Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Removed magrittr dependency in callbacks.R (#6855)

Browse Source
This commit is contained in:
ReeceGoding 2021-04-15 11:45:17 +01:00 committed by GitHub
parent 4224c08cac
commit 2e8c101b4a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
R-package/R/callbacks.R
View File

@ -560,7 +560,6 @@ cb.cv.predict <- function(save_models = FALSE) {
#' # #' #
#' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest #' # In the iris dataset, it is hard to linearly separate Versicolor class from the rest
#' # without considering the 2nd order interactions: #' # without considering the 2nd order interactions:
#' require(magrittr)
#' x <- model.matrix(Species ~ .^2, iris)[,-1] #' x <- model.matrix(Species ~ .^2, iris)[,-1]
#' colnames(x) #' colnames(x)
#' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor")) #' dtrain <- xgb.DMatrix(scale(x), label = 1*(iris$Species == "versicolor"))
@ -581,7 +580,7 @@ cb.cv.predict <- function(save_models = FALSE) {
#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8, #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 200, eta = 0.8,
#' updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1, #' updater = 'coord_descent', feature_selector = 'thrifty', top_k = 1,
#' callbacks = list(cb.gblinear.history())) #' callbacks = list(cb.gblinear.history()))
#' xgb.gblinear.history(bst) %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst), type = 'l')
#' # Componentwise boosting is known to have similar effect to Lasso regularization. #' # Componentwise boosting is known to have similar effect to Lasso regularization.
#' # Try experimenting with various values of top_k, eta, nrounds, #' # Try experimenting with various values of top_k, eta, nrounds,
#' # as well as different feature_selectors. #' # as well as different feature_selectors.
@ -590,7 +589,7 @@ cb.cv.predict <- function(save_models = FALSE) {
#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8, #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 100, eta = 0.8,
#' callbacks = list(cb.gblinear.history())) #' callbacks = list(cb.gblinear.history()))
#' # coefficients in the CV fold #3 #' # coefficients in the CV fold #3
#' xgb.gblinear.history(bst)[[3]] %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst)[[3]], type = 'l')
#' #'
#' #'
#' #### Multiclass classification: #' #### Multiclass classification:
@ -603,15 +602,15 @@ cb.cv.predict <- function(save_models = FALSE) {
#' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5, #' bst <- xgb.train(param, dtrain, list(tr=dtrain), nrounds = 70, eta = 0.5,
#' callbacks = list(cb.gblinear.history())) #' callbacks = list(cb.gblinear.history()))
#' # Will plot the coefficient paths separately for each class: #' # Will plot the coefficient paths separately for each class:
#' xgb.gblinear.history(bst, class_index = 0) %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst, class_index = 0), type = 'l')
#' xgb.gblinear.history(bst, class_index = 1) %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst, class_index = 1), type = 'l')
#' xgb.gblinear.history(bst, class_index = 2) %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst, class_index = 2), type = 'l')
#' #'
#' # CV: #' # CV:
#' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5, #' bst <- xgb.cv(param, dtrain, nfold = 5, nrounds = 70, eta = 0.5,
#' callbacks = list(cb.gblinear.history(FALSE))) #' callbacks = list(cb.gblinear.history(FALSE)))
#' # 1st forld of 1st class #' # 1st fold of 1st class
#' xgb.gblinear.history(bst, class_index = 0)[[1]] %>% matplot(type = 'l') #' matplot(xgb.gblinear.history(bst, class_index = 0)[[1]], type = 'l')
#' #'
#' @export #' @export
cb.gblinear.history <- function(sparse=FALSE) { cb.gblinear.history <- function(sparse=FALSE) {