romainkp / stremr

Streamlined Estimation for Static, Dynamic and Stochastic Treatment Regimes in Longitudinal Data

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Problem with CVTMLE

rfherrerac opened this issue · comments

Hi, thanks a lot for this wonderful package. I wanted to run CVTMLE, and I am getting this error:
Error in UseMethod("predict_SL") :
no applicable method for 'predict_SL' applied to an object of class "c('Lrnr_sl', 'Lrnr_base', 'R6')"

I guess it is something to do with gridsl::predict_SL.
My function:
params <- gridisl::defModel(estimator = "speedglm__glm")
IPW <- getIPWeights(Odata, intervened_TRT = "Intervention_1", holdout = TRUE)
qwigh <- quantile(IPW[cum.IPAW>0,][["cum.IPAW"]], c(0.99))
gcomp_est <- fit_GCOMP(Odata, tvals = tvals,
TMLE = TRUE,
CVTMLE = TRUE,
Qforms = Qforms,
intervened_TRT = "Intervention_1"
models = params,
stratifyQ_by_rule = FALSE,
stratify_by_last = TRUE,
trunc_weights = qwigh,
fit_method = "cv",
byfold_Q = FALSE,
IPWeights = IPW)

Regards!