Python code for modeling suitable habitats of tea (Camellia sinensis) under future climate scenarios in China

This repository contains the Python source code used in the study to model and evaluate the habitat suitability of tea (Camellia sinensis) in China under current and future climate scenarios using the Random Forest algorithm. The code includes data preprocessing, model training, evaluation with ROC curves, and visualization of feature importance. The climatic data were sourced from the WorldClim database, and species presence records were obtained from the Global Biodiversity Information Facility (GBIF). The code was developed and tested in a Python environment using the scikit-learn, pandas, matplotlib, seaborn, and numpy libraries. This dataset supports the results reported in the manuscript submitted to PLOS ONE, titled:“ Prediction of Changes in Suitable Habitats for Tea Plants in China’s Four Major Tea-Producing Regions Based on Machine Learning Models ”