Dataset and code for the paper titled "Rooted in scent: Machine Learning reveals reproducible substrate-associated floral VOC signatures in two Brassicaceae species"

The archive contains: data directory, which includes CSV files with the floral VOC datasets collected for our study. Separate files are provided for the different datasets involved in our study. Specifically: clean_rafano_dataset.csv contains the Raphanus raphanistrum dataset clean_add_rafano_test.csv contains the validation dataset for the Raphanus raphanistrum study clean_incana_odori_dataset.csv contains the Brassica incana dataset src_06_08_2026 directory, which contains Python scripts and instructions to replicate the results presented in our study.