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

replace nround with nrounds to match actual parameter (#3592)

Browse Source
This commit is contained in:
Jakob Richter
2018-08-15 20:13:53 +02:00
committed by Philip Hyunsu Cho
parent 73bd590a1d
commit 725f4c36f2
17 changed files with 51 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
R-package/R/callbacks.R
View File

@@ -168,7 +168,7 @@ cb.evaluation.log <- function() {
#' at the beginning of each iteration.
#'
#' Note that when training is resumed from some previous model, and a function is used to
#' reset a parameter value, the \code{nround} argument in this function would be the
#' reset a parameter value, the \code{nrounds} argument in this function would be the
#' the number of boosting rounds in the current training.
#'
#' Callback function expects the following values to be set in its calling frame:

6
R-package/R/xgb.create.features.R
View File

@@ -52,9 +52,9 @@
#' dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
#'
#' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
#' nround = 4
#' nrounds = 4
#'
#' bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
#' bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
#'
#' # Model accuracy without new features
#' accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
@@ -68,7 +68,7 @@
#' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
#' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
#' watchlist <- list(train = new.dtrain)
#' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
#' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
#'
#' # Model accuracy with new features
#' accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /

2
R-package/R/xgb.train.R
View File

@@ -22,7 +22,7 @@
#' \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
#' \item \code{max_depth} maximum depth of a tree. Default: 6
#' \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
#' \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nround}. Default: 1
#' \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
#' \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
#' \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample < 1} and \code{round = 1}) accordingly. Default: 1
#' \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.

10
R-package/demo/cross_validation.R
View File

@@ -5,20 +5,20 @@ data(agaricus.test, package='xgboost')
dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
nround <- 2
nrounds <- 2
param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
cat('running cross validation\n')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value+std_value
# std_value is standard deviation of the metric
xgb.cv(param, dtrain, nround, nfold=5, metrics={'error'})
xgb.cv(param, dtrain, nrounds, nfold=5, metrics={'error'})
cat('running cross validation, disable standard deviation display\n')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value+std_value
# std_value is standard deviation of the metric
xgb.cv(param, dtrain, nround, nfold=5,
xgb.cv(param, dtrain, nrounds, nfold=5,
metrics='error', showsd = FALSE)
###
@@ -43,9 +43,9 @@ evalerror <- function(preds, dtrain) {
param <- list(max_depth=2, eta=1, silent=1,
objective = logregobj, eval_metric = evalerror)
# train with customized objective
xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5)
xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)
# do cross validation with prediction values for each fold
res <- xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5, prediction = TRUE)
res <- xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5, prediction = TRUE)
res$evaluation_log
length(res$pred)

4
R-package/demo/predict_first_ntree.R
View File

@@ -7,10 +7,10 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
watchlist <- list(eval = dtest, train = dtrain)
nround = 2
nrounds = 2
# training the model for two rounds
bst = xgb.train(param, dtrain, nround, nthread = 2, watchlist)
bst = xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
cat('start testing prediction from first n trees\n')
labels <- getinfo(dtest,'label')

6
R-package/demo/predict_leaf_indices.R
View File

@@ -11,10 +11,10 @@ dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
nround = 4
nrounds = 4
# training the model for two rounds
bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
# Model accuracy without new features
accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
@@ -43,7 +43,7 @@ new.features.test <- create.new.tree.features(bst, agaricus.test$data)
new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
watchlist <- list(train = new.dtrain)
bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
# Model accuracy with new features
accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)

2
R-package/man/cb.reset.parameters.Rd
View File

@@ -22,7 +22,7 @@ This is a "pre-iteration" callback function used to reset booster's parameters
at the beginning of each iteration.
Note that when training is resumed from some previous model, and a function is used to
reset a parameter value, the \code{nround} argument in this function would be the
reset a parameter value, the \code{nrounds} argument in this function would be the
the number of boosting rounds in the current training.
Callback function expects the following values to be set in its calling frame:

6
R-package/man/xgb.create.features.Rd
View File

@@ -63,9 +63,9 @@ dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
nround = 4
nrounds = 4
bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
# Model accuracy without new features
accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
@@ -79,7 +79,7 @@ new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
watchlist <- list(train = new.dtrain)
bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
# Model accuracy with new features
accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /

2
R-package/man/xgb.train.Rd
View File

@@ -35,7 +35,7 @@ xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
\item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be.
\item \code{max_depth} maximum depth of a tree. Default: 6
\item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
\item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nround}. Default: 1
\item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1
\item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
\item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample < 1} and \code{round = 1}) accordingly. Default: 1
\item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.

2
R-package/tests/testthat/test_gc_safety.R
View File

@@ -9,7 +9,7 @@ test_that("train and prediction when gctorture is on", {
test <- agaricus.test
gctorture(TRUE)
bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
pred <- predict(bst, test$data)
gctorture(FALSE)
})