This project aims to predict the CO2 emissions of vehicles based on their characteristics using a linear regression model. The model was trained using a dataset of car specifications, including features such as fuel efficiency, engine information, and dimensions. The project demonstrates the application of machine learning for environmental impact analysis.
Data cleaning and preprocessing Feature engineering Model training and evaluation CO2 emissions prediction Environmental impact analysis
Data Collection: A dataset containing vehicle specifications was used. Data Cleaning: Missing values were handled, and outliers were addressed. Feature Engineering: New features were created to enhance the model's performance, including interaction and logarithmic features. Model Training: The linear regression model was trained on the preprocessed data. Model Evaluation: The model was evaluated using metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared. Prediction: The model can be used to predict the CO2 emissions of vehicles based on their characteristics.
The linear regression model achieved a satisfactory performance, with reasonable values for MAE, MSE, and R-squared. The model is capable of predicting CO2 emissions with good accuracy.
This project successfully built a linear regression model for predicting CO2 emissions of vehicles based on their characteristics. This work contributes to environmental impact analysis and provides insights into the relationship between vehicle features and emissions.
The Python code for this project is available in this repository. It includes data cleaning, feature engineering, model training, and evaluation.
Python 3 Pandas NumPy Scikit-learn Usage:
Clone this repository. Install the required dependencies. Run the Python script to train and use the model.
This project is for educational and informational purposes only. The predictions made by the model are estimates and may not be perfectly accurate.