Merge pull request #124 from pommedeterresautee/master

Add a new function to see importance of features in a model

.gitignore

@@ -44,3 +44,4 @@ Debug
 *dump
 *save
 *csv
+.Rproj.user

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: eXtreme Gradient Boosting
-Version: 0.3-2
-Date: 2014-08-23
+Version: 0.3-3
+Date: 2014-12-28
 Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>
 Maintainer: Tong He <hetong007@gmail.com>
 Description: This package is a R wrapper of xgboost, which is short for eXtreme
@@ -21,4 +21,6 @@ Depends:
     R (>= 2.10)
 Imports:
     Matrix (>= 1.1-0),
-    methods
+    methods,
+    data.table (>= 1.9),
+    magrittr (>= 1.5)

R-package/NAMESPACE

@@ -1,4 +1,4 @@
-# Generated by roxygen2 (4.0.1): do not edit by hand
+# Generated by roxygen2 (4.1.0): do not edit by hand
 
 export(getinfo)
 export(setinfo)
@@ -7,6 +7,7 @@ export(xgb.DMatrix)
 export(xgb.DMatrix.save)
 export(xgb.cv)
 export(xgb.dump)
+export(xgb.importance)
 export(xgb.load)
 export(xgb.save)
 export(xgb.train)
@@ -15,3 +16,6 @@ exportMethods(predict)
 import(methods)
 importClassesFrom(Matrix,dgCMatrix)
 importClassesFrom(Matrix,dgeMatrix)
+importFrom(data.table,":=")
+importFrom(data.table,data.table)
+importFrom(magrittr,"%>%")

R-package/R/xgb.importance.R

@@ -0,0 +1,56 @@
+#' Show importance of features in a model
+#' 
+#' Read a xgboost model in text file format. 
+#' Can be tree or linear model (text dump of linear model are only supported in dev version of Xgboost for now).
+#' 
+#' Return a data.table of the features with their weight.
+#' #' 
+#' @importFrom data.table data.table
+#' @importFrom magrittr %>%
+#' @importFrom data.table :=
+#' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix.
+#' @param filename_dump the name of the text file.
+#'
+#' @examples
+#' data(agaricus.train, package='xgboost')
+#' data(agaricus.test, package='xgboost')
+#' 
+#' #Both dataset are list with two items, a sparse matrix and labels (outcome column which will be learned). 
+#' #Each column of the sparse Matrix is a feature in one hot encoding format.
+#' train <- agaricus.train
+#' test <- agaricus.test
+#' 
+#' bst <- xgboost(data = train$data, label = train$label, max.depth = 2, 
+#'                eta = 1, nround = 2,objective = "binary:logistic")
+#' xgb.dump(bst, 'xgb.model.dump')
+#' 
+#' #agaricus.test$data@@Dimnames[[2]] represents the column name of the sparse matrix.
+#' xgb.importance(agaricus.test$data@@Dimnames[[2]], 'xgb.model.dump')
+#' 
+#' @export
+xgb.importance <- function(feature_names, filename_dump){  
+  text <- readLines(filename_dump)  
+  if(text[2] == "bias:"){
+    result <- linearDump(feature_names, text)
+  }  else {
+    result <- treeDump(feature_names, text)
+  }
+  result
+}
+
+treeDump <- function(feature_names, text){  
+  result <- c()
+  for(line in text){
+    p <- regexec("\\[f.*\\]", line) %>% regmatches(line, .)
+    if (length(p[[1]]) > 0) {      
+      splits <- sub("\\[f", "", p[[1]]) %>% sub("\\]", "", .) %>% strsplit("<") %>% .[[1]] %>% as.numeric
+      result <- c(result, feature_names[splits[1]+ 1])
+    }
+  }
+  #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 = .)
+}

R-package/man/agaricus.test.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgboost.R
 \docType{data}
 \name{agaricus.test}
 \alias{agaricus.test}

R-package/man/agaricus.train.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgboost.R
 \docType{data}
 \name{agaricus.train}
 \alias{agaricus.train}

R-package/man/getinfo.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/getinfo.xgb.DMatrix.R
 \docType{methods}
 \name{getinfo}
 \alias{getinfo}
@@ -12,9 +13,9 @@ getinfo(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
-\item{name}{the name of the field to get}
-
 \item{...}{other parameters}
+
+\item{name}{the name of the field to get}
 }
 \description{
 Get information of an xgb.DMatrix object

