Skip to content

Latest commit

 

History

History
117 lines (85 loc) · 3.84 KB

README.md

File metadata and controls

117 lines (85 loc) · 3.84 KB

Autism Spectrum Disorder (ASD) Detection and Analysis

Contributors Stars Issues License Python

Report Bug | Request Feature | View Repo

🌟 Project Overview

This project uses Python and machine learning techniques for the detection and analysis of Autism Spectrum Disorder (ASD). It applies data preprocessing and classification models, such as Random Forest, to predict ASD based on behavioral data. The project includes data visualizations and insights, offering a comprehensive analysis of ASD patterns.

📂 Project Structure

ASD_Detection_Project/
│
├── data/
│   └── autism_data.csv           
│
├── notebooks/
│   └── eda.ipynb                 
│
├── src/
│   ├── __init__.py               
│   ├── preprocess.py            
│   ├── model.py                  
│   └── visualize.py              
│
├── scripts/
│   └── train_model.py           
│
├── requirements.txt              
├── README.md                     
└── .gitignore

🚀 Features

  • Data Preprocessing: Handles missing values and encodes categorical data.
  • Classification Models: Uses Random Forest to classify and predict ASD.
  • Data Visualizations: Includes confusion matrices, correlation heatmaps, and feature importance plots for deeper insights.

💻 How to Run

Clone the repository:

git clone https://github.com/2100031988/Autism-Spectrum-Disorder-Detection-and-Analysis.git
cd ASD_Detection_Project

Install the required dependencies:

pip install -r requirements.txt

Download the dataset and place it in the data/ folder (if not already included):

Explore the dataset:

Open the exploratory analysis Jupyter notebook:

jupyter notebook notebooks/eda.ipynb

Train and evaluate the model:

Run the train_model.py script to load the data, preprocess it, train the model, and evaluate the results:

python scripts/train_model.py

📊 Visualizations

  • Confusion Matrix: Displays the performance of the classification model.
  • Correlation Heatmap: Shows relationships between numeric features.
  • Feature Importance: Highlights the most influential features in the prediction model.

📝 License

This project is licensed under the MIT License. See the LICENSE file for more details.

👥 Contributors

Thanks to these people who have contributed to this project:

For more contributors, check out the CONTRIBUTORS.md file.

© Copyright

© 2024 Sabyasachi Kumar. All rights reserved.