[R] On-demand serialization + standardization of attributes (#9924)

---------

Co-authored-by: Jiaming Yuan <jm.yuan@outlook.com>

R-package/demo/00Index

@@ -1,5 +1,4 @@
 basic_walkthrough               Basic feature walkthrough
-caret_wrapper                   Use xgboost to train in caret library
 custom_objective                Customize loss function, and evaluation metric
 boost_from_prediction           Boosting from existing prediction
 predict_first_ntree             Predicting using first n trees

R-package/demo/README.md

@@ -1,7 +1,6 @@
 XGBoost R Feature Walkthrough
 ====
 * [Basic walkthrough of wrappers](basic_walkthrough.R)
-* [Train a xgboost model from caret library](caret_wrapper.R)
 * [Customize loss function, and evaluation metric](custom_objective.R)
 * [Boosting from existing prediction](boost_from_prediction.R)
 * [Predicting using first n trees](predict_first_ntree.R)

R-package/demo/caret_wrapper.R

@@ -1,44 +0,0 @@
-# install development version of caret library that contains xgboost models
-require(caret)
-require(xgboost)
-require(data.table)
-require(vcd)
-require(e1071)
-
-# Load Arthritis dataset in memory.
-data(Arthritis)
-# Create a copy of the dataset with data.table package
-# (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent
-# and its performance are really good).
-df <- data.table(Arthritis, keep.rownames = FALSE)
-
-# Let's add some new categorical features to see if it helps.
-# Of course these feature are highly correlated to the Age feature.
-# Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features,
-# even in case of highly correlated features.
-# For the first feature we create groups of age by rounding the real age.
-# Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.
-df[, AgeDiscret := as.factor(round(Age / 10, 0))]
-
-# Here is an even stronger simplification of the real age with an arbitrary split at 30 years old.
-# I choose this value based on nothing.
-# We will see later if simplifying the information based on arbitrary values is a good strategy
-# (I am sure you already have an idea of how well it will work!).
-df[, AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
-
-# We remove ID as there is nothing to learn from this feature (it will just add some noise as the dataset is small).
-df[, ID := NULL]
-
-#-------------Basic Training using XGBoost in caret Library-----------------
-# Set up control parameters for caret::train
-# Here we use 10-fold cross-validation, repeating twice, and using random search for tuning hyper-parameters.
-fitControl <- trainControl(method = "repeatedcv", number = 10, repeats = 2, search = "random")
-# train a xgbTree model using caret::train
-model <- train(factor(Improved) ~ ., data = df, method = "xgbTree", trControl = fitControl)
-
-# Instead of tree for our boosters, you can also fit a linear regression or logistic regression model
-# using xgbLinear
-# model <- train(factor(Improved)~., data = df, method = "xgbLinear", trControl = fitControl)
-
-# See model results
-print(model)

R-package/demo/predict_leaf_indices.R

@@ -27,7 +27,7 @@ head(pred_with_leaf)
 create.new.tree.features <- function(model, original.features) {
   pred_with_leaf <- predict(model, original.features, predleaf = TRUE)
   cols <- list()
-  for (i in 1:model$niter) {
+  for (i in 1:xgb.get.num.boosted.rounds(model)) {
     # max is not the real max but it s not important for the purpose of adding features
     leaf.id <- sort(unique(pred_with_leaf[, i]))
     cols[[i]] <- factor(x = pred_with_leaf[, i], level = leaf.id)

R-package/demo/runall.R

@@ -9,6 +9,5 @@ demo(create_sparse_matrix, package = 'xgboost')
 demo(predict_leaf_indices, package = 'xgboost')
 demo(early_stopping, package = 'xgboost')
 demo(poisson_regression, package = 'xgboost')
-demo(caret_wrapper, package = 'xgboost')
 demo(tweedie_regression, package = 'xgboost')
 #demo(gpu_accelerated, package = 'xgboost')  # can only run when built with GPU support