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

Deprecate reg:linear' in favor of reg:squarederror'. (#4267)

Browse Source 
* Deprecate `reg:linear' in favor of `reg:squarederror'.
* Replace the use of `reg:linear'.
* Replace the use of `silent`.
This commit is contained in:
Jiaming Yuan 2019-03-17 17:55:04 +08:00 committed by GitHub
parent cf8d5b9b76
commit 29a1356669
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
34 changed files with 210 additions and 193 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
R-package/R/utils.R
View File

@ -28,12 +28,12 @@ NVL <- function(x, val) {
# Merges booster params with whatever is provided in ...
# plus runs some checks
check.booster.params <- function(params, ...) {
if (typeof(params) != "list")
if (typeof(params) != "list")
stop("params must be a list")
# in R interface, allow for '.' instead of '_' in parameter names
names(params) <- gsub("\\.", "_", names(params))
# merge parameters from the params and the dots-expansion
dot_params <- list(...)
names(dot_params) <- gsub("\\.", "_", names(dot_params))
@ -41,15 +41,15 @@ check.booster.params <- function(params, ...) {
names(dot_params))) > 0)
stop("Same parameters in 'params' and in the call are not allowed. Please check your 'params' list.")
params <- c(params, dot_params)
# providing a parameter multiple times makes sense only for 'eval_metric'
name_freqs <- table(names(params))
multi_names <- setdiff(names(name_freqs[name_freqs > 1]), 'eval_metric')
if (length(multi_names) > 0) {
warning("The following parameters were provided multiple times:\n\t",
paste(multi_names, collapse = ', '), "\n Only the last value for each of them will be used.\n")
# While xgboost internals would choose the last value for a multiple-times parameter,
# enforce it here in R as well (b/c multi-parameters might be used further in R code,
# While xgboost internals would choose the last value for a multiple-times parameter,
# enforce it here in R as well (b/c multi-parameters might be used further in R code,
# and R takes the 1st value when multiple elements with the same name are present in a list).
for (n in multi_names) {
del_idx <- which(n == names(params))
@ -57,25 +57,25 @@ check.booster.params <- function(params, ...) {
params[[del_idx]] <- NULL
}
}
# for multiclass, expect num_class to be set
if (typeof(params[['objective']]) == "character" &&
substr(NVL(params[['objective']], 'x'), 1, 6) == 'multi:' &&
as.numeric(NVL(params[['num_class']], 0)) < 2) {
stop("'num_class' > 1 parameter must be set for multiclass classification")
}
# monotone_constraints parser
if (!is.null(params[['monotone_constraints']]) &&
typeof(params[['monotone_constraints']]) != "character") {
vec2str = paste(params[['monotone_constraints']], collapse = ',')
vec2str = paste0('(', vec2str, ')')
params[['monotone_constraints']] = vec2str
}
# interaction constraints parser (convert from list of column indices to string)
if (!is.null(params[['interaction_constraints']]) &&
if (!is.null(params[['interaction_constraints']]) &&
typeof(params[['interaction_constraints']]) != "character"){
# check input class
if (class(params[['interaction_constraints']]) != 'list') stop('interaction_constraints should be class list')
@ -96,10 +96,10 @@ check.booster.params <- function(params, ...) {
check.custom.obj <- function(env = parent.frame()) {
if (!is.null(env$params[['objective']]) && !is.null(env$obj))
stop("Setting objectives in 'params' and 'obj' at the same time is not allowed")
if (!is.null(env$obj) && typeof(env$obj) != 'closure')
stop("'obj' must be a function")
# handle the case when custom objective function was provided through params
if (!is.null(env$params[['objective']]) &&
typeof(env$params$objective) == 'closure') {
@ -113,21 +113,21 @@ check.custom.obj <- function(env = parent.frame()) {
check.custom.eval <- function(env = parent.frame()) {
if (!is.null(env$params[['eval_metric']]) && !is.null(env$feval))
stop("Setting evaluation metrics in 'params' and 'feval' at the same time is not allowed")
if (!is.null(env$feval) && typeof(env$feval) != 'closure')
stop("'feval' must be a function")
# handle a situation when custom eval function was provided through params
if (!is.null(env$params[['eval_metric']]) &&
typeof(env$params$eval_metric) == 'closure') {
env$feval <- env$params$eval_metric
env$params$eval_metric <- NULL
}
# require maximize to be set when custom feval and early stopping are used together
if (!is.null(env$feval) &&
is.null(env$maximize) && (
!is.null(env$early_stopping_rounds) ||
!is.null(env$early_stopping_rounds) ||
has.callbacks(env$callbacks, 'cb.early.stop')))
stop("Please set 'maximize' to indicate whether the evaluation metric needs to be maximized or not")
}
@ -154,15 +154,15 @@ xgb.iter.update <- function(booster_handle, dtrain, iter, obj = NULL) {
# Evaluate one iteration.
# Returns a named vector of evaluation metrics
# Returns a named vector of evaluation metrics
# with the names in a 'datasetname-metricname' format.
xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
if (!identical(class(booster_handle), "xgb.Booster.handle"))
stop("class of booster_handle must be xgb.Booster.handle")
if (length(watchlist) == 0)
if (length(watchlist) == 0)
return(NULL)
evnames <- names(watchlist)
if (is.null(feval)) {
msg <- .Call(XGBoosterEvalOneIter_R, booster_handle, as.integer(iter), watchlist, as.list(evnames))
@ -189,7 +189,7 @@ xgb.iter.eval <- function(booster_handle, watchlist, iter, feval = NULL) {
# Generates random (stratified if needed) CV folds
generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
# cannot do it for rank
if (exists('objective', where = params) &&
is.character(params$objective) &&
@ -209,13 +209,14 @@ generate.cv.folds <- function(nfold, nrows, stratified, label, params) {
if (exists('objective', where = params) &&
is.character(params$objective)) {
# If 'objective' provided in params, assume that y is a classification label
# unless objective is reg:linear
if (params$objective != 'reg:linear')
# unless objective is reg:squarederror
if (params$objective != 'reg:squarederror')
y <- factor(y)
} else {
# If no 'objective' given in params, it means that user either wants to use
# the default 'reg:linear' objective or has provided a custom obj function.
# Here, assume classification setting when y has 5 or less unique values:
# If no 'objective' given in params, it means that user either wants to
# use the default 'reg:squarederror' objective or has provided a custom
# obj function. Here, assume classification setting when y has 5 or less
# unique values:
if (length(unique(y)) <= 5)
y <- factor(y)
}
@ -293,22 +294,22 @@ xgb.createFolds <- function(y, k = 10)
#
#' Deprecation notices.
#'
#'
#' At this time, some of the parameter names were changed in order to make the code style more uniform.
#' The deprecated parameters would be removed in the next release.
#'
#'
#' To see all the current deprecated and new parameters, check the \code{xgboost:::depr_par_lut} table.
#'
#' A deprecation warning is shown when any of the deprecated parameters is used in a call.
#' An additional warning is shown when there was a partial match to a deprecated parameter
#'
#' A deprecation warning is shown when any of the deprecated parameters is used in a call.
#' An additional warning is shown when there was a partial match to a deprecated parameter
#' (as R is able to partially match parameter names).
#'
#'
#' @name xgboost-deprecated
NULL
# Lookup table for the deprecated parameters bookkeeping
depr_par_lut <- matrix(c(
'print.every.n', 'print_every_n',
'print.every.n', 'print_every_n',
'early.stop.round', 'early_stopping_rounds',
'training.data', 'data',
'with.stats', 'with_stats',

