Open
Description
Description
Defining a lgb.Dataset with free_raw_data = FALSE. Then slicing it in two parts and using them as train/validation sets in lightgbm (R). The call lgb.train(... fails with an error
please set ‘free_raw_data = FALSE’ when you construct lgb.Dataset"
Don't understand why. Can anyone help please?
Reproducible example
library(lightgbm)
boston = MASS::Boston
str(boston)
dim(boston)
set.seed(12)
boston_lgb_dataset = lgb.Dataset(scale(boston[, -14]), label = boston[, 14] ,free_raw_data = FALSE)
dtrain = lightgbm::slice(boston_lgb_dataset, c(1:350))
dtest = lightgbm::slice(boston_lgb_dataset, c(351:506))
params = list(
objective = "regression"
, metric = "l2"
, min_data = 1L
, learning_rate = .3
)
model = lgb.train(
params = params
, data = dtrain
, nrounds = 20L
, valids = list( test = dtest)
)Environment info
R version 4.2.0
LightGBM version: 3.3.5