non-numeric argument to binary operator

[yangliu6768]

Hi,

When I tried to learn the individualized best treatment effect, I found an error called non-numeric argument to binary operator.

Here is my code:

library(data.table)
library(sl3)
library(tmle3)
library(tmle3mopttx)
library(devtools)
set.seed(111)

data <- read.csv("updated_dat_r.csv",header = TRUE)
node_list <- list(
W = colnames(data)[1:148],
A = 'tm_grp',
Y = "death.no_readmission"
)
processed <- process_missing(data, node_list)
data <- processed$data
node_list <- processed$node_list

Initialize few of the learners:

lrn_xgboost_50 <- Lrnr_xgboost$new(nrounds = 50)
lrn_xgboost_100 <- Lrnr_xgboost$new(nrounds = 100)
lrn_xgboost_500 <- Lrnr_xgboost$new(nrounds = 500)
lrn_mean <- Lrnr_mean$new()
lrn_glm <- Lrnr_glm_fast$new()

Define the Q learner, which is just a regular learner:

Q_learner <- Lrnr_sl$new(
learners = list(lrn_glm #,
# lrn_xgboost_100, lrn_mean,
),
metalearner = Lrnr_nnls$new()
)

Q_learner <- Lrnr_hal9001$new()

Define the g learner, which is a multinomial learner:

specify the appropriate loss of the multinomial learner:

mn_metalearner <- make_learner(Lrnr_solnp,
eval_function = loss_loglik_multinomial,
learner_function = metalearner_linear_multinomial
)
g_learner <- make_learner(Lrnr_sl, list(# lrn_glm
lrn_xgboost_50

lrn_xgboost_100, lrn_xgboost_500, lrn_mean

),
mn_metalearner)

g_learner <- Lrnr_hal9001$new()

Define the Blip learner, which is a multivariate learner:

learners <- list(
lrn_xgboost_50,

lrn_xgboost_100, lrn_xgboost_500,

lrn_mean,

lrn_glm)
b_learner <- create_mv_learners(learners = learners)

specify outcome and treatment regressions and create learner list

learner_list <- list(Y = Q_learner, A = g_learner, B = b_learner)

initialize a tmle specification

tmle_spec <- tmle3_mopttx_blip_revere(
type = "blip3",
learners = learner_list,
maximize = FALSE, complex = TRUE,
realistic = FALSE, resource = 1
)

complex = TRUE must use all V to determine treatment rule

realistic = TRUE: respect the possitivity issue

resource: 0.5, can only give half of them treatment

fit the TML estimator

fit <- tmle3(tmle_spec, data, node_list, learner_list)
fit

And here is the error:

Error in .Primitive("*")(dots[[1L]][[1L]], dots[[2L]][[1L]]) :
non-numeric argument to binary operator

And the traceback:

8.stop(first_error$value)
7.self$compute_step()
6.scheduler$compute()
5.delayed_fit$compute(job_type = sl3_delayed_job_type(), progress = verbose)
4.likelihood_def$train(tmle_task)
3.point_tx_likelihood(tmle_task, learner_list)
2.tmle_spec$make_initial_likelihood(tmle_task, learner_list)
1.tmle3(tmle_spec, data, node_list, learner_list)

Could you please help me? Thank you very much! I appreciate your help.

[yangliu6768]

Here is the data.
updated_dat_r.csv