Error in check_hyper_limits(hyperparameters_ordered, "thetas")

[jone735]

Project Robyn

Describe issue

Im getting this error in R, when trying to set-up the Demo_Docker for use.

Error in check_hyper_limits(hyperparameters_ordered, "thetas") : print_S_thetas's hyperparameter must have upper bound <1

My Upper bound for the print_S_thetas hyperparameter is currently set to <1. Thanks for the help!

Provide reproducible example

library(Robyn) # remotes::install_github("facebookexperimental/Robyn/R") library(reticulate) library(remotes) set.seed(123)

Sys.setenv(R_FUTURE_FORK_ENABLE = "true") options(future.fork.enable = TRUE)

data("dt_simulated_weekly") head(dt_simulated_weekly)

data("dt_prophet_holidays") head(dt_prophet_holidays)

robyn_object <- "~/Desktop/MyRobyn.RDS"

plot_adstock(plot = T) plot_saturation(plot = T)

hyperparameters <- list( facebook_I_alphas = c(0.5, 3), facebook_I_gammas = c(0.3, 1), facebook_I_thetas = c(0, 0.3), print_S_alphas = c(0.5, 0.7), print_S_gammas = c(0.3, 0.4), print_S_thetas = c(0.1, 0.2), tv_S_alphas = c(0.5, 3), tv_S_gammas = c(0.3, 1), tv_S_thetas = c(0.3, 0.8), search_clicks_P_alphas = c(0.5, 3), search_clicks_P_gammas = c(0.3, 1), search_clicks_P_thetas = c(0, 0.3), ooh_S_alphas = c(0.5, 3), ooh_S_gammas = c(0.3, 1), ooh_S_thetas = c(0.1, 0.4), newsletter_alphas = c(0.5, 3), newsletter_gammas = c(0.3, 1), newsletter_thetas = c(0.1, 0.4), train_size = c(0.5, 0.8) )

InputCollect <- robyn_inputs( dt_input = dt_simulated_weekly, dt_holidays = dt_prophet_holidays, date_var = "DATE", dep_var = "revenue", dep_var_type = "revenue", prophet_vars = c("trend", "season", "holiday"), prophet_signs = c("default", "default", "default"), prophet_country = "DE", context_vars = c("competitor_sales_B", "events"), context_signs = c("default", "default"), paid_media_vars = c("tv_S", "ooh_S", "print_S", "facebook_I", "search_clicks_P"), paid_media_signs = c("positive", "positive", "positive", "positive", "positive"), paid_media_spends = c("tv_S", "ooh_S", "print_S", "facebook_S", "search_S"), organic_vars = "newsletter", organic_signs = "positive", factor_vars = "events", window_start = "2016-11-23", window_end = "2018-08-22", adstock = "geometric", iterations = 100, trials = 2, hyperparameters = hyperparameters )

hyper_names(adstock = InputCollect$adstock, all_media = InputCollect$all_media)

OutputCollect <- robyn_run( InputCollect = InputCollect, # feed in all model specification plot_folder = robyn_object, # plots will be saved in the same folder as robyn_object pareto_fronts = 1, plot_pareto = TRUE, )

Make sure you're using the latest Robyn version before you post an issue.

• packageVersion("Robyn") [1] ‘3.10.4.9000’
• R version 4.3.0 (2023-04-21)

[gufengzhou]

Hey, I realise you're using the .RDS file which is from a very old version. Please follow our latest demo.R without using the RDS in robyn_run and retry

[onalivaiko]

Hello! I'm getting exactly the same error without using .RDS

[onalivaiko]

@jone735 I figured it out. You need to base your paid media hyperparameters only on spend variables, not on impressions or other exposure variables. Here you need to switch to spend: facebook_I_alphas = c(0.5, 3), facebook_I_gammas = c(0.3, 1), facebook_I_thetas = c(0, 0.3), ... search_clicks_P_alphas = c(0.5, 3), search_clicks_P_gammas = c(0.3, 1), search_clicks_P_thetas = c(0, 0.3)

[malaman5]

I am getting the same issue, the error I am getting is: "Error in check_hyper_limits(hyperparameters_ordered, "thetas") : pinterest_spend_thetas's hyperparameter must have upper bound <1". I used the Robyn version 3.10.3 and now with the 3.11.0, I got the same issue.

The hyperparameters are loaded via json: input_collect <- robyn_inputs( dt_holidays = dt_prophet_holidays, dt_input = dataset, json_file = parameters_file )

"pinterest_spend_alphas": [ 0.5, 3 ], "pinterest_spend_gammas": [ 0.3, 1 ], "pinterest_spend_thetas": [ 0.1, 0.4 ],

and "exposure_vars": [ "facebook_spend", "pinterest_spend", "tiktok_spend", "ext.GoogleTotalAd_spend" ], "paid_media_vars": [ "facebook_spend", "pinterest_spend", "tiktok_spend", "ext.GoogleTotalAd_spend" ], "mediaVarCount": 4, "all_media": [ "facebook_spend", "pinterest_spend", "ext.GoogleTotalAd_spend", "tiktok_spend" ], "paid_media_spends": [ "facebook_spend", "pinterest_spend", "ext.GoogleTotalAd_spend", "tiktok_spend" ],

The details of the session: R version 4.3.2 (2023-10-31) Platform: x86_64-pc-linux-gnu (64-bit) Running under: Ubuntu 22.04.3 LTS attached base packages: [1] stats graphics grDevices datasets utils methods base

other attached packages: [1] jsonlite_1.8.7 Robyn_3.11.0

loaded via a namespace (and not attached): [1] tidyr_1.3.0 utf8_1.2.3 generics_0.1.3 renv_1.0.3 prophet_1.0
[6] xml2_1.3.5 bitops_1.0-7 h2o_3.42.0.2 shape_1.4.6 stringi_1.7.12
[11] lattice_0.22-5 digest_0.6.33 magrittr_2.0.3 pROC_1.18.4 grid_4.3.2
[16] timechange_0.2.0 iterators_1.0.14 foreach_1.5.2 doParallel_1.0.17 plyr_1.8.9
[21] glmnet_4.1-8 Matrix_1.6-3 zip_2.3.0 survival_3.5-7 httr_1.4.7
[26] rvest_1.0.3 rpart.plot_3.1.1 purrr_1.0.2 fansi_1.0.4 doRNG_1.8.6
[31] scales_1.2.1 codetools_0.2-19 cli_3.6.1 rlang_1.1.1 munsell_0.5.0
[36] splines_4.3.2 withr_2.5.1 yaml_2.3.7 tools_4.3.2 parallel_4.3.2
[41] nloptr_2.0.3 minpack.lm_1.2-4 dplyr_1.1.3 colorspace_2.1-0 ggplot2_3.4.3
[46] rngtools_1.5.2 reticulate_1.32.0 png_0.1-8 vctrs_0.6.3 lares_5.2.2
[51] R6_2.5.1 rpart_4.1.23 ggridges_0.5.4 lifecycle_1.0.3 lubridate_1.9.3
[56] stringr_1.5.0 pkgconfig_2.0.3 RcppParallel_5.1.7 pillar_1.9.0 openxlsx_4.2.5.2
[61] gtable_0.3.4 glue_1.6.2 Rcpp_1.0.11 tibble_3.2.1 tidyselect_1.2.0
[66] patchwork_1.1.3 compiler_4.3.2 RCurl_1.98-1.12