Replace cBind by cbind (#3203)

* modify test_helper.R

* fix noLD

* update desc

* fix solaris test

* fix desc

* improve fix

* fix url

* change Matrix cBind to cbind

* fix

* fix error in demo

* fix examples

R-package/NAMESPACE

@@ -51,7 +51,6 @@ export(xgboost)
 import(methods)
 importClassesFrom(Matrix,dgCMatrix)
 importClassesFrom(Matrix,dgeMatrix)
-importFrom(Matrix,cBind)
 importFrom(Matrix,colSums)
 importFrom(Matrix,sparse.model.matrix)
 importFrom(Matrix,sparseMatrix)

R-package/R/callbacks.R

@@ -554,6 +554,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #' #
 #' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
 #' # without considering the 2nd order interactions:
+#' require(magrittr)
 #' x <- model.matrix(Species ~ .^2, iris)[,-1]
 #' colnames(x)
 #' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
@@ -602,7 +603,7 @@ cb.cv.predict <- function(save_models = FALSE) {
 #'
 #' # CV:
 #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
-#'               callbacks = list(cb.gblinear.history(F)))
+#'               callbacks = list(cb.gblinear.history(FALSE)))
 #' # 1st forld of 1st class
 #' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l')
 #'
@@ -691,7 +692,9 @@ cb.gblinear.history <- function(sparse=FALSE) {
 #' corresponding to CV folds.
 #'
 #' @examples
+#' \dontrun{
 #' See \code{\link{cv.gblinear.history}}
+#' }
 #'
 #' @export
 xgb.gblinear.history <- function(model, class_index = NULL) {

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

@@ -83,5 +83,5 @@ xgb.create.features <- function(model, data, ...){
   check.deprecation(...)
   pred_with_leaf <- predict(model, data, predleaf = TRUE)
   cols <- lapply(as.data.frame(pred_with_leaf), factor)
-  cBind(data, sparse.model.matrix( ~ . -1, cols))
+  cbind(data, sparse.model.matrix( ~ . -1, cols))
 }

R-package/R/xgboost.R

@@ -77,7 +77,6 @@ NULL
 
 # Various imports
 #' @importClassesFrom Matrix dgCMatrix dgeMatrix
-#' @importFrom Matrix cBind
 #' @importFrom Matrix colSums
 #' @importFrom Matrix sparse.model.matrix
 #' @importFrom Matrix sparseVector

R-package/demo/predict_leaf_indices.R

@@ -32,7 +32,7 @@ create.new.tree.features <- function(model, original.features){
     leaf.id <- sort(unique(pred_with_leaf[,i]))
     cols[[i]] <- factor(x = pred_with_leaf[,i], level = leaf.id)
   }
-  cBind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
+  cbind(original.features, sparse.model.matrix( ~ . -1, as.data.frame(cols)))
 }
 
