README.md

metadata

title: AutoML - MCP Hackathon
emoji: 📈
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
license: mit
tags:
  - machine-learning
  - mcp
  - hackathon
  - automl
  - lazypredict
  - gradio
  - mcp-server-track
  - agent-demo-track
short_description: Automated ML model comparison with LazyPredict

🤖 AutoML - MCP Hackathon Submission

Automated Machine Learning Platform with LazyPredict and Model Context Protocol Integration

Video Links

• Gradio Demo Link : https://youtu.be/TNStp8Xae1o
• MCP Client Demo Link: https://youtu.be/mdUpdxX_Rcw

🏆 Hackathon Track

Agents & MCP Hackathon - Track 1: MCP Tool / Server

🛠️ How It Works

The AutoML provides a streamlined pipeline for automated machine learning:

Agent-Friendly Design

• Single Entry Point: The run_pipeline() function serves as the primary interface for AI agents
• Flexible Input Handling: Automatically determines whether input is a file path or URL
• Comprehensive Output: Returns all generated artifacts (models, reports, visualizations)
• Error Resilience: Robust error handling with informative feedback

🚀 Quick Start

Installation & Running the Application

# Clone the repository
git clone [repository-url]
cd AutoML

# Install dependencies
pip install -r requirements.txt

# Run the main application
python app.py

🏆 Demo Scenarios

College Placement Analysis

• Upload collegePlace.csv included in the project with url: (https://raw.githubusercontent.com/daniel-was-taken/Placement-Prediction/refs/heads/master/collegePlace.csv)
• Automatic feature analysis and model comparison
• Export trained model for future predictions

📈 Current Features

• 🔄 Dual Input Support: Upload local CSV files or provide public URLs for data loading
• 🤖 One-Click AutoML: Complete ML pipeline from data upload to trained model export
• 🎯 Intelligent Task Detection: Automatic classification vs regression detection based on target variable analysis
• 📊 Multi-Algorithm Comparison: Simultaneous comparison of 20+ algorithms with LazyPredict
• 📋 Comprehensive EDA: Detailed dataset profiling with statistical analysis and data quality reports
• 💾 Model Export: Download best performing model as pickle file for production deployment
• 📈 Performance Visualization: Clear charts showing algorithm comparison and performance metrics
• 🌐 MCP Server Integration: Full Model Context Protocol support for seamless AI assistant integration
• 🛡️ Robust Error Handling: Comprehensive validation with informative user feedback
• 🎨 Modern UI: Clean, responsive interface optimized for both human and agent interactions

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference