diff --git a/model.rds b/model.rds
deleted file mode 100644
index 4a53e28..0000000
Binary files a/model.rds and /dev/null differ
diff --git a/packages.R b/packages.R
deleted file mode 100644
index a256803..0000000
--- a/packages.R
+++ /dev/null
@@ -1,3 +0,0 @@
-#!/usr/bin/env Rscript
-
-install.packages(c("dplyr","data.table","tidyr"), repos="https://cran.r-project.org", dependencies=TRUE)
diff --git a/r.Dockerfile b/r.Dockerfile
deleted file mode 100644
index 5a90f7f..0000000
--- a/r.Dockerfile
+++ /dev/null
@@ -1,12 +0,0 @@
-FROM rocker/r2u:22.04
-
-
-RUN mkdir /app
-WORKDIR /app
-
-COPY *.R /app
-COPY *.rds /app
-
-RUN Rscript packages.R
-
-ENTRYPOINT ["Rscript", "run.R"]
\ No newline at end of file
diff --git a/run.R b/run.R
deleted file mode 100644
index 82274fe..0000000
--- a/run.R
+++ /dev/null
@@ -1,83 +0,0 @@
-#!/usr/bin/env Rscript
-
-# This script calls submission.R. 
-# Add your method there.
-
-# To test your submission use the following command: 
-# Rscript run.R PreFer_fake_data.csv PreFer_fake_background_data.csv
-
-# Install required packages with Rscript packages.R
-
-library(dplyr)
-library(tidyr)
-
-
-source("submission.R")
-
-print_usage <- function() {
-  cat("Usage:\n")
-  cat("  Rscript script.R DATA_FILE BACKGROUND_DATA_FILE [--output OUTPUT_FILE]\n")
-}
-
-parse_arguments <- function() {
-  args <- list()
-  command_args <- commandArgs(trailingOnly = TRUE)
-  if (length(command_args) < 2) {
-    return(args)
-  }    
-    
-  args$data <- commandArgs(trailingOnly = TRUE)[1]
-  args$background_data <- commandArgs(trailingOnly = TRUE)[2]
-  args$output <- get_argument("--output")
-  return(args)
-}
-
-get_argument <- function(arg_name) {
-  if (arg_name %in% commandArgs(trailingOnly = TRUE)) {
-    arg_index <- which(commandArgs(trailingOnly = TRUE) == arg_name)
-    if (arg_index < length(commandArgs(trailingOnly = TRUE))) {
-      return(commandArgs(trailingOnly = TRUE)[arg_index + 1])
-    }
-  }
-  return(NULL)
-}
-
-parse_and_run_predict <- function(args) {
-  if (is.null(args$data)||is.null(args$background_data)) {
-    stop("Error: Please provide data and background_data argument for prediction.")
-  }
-  
-  cat("Processing input data for prediction from:", args$data, " ", args$background_data, "\n")
-  if (!is.null(args$output)) {
-    cat("Output will be saved to:", args$output, "\n")
-  }
-  run_predict(args$data, args$background_data, args$output)
-}
-
-run_predict <- function(data_path, background_data_path, output=NULL) {
-  if (is.null(output)) {
-    output <- stdout()
-  }
-  df <- read.csv(data_path, encoding="latin1")
-  background_df <- read.csv(background_data_path, encoding="latin1")
-  
-  predictions <- predict_outcomes(df, background_df)
-  
-  # Check if predictions have the required format
-  stopifnot(ncol(predictions) == 2,
-            all(c("nomem_encr", "prediction") %in% colnames(predictions)))
-  
-  # Write predictions to output file
-  write.csv(predictions, output, row.names = FALSE)
-}
-
-
-# Main function
-main <- function() {
-  args <- parse_arguments()
-  
-  parse_and_run_predict(args)
-}
-
-# Call main function
-main()
diff --git a/submission.R b/submission.R
deleted file mode 100644
index 56b1b00..0000000
--- a/submission.R
+++ /dev/null
@@ -1,94 +0,0 @@
-# This is an example script to generate the outcome variable given the input dataset.
-# 
-# This script should be modified to prepare your own submission that predicts 
-# the outcome for the benchmark challenge by changing the clean_df and predict_outcomes function.
-# 
-# The predict_outcomes function takes a data frame. The return value must
-# be a data frame with two columns: nomem_encr and outcome. The nomem_encr column
-# should contain the nomem_encr column from the input data frame. The outcome
-# column should contain the predicted outcome for each nomem_encr. The outcome
-# should be 0 (no child) or 1 (having a child).
-# 
-# clean_df should be used to clean (preprocess) the data.
-# 
-# run.R can be used to test your submission.
