, dtrain, gpair)
}
if (length(watchlist) != 0) {
if (is.null(feval)) {
msg <- xgb.iter.eval(bst, watchlist, i - 1)
cat(msg)
cat("\n")
} else {
cat("[")
cat(i)
cat("]")
for (j in 1:length(watchlist)) {
w <- watchlist[j]
if (length(names(w)) == 0) {
stop("xgb.eval: name tag must be presented for every elements in watchlist")
}
ret <- feval(xgb.predict(bst, w[[1]]), w[[1]])
cat("\t")
cat(names(w))
cat("-")
cat(ret$metric)
cat(":")
cat(ret$value)
}
cat("\n")
}
}
}
return(bst)
}

45
R-package/R/xgboost.R
View File

@ -1,24 +1,33 @@
# Main function for xgboost-package
xgboost = function(x=NULL,y=NULL,file=NULL,nrounds=10,params,watchlist=list(),
obj=NULL, feval=NULL, margin=NULL)
{
if (is.null(x) && is.null(y))
{
if (is.null(file))
stop('xgboost need input data, either R objects or local files.')
dtrain = xgb.DMatrix(file)
xgboost <- function(data = NULL, label = NULL, params = list(), nrounds = 10,
verbose = 1, ...) {
inClass <- class(data)
if (inClass == "dgCMatrix" || inClass == "matrix") {
if (is.null(label))
stop("xgboost: need label when data is a matrix")
dtrain <- xgb.DMatrix(data, label = label)
} else {
if (!is.null(label))
warning("xgboost: label will be ignored.")
if (inClass == "character")
dtrain <- xgb.DMatrix(data) else if (inClass == "xgb.DMatrix")
dtrain <- data else stop("xgboost: Invalid input of data")
}
else
dtrain = xgb.DMatrix(x, info=list(label=y))
if (!is.null(margin))
{
succ <- xgb.setinfo(dtrain, "base_margin", margin)
if (!succ)
warning('Attemp to use margin failed.')
if (verbose > 1) {
silent <- 0
} else {
silent <- 1
}
bst <- xgb.train(params, dtrain, nrounds, watchlist, obj, feval)
params <- append(params, list(silent = silent))
params <- append(params, list(...))
if (verbose > 0)
watchlist <- list(train = dtrain) else watchlist <- list()
bst <- xgb.train(params, dtrain, nrounds, watchlist)
return(bst)
}

4
R-package/README.md
View File

@ -1,10 +1,10 @@
This is subfolder for experimental version of R package.
Not yet ready.
Installation:
```r
require(devtools)
install_github('xgboost','tqchen',subdir='R-package')
```
Please visit [demo](https://github.com/tqchen/xgboost/blob/master/R-package/demo/demo.R) for more details.

