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

[R] Redesigned xgboost() interface skeleton (#10456)

Browse Source 
---------

Co-authored-by: Michael Mayer <mayermichael79@gmail.com>
This commit is contained in:
david-cortes
2024-07-15 12:44:58 +02:00
committed by GitHub
parent 17c64300e3
commit ab982e7873
35 changed files with 1997 additions and 242 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
R-package/man/print.xgb.Booster.Rd
View File

@@ -21,9 +21,8 @@ Print information about \code{xgb.Booster}.
data(agaricus.train, package = "xgboost")
train <- agaricus.train
bst <- xgboost(
data = train$data,
label = train$label,
bst <- xgb.train(
data = xgb.DMatrix(train$data, label = train$label),
max_depth = 2,
eta = 1,
nthread = 2,

5
R-package/man/xgb.attr.Rd
View File

@@ -64,9 +64,8 @@ example of these behaviors).
data(agaricus.train, package = "xgboost")
train <- agaricus.train
bst <- xgboost(
data = train$data,
label = train$label,
bst <- xgb.train(
data = xgb.DMatrix(train$data, label = train$label),
max_depth = 2,
eta = 1,
nthread = 2,

5
R-package/man/xgb.config.Rd
View File

@@ -35,9 +35,8 @@ nthread <- 1
data.table::setDTthreads(nthread)
train <- agaricus.train
bst <- xgboost(
data = train$data,
label = train$label,
bst <- xgb.train(
data = xgb.DMatrix(train$data, label = train$label),
max_depth = 2,
eta = 1,
nthread = nthread,

4
R-package/man/xgb.dump.Rd
View File

@@ -49,8 +49,8 @@ data(agaricus.train, package='xgboost')
data(agaricus.test, package='xgboost')
train <- agaricus.train
test <- agaricus.test
bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
bst <- xgb.train(data = xgb.DMatrix(train$data, label = train$label), max_depth = 2,
eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
# save the model in file 'xgb.model.dump'
dump_path = file.path(tempdir(), 'model.dump')
xgb.dump(bst, dump_path, with_stats = TRUE)

26
R-package/man/xgb.importance.Rd
View File

@@ -70,9 +70,8 @@ be on the same scale (which is also recommended when using L1 or L2 regularizati
# binomial classification using "gbtree":
data(agaricus.train, package = "xgboost")
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
max_depth = 2,
eta = 1,
nthread = 2,
@@ -83,9 +82,8 @@ bst <- xgboost(
xgb.importance(model = bst)
# binomial classification using "gblinear":
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
booster = "gblinear",
eta = 0.3,
nthread = 1,
@@ -97,9 +95,11 @@ xgb.importance(model = bst)
# multiclass classification using "gbtree":
nclass <- 3
nrounds <- 10
mbst <- xgboost(
data = as.matrix(iris[, -5]),
label = as.numeric(iris$Species) - 1,
mbst <- xgb.train(
data = xgb.DMatrix(
as.matrix(iris[, -5]),
label = as.numeric(iris$Species) - 1
),
max_depth = 3,
eta = 0.2,
nthread = 2,
@@ -123,9 +123,11 @@ xgb.importance(
)
# multiclass classification using "gblinear":
mbst <- xgboost(
data = scale(as.matrix(iris[, -5])),
label = as.numeric(iris$Species) - 1,
mbst <- xgb.train(
data = xgb.DMatrix(
scale(as.matrix(iris[, -5])),
label = as.numeric(iris$Species) - 1
),
booster = "gblinear",
eta = 0.2,
nthread = 1,

5
R-package/man/xgb.model.dt.tree.Rd
View File

@@ -63,9 +63,8 @@ data(agaricus.train, package = "xgboost")
nthread <- 1
data.table::setDTthreads(nthread)
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
max_depth = 2,
eta = 1,
nthread = nthread,

5
R-package/man/xgb.parameters.Rd
View File

@@ -33,9 +33,8 @@ will reset its number of rounds indicator to zero.
data(agaricus.train, package = "xgboost")
train <- agaricus.train
bst <- xgboost(
data = train$data,
label = train$label,
bst <- xgb.train(
data = xgb.DMatrix(train$data, label = train$label),
max_depth = 2,
eta = 1,
nthread = 2,