120
R-package/R/xgb.cv.R
View File

@ -1,12 +1,12 @@
#' Cross Validation
#'
#'
#' The cross validation function of xgboost
#'
#'
#' @param params the list of parameters. Commonly used ones are:
#' \itemize{
#' \item \code{objective} objective function, common ones are
#' \itemize{
#' \item \code{reg:linear} linear regression
#' \item \code{reg:squarederror} Regression with squared loss
#' \item \code{binary:logistic} logistic regression for classification
#' }
#' \item \code{eta} step size of each boosting step
@ -18,12 +18,12 @@
#' See also demo/ for walkthrough example in R.
#' @param data takes an \code{xgb.DMatrix}, \code{matrix}, or \code{dgCMatrix} as the input.
#' @param nrounds the max number of iterations
#' @param nfold the original dataset is randomly partitioned into \code{nfold} equal size subsamples.
#' @param nfold the original dataset is randomly partitioned into \code{nfold} equal size subsamples.
#' @param label vector of response values. Should be provided only when data is an R-matrix.
#' @param missing is only used when input is a dense matrix. By default is set to NA, which means
#' that NA values should be considered as 'missing' by the algorithm.
#' @param missing is only used when input is a dense matrix. By default is set to NA, which means
#' that NA values should be considered as 'missing' by the algorithm.
#' Sometimes, 0 or other extreme value might be used to represent missing values.
#' @param prediction A logical value indicating whether to return the test fold predictions
#' @param prediction A logical value indicating whether to return the test fold predictions
#' from each CV model. This parameter engages the \code{\link{cb.cv.predict}} callback.
#' @param showsd \code{boolean}, whether to show standard deviation of cross validation
#' @param metrics, list of evaluation metrics to be used in cross validation,
@ -37,22 +37,22 @@
#' \item \code{aucpr} Area under PR curve
#' \item \code{merror} Exact matching error, used to evaluate multi-class classification
#' }
#' @param obj customized objective function. Returns gradient and second order
#' @param obj customized objective function. Returns gradient and second order
#' gradient with given prediction and dtrain.
#' @param feval custimized evaluation function. Returns
#' \code{list(metric='metric-name', value='metric-value')} with given
#' @param feval custimized evaluation function. Returns
#' \code{list(metric='metric-name', value='metric-value')} with given
#' prediction and dtrain.
#' @param stratified a \code{boolean} indicating whether sampling of folds should be stratified
#' @param stratified a \code{boolean} indicating whether sampling of folds should be stratified
#' by the values of outcome labels.
#' @param folds \code{list} provides a possibility to use a list of pre-defined CV folds
#' (each element must be a vector of test fold's indices). When folds are supplied,
#' (each element must be a vector of test fold's indices). When folds are supplied,
#' the \code{nfold} and \code{stratified} parameters are ignored.
#' @param verbose \code{boolean}, print the statistics during the process
#' @param print_every_n Print each n-th iteration evaluation messages when \code{verbose>0}.
#' Default is 1 which means all messages are printed. This parameter is passed to the
#' Default is 1 which means all messages are printed. This parameter is passed to the
#' \code{\link{cb.print.evaluation}} callback.
#' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
#' If set to an integer \code{k}, training with a validation set will stop if the performance
#' @param early_stopping_rounds If \code{NULL}, the early stopping function is not triggered.
#' If set to an integer \code{k}, training with a validation set will stop if the performance
#' doesn't improve for \code{k} rounds.
#' Setting this parameter engages the \code{\link{cb.early.stop}} callback.
#' @param maximize If \code{feval} and \code{early_stopping_rounds} are set,
@ -60,46 +60,46 @@
#' When it is \code{TRUE}, it means the larger the evaluation score the better.
#' This parameter is passed to the \code{\link{cb.early.stop}} callback.
#' @param callbacks a list of callback functions to perform various task during boosting.
#' See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
#' parameters' values. User can provide either existing or their own callback methods in order
#' See \code{\link{callbacks}}. Some of the callbacks are automatically created depending on the
#' parameters' values. User can provide either existing or their own callback methods in order
#' to customize the training process.
#' @param ... other parameters to pass to \code{params}.
#'
#' @details
#' The original sample is randomly partitioned into \code{nfold} equal size subsamples.
#'
#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
#'
#'
#' @details
#' The original sample is randomly partitioned into \code{nfold} equal size subsamples.
#'
#' Of the \code{nfold} subsamples, a single subsample is retained as the validation data for testing the model, and the remaining \code{nfold - 1} subsamples are used as training data.
#'
#' The cross-validation process is then repeated \code{nrounds} times, with each of the \code{nfold} subsamples used exactly once as the validation data.
#'
#'
#' All observations are used for both training and validation.
#'
#'
#' Adapted from \url{http://en.wikipedia.org/wiki/Cross-validation_\%28statistics\%29#k-fold_cross-validation}
#'
#' @return
#' @return
#' An object of class \code{xgb.cv.synchronous} with the following elements:
#' \itemize{
#' \item \code{call} a function call.
#' \item \code{params} parameters that were passed to the xgboost library. Note that it does not
#' \item \code{params} parameters that were passed to the xgboost library. Note that it does not
#' capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
#' \item \code{callbacks} callback functions that were either automatically assigned or
#' \item \code{callbacks} callback functions that were either automatically assigned or
#' explicitly passed.
#' \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
