Disclaimer

This project might not have precise data on model performance and accuracy, but it can give a general overview of machine learning models using Orange and some Python libraries.

Carbon Emission Predictor (CO₂)

Carbon emission calculator using Machine learning. This involves testing with a variety of models including Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), Linear Regression, Support Vector Machines (SVM), Random Forest, Gradient Boosting, AdaBoost, and Decision Trees.

Analysis

Model Performance & Analysis

Dependencies

You must have Python installed and the following libraries to view the project:

# Versions
- orange3:            3.37.0
- scikit-learn:        1.3.2
- PySide6:             6.7.2
- matplotlib:         3.9.1
- pandas:              2.2.2

Installation Instructions

1. Navigate to the latest release page and download the carbon-predictor.zip file.
2. Extract the zip file using a tool like WinRAR or 7-Zip.
3. Open the extracted folder and double-click the executable file named Carbon Predictor to launch the program.

Build

xgboost.dll

When building your project into an executable using PyInstaller, include the DLL and version file in a folder named "bin". You can either place the "bin" folder inside your project's source directory. This ensures that the main.spec file correctly resolves its dependencies.