resolving not-CRAN issues

R-package/DESCRIPTION

@@ -25,5 +25,4 @@ Imports:
     data.table (>= 1.9),
     magrittr (>= 1.5),
     stringr,
-    DiagrammeR,
+    DiagrammeR
-    vcd

R-package/R/predict.xgb.Booster.R

@@ -11,10 +11,10 @@ setClass("xgb.Booster")
 #'   value of sum of functions, when outputmargin=TRUE, the prediction is 
 #'   untransformed margin value. In logistic regression, outputmargin=T will
 #'   output value before logistic transformation.
-#' @param predleaf whether predict leaf index instead. If set to TRUE, the output will be a matrix object.
 #' @param ntreelimit limit number of trees used in prediction, this parameter is
 #'  only valid for gbtree, but not for gblinear. set it to be value bigger 
 #'  than 0. It will use all trees by default.
+#' @param predleaf whether predict leaf index instead. If set to TRUE, the output will be a matrix object.
 #' @examples
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')

R-package/R/xgb.cv.R

@@ -32,7 +32,7 @@
 #' @param nfold number of folds used
 #' @param label option field, when data is Matrix
 #' @param missing Missing is only used when input is dense matrix, pick a float
-#     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
+#'    value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
 #' @param prediction A logical value indicating whether to return the prediction vector.
 #' @param showsd \code{boolean}, whether show standard deviation of cross validation
 #' @param metrics, list of evaluation metrics to be used in corss validation,

R-package/R/xgb.dump.R

@@ -29,7 +29,7 @@
 #' bst <- xgboost(data = train$data, label = train$label, max.depth = 2, 
 #'                eta = 1, nround = 2,objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
-#' xgb.dump(bst, 'xgb.model.dump', with.stats = T)
+#' xgb.dump(bst, 'xgb.model.dump', with.stats = TRUE)
 #' 
 #' # print the model without saving it to a file
 #' print(xgb.dump(bst))
@@ -54,4 +54,4 @@ xgb.dump <- function(model = NULL, fname = NULL, fmap = "", with.stats=FALSE) {
     result %>% str_split("\n") %>% unlist %>% Filter(function(x) x != "", .) %>% writeLines(fname)
     return(TRUE)
   }
-}
+}

R-package/R/xgb.importance.R

@@ -32,7 +32,8 @@
 #' data(agaricus.train, package='xgboost')
 #' data(agaricus.test, package='xgboost')
 #' 
-#' #Both dataset are list with two items, a sparse matrix and labels (labels = outcome column which will be learned). 
+#' #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
 #' test <- agaricus.test

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

@@ -42,7 +42,8 @@
 #' @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). 
+#' #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
 #' 

R-package/R/xgb.plot.tree.R

@@ -42,7 +42,8 @@
 #' @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). 
+#' #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
 #' 

R-package/demo/00Index

@@ -4,4 +4,5 @@ boost_from_prediction           Boosting from existing prediction
 predict_first_ntree             Predicting using first n trees
 generalized_linear_model        Generalized Linear Model
 cross_validation                Cross validation
-create_sparse_matrix
+create_sparse_matrix            Create Sparse Matrix
+predict_leaf_indices            Predicting the corresponding leaves

R-package/demo/create_sparse_matrix.R

@@ -1,7 +1,7 @@
 require(xgboost)
 require(Matrix)
 require(data.table)
-require(vcd) #Available in Cran. Used for its dataset with categorical values.
+if (!require(vcd)) install.packages('vcd') #Available in Cran. Used for its dataset with categorical values.
 
 # According to its documentation, Xgboost works only on numbers.
 # Sometimes the dataset we have to work on have categorical data. 
@@ -86,4 +86,4 @@ print(chisq.test(df$AgeCat, df$Y))
 
 # As you can see, in general destroying information by simplying it won't improve your model. Chi2 just demonstrates that. But in more complex cases, creating a new feature based on existing one which makes link with the outcome more obvious may help the algorithm and improve the model. The case studied here is not enough complex to show that. Check Kaggle forum for some challenging datasets.
 # However it's almost always worse when you add some arbitrary rules.
-# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.
+# Moreover, you can notice that even if we have added some not useful new features highly correlated with other features, the boosting tree algorithm have been able to choose the best one, which in this case is the Age. Linear model may not be that strong in these scenario.