#' first column corresponding to iteration number and the rest corresponding to the
#' first column corresponding to iteration number and the rest corresponding to the
#' CV-based evaluation means and standard deviations for the training and test CV-sets.
#' It is created by the \code{\link{cb.evaluation.log}} callback.
#' \item \code{niter} number of boosting iterations.
#' \item \code{nfeatures} number of features in training data.
#' \item \code{folds} the list of CV folds' indices - either those passed through the \code{folds}
#' \item \code{folds} the list of CV folds' indices - either those passed through the \code{folds}
#' parameter or randomly generated.
#' \item \code{best_iteration} iteration number with the best evaluation metric value
#' (only available with early stopping).
#' \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
#' \item \code{best_ntreelimit} the \code{ntreelimit} value corresponding to the best iteration,
#' which could further be used in \code{predict} method
#' (only available with early stopping).
#' \item \code{pred} CV prediction values available when \code{prediction} is set.
#' \item \code{pred} CV prediction values available when \code{prediction} is set.
#' It is either vector or matrix (see \code{\link{cb.cv.predict}}).
#' \item \code{models} a liost of the CV folds' models. It is only available with the explicit
#' \item \code{models} a liost of the CV folds' models. It is only available with the explicit
#' setting of the \code{cb.cv.predict(save_models = TRUE)} callback.
#' }
#'
@ -110,32 +110,32 @@
#' max_depth = 3, eta = 1, objective = "binary:logistic")
#' print(cv)
#' print(cv, verbose=TRUE)
#'
#'
#' @export
xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NA,
prediction = FALSE, showsd = TRUE, metrics=list(),
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
verbose = TRUE, print_every_n=1L,
early_stopping_rounds = NULL, maximize = NULL, callbacks = list(), ...) {
check.deprecation(...)
params <- check.booster.params(params, ...)
# TODO: should we deprecate the redundant 'metrics' parameter?
for (m in metrics)
params <- c(params, list("eval_metric" = m))
check.custom.obj()
check.custom.eval()
#if (is.null(params[['eval_metric']]) && is.null(feval))
# stop("Either 'eval_metric' or 'feval' must be provided for CV")
# Check the labels
if ( (inherits(data, 'xgb.DMatrix') && is.null(getinfo(data, 'label'))) ||
(!inherits(data, 'xgb.DMatrix') && is.null(label)))
stop("Labels must be provided for CV either through xgb.DMatrix, or through 'label=' when 'data' is matrix")
# CV folds
if(!is.null(folds)) {
if(!is.list(folds) || length(folds) < 2)
@ -146,7 +146,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
stop("'nfold' must be > 1")
folds <- generate.cv.folds(nfold, nrow(data), stratified, label, params)
}
# Potential TODO: sequential CV
#if (strategy == 'sequential')
# stop('Sequential CV strategy is not yet implemented')
@ -166,7 +166,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
stop_condition <- FALSE
if (!is.null(early_stopping_rounds) &&
!has.callbacks(callbacks, 'cb.early.stop')) {
callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
callbacks <- add.cb(callbacks, cb.early.stop(early_stopping_rounds,
maximize = maximize, verbose = verbose))
}
# CV-predictions callback
@ -177,7 +177,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
# Sort the callbacks into categories
cb <- categorize.callbacks(callbacks)
# create the booster-folds
dall <- xgb.get.DMatrix(data, label, missing)
bst_folds <- lapply(seq_along(folds), function(k) {
@ -197,12 +197,12 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
# those are fixed for CV (no training continuation)
begin_iteration <- 1
end_iteration <- nrounds
# synchronous CV boosting: run CV folds' models within each iteration
for (iteration in begin_iteration:end_iteration) {
for (f in cb$pre_iter) f()
msg <- lapply(bst_folds, function(fd) {
xgb.iter.update(fd$bst, fd$dtrain, iteration - 1, obj)
xgb.iter.eval(fd$bst, fd$watchlist, iteration - 1, feval)
@ -210,9 +210,9 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
msg <- simplify2array(msg)
bst_evaluation <- rowMeans(msg)
bst_evaluation_err <- sqrt(rowMeans(msg^2) - bst_evaluation^2)
for (f in cb$post_iter) f()
if (stop_condition) break
}
for (f in cb$finalize) f(finalize = TRUE)
@ -236,17 +236,17 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
#' Print xgb.cv result
#'
#'
#' Prints formatted results of \code{xgb.cv}.
#'
#'
#' @param x an \code{xgb.cv.synchronous} object
#' @param verbose whether to print detailed data
#' @param ... passed to \code{data.table.print}
#'
#'
#' @details
#' When not verbose, it would only print the evaluation results,
#' When not verbose, it would only print the evaluation results,
#' including the best iteration (when available).
#'
#'
#' @examples
#' data(agaricus.train, package='xgboost')
#' train <- agaricus.train
@ -254,13 +254,13 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
#' eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
#' print(cv)
#' print(cv, verbose=TRUE)
#'
#'
#' @rdname print.xgb.cv
#' @method print xgb.cv.synchronous
#' @export
print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
cat('##### xgb.cv ', length(x$folds), '-folds\n', sep = '')
if (verbose) {
if (!is.null(x$call)) {
cat('call:\n ')
@ -268,8 +268,8 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
}
if (!is.null(x$params)) {
cat('params (as set within xgb.cv):\n')
cat( ' ',
paste(names(x$params),
cat( ' ',
paste(names(x$params),
paste0('"', unlist(x$params), '"'),
sep = ' = ', collapse = ', '), '\n', sep = '')
}
@ -280,9 +280,9 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
print(x)
})
}
for (n in c('niter', 'best_iteration', 'best_ntreelimit')) {
if (is.null(x[[n]]))
if (is.null(x[[n]]))
next
cat(n, ': ', x[[n]], '\n', sep = '')
}
@ -293,10 +293,10 @@ print.xgb.cv.synchronous <- function(x, verbose = FALSE, ...) {
}
}
if (verbose)
if (verbose)
cat('evaluation_log:\n')
print(x$evaluation_log, row.names = FALSE, ...)
if (!is.null(x$best_iteration)) {
cat('Best iteration:\n')
print(x$evaluation_log[x$best_iteration], row.names = FALSE, ...)