151
R-package/demo/demo.R Normal file
View File

@ -0,0 +1,151 @@
require(xgboost)
require(methods)
# helper function to read libsvm format this is very badly written, load in dense, and convert to sparse
# use this only for demo purpose adopted from
# https://github.com/zygmuntz/r-libsvm-format-read-write/blob/master/f_read.libsvm.r
read.libsvm <- function(fname, maxcol) {
content <- readLines(fname)
nline <- length(content)
label <- numeric(nline)
mat <- matrix(0, nline, maxcol + 1)
for (i in 1:nline) {
arr <- as.vector(strsplit(content[i], " ")[[1]])
label[i] <- as.numeric(arr[[1]])
for (j in 2:length(arr)) {
kv <- strsplit(arr[j], ":")[[1]]
# to avoid 0 index
findex <- as.integer(kv[1]) + 1
fvalue <- as.numeric(kv[2])
mat[i, findex] <- fvalue
}
}
mat <- as(mat, "sparseMatrix")
return(list(label = label, data = mat))
}
############################ Test xgb.DMatrix with local file, sparse matrix and dense matrix in R.
# Directly read in local file
dtrain <- xgb.DMatrix("agaricus.txt.train")
class(dtrain)
# read file in R
csc <- read.libsvm("agaricus.txt.train", 126)
y <- csc$label
x <- csc$data
# x as Sparse Matrix
class(x)
dtrain <- xgb.DMatrix(x, label = y)
# x as dense matrix
dense.x <- as.matrix(x)
dtrain <- xgb.DMatrix(dense.x, label = y)
############################ Test xgboost with local file, sparse matrix and dense matrix in R.
# Test with DMatrix object
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
objective = "binary:logistic")
# Verbose = 0,1,2
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
objective = "binary:logistic", verbose = 0)
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
objective = "binary:logistic", verbose = 1)
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
objective = "binary:logistic", verbose = 2)
# Test with local file
bst <- xgboost(data = "agaricus.txt.train", max_depth = 2, eta = 1,
objective = "binary:logistic")
# Test with Sparse Matrix
bst <- xgboost(data = x, label = y, max_depth = 2, eta = 1,
objective = "binary:logistic")
# Test with dense Matrix
bst <- xgboost(data = dense.x, label = y, max_depth = 2, eta = 1,
objective = "binary:logistic")
############################ Test predict
# Prediction with DMatrix object
dtest <- xgb.DMatrix("agaricus.txt.test")
pred <- predict(bst, dtest)
# Prediction with local test file
pred <- predict(bst, "agaricus.txt.test")
# Prediction with Sparse Matrix
csc <- read.libsvm("agaricus.txt.test", 126)
test.y <- csc$label
test.x <- csc$data
pred <- predict(bst, test.x)
# Extrac label with getinfo
labels <- getinfo(dtest, "label")
err <- as.numeric(sum(as.integer(pred > 0.5) != labels))/length(labels)
print(paste("error=", err))
############################ Save and load model to hard disk
# save model to binary local file
xgb.save(bst, "model.save")
# load binary model to R
bst <- xgb.load("model.save")
pred <- predict(bst, test.x)
# save model to text file
xgb.dump(bst, "model.dump")
# save a DMatrix object to hard disk
xgb.DMatrix.save(dtrain, "dtrain.save")
# load a DMatrix object to R
dtrain <- xgb.DMatrix("dtrain.save")
############################ More flexible training function xgb.train
param <- list(max_depth = 2, eta = 1, silent = 1, objective = "binary:logistic")
watchlist <- list(eval = dtest, train = dtrain)
# training xgboost model
bst <- xgb.train(param, dtrain, nround = 2, watchlist = watchlist)
############################ cutomsized loss function
param <- list(max_depth = 2, eta = 1, silent = 1)
# note: for customized objective function, we leave objective as default note: what we are getting is
# margin value in prediction you must know what you are doing
# user define objective function, given prediction, return gradient and second order gradient this is
# loglikelihood loss
logregobj <- function(preds, dtrain) {
labels <- getinfo(dtrain, "label")
preds <- 1/(1 + exp(-preds))
grad <- preds - labels
hess <- preds * (1 - preds)
return(list(grad = grad, hess = hess))
}
# user defined evaluation function, return a list(metric='metric-name', value='metric-value') NOTE: when
# you do customized loss function, the default prediction value is margin this may make buildin
# evalution metric not function properly for example, we are doing logistic loss, the prediction is
# score before logistic transformation the buildin evaluation error assumes input is after logistic
# transformation Take this in mind when you use the customization, and maybe you need write customized
# evaluation function
evalerror <- function(preds, dtrain) {
labels <- getinfo(dtrain, "label")
err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
return(list(metric = "error", value = err))
}
# training with customized objective, we can also do step by step training simply look at xgboost.py's
# implementation of train
bst <- xgb.train(param, dtrain, nround = 2, watchlist, logregobj, evalerror)

