Metadata-Version: 2.4
Name: claude-deepdata
Version: 0.1.0
Summary: An agent framework built on Claude SDK for data analysis, visualization, and ML automation
Project-URL: Homepage, https://github.com/YiyangLu/Deep-Data
Project-URL: Documentation, https://github.com/YiyangLu/Deep-Data#readme
Project-URL: Repository, https://github.com/YiyangLu/Deep-Data
Project-URL: Issues, https://github.com/YiyangLu/Deep-Data/issues
Author: Deep Data Team
License-Expression: MIT
Keywords: agent,claude,data-analysis,ml,plotly,visualization
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Visualization
Requires-Python: >=3.10
Requires-Dist: claude-agent-sdk>=0.1.0
Requires-Dist: fastapi>=0.104.0
Requires-Dist: flask>=3.0.0
Requires-Dist: gitpython>=3.1.0
Requires-Dist: jinja2>=3.1.0
Requires-Dist: kaleido==0.2.1
Requires-Dist: pandas>=2.0.0
Requires-Dist: plotly<6.0.0,>=5.18.0
Requires-Dist: python-multipart>=0.0.6
Requires-Dist: requests>=2.28.0
Requires-Dist: rich>=13.0.0
Requires-Dist: uvicorn[standard]>=0.24.0
Requires-Dist: websockets>=12.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Provides-Extra: ml
Requires-Dist: catboost>=1.2.0; extra == 'ml'
Requires-Dist: lightgbm>=4.0.0; extra == 'ml'
Requires-Dist: optuna>=3.4.0; extra == 'ml'
Requires-Dist: scikit-learn>=1.3.0; extra == 'ml'
Requires-Dist: xgboost>=2.0.0; extra == 'ml'
Description-Content-Type: text/markdown

<h1 align="center">
  🌠Deep Data
</h1>

<p align="center">
  <i>An agent framework built on Claude SDK for data analysis, visualization, and ML automation.</i>
</p>

https://github.com/user-attachments/assets/facf50b3-5d07-4003-9c63-3cb01925784f

## Features

1. **Agent** - Coding agent with Visualization State API (IVG) for interactive chart creation and verification

   <p align="center">
     <img src="assets/agent.png" alt="Deep Plot Banner" width="70%">
   </p>


2. **Deep Plot** - Autonomous data analysis agent with iterative exploration and explanation
   
   <p align="center">
     <img src="assets/deepplot.png" alt="Deep Plot Banner" width="70%">
   </p>

3. **MLE** - MCTS-based ML solution search with parallel workers (isolated in Git worktrees)

   <p align="center">
     <img src="assets/mle.png" alt="Deep Plot Banner" width="70%">
   </p>

## Requirements

- **Python**: 3.10+
- **Claude API**: Via [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code)

## Installation

```bash
pip install claude-deepdata
```

With ML dependencies (for MLE feature):
```bash
pip install claude-deepdata[ml]
```

## Quick Start

```bash
# Start web server
deepdata

# With custom port
deepdata --port 8080

# Set working directory
deepdata --cwd /path/to/project
```

Visit `http://localhost:8000` for the Web UI.

## Development Setup

For contributors who want to modify the code:

```bash
# Clone the repository
git clone https://github.com/YiyangLu/Deep-Data.git
cd Deep-Data

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install in editable mode with dev dependencies
pip install -e ".[dev,ml]"

# Build frontend (requires Node.js 18+)
cd deepdata/web/frontend
npm install
npm run build
cd ../../..

# Run the server
deepdata
```

## Paper

Our paper describing the IVG framework benchmark is coming soon on arXiv.