5
R-package/man/xgb.plot.deepness.Rd
View File

@@ -73,9 +73,8 @@ nthread <- 2
data.table::setDTthreads(nthread)
## Change max_depth to a higher number to get a more significant result
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
max_depth = 6,
nthread = nthread,
nrounds = 50,

5
R-package/man/xgb.plot.importance.Rd
View File

@@ -88,9 +88,8 @@ data(agaricus.train)
nthread <- 2
data.table::setDTthreads(nthread)
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
max_depth = 3,
eta = 1,
nthread = nthread,

5
R-package/man/xgb.plot.multi.trees.Rd
View File

@@ -67,9 +67,8 @@ data(agaricus.train, package = "xgboost")
nthread <- 2
data.table::setDTthreads(nthread)
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
max_depth = 15,
eta = 1,
nthread = nthread,

10
R-package/man/xgb.plot.shap.Rd
View File

@@ -135,9 +135,8 @@ nthread <- 1
data.table::setDTthreads(nthread)
nrounds <- 20
bst <- xgboost(
agaricus.train$data,
agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, agaricus.train$label),
nrounds = nrounds,
eta = 0.1,
max_depth = 3,
@@ -161,9 +160,8 @@ x <- as.matrix(iris[, -5])
set.seed(123)
is.na(x[sample(nrow(x) * 4, 30)]) <- TRUE # introduce some missing values
mbst <- xgboost(
data = x,
label = as.numeric(iris$Species) - 1,
mbst <- xgb.train(
data = xgb.DMatrix(x, label = as.numeric(iris$Species) - 1),
nrounds = nrounds,
max_depth = 2,
eta = 0.3,

5
R-package/man/xgb.plot.tree.Rd
View File

@@ -96,9 +96,8 @@ This function uses \href{https://www.graphviz.org/}{GraphViz} as DiagrammeR back
\examples{
data(agaricus.train, package = "xgboost")
bst <- xgboost(
data = agaricus.train$data,
label = agaricus.train$label,
bst <- xgb.train(
data = xgb.DMatrix(agaricus.train$data, agaricus.train$label),
max_depth = 3,
eta = 1,
nthread = 2,

35
R-package/man/xgb.train.Rd
View File

@@ -1,8 +1,7 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/xgb.train.R, R/xgboost.R
% Please edit documentation in R/xgb.train.R
\name{xgb.train}
\alias{xgb.train}
\alias{xgboost}
\title{eXtreme Gradient Boosting Training}
\usage{
xgb.train(
@@ -22,24 +21,6 @@ xgb.train(
callbacks = list(),
...
)
xgboost(
data = NULL,
label = NULL,
missing = NA,
weight = NULL,
params = list(),
nrounds,
verbose = 1,
print_every_n = 1L,
early_stopping_rounds = NULL,
maximize = NULL,
save_period = NULL,
save_name = "xgboost.model",
xgb_model = NULL,
callbacks = list(),
...
)
}
\arguments{
\item{params}{the list of parameters. The complete list of parameters is
@@ -240,15 +221,6 @@ to customize the training process.
}\if{html}{\out{</div>}}}
\item{...}{other parameters to pass to \code{params}.}
\item{label}{vector of response values. Should not be provided when data is
a local data file name or an \code{xgb.DMatrix}.}
\item{missing}{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.
This parameter is only used when input is a dense matrix.}
\item{weight}{a vector indicating the weight for each row of the input.}
}
\value{
An object of class \code{xgb.Booster}.
@@ -383,9 +355,8 @@ bst <- xgb.train(param, dtrain, nrounds = 25, evals = evals,
early_stopping_rounds = 3)
## An 'xgboost' interface example:
bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label,
max_depth = 2, eta = 1, nthread = nthread, nrounds = 2,
objective = "binary:logistic")
bst <- xgboost(x = agaricus.train$data, y = factor(agaricus.train$label),
params = list(max_depth = 2, eta = 1), nthread = nthread, nrounds = 2)
pred <- predict(bst, agaricus.test$data)
}