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

@ -42,7 +42,7 @@
#' \itemize{
#' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
#' \itemize{
#' \item \code{reg:linear} linear regression (Default).
#' \item \code{reg:squarederror} Regression with squared loss (Default).
#' \item \code{reg:logistic} logistic regression.
#' \item \code{binary:logistic} logistic regression for binary classification. Output probability.
#' \item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.

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

@ -16,7 +16,7 @@ xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
\itemize{
\item \code{objective} objective function, common ones are
\itemize{
\item \code{reg:linear} linear regression
\item \code{reg:squarederror} Regression with squared loss.
\item \code{binary:logistic} logistic regression for classification
}
\item \code{eta} step size of each boosting step

10
R-package/man/xgb.train.Rd
View File

@ -56,7 +56,7 @@ xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
\itemize{
\item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
\itemize{
\item \code{reg:linear} linear regression (Default).
\item \code{reg:squarederror} Regression with squared loss (Default).
\item \code{reg:logistic} logistic regression.
\item \code{binary:logistic} logistic regression for binary classification. Output probability.
\item \code{binary:logitraw} logistic regression for binary classification, output score before logistic transformation.
@ -210,7 +210,7 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
watchlist <- list(train = dtrain, eval = dtest)
## A simple xgb.train example:
param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
param <- list(max_depth = 2, eta = 1, verbosity = 0, nthread = 2,
objective = "binary:logistic", eval_metric = "auc")
bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
@ -231,12 +231,12 @@ evalerror <- function(preds, dtrain) {
# These functions could be used by passing them either:
# as 'objective' and 'eval_metric' parameters in the params list:
param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
param <- list(max_depth = 2, eta = 1, verbosity = 0, nthread = 2,
objective = logregobj, eval_metric = evalerror)
bst <- xgb.train(param, dtrain, nrounds = 2, watchlist)
# or through the ... arguments:
param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2)
param <- list(max_depth = 2, eta = 1, verbosity = 0, nthread = 2)
bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
objective = logregobj, eval_metric = evalerror)
@ -246,7 +246,7 @@ bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
## An xgb.train example of using variable learning rates at each iteration:
param <- list(max_depth = 2, eta = 1, silent = 1, nthread = 2,
param <- list(max_depth = 2, eta = 1, verbosity = 0, nthread = 2,
objective = "binary:logistic", eval_metric = "auc")
my_etas <- list(eta = c(0.5, 0.1))
bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,

16
R-package/tests/testthat/test_dmatrix.R
View File

@ -10,12 +10,12 @@ test_label <- agaricus.test$label[1:100]
test_that("xgb.DMatrix: basic construction", {
# from sparse matrix
dtest1 <- xgb.DMatrix(test_data, label=test_label)
# from dense matrix
# from dense matrix
dtest2 <- xgb.DMatrix(as.matrix(test_data), label=test_label)
expect_equal(getinfo(dtest1, 'label'), getinfo(dtest2, 'label'))
expect_equal(dim(dtest1), dim(dtest2))
#from dense integer matrix
int_data <- as.matrix(test_data)
storage.mode(int_data) <- "integer"
@ -33,7 +33,7 @@ test_that("xgb.DMatrix: saving, loading", {
expect_output(dtest3 <- xgb.DMatrix(tmp_file, silent = TRUE), NA)
unlink(tmp_file)
expect_equal(getinfo(dtest1, 'label'), getinfo(dtest3, 'label'))
# from a libsvm text file
tmp <- c("0 1:1 2:1","1 3:1","0 1:1")
tmp_file <- 'tmp.libsvm'
@ -49,7 +49,7 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
expect_true(setinfo(dtest, 'label', test_label))
labels <- getinfo(dtest, 'label')
expect_equal(test_label, getinfo(dtest, 'label'))
expect_true(length(getinfo(dtest, 'weight')) == 0)
expect_true(length(getinfo(dtest, 'base_margin')) == 0)
@ -57,10 +57,10 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
expect_true(setinfo(dtest, 'base_margin', test_label))
expect_true(setinfo(dtest, 'group', c(50,50)))
expect_error(setinfo(dtest, 'group', test_label))
# providing character values will give a warning
expect_warning( setinfo(dtest, 'weight', rep('a', nrow(test_data))) )
# any other label should error
expect_error(setinfo(dtest, 'asdf', test_label))
})
@ -71,7 +71,7 @@ test_that("xgb.DMatrix: slice, dim", {
dsub1 <- slice(dtest, 1:42)
expect_equal(nrow(dsub1), 42)
expect_equal(ncol(dsub1), ncol(test_data))
dsub2 <- dtest[1:42,]
expect_equal(dim(dtest), dim(test_data))
expect_equal(getinfo(dsub1, 'label'), getinfo(dsub2, 'label'))

