This project aims to detect autism in early childhood screening using Support Vector Machine (SVM) machine learning models. Two models were developed to empower early intervention:
-
Autism_model.ipynb: This notebook trains a model on a verified dataset from a reliable source. It includes code for training, confusion matrices, and compelling visualizations.
-
Autism_input_model.ipynb: This user-friendly notebook allows you to input data and leverage machine learning based on the trained model. It's designed to take user input and predict potential outcomes.
- Python
- Jupyter Notebook
- Support Vector Machine (SVM)
- Matplotlib (for Data Visualization)
- Seaborn (for Advanced Data Visualization)
Visualizations:
These visualizations offer valuable insights into the model's performance and data characteristics.
Get Started:
- Jupyter Notebook: Ensure you have Jupyter Notebook installed. Alternatively, install the Jupyter extension in VS Code.
- Clone/Download: Clone or download the project repository.
- Install Modules: Install all required Python modules (instructions in notebooks).
- Run Models: Open the respective notebooks:
Autism_model.ipynb(for in-depth exploration)Autism_input_model.ipynb(for user input and predictions)
- Follow Instructions: Each notebook provides detailed guidance on execution and interaction.
The dataset used for training and testing the models is obtained from a verified source (details provided within).
- KAMLESH BAHETI (Reach out: [email protected])
This project is licensed under the Apache License 2.0.
Feel free to contribute and improve this project! Your insights and expertise are valuable.