R-package/man/predict-xgb.Booster-method.Rd

@@ -1,11 +1,12 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/predict.xgb.Booster.R
 \docType{methods}
 \name{predict,xgb.Booster-method}
 \alias{predict,xgb.Booster-method}
 \title{Predict method for eXtreme Gradient Boosting model}
 \usage{
-\S4method{predict}{xgb.Booster}(object, newdata, outputmargin = FALSE,
-  ntreelimit = NULL)
+\S4method{predict}{xgb.Booster}(object, newdata, missing = NULL,
+  outputmargin = FALSE, ntreelimit = NULL)
 }
 \arguments{
 \item{object}{Object of class "xgb.Boost"}

R-package/man/setinfo.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/setinfo.xgb.DMatrix.R
 \docType{methods}
 \name{setinfo}
 \alias{setinfo}
@@ -12,11 +13,11 @@ setinfo(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
+\item{...}{other parameters}
+
 \item{name}{the name of the field to get}
 
 \item{info}{the specific field of information to set}
-
-\item{...}{other parameters}
 }
 \description{
 Set information of an xgb.DMatrix object

R-package/man/slice.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/slice.xgb.DMatrix.R
 \docType{methods}
 \name{slice}
 \alias{slice}
@@ -13,9 +14,9 @@ slice(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
-\item{idxset}{a integer vector of indices of rows needed}
-
 \item{...}{other parameters}
+
+\item{idxset}{a integer vector of indices of rows needed}
 }
 \description{
 Get a new DMatrix containing the specified rows of

R-package/man/xgb.DMatrix.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.DMatrix.R
 \name{xgb.DMatrix}
 \alias{xgb.DMatrix}
 \title{Contruct xgb.DMatrix object}

R-package/man/xgb.DMatrix.save.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.DMatrix.save.R
 \name{xgb.DMatrix.save}
 \alias{xgb.DMatrix.save}
 \title{Save xgb.DMatrix object to binary file}

R-package/man/xgb.cv.Rd

@@ -1,10 +1,12 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.cv.R
 \name{xgb.cv}
 \alias{xgb.cv}
 \title{Cross Validation}
 \usage{
-xgb.cv(params = list(), data, nrounds, nfold, label = NULL, showsd = TRUE,
-  metrics = list(), obj = NULL, feval = NULL, ...)
+xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
+  missing = NULL, showsd = TRUE, metrics = list(), obj = NULL,
+  feval = NULL, ...)
 }
 \arguments{
 \item{params}{the list of parameters. Commonly used ones are:

R-package/man/xgb.dump.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.dump.R
 \name{xgb.dump}
 \alias{xgb.dump}
 \title{Save xgboost model to text file}

R-package/man/xgb.importance.Rd

@@ -0,0 +1,33 @@
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.importance.R
+\name{xgb.importance}
+\alias{xgb.importance}
+\title{Show importance of features in a model}
+\usage{
+xgb.importance(feature_names, filename_dump)
+}
+\arguments{
+\item{feature_names}{names of each feature as a character vector. Can be extracted from a sparse matrix.}
+
+\item{filename_dump}{the name of the text file.}
+}
+\description{
+Read a xgboost model in text file format. Return a data.table of the features with their weight.
+}
+\examples{
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
+
+#Both dataset are list with two items, a sparse matrix and labels (outcome column which will be learned).
+#Each column of the sparse Matrix is a feature in one hot encoding format.
+train <- agaricus.train
+test <- agaricus.test
+
+bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
+               eta = 1, nround = 2,objective = "binary:logistic")
+xgb.dump(bst, 'xgb.model.dump')
+
+#agaricus.test$data@Dimnames[[2]] represents the column name of the sparse matrix.
+xgb.importance(agaricus.test$data@Dimnames[[2]], 'xgb.model.dump')
+}
+

R-package/man/xgb.load.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.load.R
 \name{xgb.load}
 \alias{xgb.load}
 \title{Load xgboost model from binary file}

R-package/man/xgb.save.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.save.R
 \name{xgb.save}
 \alias{xgb.save}
 \title{Save xgboost model to binary file}

R-package/man/xgb.train.Rd

@@ -1,4 +1,5 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgb.train.R
 \name{xgb.train}
 \alias{xgb.train}
 \title{eXtreme Gradient Boosting Training}

R-package/man/xgboost.Rd

@@ -1,10 +1,11 @@
-% Generated by roxygen2 (4.0.1): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/xgboost.R
 \name{xgboost}
 \alias{xgboost}
 \title{eXtreme Gradient Boosting (Tree) library}
 \usage{
-xgboost(data = NULL, label = NULL, params = list(), nrounds,
-  verbose = 1, ...)
+xgboost(data = NULL, label = NULL, missing = NULL, params = list(),
+  nrounds, verbose = 1, ...)
 }
 \arguments{
 \item{data}{takes \code{matrix}, \code{dgCMatrix}, local data file or