1611
R-package/inst/examples/agaricus.txt.test
View File

File diff suppressed because it is too large Load Diff

6513
R-package/inst/examples/agaricus.txt.train
View File

File diff suppressed because it is too large Load Diff

127
R-package/inst/examples/demo-old.R
View File

@ -1,127 +0,0 @@
# load xgboost library
require(xgboost)
require(methods)
# helper function to read libsvm format
# this is very badly written, load in dense, and convert to sparse
# use this only for demo purpose
# adopted from https://github.com/zygmuntz/r-libsvm-format-read-write/blob/master/f_read.libsvm.r
read.libsvm <- function(fname, maxcol) {
content <- readLines(fname)
nline <- length(content)
label <- numeric(nline)
mat <- matrix(0, nline, maxcol+1)
for (i in 1:nline) {
arr <- as.vector(strsplit(content[i], " ")[[1]])
label[i] <- as.numeric(arr[[1]])
for (j in 2:length(arr)) {
kv <- strsplit(arr[j], ":")[[1]]
# to avoid 0 index
findex <- as.integer(kv[1]) + 1
fvalue <- as.numeric(kv[2])
mat[i,findex] <- fvalue
}
}
mat <- as(mat, "sparseMatrix")
return(list(label=label, data=mat))
}
# test code here
dtrain <- xgb.DMatrix("agaricus.txt.train")
dtest <- xgb.DMatrix("agaricus.txt.test")
param = list("bst:max_depth"=2, "bst:eta"=1, "silent"=1, "objective"="binary:logistic")
watchlist <- list("eval"=dtest,"train"=dtrain)
# training xgboost model
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
# make prediction
preds <- xgb.predict(bst, dtest)
labels <- xgb.getinfo(dtest, "label")
err <- as.numeric(sum(as.integer(preds > 0.5) != labels)) / length(labels)
# print error rate
print(paste("error=",err))
# dump model
xgb.dump(bst, "dump.raw.txt")
# dump model with feature map
xgb.dump(bst, "dump.nice.txt", "featmap.txt")
# save dmatrix into binary buffer
succ <- xgb.save(dtest, "dtest.buffer")
# save model into file
succ <- xgb.save(bst, "xgb.model")
# load model and data in
bst2 <- xgb.Booster(modelfile="xgb.model")
dtest2 <- xgb.DMatrix("dtest.buffer")
preds2 <- xgb.predict(bst2, dtest2)
# assert they are the same
stopifnot(sum(abs(preds2-preds)) == 0)
###
# build dmatrix from sparseMatrix
###
print ('start running example of build DMatrix from R.sparseMatrix')
csc <- read.libsvm("agaricus.txt.train", 126)
label <- csc$label
data <- csc$data
dtrain <- xgb.DMatrix(data, info=list(label=label) )
watchlist <- list("eval"=dtest,"train"=dtrain)
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
###
# build dmatrix from dense matrix
###
print ('start running example of build DMatrix from R.Matrix')
mat = as.matrix(data)
dtrain <- xgb.DMatrix(mat, info=list(label=label) )
watchlist <- list("eval"=dtest,"train"=dtrain)
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
###
# advanced: cutomsized loss function
#
print("start running example to used cutomized objective function")
# note: for customized objective function, we leave objective as default
# note: what we are getting is margin value in prediction
# you must know what you are doing
param <- list("bst:max_depth" = 2, "bst:eta" = 1, "silent" =1)
# user define objective function, given prediction, return gradient and second order gradient
# this is loglikelihood loss
logregobj <- function(preds, dtrain) {
labels <- xgb.getinfo(dtrain, "label")
preds <- 1.0 / (1.0 + exp(-preds))
grad <- preds - labels
hess <- preds * (1.0-preds)
return(list(grad=grad, hess=hess))
}
# user defined evaluation function, return a list(metric="metric-name", value="metric-value")
# NOTE: when you do customized loss function, the default prediction value is margin
# this may make buildin evalution metric not function properly
# for example, we are doing logistic loss, the prediction is score before logistic transformation
# the buildin evaluation error assumes input is after logistic transformation
# Take this in mind when you use the customization, and maybe you need write customized evaluation function
evalerror <- function(preds, dtrain) {
labels <- xgb.getinfo(dtrain, "label")
err <- as.numeric(sum(labels != (preds > 0.0))) / length(labels)
return(list(metric="error", value=err))
}
# training with customized objective, we can also do step by step training
# simply look at xgboost.py"s implementation of train
bst <- xgb.train(param, dtrain, nround=2, watchlist, logregobj, evalerror)
###
# advanced: start from a initial base prediction
#
print ("start running example to start from a initial prediction")
# specify parameters via map, definition are same as c++ version
param = list("bst:max_depth"=2, "bst:eta"=1, "silent"=1, "objective"="binary:logistic")
# train xgboost for 1 round
bst <- xgb.train( param, dtrain, 1, watchlist )
# Note: we need the margin value instead of transformed prediction in set_base_margin
# do predict with output_margin=True, will always give you margin values before logistic transformation
ptrain <- xgb.predict(bst, dtrain, outputmargin=TRUE)
ptest <- xgb.predict(bst, dtest, outputmargin=TRUE)
succ <- xgb.setinfo(dtrain, "base_margin", ptrain)
succ <- xgb.setinfo(dtest, "base_margin", ptest)
print ("this is result of running from initial prediction")
bst <- xgb.train( param, dtrain, 1, watchlist )