 # Convert previous features to one hot encoding

R-package/man/cb.gblinear.history.Rd

@@ -0,0 +1,95 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{cb.gblinear.history}
+\alias{cb.gblinear.history}
+\title{Callback closure for collecting the model coefficients history of a gblinear booster
+during its training.}
+\usage{
+cb.gblinear.history(sparse = FALSE)
+}
+\arguments{
+\item{sparse}{when set to FALSE/TURE, a dense/sparse matrix is used to store the result.
+Sparse format is useful when one expects only a subset of coefficients to be non-zero,
+when using the "thrifty" feature selector with fairly small number of top features
+selected per iteration.}
+}
+\value{
+Results are stored in the \code{coefs} element of the closure.
+The \code{\link{xgb.gblinear.history}} convenience function provides an easy way to access it.
+With \code{xgb.train}, it is either a dense of a sparse matrix.
+While with \code{xgb.cv}, it is a list (an element per each fold) of such matrices.
+}
+\description{
+Callback closure for collecting the model coefficients history of a gblinear booster
+during its training.
+}
+\details{
+To keep things fast and simple, gblinear booster does not internally store the history of linear
+model coefficients at each boosting iteration. This callback provides a workaround for storing
+the coefficients' path, by extracting them after each training iteration.
+
+Callback function expects the following values to be set in its calling frame:
+\code{bst} (or \code{bst_folds}).
+}
+\examples{
+#### Binary classification:
+#
+# In the iris dataset, it is hard to linearly separate Versicolor class from the rest
+# without considering the 2nd order interactions:
+require(magrittr)
+x <- model.matrix(Species ~ .^2, iris)[,-1]
+colnames(x)
+dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
+param <- list(booster = "gblinear", objective = "reg:logistic", eval_metric = "auc",
+              lambda = 0.0003, alpha = 0.0003, nthread = 2)
+# For 'shotgun', which is a default linear updater, using high eta values may result in
+# unstable behaviour in some datasets. With this simple dataset, however, the high learning
+# rate does not break the convergence, but allows us to illustrate the typical pattern of
+# "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 1.,
+                 callbacks = list(cb.gblinear.history()))
+# Extract the coefficients' path and plot them vs boosting iteration number:
+coef_path <- xgb.gblinear.history(bst)
+matplot(coef_path, type = 'l')
+
+# With the deterministic coordinate descent updater, it is safer to use higher learning rates.
+# Will try the classical componentwise boosting which selects a single best feature per round:
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
+                 updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
+                 callbacks = list(cb.gblinear.history()))
+xgb.gblinear.history(bst) \%>\% matplot(type = 'l')
+#  Componentwise boosting is known to have similar effect to Lasso regularization.
+# Try experimenting with various values of top_k, eta, nrounds,
+# as well as different feature_selectors.
+
+# For xgb.cv:
+bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
+             callbacks = list(cb.gblinear.history()))
+# coefficients in the CV fold #3
+xgb.gblinear.history(bst)[[3]] \%>\% matplot(type = 'l')
+
+
+#### Multiclass classification:
+#
+dtrain <- xgb.DMatrix(scale(x), label = as.numeric(iris$Species) - 1)
+param <- list(booster = "gblinear", objective = "multi:softprob", num_class = 3,
+              lambda = 0.0003, alpha = 0.0003, nthread = 2)
+# For the default linear updater 'shotgun' it sometimes is helpful
+# to use smaller eta to reduce instability
+bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
+                 callbacks = list(cb.gblinear.history()))
+# Will plot the coefficient paths separately for each class:
+xgb.gblinear.history(bst, class_index = 0) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 1) \%>\% matplot(type = 'l')
+xgb.gblinear.history(bst, class_index = 2) \%>\% matplot(type = 'l')
+
+# CV:
+bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
+              callbacks = list(cb.gblinear.history(FALSE)))
+# 1st forld of 1st class
+xgb.gblinear.history(bst, class_index = 0)[[1]] \%>\% matplot(type = 'l')
+
+}
+\seealso{
+\code{\link{callbacks}}, \code{\link{xgb.gblinear.history}}.
+}

R-package/man/xgb.gblinear.history.Rd

@@ -0,0 +1,35 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/callbacks.R
+\name{xgb.gblinear.history}
+\alias{xgb.gblinear.history}
+\title{Extract gblinear coefficients history.}
+\usage{
+xgb.gblinear.history(model, class_index = NULL)
+}
+\arguments{
+\item{model}{either an \code{xgb.Booster} or a result of \code{xgb.cv()}, trained
+using the \code{cb.gblinear.history()} callback.}
+
+\item{class_index}{zero-based class index to extract the coefficients for only that
+specific class in a multinomial multiclass model. When it is NULL, all the
+coeffients are returned. Has no effect in non-multiclass models.}
+}
+\value{
+For an \code{xgb.train} result, a matrix (either dense or sparse) with the columns
+corresponding to iteration's coefficients (in the order as \code{xgb.dump()} would
+return) and the rows corresponding to boosting iterations.
+
+For an \code{xgb.cv} result, a list of such matrices is returned with the elements
+corresponding to CV folds.
+}
+\description{
+A helper function to extract the matrix of linear coefficients' history
+from a gblinear model created while using the \code{cb.gblinear.history()}
+callback.
+}
+\examples{
+\dontrun{
+See \\code{\\link{cv.gblinear.history}}
+}
+
+}