Thermobarometry is a fundamental tool to quantitatively interrogate magma plumbing systems and broaden our appreciation of volcanic processes. Developments in random forest-based machine learning lend themselves to a more data-driven approach to clinopyroxene thermobarometry. This can include allowing users to access and filter large experimental datasets that can be tailored to individual applications in Earth Sciences. Here we present a methodological assessment of random forest thermobarometry, using the R freeware package “extraTrees”, by investigating the model performance, tuning hyperparameters, and evaluating different methods for calculating uncertainties. We determine that deviating from the default hyperparameters used in the “extraTrees” package results in little difference in overall model performance (<0.2 kbar and <3 ⁰C difference in mean SEE). However, accuracy is greatly affected by how the final pressure or temperature (PT) value from the voting distribution of trees in the random forest is selected (mean, median or mode). This thus far has been unapproached in machine learning thermobarometry. Using the mean value leads to a higher residual between experimental and predicted PT, whereas using median values produces smaller residuals. Additionally, this work provides two comprehensive R scripts for users to apply the random forest methodology to natural datasets. The first script permits modification and filtering of the model calibration dataset. The second script contains pre-made models in which users can rapidly input their data to recover pressure and temperature estimates. These scripts are open source and can be accessed at https://github.com/corinjorgenson/RandomForest-cpx-thermobarometer.