102
R-package/inst/examples/demo.R
View File

@ -1,102 +0,0 @@
require(xgboost)
# helper function to read libsvm format
# this is very badly written, load in dense, and convert to sparse
# use this only for demo purpose
# adopted from https://github.com/zygmuntz/r-libsvm-format-read-write/blob/master/f_read.libsvm.r
read.libsvm = function(fname, maxcol) {
content = readLines(fname)
nline = length(content)
label = numeric(nline)
mat = matrix(0, nline, maxcol+1)
for (i in 1:nline) {
arr = as.vector(strsplit(content[i], " ")[[1]])
label[i] = as.numeric(arr[[1]])
for (j in 2:length(arr)) {
kv = strsplit(arr[j], ":")[[1]]
# to avoid 0 index
findex = as.integer(kv[1]) + 1
fvalue = as.numeric(kv[2])
mat[i,findex] = fvalue
}
}
mat = as(mat, "sparseMatrix")
return(list(label=label, data=mat))
}
# Parameter setting
dtrain <- xgb.DMatrix("agaricus.txt.train")
dtest <- xgb.DMatrix("agaricus.txt.test")
param = list("bst:max_depth"=2, "bst:eta"=1, "silent"=1, "objective"="binary:logistic")
watchlist = list("eval"=dtest,"train"=dtrain)
###########################
# Train from local file
###########################
# Training
bst = xgboost(file='agaricus.txt.train',params=param,watchlist=watchlist)
# Prediction
pred = predict(bst, 'agaricus.txt.test')
# Performance
labels = xgb.getinfo(dtest, "label")
err = as.numeric(sum(as.integer(pred > 0.5) != labels)) / length(labels)
print(paste("error=",err))
###########################
# Train from R object
###########################
csc = read.libsvm("agaricus.txt.train", 126)
y = csc$label
x = csc$data
# x as Sparse Matrix
class(x)
# Training
bst = xgboost(x,y,params=param,watchlist=watchlist)
# Prediction
pred = predict(bst, 'agaricus.txt.test')
# Performance
labels = xgb.getinfo(dtest, "label")
err = as.numeric(sum(as.integer(pred > 0.5) != labels)) / length(labels)
print(paste("error=",err))
# Training with dense matrix
x = as.matrix(x)
bst = xgboost(x,y,params=param,watchlist=watchlist)
###########################
# Train with customization
###########################
# user define objective function, given prediction, return gradient and second order gradient
# this is loglikelihood loss
logregobj = function(preds, dtrain) {
labels = xgb.getinfo(dtrain, "label")
preds = 1.0 / (1.0 + exp(-preds))
grad = preds - labels
hess = preds * (1.0-preds)
return(list(grad=grad, hess=hess))
}
# user defined evaluation function, return a list(metric="metric-name", value="metric-value")
# NOTE: when you do customized loss function, the default prediction value is margin
# this may make buildin evalution metric not function properly
# for example, we are doing logistic loss, the prediction is score before logistic transformation
# the buildin evaluation error assumes input is after logistic transformation
# Take this in mind when you use the customization, and maybe you need write customized evaluation function
evalerror = function(preds, dtrain) {
labels = xgb.getinfo(dtrain, "label")
err = as.numeric(sum(labels != (preds > 0.0))) / length(labels)
return(list(metric="error", value=err))
}
bst = xgboost(x,y,params=param,watchlist=watchlist,obj=logregobj, feval=evalerror)
############################
# Train with previous result
############################
bst = xgboost(x,y,params=param,watchlist=watchlist)
pred = predict(bst, 'agaricus.txt.train', outputmargin=TRUE)
bst2 = xgboost(x,y,params=param,watchlist=watchlist,margin=pred)