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

@ -98,7 +98,7 @@ test_that("SHAP contribution values are not NAN", {
fit <- xgboost(
verbose = 0,
params = list(
objective = "reg:linear",
objective = "reg:squarederror",
eval_metric = "rmse"),
data = as.matrix(subset(d, fold == 2)[, ivs]),
label = subset(d, fold == 2)$y,

4
demo/regression/README.md
View File

@ -6,9 +6,9 @@ Using XGBoost for regression is very similar to using it for binary classificati
The dataset we used is the [computer hardware dataset from UCI repository](https://archive.ics.uci.edu/ml/datasets/Computer+Hardware). The demo for regression is almost the same as the [binary classification demo](../binary_classification), except a little difference in general parameter:
```
# General parameter
# this is the only difference with classification, use reg:linear to do linear regression
# this is the only difference with classification, use reg:squarederror to do linear regression
# when labels are in [0,1] we can also use reg:logistic
objective = reg:linear
objective = reg:squarederror
...
```

4
demo/regression/machine.conf
View File

@ -1,9 +1,9 @@
# General Parameters, see comment for each definition
# choose the tree booster, can also change to gblinear
booster = gbtree
# this is the only difference with classification, use reg:linear to do linear classification
# this is the only difference with classification, use reg:squarederror to do linear classification
# when labels are in [0,1] we can also use reg:logistic
objective = reg:linear
objective = reg:squarederror
# Tree Booster Parameters
# step size shrinkage

13
demo/yearpredMSD/yearpredMSD.conf
View File

@ -1,17 +1,17 @@
# General Parameters, see comment for each definition
# choose the tree booster, can also change to gblinear
booster = gbtree
# this is the only difference with classification, use reg:linear to do linear classification
# this is the only difference with classification, use reg:squarederror to do linear classification
# when labels are in [0,1] we can also use reg:logistic
objective = reg:linear
objective = reg:squarederror
# Tree Booster Parameters
# step size shrinkage
eta = 1.0
# minimum loss reduction required to make a further partition
gamma = 1.0
gamma = 1.0
# minimum sum of instance weight(hessian) needed in a child
min_child_weight = 1
min_child_weight = 1
# maximum depth of a tree
max_depth = 5
@ -20,11 +20,10 @@ base_score = 2001
# the number of round to do boosting
num_round = 100
# 0 means do not save any model except the final round model
save_period = 0
save_period = 0
# The path of training data
data = "yearpredMSD.libsvm.train"
# The path of validation data, used to monitor training process, here [test] sets name of the validation set
eval[test] = "yearpredMSD.libsvm.test"
# The path of test data
# The path of test data
#test:data = "yearpredMSD.libsvm.test"

2
doc/gpu/index.rst
View File

@ -92,7 +92,7 @@ Most of the objective functions implemented in XGBoost can be run on GPU. Follo
+-----------------+-------------+
| Objectives | GPU support |
+-----------------+-------------+
| reg:linear | |tick| |
| reg:squarederror| |tick| |
+-----------------+-------------+
| reg:logistic | |tick| |
+-----------------+-------------+

4
doc/parameter.rst
View File

@ -293,9 +293,9 @@ Learning Task Parameters
************************
Specify the learning task and the corresponding learning objective. The objective options are below:
* ``objective`` [default=reg:linear]
* ``objective`` [default=reg:squarederror]
- ``reg:linear``: linear regression
- ``reg:squarederror``: regression with squared loss
- ``reg:logistic``: logistic regression
- ``binary:logistic``: logistic regression for binary classification, output probability
- ``binary:logitraw``: logistic regression for binary classification, output score before logistic transformation

2
doc/rf.rst
View File

@ -36,7 +36,7 @@ The following parameters must be set to enable random forest training.
Other parameters should be set in a similar way they are set for gradient boosting. For
instance, ``objective`` will typically be ``reg:linear`` for regression and
instance, ``objective`` will typically be ``reg:squarederror`` for regression and
``binary:logistic`` for classification, ``lambda`` should be set according to a desired
regularization weight, etc.

8
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/params/LearningTaskParams.scala
View File

@ -24,8 +24,8 @@ private[spark] trait LearningTaskParams extends Params {
/**
* Specify the learning task and the corresponding learning objective.
* options: reg:linear, reg:logistic, binary:logistic, binary:logitraw, count:poisson,
* multi:softmax, multi:softprob, rank:pairwise, reg:gamma. default: reg:linear
* options: reg:squarederror, reg:logistic, binary:logistic, binary:logitraw, count:poisson,
* multi:softmax, multi:softprob, rank:pairwise, reg:gamma. default: reg:squarederror
*/
final val objective = new Param[String](this, "objective", "objective function used for " +
s"training, options: {${LearningTaskParams.supportedObjective.mkString(",")}",
@ -94,12 +94,12 @@ private[spark] trait LearningTaskParams extends Params {
final def getMaximizeEvaluationMetrics: Boolean = $(maximizeEvaluationMetrics)
setDefault(objective -> "reg:linear", baseScore -> 0.5,
setDefault(objective -> "reg:squarederror", baseScore -> 0.5,
trainTestRatio -> 1.0, numEarlyStoppingRounds -> 0)
}
private[spark] object LearningTaskParams {
val supportedObjective = HashSet("reg:linear", "reg:logistic", "binary:logistic",
val supportedObjective = HashSet("reg:squarederror", "reg:logistic", "binary:logistic",
"binary:logitraw", "count:poisson", "multi:softmax", "multi:softprob", "rank:pairwise",
"rank:ndcg", "rank:map", "reg:gamma", "reg:tweedie")

