How to save mlr3 lightgbm model correctly?

Question

I have some following codes. I met error when save trained model. It's only error when i using lightgbm.

library(mlr3)
library(mlr3pipelines)
library(mlr3extralearners)

data = tsk("german_credit")$data()
data = data[, c("credit_risk", "amount", "purpose", "age")]
task = TaskClassif$new("boston", backend = data, target = "credit_risk")

g = po("imputemedian") %>>%
  po("imputeoor") %>>%
  po("fixfactors") %>>%
  po("encodeimpact") %>>% 
  lrn("classif.lightgbm")

gl = GraphLearner$new(g)

gl$train(task)

# predict 
newdata <- data[1,]
gl$predict_newdata(newdata) 
saveRDS(gl, "gl.rds")

# read model from disk ----------------
gl <- readRDS("gl.rds")
newdata <- data[1,]

# error when predict ------------------
gl$predict_newdata(newdata)

score 4 · Accepted Answer · answered Nov 01 '21 at 08:17

lightgbm uses special functions to save and read models. You have to extract the model before saving and add it to the graph learner after loading. However, this might be not practical for benchmarks. We will look into it.

library(mlr3)
library(mlr3pipelines)
library(mlr3extralearners)
library(lightgbm)

data = tsk("german_credit")$data()
data = data[, c("credit_risk", "amount", "purpose", "age")]
task = TaskClassif$new("boston", backend = data, target = "credit_risk")

g = po("imputemedian") %>>%
  po("imputeoor") %>>%
  po("fixfactors") %>>%
  po("encodeimpact") %>>% 
  lrn("classif.lightgbm")

gl = GraphLearner$new(g)

gl$train(task)

# save model
saveRDS.lgb.Booster(gl$model$classif.lightgbm$model, "model.rda")

# save graph learner
saveRDS(gl, "gl.rda")

# load model
model = readRDS.lgb.Booster("model.rda")

# load graph learner
gl = readRDS("gl.rda")

# add model to graph learner
gl$state$model$classif.lightgbm$model = model

# predict
newdata <- data[1,]
gl$predict_newdata(newdata)

How to save mlr3 lightgbm model correctly?

1 Answers1