Code and Data for the ECJ submission: Generation of Continuous Optimization Benchmark Problems Guided by Deep Exploratory Landscape Analysis

Code and Data for reproducibility of the work in the ECJ submission "Generation of Continuous Optimization Benchmark Problems Guided by Deep Exploratory Landscape Analysis".To be able to run the code you can proceed as follows (replace mamba by conda if you do not have it installed): # Create the env mamba create -n deepela-genfun -c conda-forge python=3.11.5 pip -y # Activate it mamba activate deepela-genfun # Install requirements pip install -r requirements.txt If you want to use a virtual env instead first make sure you have Python/3.11.5 installed. # Make sure this prints "Python 3.11.5" python -V # Create the env python -m venv ~/.venvs/deepela-genfun # Activate it source ~/.venvs/deepela-genfun/bin/activate # Install requirements pip install -r requirements.txt Finally, install the Deep ELA package alongside pflacco as described here: https://github.com/mvseiler/deep_ela.Regarding the data, it was necessary to split the zip file into larger chunks to allow for an upload to the repository.After downloading you can put the chunks back together by executing: cat data.zip.part-* > data.zip Afterwards it can be unzipped like any other zip file.