2
jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/PersistenceSuite.scala
View File

@ -96,7 +96,7 @@ class PersistenceSuite extends FunSuite with PerTest with BeforeAndAfterAll {
val testDM = new DMatrix(Regression.test.iterator)
val paramMap = Map("eta" -> "0.1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> "10", "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> "10", "num_workers" -> numWorkers)
val xgbr = new XGBoostRegressor(paramMap)
val xgbrPath = new File(tempDir, "xgbr").getPath
xgbr.write.overwrite().save(xgbrPath)

18
jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRegressorSuite.scala
View File

@ -36,7 +36,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
"eta" -> "1",
"max_depth" -> "6",
"silent" -> "1",
"objective" -> "reg:linear")
"objective" -> "reg:squarederror")
val model1 = ScalaXGBoost.train(trainingDM, paramMap, round)
val prediction1 = model1.predict(testDM)
@ -69,7 +69,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
"eta" -> "1",
"max_depth" -> "6",
"silent" -> "1",
"objective" -> "reg:linear",
"objective" -> "reg:squarederror",
"num_round" -> round,
"num_workers" -> numWorkers)
@ -80,7 +80,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
.setEta(1)
.setMaxDepth(6)
.setSilent(1)
.setObjective("reg:linear")
.setObjective("reg:squarederror")
.setNumRound(round)
.setNumWorkers(numWorkers)
.fit(trainingDF)
@ -108,7 +108,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("use weight") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val getWeightFromId = udf({id: Int => if (id == 0) 1.0f else 0.001f}, DataTypes.FloatType)
val trainingDF = buildDataFrame(Regression.train)
@ -123,7 +123,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("test predictionLeaf") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val training = buildDataFrame(Regression.train)
val testDF = buildDataFrame(Regression.test)
val groundTruth = testDF.count()
@ -137,7 +137,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("test predictionLeaf with empty column name") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val training = buildDataFrame(Regression.train)
val testDF = buildDataFrame(Regression.test)
val xgb = new XGBoostRegressor(paramMap)
@ -149,7 +149,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("test predictionContrib") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val training = buildDataFrame(Regression.train)
val testDF = buildDataFrame(Regression.test)
val groundTruth = testDF.count()
@ -163,7 +163,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("test predictionContrib with empty column name") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val training = buildDataFrame(Regression.train)
val testDF = buildDataFrame(Regression.test)
val xgb = new XGBoostRegressor(paramMap)
@ -175,7 +175,7 @@ class XGBoostRegressorSuite extends FunSuite with PerTest {
test("test predictionLeaf and predictionContrib") {
val paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear", "num_round" -> 5, "num_workers" -> numWorkers)
"objective" -> "reg:squarederror", "num_round" -> 5, "num_workers" -> numWorkers)
val training = buildDataFrame(Regression.train)
val testDF = buildDataFrame(Regression.test)
val groundTruth = testDF.count()

12
src/objective/regression_obj.cu
View File

@ -128,8 +128,8 @@ class RegLossObj : public ObjFunction {
// register the objective functions
DMLC_REGISTER_PARAMETER(RegLossParam);
XGBOOST_REGISTER_OBJECTIVE(LinearRegression, "reg:linear")
.describe("Linear regression.")
XGBOOST_REGISTER_OBJECTIVE(SquaredLossRegression, "reg:squarederror")
.describe("Regression with squared error.")
.set_body([]() { return new RegLossObj<LinearSquareLoss>(); });
XGBOOST_REGISTER_OBJECTIVE(LogisticRegression, "reg:logistic")
@ -145,7 +145,13 @@ XGBOOST_REGISTER_OBJECTIVE(LogisticRaw, "binary:logitraw")
"before logistic transformation.")
.set_body([]() { return new RegLossObj<LogisticRaw>(); });
// Deprecated GPU functions
// Deprecated functions
XGBOOST_REGISTER_OBJECTIVE(LinearRegression, "reg:linear")
.describe("Regression with squared error.")
.set_body([]() {
LOG(WARNING) << "reg:linear is now deprecated in favor of reg:squarederror.";
return new RegLossObj<LinearSquareLoss>(); });
XGBOOST_REGISTER_OBJECTIVE(GPULinearRegression, "gpu:reg:linear")
.describe("Deprecated. Linear regression (computed on GPU).")
.set_body([]() {

3
tests/cpp/objective/test_objective.cc
View File

@ -1,4 +1,5 @@
// Copyright by Contributors
#include <gtest/gtest.h>
#include <xgboost/objective.h>
#include "../helpers.h"
@ -6,7 +7,7 @@
TEST(Objective, UnknownFunction) {
xgboost::ObjFunction* obj = nullptr;
EXPECT_ANY_THROW(obj = xgboost::ObjFunction::Create("unknown_name"));
EXPECT_NO_THROW(obj = xgboost::ObjFunction::Create("reg:linear"));
EXPECT_NO_THROW(obj = xgboost::ObjFunction::Create("reg:squarederror"));
if (obj) {
delete obj;
}

5
tests/cpp/objective/test_regression_obj.cc
View File

@ -1,12 +1,13 @@
/*!
* Copyright 2017-2018 XGBoost contributors
* Copyright 2017-2019 XGBoost contributors
*/
#include <gtest/gtest.h>
#include <xgboost/objective.h>
#include "../helpers.h"
TEST(Objective, DeclareUnifiedTest(LinearRegressionGPair)) {
xgboost::ObjFunction * obj = xgboost::ObjFunction::Create("reg:linear");
xgboost::ObjFunction * obj = xgboost::ObjFunction::Create("reg:squarederror");
std::vector<std::pair<std::string, std::string> > args;
obj->Configure(args);
CheckObjFunction(obj,

