- create a python virtual environment
python3 -m venv env_synth- activate your enviornment
- download the files into that new directory
- make sure you have a data directory - this is where it will write your csv file
- install requirements
pip3 install -r requirements.txt- run the sample make_synthetic.py
python3 make_synthetic.py config_example_110k.json It's not perfect but will generate AFD OFI ready datasets.
the program will generate a synthietic CSV dataset with predictive performance; AND a txt summary of the file with a profile of the datset, expected performance, and variable importance