126
R-package/inst/examples/featmap.txt
View File

@ -1,126 +0,0 @@
0 cap-shape=bell i
1 cap-shape=conical i
2 cap-shape=convex i
3 cap-shape=flat i
4 cap-shape=knobbed i
5 cap-shape=sunken i
6 cap-surface=fibrous i
7 cap-surface=grooves i
8 cap-surface=scaly i
9 cap-surface=smooth i
10 cap-color=brown i
11 cap-color=buff i
12 cap-color=cinnamon i
13 cap-color=gray i
14 cap-color=green i
15 cap-color=pink i
16 cap-color=purple i
17 cap-color=red i
18 cap-color=white i
19 cap-color=yellow i
20 bruises?=bruises i
21 bruises?=no i
22 odor=almond i
23 odor=anise i
24 odor=creosote i
25 odor=fishy i
26 odor=foul i
27 odor=musty i
28 odor=none i
29 odor=pungent i
30 odor=spicy i
31 gill-attachment=attached i
32 gill-attachment=descending i
33 gill-attachment=free i
34 gill-attachment=notched i
35 gill-spacing=close i
36 gill-spacing=crowded i
37 gill-spacing=distant i
38 gill-size=broad i
39 gill-size=narrow i
40 gill-color=black i
41 gill-color=brown i
42 gill-color=buff i
43 gill-color=chocolate i
44 gill-color=gray i
45 gill-color=green i
46 gill-color=orange i
47 gill-color=pink i
48 gill-color=purple i
49 gill-color=red i
50 gill-color=white i
51 gill-color=yellow i
52 stalk-shape=enlarging i
53 stalk-shape=tapering i
54 stalk-root=bulbous i
55 stalk-root=club i
56 stalk-root=cup i
57 stalk-root=equal i
58 stalk-root=rhizomorphs i
59 stalk-root=rooted i
60 stalk-root=missing i
61 stalk-surface-above-ring=fibrous i
62 stalk-surface-above-ring=scaly i
63 stalk-surface-above-ring=silky i
64 stalk-surface-above-ring=smooth i
65 stalk-surface-below-ring=fibrous i
66 stalk-surface-below-ring=scaly i
67 stalk-surface-below-ring=silky i
68 stalk-surface-below-ring=smooth i
69 stalk-color-above-ring=brown i
70 stalk-color-above-ring=buff i
71 stalk-color-above-ring=cinnamon i
72 stalk-color-above-ring=gray i
73 stalk-color-above-ring=orange i
74 stalk-color-above-ring=pink i
75 stalk-color-above-ring=red i
76 stalk-color-above-ring=white i
77 stalk-color-above-ring=yellow i
78 stalk-color-below-ring=brown i
79 stalk-color-below-ring=buff i
80 stalk-color-below-ring=cinnamon i
81 stalk-color-below-ring=gray i
82 stalk-color-below-ring=orange i
83 stalk-color-below-ring=pink i
84 stalk-color-below-ring=red i
85 stalk-color-below-ring=white i
86 stalk-color-below-ring=yellow i
87 veil-type=partial i
88 veil-type=universal i
89 veil-color=brown i
90 veil-color=orange i
91 veil-color=white i
92 veil-color=yellow i
93 ring-number=none i
94 ring-number=one i
95 ring-number=two i
96 ring-type=cobwebby i
97 ring-type=evanescent i
98 ring-type=flaring i
99 ring-type=large i
100 ring-type=none i
101 ring-type=pendant i
102 ring-type=sheathing i
103 ring-type=zone i
104 spore-print-color=black i
105 spore-print-color=brown i
106 spore-print-color=buff i
107 spore-print-color=chocolate i
108 spore-print-color=green i
109 spore-print-color=orange i
110 spore-print-color=purple i
111 spore-print-color=white i
112 spore-print-color=yellow i
113 population=abundant i
114 population=clustered i
115 population=numerous i
116 population=scattered i
117 population=several i
118 population=solitary i
119 habitat=grasses i
120 habitat=leaves i
121 habitat=meadows i
122 habitat=paths i
123 habitat=urban i
124 habitat=waste i
125 habitat=woods i