213
R-package/man/xgboost.Rd Normal file
View File

@@ -0,0 +1,213 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/xgboost.R
\name{xgboost}
\alias{xgboost}
\title{Fit XGBoost Model}
\usage{
xgboost(
x,
y,
objective = NULL,
nrounds = 100L,
weights = NULL,
verbosity = 0L,
nthreads = parallel::detectCores(),
seed = 0L,
monotone_constraints = NULL,
interaction_constraints = NULL,
feature_weights = NULL,
base_margin = NULL,
...
)
}
\arguments{
\item{x}{The features / covariates. Can be passed as:\itemize{
\item A numeric or integer `matrix`.
\item A `data.frame`, in which all columns are one of the following types:\itemize{
\item `numeric`
\item `integer`
\item `logical`
\item `factor`
}
Columns of `factor` type will be assumed to be categorical, while other column types will
be assumed to be numeric.
\item A sparse matrix from the `Matrix` package, either as `dgCMatrix` or `dgRMatrix` class.
}
Note that categorical features are only supported for `data.frame` inputs, and are automatically
determined based on their types. See \link{xgb.train} with \link{xgb.DMatrix} for more flexible
variants that would allow something like categorical features on sparse matrices.}
\item{y}{The response variable. Allowed values are:\itemize{
\item A numeric or integer vector (for regression tasks).
\item A factor or character vector (for binary and multi-class classification tasks).
\item A logical (boolean) vector (for binary classification tasks).
\item A numeric or integer matrix or `data.frame` with numeric/integer columns
(for multi-task regression tasks).
\item A `Surv` object from the `survival` package (for survival tasks).
}
If `objective` is `NULL`, the right task will be determined automatically based on
the class of `y`.
If `objective` is not `NULL`, it must match with the type of `y` - e.g. `factor` types of `y`
can only be used with classification objectives and vice-versa.
For binary classification, the last factor level of `y` will be used as the "positive"
class - that is, the numbers from `predict` will reflect the probabilities of belonging to this
class instead of to the first factor level. If `y` is a `logical` vector, then `TRUE` will be
set as the last level.}
\item{objective}{Optimization objective to minimize based on the supplied data, to be passed
by name as a string / character (e.g. `reg:absoluteerror`). See the
\href{https://xgboost.readthedocs.io/en/stable/parameter.html#learning-task-parameters}{
Learning Task Parameters} page for more detailed information on allowed values.
If `NULL` (the default), will be automatically determined from `y` according to the following
logic:\itemize{
\item If `y` is a factor with 2 levels, will use `binary:logistic`.
\item If `y` is a factor with more than 2 levels, will use `multi:softprob` (number of classes
will be determined automatically, should not be passed under `params`).
\item If `y` is a `Surv` object from the `survival` package, will use `survival:aft` (note that
the only types supported are left / right / interval censored).
\item Otherwise, will use `reg:squarederror`.
}
If `objective` is not `NULL`, it must match with the type of `y` - e.g. `factor` types of `y`
can only be used with classification objectives and vice-versa.
Note that not all possible `objective` values supported by the core XGBoost library are allowed
here - for example, objectives which are a variation of another but with a different default
prediction type (e.g. `multi:softmax` vs. `multi:softprob`) are not allowed, and neither are
ranking objectives, nor custom objectives at the moment.}
\item{nrounds}{Number of boosting iterations / rounds.
Note that the number of default boosting rounds here is not automatically tuned, and different
problems will have vastly different optimal numbers of boosting rounds.}
\item{weights}{Sample weights for each row in `x` and `y`. If `NULL` (the default), each row
will have the same weight.
If not `NULL`, should be passed as a numeric vector with length matching to the number of
rows in `x`.}
\item{verbosity}{Verbosity of printing messages. Valid values of 0 (silent), 1 (warning),
2 (info), and 3 (debug).}
\item{nthreads}{Number of parallel threads to use. If passing zero, will use all CPU threads.}
\item{seed}{Seed to use for random number generation. If passing `NULL`, will draw a random
number using R's PRNG system to use as seed.}
\item{monotone_constraints}{Optional monotonicity constraints for features.
Can be passed either as a named list (when `x` has column names), or as a vector. If passed
as a vector and `x` has column names, will try to match the elements by name.
A value of `+1` for a given feature makes the model predictions / scores constrained to be
a monotonically increasing function of that feature (that is, as the value of the feature
increases, the model prediction cannot decrease), while a value of `-1` makes it a monotonically
decreasing function. A value of zero imposes no constraint.
The input for `monotone_constraints` can be a subset of the columns of `x` if named, in which
