Merge pull request dmlc#679 from pommedeterresautee/master

Wording of R doc in new functions

Author: pommedeterresautee

R-package/R/xgb.create.features.R

@@ -14,7 +14,7 @@
 #' @details 
 #' This is the function inspired from the paragraph 3.1 of the paper:
 #' 
-#' \strong{"Practical Lessons from Predicting Clicks on Ads at Facebook"}
+#' \strong{Practical Lessons from Predicting Clicks on Ads at Facebook}
 #' 
 #' \emph{(Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yan, xin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, 
 #' Joaquin Quiñonero Candela)}

R-package/R/xgb.importance.R

@@ -21,7 +21,7 @@
 #' @details 
 #' This is the function to understand the model trained (and through your model, your data).
 #' 
-#' Results are returned for both linear and tree models.
+#' This function is for both linear and tree models.
 #' 
 #' \code{data.table} is returned by the function. 
 #' The columns are :
@@ -32,8 +32,9 @@
 #'   \item \code{Weight} percentage representing the relative number of times a feature have been taken into trees.
 #' }
 #' 
-#' If you don't provide name, index of the features are used.
-#' They are extracted from the boost dump (made on the C++ side), the index starts at 0 (usual in C++) instead of 1 (usual in R).
+#' If you don't provide \code{feature_names}, index of the features will be used instead.
+#' 
+#' Because the index is extracted from the model dump (made on the C++ side), it starts at 0 (usual in C++) instead of 1 (usual in R).
 #' 
 #' Co-occurence count
 #' ------------------
@@ -47,10 +48,6 @@
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' 
-#' # Both dataset are list with two items, a sparse matrix and labels 
-#' # (labels = outcome column which will be learned). 
-#' # Each column of the sparse Matrix is a feature in one hot encoding format.
-#' 
 #' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2, 
 #'                eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
 #' 
@@ -114,8 +111,6 @@ xgb.importance <- function(feature_names = NULL, model = NULL, data = NULL, labe
   result
 }
 
-
-
 # Avoid error messages during CRAN check.
 # The reason is that these variables are never declared
 # They are mainly column names inferred by Data.table...

R-package/R/xgb.model.dt.tree.R

@@ -1,6 +1,6 @@
-#' Convert tree model dump to data.table
+#' Parse boosted tree model text dump
 #' 
-#' Read a tree model text dump and return a data.table.
+#' Parse a boosted tree model text dump and return a \code{data.table}.
 #' 
 #' @importFrom data.table data.table
 #' @importFrom data.table set
@@ -13,17 +13,19 @@
 #' @importFrom stringr str_extract
 #' @importFrom stringr str_split
 #' @importFrom stringr str_trim
-#' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.
-#' @param model dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.
-#' @param text dump generated by the \code{xgb.dump} function. Avoid the creation of a dump file. Model dump must include the gain per feature and per tree (parameter \code{with.stats = T} in function \code{xgb.dump}).
-#' @param n_first_tree limit the plot to the n first trees. If \code{NULL}, all trees of the model are plotted. Performance can be low for huge models.
+#' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If the model already contains feature names, this argument should be \code{NULL} (default value).
+#' @param model object created by the \code{xgb.train} function.
+#' @param text \code{character} vector generated by the \code{xgb.dump} function. Model dump must include the gain per feature and per tree (parameter \code{with.stats = TRUE} in function \code{xgb.dump}).
+#' @param n_first_tree limit the plot to the \code{n} first trees. If set to \code{NULL}, all trees of the model are plotted. Performance can be low depending of the size of the model.
 #'
-#' @return A \code{data.table} of the features used in the model with their gain, cover and few other thing.
+#' @return A \code{data.table} of the features used in the model with their gain, cover and few other information.
 #'
 #' @details 
-#' General function to convert a text dump of tree model to a Matrix. The purpose is to help user to explore the model and get a better understanding of it.
+#' General function to convert a text dump of tree model to a \code{data.table}. 
 #' 
-#' The content of the \code{data.table} is organised that way:
+#' The purpose is to help user to explore the model and get a better understanding of it.
+#' 
+#' The columns of the \code{data.table} are:
 #' 
 #' \itemize{
 #' \item \code{ID}: unique identifier of a node ;
@@ -35,21 +37,16 @@
 #'  \item \code{Quality}: it's the gain related to the split in this specific node ;
 #'  \item \code{Cover}: metric to measure the number of observation affected by the split ;
 #'  \item \code{Tree}: ID of the tree. It is included in the main ID ;
-#'  \item \code{Yes.X} or \code{No.X}: data related to the pointer in \code{Yes} or \code{No} column ;
+#'  \item \code{Yes.Feature}, \code{No.Feature}, \code{Yes.Cover}, \code{No.Cover}, \code{Yes.Quality} and \code{No.Quality}: data related to the pointer in \code{Yes} or \code{No} column ;
 #' } 
 #'   
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' 
-#' #Both dataset are list with two items, a sparse matrix and labels 
-#' #(labels = outcome column which will be learned). 
-#' #Each column of the sparse Matrix is a feature in one hot encoding format.
-#' train <- agaricus.train
-#' 
-#' bst <- xgboost(data = train$data, label = train$label, max.depth = 2, 
+#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label, max.depth = 2, 
 #'                eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
 #' 
-#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix.
+#' # agaricus.train$data@@Dimnames[[2]] represents the column names of the sparse matrix.
 #' xgb.model.dt.tree(feature_names = agaricus.train$data@@Dimnames[[2]], model = bst)
 #' 
 #' @export

R-package/R/xgb.plot.deepness.R

@@ -76,6 +76,7 @@ get.paths.to.leaf <- function(dt.tree) {
 #' @details
 #' Display both the number of \code{leaf} and the distribution of \code{weighted observations}
 #' by tree deepness level.
+#' 
 #' The purpose of this function is to help the user to find the best trade-off to set
 #' the \code{max.depth} and \code{min_child_weight} parameters according to the bias / variance trade-off.
 #' 
@@ -88,7 +89,7 @@ get.paths.to.leaf <- function(dt.tree) {
 #'  \item Weighted cover: noramlized weighted cover per Leaf (weighted number of instances).
 #' }
 #'
-#' This function is inspired by this blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html}
+#' This function is inspired by the blog post \url{http://aysent.github.io/2015/11/08/random-forest-leaf-visualization.html}
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')