lgb.train.Rd

% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.train.R
\name{lgb.train}
\alias{lgb.train}
\title{Main training logic for LightGBM}
\usage{
lgb.train(
  params = list(),
  data,
  nrounds = 100L,
  valids = list(),
  obj = NULL,
  eval = NULL,
  verbose = 1L,
  record = TRUE,
  eval_freq = 1L,
  init_model = NULL,
  colnames = NULL,
  categorical_feature = NULL,
  early_stopping_rounds = NULL,
  callbacks = list(),
  reset_data = FALSE,
  ...
)
}
\arguments{
\item{params}{a list of parameters. See \href{https://lightgbm.readthedocs.io/en/latest/Parameters.html}{
the "Parameters" section of the documentation} for a list of parameters and valid values.}

\item{data}{a \code{lgb.Dataset} object, used for training. Some functions, such as \code{\link{lgb.cv}},
may allow you to pass other types of data like \code{matrix} and then separately supply
\code{label} as a keyword argument.}

\item{nrounds}{number of training rounds}

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

\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(s). This can be a character vector, function, or list with a mixture of
            strings and functions.

            \itemize{
                \item{\bold{a. character vector}:
                    If you provide a character vector to this argument, it should contain strings with valid
                    evaluation metrics.
                    See \href{https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric}{
                    The "metric" section of the documentation}
                    for a list of valid metrics.
                }
                \item{\bold{b. function}:
                     You can provide a custom evaluation function. This
                     should accept the keyword arguments \code{preds} and \code{dtrain} and should return a named
                     list with three elements:
                     \itemize{
                         \item{\code{name}: A string with the name of the metric, used for printing
                             and storing results.
                         }
                         \item{\code{value}: A single number indicating the value of the metric for the
                             given predictions and true values
                         }
                         \item{
                             \code{higher_better}: A boolean indicating whether higher values indicate a better fit.
                             For example, this would be \code{FALSE} for metrics like MAE or RMSE.
                         }
                     }
                }
                \item{\bold{c. list}:
                    If a list is given, it should only contain character vectors and functions.
                    These should follow the requirements from the descriptions above.
                }
            }}

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

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

\item{eval_freq}{evaluation 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}{categorical features. This can either be a character vector of feature
names or an integer vector with the indices of the features (e.g.
\code{c(1L, 10L)} to say "the first and tenth columns").}

\item{early_stopping_rounds}{int. Activates early stopping. When this parameter is non-null,
training will stop if the evaluation of any metric on any validation set
fails to improve for \code{early_stopping_rounds} consecutive boosting rounds.
If training stops early, the returned model will have attribute \code{best_iter}
set to the iteration number of the best iteration.}

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

\item{reset_data}{Boolean, setting it to TRUE (not the default value) will transform the
booster model into a predictor model which frees up memory and the
original datasets}

\item{...}{other parameters, see \href{https://lightgbm.readthedocs.io/en/latest/Parameters.html}{
the "Parameters" section of the documentation} for more information. A few key parameters:
\itemize{
    \item{\code{boosting}: Boosting type. \code{"gbdt"}, \code{"rf"}, \code{"dart"} or \code{"goss"}.}
    \item{\code{num_leaves}: Maximum number of leaves in one tree.}
    \item{\code{max_depth}: Limit the max depth for tree model. This is used to deal with
                     overfitting. Tree still grow by leaf-wise.}
    \item{\code{num_threads}: Number of threads for LightGBM. For the best speed, set this to
                 the number of real CPU cores(\code{parallel::detectCores(logical = FALSE)}),
                 not the number of threads (most CPU using hyper-threading to generate 2 threads
                 per CPU core).}
}}
}
\value{
a trained booster model \code{lgb.Booster}.
}
\description{
Logic to train with LightGBM
}
\section{Early Stopping}{


         "early stopping" refers to stopping the training process if the model's performance on a given
         validation set does not improve for several consecutive iterations.

         If multiple arguments are given to \code{eval}, their order will be preserved. If you enable
         early stopping by setting \code{early_stopping_rounds} in \code{params}, by default all
         metrics will be considered for early stopping.

         If you want to only consider the first metric for early stopping, pass
         \code{first_metric_only = TRUE} in \code{params}. Note that if you also specify \code{metric}
         in \code{params}, that metric will be considered the "first" one. If you omit \code{metric},
         a default metric will be used based on your choice for the parameter \code{obj} (keyword argument)
         or \code{objective} (passed into \code{params}).
}

\examples{
\donttest{
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 = params
  , data = dtrain
  , nrounds = 5L
  , valids = valids
  , min_data = 1L
  , learning_rate = 1.0
  , early_stopping_rounds = 3L
)
}
}