lgb.cv.Rd 4.2 KB
Newer Older
James Lamb's avatar
James Lamb committed
1
2
3
4
5
6
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/lgb.cv.R
\name{lgb.cv}
\alias{lgb.cv}
\title{Main CV logic for LightGBM}
\usage{
7
8
9
lgb.cv(
  params = list(),
  data,
10
11
  nrounds = 10L,
  nfold = 3L,
12
13
14
15
  label = NULL,
  weight = NULL,
  obj = NULL,
  eval = NULL,
16
  verbose = 1L,
17
18
  record = TRUE,
  eval_freq = 1L,
19
  showsd = TRUE,
20
21
22
23
24
25
26
27
28
29
  stratified = TRUE,
  folds = NULL,
  init_model = NULL,
  colnames = NULL,
  categorical_feature = NULL,
  early_stopping_rounds = NULL,
  callbacks = list(),
  reset_data = FALSE,
  ...
)
James Lamb's avatar
James Lamb committed
30
31
32
33
}
\arguments{
\item{params}{List of parameters}

34
35
36
\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.}
James Lamb's avatar
James Lamb committed
37
38
39
40
41

\item{nrounds}{number of training rounds}

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

42
\item{label}{Vector of labels, used if \code{data} is not an \code{\link{lgb.Dataset}}}
James Lamb's avatar
James Lamb committed
43
44
45

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

46
\item{obj}{objective function, can be character or custom objective function. Examples include
James Lamb's avatar
James Lamb committed
47
\code{regression}, \code{regression_l1}, \code{huber},
48
 \code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}
James Lamb's avatar
James Lamb committed
49
50
51
52
53
54
55
56
57

\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 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}

58
59
\item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}

James Lamb's avatar
James Lamb committed
60
61
62
63
64
65
66
67
68
69
70
\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 training from this model}

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

71
72
73
\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").}
James Lamb's avatar
James Lamb committed
74

75
76
77
78
\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
except the training data. Returns the model with (best_iter + early_stopping_rounds).
If early stopping occurs, the model will have 'best_iter' field.}
James Lamb's avatar
James Lamb committed
79

80
\item{callbacks}{List of callback functions that are applied at each iteration.}
James Lamb's avatar
James Lamb committed
81

82
83
\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}
84

James Lamb's avatar
James Lamb committed
85
86
\item{...}{other parameters, see Parameters.rst for more information. A few key parameters:
\itemize{
87
88
89
    \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
James Lamb's avatar
James Lamb committed
90
                     overfit when #data is small. Tree still grow by leaf-wise.}
91
    \item{\code{num_threads}: Number of threads for LightGBM. For the best speed, set this to
92
                       the number of real CPU cores, not the number of threads (most
James Lamb's avatar
James Lamb committed
93
94
95
96
97
98
99
100
101
102
103
104
105
106
                       CPU using hyper-threading to generate 2 threads per CPU core).}
}}
}
\value{
a trained model \code{lgb.CVBooster}.
}
\description{
Cross validation logic used by LightGBM
}
\examples{
data(agaricus.train, package = "lightgbm")
train <- agaricus.train
dtrain <- lgb.Dataset(train$data, label = train$label)
params <- list(objective = "regression", metric = "l2")
107
108
109
model <- lgb.cv(
  params = params
  , data = dtrain
110
  , nrounds = 5L
111
112
113
  , nfold = 3L
  , min_data = 1L
  , learning_rate = 1.0
114
)
James Lamb's avatar
James Lamb committed
115
}