Digitalization in rock engineering has resulted in significant technological advancements and the increasing use of machine learning techniques. As rock engineering transitions into becoming more data-driven, machine learning can help rock engineers improve the efficiency and utilization of large data sets in the design process. While machine learning is a powerful tool, the success of machine learning algorithms is intrinsically related to the quality and quantity of data available. It is commonly accepted that machine learning algorithms that are trained on poor quality data will result in poor and inaccurate (i.e. highly subjective) results. To limit the human factors that result from using data that represent qualitative assessments rather than objective measurements of physical properties, it is imperative to improve the data analysis and preparation/labelling process. Data preparation is especially important when applying machine learning to rock engineering problems due to the inductive and empirical nature of the design process as a result of the inherent variability of geological materials. Despite data preparation accounting for more than half of the machine learning process, there is limited research on data preparation for machine learning in rock engineering. This paper aims to fill this gap by providing a set of guidelines on the necessary data preparation steps for applying machine learning to rock engineering problems, thereby helping rock engineers improve the performance of their machine learning models.