Trinandini-N/CaloriePrediction ? reverse-engineered prompt

Build me a Jupyter notebook that predicts calorie values from the exercise and calorie data in this folder.

I want the notebook to load the two CSV files, clean and prepare the data, then train a few different regression models so I can compare how well they work. Please include basic preprocessing, a clear train and test split, and evaluation with R squared, MAE, MSE, and cross validation. I’d like to see results for a simple baseline model, a random forest model, and an XGBoost model, then a clear comparison of which one performs best.

Make the notebook easy to run from top to bottom, with readable steps and short explanations in between. If you need to check current docs or best practices for any library, go ahead and look them up online. At the end, show the final model performance clearly so I can understand the prediction quality at a glance.