-
-# List your packages here. Don't forget to update packages.R!
-library(dplyr) # as an example, not used here
-
-clean_df <- function(df, background_df = NULL){
-  # Preprocess the input dataframe to feed the model.
-  ### If no cleaning is done (e.g. if all the cleaning is done in a pipeline) leave only the "return df" command
-
-  # Parameters:
-  # df (dataframe): The input dataframe containing the raw data (e.g., from PreFer_train_data.csv or PreFer_fake_data.csv).
-  # background (dataframe): Optional input dataframe containing background data (e.g., from PreFer_train_background_data.csv or PreFer_fake_background_data.csv).
-
-  # Returns:
-  # data frame: The cleaned dataframe with only the necessary columns and processed variables.
-
-  ## This script contains a bare minimum working example
-  # Create new age variable
-  df$age <- 2024 - df$birthyear_bg
-
-  # Selecting variables for modelling
-
-  keepcols = c('nomem_encr', # ID variable required for predictions,
-               'age')        # newly created variable
-  
-  ## Keeping data with variables selected
-  df <- df[ , keepcols ]
-
-  return(df)
-}
-
-predict_outcomes <- function(df, background_df = NULL, model_path = "./model.rds"){
-  # Generate predictions using the saved model and the input dataframe.
-    
-  # The predict_outcomes function accepts a dataframe as an argument
-  # and returns a new dataframe with two columns: nomem_encr and
-  # prediction. The nomem_encr column in the new dataframe replicates the
-  # corresponding column from the input dataframe The prediction
-  # column contains predictions for each corresponding nomem_encr. Each
-  # prediction is represented as a binary value: '0' indicates that the
-  # individual did not have a child during 2021-2023, while '1' implies that
-  # they did.
-  
-  # Parameters:
-  # df (dataframe): The data dataframe for which predictions are to be made.
-  # background_df (dataframe): The background data dataframe for which predictions are to be made.
-  # model_path (str): The path to the saved model file (which is the output of training.R).
-
-  # Returns:
-  # dataframe: A dataframe containing the identifiers and their corresponding predictions.
-  
-  ## This script contains a bare minimum working example
-  if( !("nomem_encr" %in% colnames(df)) ) {
-    warning("The identifier variable 'nomem_encr' should be in the dataset")
-  }
-
-  # Load the model
-  model <- readRDS(model_path)
-    
-  # Preprocess the fake / holdout data
-  df <- clean_df(df, background_df)
-
-  # Exclude the variable nomem_encr if this variable is NOT in your model
-  vars_without_id <- colnames(df)[colnames(df) != "nomem_encr"]
-  
-  # Generate predictions from model
-  predictions <- predict(model, 
-                         subset(df, select = vars_without_id), 
-                         type = "response") 
-  
-  # Create predictions that should be 0s and 1s rather than, e.g., probabilities
-  predictions <- ifelse(predictions > 0.5, 1, 0)  
-  
-  # Output file should be data.frame with two columns, nomem_encr and predictions
-  df_predict <- data.frame("nomem_encr" = df[ , "nomem_encr" ], "prediction" = predictions)
-  # Force columnnames (overrides names that may be given by `predict`)
-  names(df_predict) <- c("nomem_encr", "prediction") 
-  
-  # Return only dataset with predictions and identifier
-  return( df_predict )
-}
diff --git a/training.R b/training.R
deleted file mode 100644
index 6e79a3e..0000000
--- a/training.R
+++ /dev/null
@@ -1,27 +0,0 @@
-# This is an example script to train your model given the (cleaned) input dataset.
-# 
-# This script will not be run on the holdout data, 
-# but the resulting model model.joblib will be applied to the holdout data.
-# 
-# It is important to document your training steps here, including seed, 
-# number of folds, model, et cetera
-
-train_save_model <- function(cleaned_df, outcome_df) {
-  # Trains a model using the cleaned dataframe and saves the model to a file.
-
-  # Parameters:
-  # cleaned_df (dataframe): The cleaned data from clean_df function to be used for training the model.
-  # outcome_df (dataframe): The data with the outcome variable (e.g., from PreFer_train_outcome.csv or PreFer_fake_outcome.csv).
-
-  ## This script contains a bare minimum working example
-  set.seed(1) # not useful here because logistic regression deterministic
-  
-  # Combine cleaned_df and outcome_df
-  model_df <- merge(cleaned_df, outcome_df, by = "nomem_encr")
-  
-  # Logistic regression model
-  model <- glm(new_child ~ age, family = "binomial", data = model_df)
-  
-  # Save the model
-  saveRDS(model, "model.rds")
-}