case the columns that are not referred to in `monotone_constraints` will be assumed to have
a value of zero (no constraint imposed on the model for those features).
See the tutorial \href{https://xgboost.readthedocs.io/en/stable/tutorials/monotonic.html}{
Monotonic Constraints} for a more detailed explanation.}
\item{interaction_constraints}{Constraints for interaction representing permitted interactions.
The constraints must be specified in the form of a list of vectors referencing columns in the
data, e.g. `list(c(1, 2), c(3, 4, 5))` (with these numbers being column indices, numeration
starting at 1 - i.e. the first sublist references the first and second columns) or
`list(c("Sepal.Length", "Sepal.Width"), c("Petal.Length", "Petal.Width"))` (references
columns by names), where each vector is a group of indices of features that are allowed to
interact with each other.
See the tutorial
\href{https://xgboost.readthedocs.io/en/stable/tutorials/feature_interaction_constraint.html}{
Feature Interaction Constraints} for more information.}
\item{feature_weights}{Feature weights for column sampling.
Can be passed either as a vector with length matching to columns of `x`, or as a named
list (only if `x` has column names) with names matching to columns of 'x'. If it is a
named vector, will try to match the entries to column names of `x` by name.
If `NULL` (the default), all columns will have the same weight.}
\item{base_margin}{Base margin used for boosting from existing model.
If passing it, will start the gradient boosting procedure from the scores that are provided
here - for example, one can pass the raw scores from a previous model, or some per-observation
offset, or similar.
Should be either a numeric vector or numeric matrix (for multi-class and multi-target objectives)
with the same number of rows as `x` and number of columns corresponding to number of optimization
targets, and should be in the untransformed scale (for example, for objective `binary:logistic`,
it should have log-odds, not probabilities; and for objective `multi:softprob`, should have
number of columns matching to number of classes in the data).
Note that, if it contains more than one column, then columns will not be matched by name to
the corresponding `y` - `base_margin` should have the same column order that the model will use
(for example, for objective `multi:softprob`, columns of `base_margin` will be matched against
`levels(y)` by their position, regardless of what `colnames(base_margin)` returns).
If `NULL`, will start from zero, but note that for most objectives, an intercept is usually
added (controllable through parameter `base_score` instead) when `base_margin` is not passed.}
\item{...}{Other training parameters. See the online documentation
\href{https://xgboost.readthedocs.io/en/stable/parameter.html}{XGBoost Parameters} for
details about possible values and what they do.
Note that not all possible values from the core XGBoost library are allowed as `params` for
'xgboost()' - in particular, values which require an already-fitted booster object (such as
`process_type`) are not accepted here.}
}
\value{
A model object, inheriting from both `xgboost` and `xgb.Booster`. Compared to the regular
`xgb.Booster` model class produced by \link{xgb.train}, this `xgboost` class will have an
additional attribute `metadata` containing information which is used for formatting prediction
outputs, such as class names for classification problems.
}
\description{
Fits an XGBoost model (boosted decision tree ensemble) to given x/y data.
See the tutorial \href{https://xgboost.readthedocs.io/en/stable/tutorials/model.html}{
Introduction to Boosted Trees} for a longer explanation of what XGBoost does.
This function is intended to provide a more user-friendly interface for XGBoost that follows
R's conventions for model fitting and predictions, but which doesn't expose all of the
possible functionalities of the core XGBoost library.
See \link{xgb.train} for a more flexible low-level alternative which is similar across different
language bindings of XGBoost and which exposes the full library's functionalities.
}
\details{
For package authors using `xgboost` as a dependency, it is highly recommended to use
\link{xgb.train} in package code instead of `xgboost()`, since it has a more stable interface
and performs fewer data conversions and copies along the way.
}
\examples{
library(xgboost)
data(mtcars)
# Fit a small regression model on the mtcars data
model_regression <- xgboost(mtcars[, -1], mtcars$mpg, nthreads = 1, nrounds = 3)
predict(model_regression, mtcars, validate_features = TRUE)
# Task objective is determined automatically according to the type of 'y'
data(iris)
model_classif <- xgboost(iris[, -5], iris$Species, nthreads = 1, nrounds = 5)
predict(model_classif, iris, validate_features = TRUE)
}
\references{
\itemize{
\item Chen, Tianqi, and Carlos Guestrin. "Xgboost: A scalable tree boosting system."
Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and
data mining. 2016.
\item \url{https://xgboost.readthedocs.io/en/stable/}
}
}