6
windows/README.md
View File

@ -1 +1,5 @@
This is a test for minimal files needed for windows version
The solution has been created with Visual Studio Express 2013.
Make sure to compile the Release version, unless you need to debug the code
(and in the latter case modify the path in xgboost.py from release to test).
Note that you have two projects in one solution and they need to be compiled to use the standalone executable from the command line
or the python module respectively.

16
windows/xgboost.sln
View File

@ -1,8 +1,12 @@

Microsoft Visual Studio Solution File, Format Version 11.00
# Visual Studio 2010
Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio Express 2013 for Windows Desktop
VisualStudioVersion = 12.0.30723.0
MinimumVisualStudioVersion = 10.0.40219.1
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "xgboost", "xgboost\xgboost.vcxproj", "{1D6A56A5-5557-4D20-9D50-3DE4C30BE00C}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "xgboost_wrapper", "xgboost_wrapper\xgboost_wrapper.vcxproj", "{2E1AF937-28BB-4832-B916-309C9A0F6C4F}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Win32 = Debug|Win32
@ -19,6 +23,14 @@ Global
{1D6A56A5-5557-4D20-9D50-3DE4C30BE00C}.Release|Win32.Build.0 = Release|Win32
{1D6A56A5-5557-4D20-9D50-3DE4C30BE00C}.Release|x64.ActiveCfg = Release|x64
{1D6A56A5-5557-4D20-9D50-3DE4C30BE00C}.Release|x64.Build.0 = Release|x64
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Debug|Win32.ActiveCfg = Debug|Win32
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Debug|Win32.Build.0 = Debug|Win32
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Debug|x64.ActiveCfg = Debug|x64
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Debug|x64.Build.0 = Debug|x64
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Release|Win32.ActiveCfg = Release|Win32
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Release|Win32.Build.0 = Release|Win32
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Release|x64.ActiveCfg = Release|x64
{2E1AF937-28BB-4832-B916-309C9A0F6C4F}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE

6
windows/xgboost/xgboost.vcxproj
View File

@ -1,5 +1,5 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
@ -27,23 +27,27 @@
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v120</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v120</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<WholeProgramOptimization>true</WholeProgramOptimization>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v120</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<WholeProgramOptimization>true</WholeProgramOptimization>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v120</PlatformToolset>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">