11
tests/python/regression_test_utilities.py
View File

@ -132,15 +132,16 @@ def run_suite(param, num_rounds=10, select_datasets=None, scale_features=False):
Run the given parameters on a range of datasets. Objective and eval metric will be automatically set
"""
datasets = [
Dataset("Boston", get_boston, "reg:linear", "rmse"),
Dataset("Boston", get_boston, "reg:squarederror", "rmse"),
Dataset("Digits", get_digits, "multi:softmax", "merror"),
Dataset("Cancer", get_cancer, "binary:logistic", "error"),
Dataset("Sparse regression", get_sparse, "reg:linear", "rmse"),
Dataset("Sparse regression", get_sparse, "reg:squarederror", "rmse"),
Dataset("Sparse regression with weights", get_sparse_weights,
"reg:linear", "rmse", has_weights=True),
"reg:squarederror", "rmse", has_weights=True),
Dataset("Small weights regression", get_small_weights,
"reg:linear", "rmse", has_weights=True),
Dataset("Boston External Memory", get_boston, "reg:linear", "rmse",
"reg:squarederror", "rmse", has_weights=True),
Dataset("Boston External Memory", get_boston,
"reg:squarederror", "rmse",
use_external_memory=True)
]

14
tests/python/test_basic.py
View File

@ -38,7 +38,7 @@ class TestBasic(unittest.TestCase):
def test_basic(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
@ -85,7 +85,7 @@ class TestBasic(unittest.TestCase):
def test_record_results(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
@ -102,7 +102,7 @@ class TestBasic(unittest.TestCase):
def test_multiclass(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'num_class': 2}
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'num_class': 2}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@ -273,7 +273,7 @@ class TestBasic(unittest.TestCase):
def test_cv(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# return np.ndarray
@ -283,7 +283,7 @@ class TestBasic(unittest.TestCase):
def test_cv_no_shuffle(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# return np.ndarray
@ -294,7 +294,7 @@ class TestBasic(unittest.TestCase):
def test_cv_explicit_fold_indices(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective':
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'objective':
'binary:logistic'}
folds = [
# Train Test
@ -310,7 +310,7 @@ class TestBasic(unittest.TestCase):
def test_cv_explicit_fold_indices_labels(self):
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'objective':
'reg:linear'}
'reg:squarederror'}
N = 100
F = 3
dm = xgb.DMatrix(data=np.random.randn(N, F), label=np.arange(N))

23
tests/python/test_basic_models.py
View File

@ -11,7 +11,7 @@ rng = np.random.RandomState(1994)
class TestModels(unittest.TestCase):
def test_glm(self):
param = {'silent': 1, 'objective': 'binary:logistic',
param = {'verbosity': 0, 'objective': 'binary:logistic',
'booster': 'gblinear', 'alpha': 0.0001, 'lambda': 1, 'nthread': 1}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 4
@ -26,7 +26,7 @@ class TestModels(unittest.TestCase):
def test_dart(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 5, 'objective': 'binary:logistic', 'booster': 'dart', 'silent': False}
param = {'max_depth': 5, 'objective': 'binary:logistic', 'booster': 'dart', 'verbosity': 1}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@ -51,7 +51,7 @@ class TestModels(unittest.TestCase):
# check whether sample_type and normalize_type work
num_round = 50
param['silent'] = True
param['verbosity'] = 0
param['learning_rate'] = 0.1
param['rate_drop'] = 0.1
preds_list = []
@ -74,7 +74,8 @@ class TestModels(unittest.TestCase):
# learning_rates as a list
# init eta with 0 to check whether learning_rates work
param = {'max_depth': 2, 'eta': 0, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'eta': 0, 'verbosity': 0,
'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0.8, 0.7, 0.6, 0.5],
evals_result=evals_result)
@ -84,7 +85,8 @@ class TestModels(unittest.TestCase):
assert eval_errors[0] > eval_errors[-1]
# init learning_rate with 0 to check whether learning_rates work
param = {'max_depth': 2, 'learning_rate': 0, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'learning_rate': 0, 'verbosity': 0,
'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0.8, 0.7, 0.6, 0.5],
evals_result=evals_result)
@ -94,7 +96,7 @@ class TestModels(unittest.TestCase):
assert eval_errors[0] > eval_errors[-1]
# check if learning_rates override default value of eta/learning_rate
param = {'max_depth': 2, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'verbosity': 0, 'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0, 0, 0, 0],
evals_result=evals_result)
@ -111,7 +113,7 @@ class TestModels(unittest.TestCase):
assert isinstance(bst, xgb.core.Booster)
def test_custom_objective(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1}
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@ -152,7 +154,8 @@ class TestModels(unittest.TestCase):
def test_multi_eval_metric(self):
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
param = {'max_depth': 2, 'eta': 0.2, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'eta': 0.2, 'verbosity': 0,
'objective': 'binary:logistic'}
param['eval_metric'] = ["auc", "logloss", 'error']
evals_result = {}
bst = xgb.train(param, dtrain, 4, watchlist, evals_result=evals_result)
@ -161,7 +164,7 @@ class TestModels(unittest.TestCase):
assert set(evals_result['eval'].keys()) == {'auc', 'error', 'logloss'}
def test_fpreproc(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
num_round = 2
@ -175,7 +178,7 @@ class TestModels(unittest.TestCase):
metrics={'auc'}, seed=0, fpreproc=fpreproc)
def test_show_stdv(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
num_round = 2
xgb.cv(param, dtrain, num_round, nfold=5,

2
tests/python/test_early_stopping.py
View File

@ -52,7 +52,7 @@ class TestEarlyStopping(unittest.TestCase):
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,

