R scripts and modeling dataset for: "Machine learning predictions for microbial eukaryotic plankton: implications from unevenly structured data"

This repository contains the modeling dataset and analysis code required to reproduce the cross-validation (CV) results presented in the manuscript “Machine Learning Predictions for Microbial Eukaryotic Plankton: Implications from Unevenly Structured Data” (currently under review). The model predicts the 18S rRNA gene Shannon Diversity Index (SDI) of marine microbial eukaryotes from seven environmental predictors using XGBoost and compares three CV strategies of increasing stringency.