154
windows/xgboost_wrapper/xgboost_wrapper.vcxproj Normal file
View File

@ -0,0 +1,154 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|Win32">
<Configuration>Release</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{2E1AF937-28BB-4832-B916-309C9A0F6C4F}</ProjectGuid>
<TargetFrameworkVersion>v4.5</TargetFrameworkVersion>
<Keyword>ManagedCProj</Keyword>
<RootNamespace>xgboost_wrapper</RootNamespace>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<PlatformToolset>v120</PlatformToolset>
<CLRSupport>true</CLRSupport>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<PlatformToolset>v120</PlatformToolset>
<CLRSupport>true</CLRSupport>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<PlatformToolset>v120</PlatformToolset>
<CLRSupport>true</CLRSupport>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<PlatformToolset>v120</PlatformToolset>
<CLRSupport>true</CLRSupport>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="PropertySheets">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="PropertySheets">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<LinkIncremental>true</LinkIncremental>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<LinkIncremental>true</LinkIncremental>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PrecompiledHeader>NotUsing</PrecompiledHeader>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalDependencies />
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PrecompiledHeader>NotUsing</PrecompiledHeader>
<OpenMPSupport>true</OpenMPSupport>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalDependencies>
</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PrecompiledHeader>Use</PrecompiledHeader>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalDependencies />
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<PrecompiledHeader>NotUsing</PrecompiledHeader>
<OpenMPSupport>true</OpenMPSupport>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalDependencies>
</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<Reference Include="System" />
<Reference Include="System.Data" />
<Reference Include="System.Xml" />
</ItemGroup>
<ItemGroup>
<ClInclude Include="..\..\src\io\io.h" />
<ClInclude Include="..\..\src\io\simple_dmatrix-inl.hpp" />
<ClInclude Include="..\..\wrapper\xgboost_wrapper.h" />
</ItemGroup>
<ItemGroup>
<ClCompile Include="..\..\src\io\io.cpp" />
<ClCompile Include="..\..\wrapper\xgboost_wrapper.cpp" />
</ItemGroup>
<ItemGroup>
<None Include="..\..\wrapper\xgboost.py" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
</ImportGroup>
</Project>

9
wrapper/xgboost.py
View File

@ -9,7 +9,10 @@ import numpy.ctypeslib
import scipy.sparse as scp
# set this line correctly
XGBOOST_PATH = os.path.dirname(__file__)+'/libxgboostwrapper.so'
if os.name == 'nt':
XGBOOST_PATH = os.path.dirname(__file__)+'/../windows/x64/Release/xgboost_wrapper.dll'
else:
XGBOOST_PATH = os.path.dirname(__file__)+'/../libxgboostwrapper.so'
# load in xgboost library
xglib = ctypes.cdll.LoadLibrary(XGBOOST_PATH)
@ -231,7 +234,7 @@ class Booster:
trees = self.get_dump(fmap)
fmap = {}
for tree in trees:
print tree
print (tree)
for l in tree.split('\n'):
arr = l.split('[')
if len(arr) == 1:
@ -263,7 +266,7 @@ def train(params, dtrain, num_boost_round = 10, evals = [], obj=None, feval=None
for i in range(num_boost_round):
bst.update( dtrain, i )
if len(evals) != 0:
sys.stderr.write(evaluate(bst, evals, i, feval)+'\n')
sys.stderr.write(evaluate(bst, evals, i, feval).decode()+'\n')
else:
# try customized objective function
for i in range(num_boost_round):

4
wrapper/xgboost_wrapper.h
View File

@ -7,7 +7,11 @@
* can be used to create wrapper of other languages
*/
#include <cstdio>
#ifdef _MSC_VER
#define XGB_DLL __declspec(dllexport)
#else
#define XGB_DLL
#endif
// manually define unsign long
typedef unsigned long bst_ulong;