Skip to content

About

This project leverages Claude Code’s powerful agent capabilities to build a multi-agent system that simulates the real-world collaboration process of a data science team. Through the division of labor among AI agents with different areas of expertise, the system delivers a complete end-to-end data science solution—from raw data to the final analysi

Topics

Resources

Stars

43 stars

Watchers

0 watching

Forks

Repository files navigation

🤖 Claude Code Data Science Team Multi-Agent System

📋 Project Overview

This project leverages the powerful Agent functionality of Claude Code to create a Multi-Agent System that simulates real data science team collaboration workflows. Through the collaborative work of AI Agents with different professional roles, it provides complete end-to-end data science solutions from raw data to final analysis reports.

🎯 Project Goals

  • Simulate Real Teams: Recreate role division and collaboration patterns in data science projects
  • Automated Workflow: Fully automated pipeline from data cleaning to model building
  • Standardized Outputs: Generate professional-grade analysis reports, visualizations, and executable Notebooks
  • Best Practices: Follow industry-standard project structure and code standards

🏗️ System Architecture

Multi-Agent Workflow

🤝 Team Members & Role Division

Role Agent Name Main Responsibilities Input Output
🎯 Project Director project-orchestrator Project planning, task scheduling, process management User requirements Final deliverables
🔧 Data Engineer data-engineer Data cleaning, preprocessing, feature engineering Raw data Clean datasets
📊 Data Analyst data-analyst-eda Exploratory data analysis, visualization Processed data EDA reports and charts
🧠 ML Scientist ml-model-scientist Model building, parameter tuning, performance evaluation Analysis results Predictive models and evaluations
📝 Technical Writer technical-writer-qa Report integration, quality assurance All outputs Final reports and Notebooks

🔄 Workflow

Our Multi-Agent system adopts a Sequential Pipeline architecture:

Phase 1: Project Initiation 🚀

User → project-orchestrator
  • Receive raw data and analysis requirements
  • Develop project plan and timeline
  • Initialize project structure

Phase 2: Data Preparation 🔧

project-orchestrator → data-engineer → project-orchestrator
  • Data quality checking and cleaning
  • Missing value handling and outlier detection
  • Feature engineering and data transformation

Phase 3: Exploratory Analysis 📊

project-orchestrator → data-analyst-eda → project-orchestrator
  • Descriptive statistical analysis
  • Data visualization and trend discovery
  • Correlation analysis and hypothesis testing

Phase 4: Model Building 🧠

project-orchestrator → ml-model-scientist → project-orchestrator
  • Model selection and training
  • Hyperparameter tuning
  • Model evaluation and validation

Phase 5: Result Integration 📝

project-orchestrator → technical-writer-qa → project-orchestrator
  • Technical documentation writing
  • Quality assurance and review
  • Final report generation

Phase 6: Project Delivery 🎁

project-orchestrator → User
  • Deliver complete analysis results
  • Provide implementation recommendations and future planning

📁 Project Structure

Each analysis project follows a standardized directory structure:

📁 project_[project_name]/
│
├── 📄 README.md                      # Project documentation
│
├── 📁 00_data/                       # Data storage area
│   ├── 📁 raw/                       # Raw data (immutable)
│   ├── 📁 processed/                 # Cleaned data
│   └── 📁 intermediate/              # Intermediate processing files
│
├── 📁 01_notebooks/                  # Jupyter Notebook workspace
│   ├── 📁 exploratory/               # Exploratory analysis drafts
│   ├── 📁 modeling/                  # Model development experiments
│   └── 📁 final/                     # Final executable Notebooks
│
├── 📁 02_src/                        # Python source code
│   ├── 📄 data_processing.py         # Data processing functions
│   ├── 📄 visualization.py           # Visualization tools
│   └── 📄 modeling.py                # Model training functions
│
├── 📁 03_reports/                    # Reports and charts
│   ├── 📁 figures/                   # Chart files
│   └── 📄 final_report.md            # Final Markdown report
│
└── 📁 04_models/                     # Trained models
    └── 📄 [model_name].pkl

🏆 Success Case: Titanic Survival Prediction

We use the classic Titanic dataset as an example to demonstrate the complete analysis workflow:

📊 Data Overview

  • Data Records: 891 training records
  • Features: 12 original features
  • Target Variable: Passenger survival rate (0/1)

🔍 Key Findings

Survival Analysis

🎯 Model Performance

  • Best Model: Random Forest
  • Accuracy: 85.5%
  • F1 Score: 82.3%

Feature Importance

🚀 Quick Start

Environment Requirements

  • Python 3.10+
  • Claude Code CLI
  • Required packages: pandas, numpy, scikit-learn, matplotlib, seaborn

Installation Steps

  1. Clone Project
git clone https://github.com/your-username/claudeCodeDataScienceTeam.git
cd claudeCodeDataScienceTeam
  1. Setup Python Environment
# Use specified Python environment
C:/Users/hunghsun/AppData/Local/anaconda3/envs/py10/python.exe -m pip install -r requirements.txt
  1. Launch Claude Code
claude

Usage Instructions

  1. Prepare Data: Place raw data in 00_data/raw/ directory
  2. Start Analysis: Use project-orchestrator Agent to begin new project
  3. Monitor Progress: Observe the work results of each phase's Agent
  4. Review Results: Check 03_reports/final_report.md for complete analysis report

🎨 Core Features

✨ Intelligent Division of Labor

  • Each Agent specializes in specific domains, ensuring professional quality
  • Automated task handover and result validation

📈 Standardized Outputs

  • Unified code style and document formats
  • Reproducible analysis workflows and results

🔄 Flexible Expansion

  • Modular design, easy to add new Agent roles
  • Support for different types of data science projects

🛡️ Quality Assurance

  • Built-in code checking and testing mechanisms
  • Technical document review and quality control

📚 Design Principles

🏗️ Architecture Principles

  1. Project Independence: Each analysis project is completely independent, avoiding cross-contamination
  2. Separation of Concerns: Data, code, and reports are stored separately by category
  3. Raw Data Immutability: Ensure traceability and reproducibility of analysis
  4. Process-Oriented: Directory structure reflects the main data processing workflow

💻 Technical Standards

  • Python Environment: Use Anaconda to manage package dependencies
  • Visualization: Support Chinese fonts, charts directly saved as files
  • Document Format: Markdown reports paired with high-quality PNG charts
  • Version Control: Git manages code, model files stored independently

Star History

Star History Chart

About

This project leverages Claude Code’s powerful agent capabilities to build a multi-agent system that simulates the real-world collaboration process of a data science team. Through the division of labor among AI agents with different areas of expertise, the system delivers a complete end-to-end data science solution—from raw data to the final analysi

Topics

Resources

Stars

43 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages