Python code and Excel data for statistical and machine learning models developed to investigate the efficiency of nutrient recovery by struvite precipitation.

The Python code consists of five machine-learning methods to evaluate the efficiency of nutrient recovery by struvite precipitation. These methods include Multiple Linear Regression (MLR), Polynomial Regression (PLR), K-Nearest Neighbors (KNN), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). Input data for the Python code used to model phosphate and ammonium recovery is provided in the Excel files. The inventory data embedded within the Python code represents the digestate of various organic feedstocks.