A GC/MS dataset with python scripts for machine learning-based classification of Thai and foreign hemp (Cannabis sativa L.) seed extracts

Abstract Objectives Due to its nutraceutical bioactive metabolites, hemp ( Cannabis sativa L.) seed extract offers health and economic benefits. However, the abundance of these active molecules can vary depending on multiple components, such as genetic variation, geographical, and environmental factors. Therefore, it is crucial to determine the origin of hemp seed extracts. The authors’ previous study reported a proof-of-concept machine learning-based classification model to distinguish Thai and foreign hemp seed extract origin using GC/MS data. Here, we presented and navigated the datasets used in our previous study (https://doi.org/10.3390/foods14213739). Data description This data note article has three essential parts. The first part is the list of necessary packages to execute Python scripts under the Anaconda distribution. The second part is GC/MS metabolic fingerprint datasets. The last part consists of Python scripts to develop the authors’ partial least squares-discriminant analysis (PLS-DA), a machine learning-based classification model.