This project focuses on building a machine learning model to predict the number of calories burnt during physical activities. By leveraging features such as age, gender, weight, height, and activity-related data, the model provides accurate calorie expenditure estimations. This tool is particularly useful for fitness enthusiasts, healthcare professionals, and researchers studying physical activity patterns.
- Dataset: The dataset contains detailed records, including demographics and activity metrics like heart rate and duration.
- Algorithms: Various machine learning algorithms are explored, including Linear Regression, Decision Trees, and Gradient Boosting.
- Evaluation: The model's performance is evaluated using metrics like R², MAE, and RMSE to ensure accuracy and reliability.
- Visualization: Libraries such as Matplotlib and Seaborn are used for EDA and presenting insights from the dataset.
The project aims to address the growing demand for personalized fitness and health tracking by providing precise calorie burn predictions. Applications include:
- Integration into fitness apps for real-time calorie tracking.
- Supporting healthcare providers in prescribing physical activity regimens.
- Assisting researchers in studying energy expenditure patterns across different demographics.
To run this project locally, follow these steps:
-
Clone the Repository:
git clone https://github.com/BhaveshBhakta/Calories-Burnt-Prediction-Using-XGBRegressor.git cd Calories-Burnt-Prediction-Using-XGBRegressor -
Run the Project:
Start the Jupyter Notebook server or execute the Python scripts.jupyter notebook
-
View Results:
Navigate to the provided notebooks or scripts to explore the data analysis, model training, and predictions.
Contributions are welcome! Feel free to fork the repository, make improvements, and submit a pull request.