lgb.train.Rd

% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.cv.R, R/lgb.train.R, R/lightgbm.R
\name{lgb.cv}
\alias{lgb.cv}
\alias{lgb.train}
\alias{lightgbm}
\title{Main CV logic for LightGBM}
\usage{
lgb.cv(params = list(), data, nrounds = 10, nfold = 3, label = NULL,
  weight = NULL, obj = NULL, eval = NULL, verbose = 1, record = TRUE,
  eval_freq = 1L, showsd = TRUE, stratified = TRUE, folds = NULL,
  init_model = NULL, colnames = NULL, categorical_feature = NULL,
  early_stopping_rounds = NULL, callbacks = list(), ...)

lgb.train(params = list(), data, nrounds = 10, valids = list(),
  obj = NULL, eval = NULL, verbose = 1, record = TRUE, eval_freq = 1L,
  init_model = NULL, colnames = NULL, categorical_feature = NULL,
  early_stopping_rounds = NULL, callbacks = list(), ...)

lightgbm(data, label = NULL, weight = NULL, params = list(),
  nrounds = 10, verbose = 1, eval_freq = 1L,
  early_stopping_rounds = NULL, save_name = "lightgbm.model",
  init_model = NULL, callbacks = list(), ...)
}
\arguments{
\item{params}{List of parameters}

\item{data}{a \code{lgb.Dataset} object, used for CV}

\item{nrounds}{number of CV rounds}

\item{nfold}{the original dataset is randomly partitioned into \code{nfold} equal size subsamples.}

\item{label}{vector of response values. Should be provided only when data is an R-matrix.}

\item{weight}{vector of response values. If not NULL, will set to dataset}

\item{obj}{objective function, can be character or custom objective function. Examples include 
\code{regression}, \code{regression_l1}, \code{huber},
\code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}

\item{eval}{evaluation function, can be (list of) character or custom eval function}

\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}

\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}

\item{eval_freq}{evalutaion output frequence, only effect when verbose > 0}

\item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}

\item{stratified}{a \code{boolean} indicating whether sampling of folds should be stratified
by the values of outcome labels.}

\item{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,
the \code{nfold} and \code{stratified} parameters are ignored.}

\item{init_model}{path of model file of \code{lgb.Booster} object, will continue train from this model}

\item{colnames}{feature names, if not null, will use this to overwrite the names in dataset}

\item{categorical_feature}{list of str or int
type int represents index,
type str represents feature names}

\item{early_stopping_rounds}{int
Activates early stopping.
Requires at least one validation data and one metric
If there's more than one, will check all of them
Returns the model with (best_iter + early_stopping_rounds)
If early stopping occurs, the model will have 'best_iter' field}

\item{callbacks}{list of callback functions
List of callback functions that are applied at each iteration.}

\item{...}{other parameters, see parameters.md for more informations}

\item{valids}{a list of \code{lgb.Dataset} objects, used for validation}

\item{boosting}{boosting type. \code{gbdt}, \code{dart}}

\item{num_leaves}{number of leaves in one tree. defaults to 127}

\item{max_depth}{Limit the max depth for tree model. This is used to deal with overfit when #data is small. 
Tree still grow by leaf-wise.}

\item{num_threads}{Number of threads for LightGBM. For the best speed, set this to the number of real CPU cores, not the number of threads (most CPU using hyper-threading to generate 2 threads per CPU core).}

\item{params}{List of parameters}

\item{data}{a \code{lgb.Dataset} object, used for training}

\item{nrounds}{number of training rounds}

\item{obj}{objective function, can be character or custom objective function. Examples include 
\code{regression}, \code{regression_l1}, \code{huber},
\code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}

\item{boosting}{boosting type. \code{gbdt}, \code{dart}}

\item{num_leaves}{number of leaves in one tree. defaults to 127}

\item{max_depth}{Limit the max depth for tree model. This is used to deal with overfit when #data is small. 
Tree still grow by leaf-wise.}

\item{num_threads}{Number of threads for LightGBM. For the best speed, set this to the number of real CPU cores, not the number of threads (most CPU using hyper-threading to generate 2 threads per CPU core).}

\item{eval}{evaluation function, can be (a list of) character or custom eval function}

\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}

\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}

\item{eval_freq}{evalutaion output frequency, only effect when verbose > 0}

\item{init_model}{path of model file of \code{lgb.Booster} object, will continue training from this model}

\item{colnames}{feature names, if not null, will use this to overwrite the names in dataset}

\item{categorical_feature}{list of str or int
type int represents index,
type str represents feature names}

\item{early_stopping_rounds}{int
Activates early stopping.
Requires at least one validation data and one metric
If there's more than one, will check all of them
Returns the model with (best_iter + early_stopping_rounds)
If early stopping occurs, the model will have 'best_iter' field}

\item{callbacks}{list of callback functions
List of callback functions that are applied at each iteration.}

\item{...}{other parameters, see parameters.md for more informations}
}
\value{
a trained model \code{lgb.CVBooster}.

a trained booster model \code{lgb.Booster}.
}
\description{
Main CV logic for LightGBM

Main training logic for LightGBM

Simple interface for training an lightgbm model.
Its documentation is combined with lgb.train.
}
\examples{
\dontrun{
  library(lightgbm)
  data(agaricus.train, package='lightgbm')
  train <- agaricus.train
  dtrain <- lgb.Dataset(train$data, label=train$label)
  params <- list(objective="regression", metric="l2")
  model <- lgb.cv(params, dtrain, 10, nfold=5, min_data=1, learning_rate=1, early_stopping_rounds=10)
}
\dontrun{
  library(lightgbm)
  data(agaricus.train, package='lightgbm')
  train <- agaricus.train
  dtrain <- lgb.Dataset(train$data, label=train$label)
  data(agaricus.test, package='lightgbm')
  test <- agaricus.test
  dtest <- lgb.Dataset.create.valid(dtrain, test$data, label=test$label)
  params <- list(objective="regression", metric="l2")
  valids <- list(test=dtest)
  model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
}
}