Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. Our mission is to democratise modeling knowledge, inspire the industry through innovation, reduce human bias in the modeling process & build a strong open source marketing science community.
Project Robyn
Describe issue
When I run robyn_refresh I get the following error:
Error: object 'InputCollect' not found Execution halted
Here's my code:
Install, load, and check (latest) Robyn version, using one of these 2 sources:
A) Install the latest stable version from CRAN:
install.packages("Robyn")
B) Install the latest dev version from GitHub:
install.packages("remotes") # Install remotes first if you haven't already remotes::install_github("facebookexperimental/Robyn/R")
library(Robyn) library(readr)
setwd("/home/media_user/Documents/Edenred") json_file <- "/home/xxx/RobynModel-5_279_2.json"
data("dt_prophet_holidays")
mmm_input <- read_csv("mmm_input2.csv", col_types = cols(DATE = col_date(format = "%d/%m/%Y")))
mmm_input$Webinar_S[is.na(mmm_input$Webinar_S)] <-- 0
################################################################
Optional: recreate old models and replicate results
From an exported JSON file (which is created automatically when exporting a model)
we can re-create a previously trained model and outputs. Note: we need to provide
the main dataset and the holidays dataset, which are NOT stored in the JSON file.
These JSON files will be automatically created in most cases.
############ WRITE ############
Manually create JSON file with inputs data only
robyn_write(InputCollect, dir = "/home/xxx")
select_model <- "5_279_2"
Manually create JSON file with inputs and specific model results
robyn_write(InputCollect, OutputCollect, select_model)
RobynRefresh <- robyn_refresh( json_file = json_file, dt_input = mmm_input,#InputCollectX$dt_input, dt_holidays = dt_prophet_holidays,#InputCollectX$dt_holidays, refresh_steps = 6, refresh_mode = "manual", refresh_iters = 1000, refresh_trials = 1 )
Thanks for your help in advance!