8
tests/python/test_eval_metrics.py
View File

@ -9,25 +9,25 @@ rng = np.random.RandomState(1337)
class TestEvalMetrics(unittest.TestCase):
xgb_params_01 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': 'error'
}
xgb_params_02 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['error']
}
xgb_params_03 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['rmse', 'error']
}
xgb_params_04 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['error', 'rmse']
}

2
tests/python/test_interaction_constraints.py
View File

@ -18,7 +18,7 @@ class TestInteractionConstraints(unittest.TestCase):
X = np.column_stack((x1, x2, x3))
dtrain = xgboost.DMatrix(X, label=y)
params = {'max_depth': 3, 'eta': 0.1, 'nthread': 2, 'silent': 1,
params = {'max_depth': 3, 'eta': 0.1, 'nthread': 2, 'verbosity': 0,
'interaction_constraints': '[[0, 1]]'}
num_boost_round = 100
# Fit a model that only allows interaction between x1 and x2

4
tests/python/test_linear.py
View File

@ -30,7 +30,7 @@ def xgb_get_weights(bst):
def assert_regression_result(results, tol):
regression_results = [r for r in results if
r["param"]["objective"] == "reg:linear"]
r["param"]["objective"] == "reg:squarederror"]
for res in regression_results:
X = scale(res["dataset"].X,
with_mean=isinstance(res["dataset"].X, np.ndarray))
@ -52,7 +52,7 @@ def assert_regression_result(results, tol):
# TODO: More robust classification tests
def assert_classification_result(results):
classification_results = [r for r in results if
r["param"]["objective"] != "reg:linear"]
r["param"]["objective"] != "reg:squarederror"]
for res in classification_results:
# Check accuracy is reasonable
assert res["eval"][-1] < 0.5, (res["dataset"].name, res["eval"][-1])

3
tests/python/test_parse_tree.py
View File

@ -16,7 +16,8 @@ class TestTreesToDataFrame(unittest.TestCase):
def build_model(self, max_depth, num_round):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
param = {'max_depth': max_depth, 'objective': 'binary:logistic', 'silent': False}
param = {'max_depth': max_depth, 'objective': 'binary:logistic',
'verbosity': 1}
num_round = num_round
bst = xgb.train(param, dtrain, num_round)
return bst

2
tests/python/test_shap.py
View File

@ -51,7 +51,7 @@ class TestSHAP(unittest.TestCase):
def fn(max_depth, num_rounds):
# train
params = {'max_depth': max_depth, 'eta': 1, 'silent': 1}
params = {'max_depth': max_depth, 'eta': 1, 'verbosity': 0}
bst = xgb.train(params, dtrain, num_boost_round=num_rounds)
# predict

2
tests/python/test_sparse_dmatrix.py
View File

@ -4,7 +4,7 @@ from scipy.sparse import rand
rng = np.random.RandomState(1)
param = {'max_depth': 3, 'objective': 'binary:logistic', 'silent': 1}
param = {'max_depth': 3, 'objective': 'binary:logistic', 'verbosity': 0}
def test_sparse_dmatrix_csr():

6
tests/python/test_training_continuation.py
View File

@ -11,18 +11,18 @@ class TestTrainingContinuation(unittest.TestCase):
num_parallel_tree = 3
xgb_params_01 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
}
xgb_params_02 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'num_parallel_tree': num_parallel_tree
}
xgb_params_03 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'num_class': 5,
'num_parallel_tree': num_parallel_tree

9
tests/python/test_tree_regularization.py
View File

@ -10,7 +10,8 @@ train_data = xgb.DMatrix(np.array([[1]]), label=np.array([1]))
class TestTreeRegularization(unittest.TestCase):
def test_alpha(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 0,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 0,
'alpha': 0.1
@ -27,7 +28,8 @@ class TestTreeRegularization(unittest.TestCase):
def test_lambda(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 0,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 1,
'alpha': 0
@ -44,7 +46,8 @@ class TestTreeRegularization(unittest.TestCase):
def test_alpha_and_lambda(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 1,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 1,
'alpha': 0.1

4
tests/python/test_updaters.py
View File

@ -33,7 +33,7 @@ class TestUpdaters(unittest.TestCase):
'max_bin': [2, 256],
'grow_policy': ['depthwise', 'lossguide'],
'max_leaves': [64, 0],
'silent': [1]}
'verbosity': [0]}
for param in parameter_combinations(variable_param):
result = run_suite(param)
assert_results_non_increasing(result, 1e-2)
@ -45,7 +45,7 @@ class TestUpdaters(unittest.TestCase):
ag_param = {'max_depth': 2,
'tree_method': 'hist',
'eta': 1,
'silent': 1,
'verbosity': 0,
'objective': 'binary:logistic',
'eval_metric': 'auc'}
hist_res = {}

14
tests/python/test_with_pandas.py
View File

@ -120,7 +120,7 @@ class TestPandas(unittest.TestCase):
def test_cv_as_pandas(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10)
@ -143,19 +143,19 @@ class TestPandas(unittest.TestCase):
u'train-error-mean', u'train-error-std'])
assert cv.columns.equals(exp)
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': 'auc'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, as_pandas=True)
assert 'eval_metric' in params
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, as_pandas=True)
assert 'eval_metric' in params
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, early_stopping_rounds=1)
@ -163,19 +163,19 @@ class TestPandas(unittest.TestCase):
assert 'auc' in cv.columns[0]
assert cv.shape[0] < 10
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics='auc')
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics=['auc'])
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics='error')

3
tests/python/test_with_sklearn.py
View File

@ -603,7 +603,8 @@ def test_RFECV():
# Regression
X, y = load_boston(return_X_y=True)
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10, n_jobs=1, objective='reg:linear',
n_estimators=10, n_jobs=1,
objective='reg:squarederror',
random_state=0, verbosity=0)
rfecv = RFECV(
estimator=bst, step=1, cv=3, scoring='neg_mean_squared_error')