Data Pro Max

The Ultimate AI-Powered Intelligence Suite for Data Science & Surveys

🌟 Overview

Data Pro is a high-performance intelligence layer designed to transform raw data into professional insight. It combines a powerful Python CLI, a versatile library, and specialized AI Agent Skills to automate the most complex parts of the data science lifecycle.

[!TIP]
This repository is the "Data Science counterpart" to the acclaimed UI UX Pro Max.

🏗️ Architecture

graph TD
    User([User / AI Agent]) --> CLI[datapro CLI]
    User --> Lib[Python Library]
    
    subgraph "Intelligence Cores"
        CLI --> Suite[data-analysis-suite]
        CLI --> Viz[data-viz]
        CLI --> Geo[geoprocessing-brazil]
        CLI --> DuckDB[duckdb-sql-master]
    end
    
    subgraph "Data Storage"
        Suite --> DB[(Database / Parquet)]
        Viz --> Assets[Assets / Images]
    end
    
    subgraph "External Integration"
        CLI --> DocConv[document-converter]
        DocConv --> PDF[PDF / DOCX Reports]
        CLI --> NLMCP[NotebookLM]
    end

⚡ Key Features

Feature	Description	Tooling
Survey Intelligence	Weighting (Raking), Drivers, and Halo Removal.	`data-analysis-suite`
Data Engine	High-performance local OLAP motor (DuckDB + Parquet).	`datapro.engine`
Advanced Visuals	Evolution plots, heatmaps, and word clouds.	`data-viz`
Geo-Spatial	Brazilian city normalization and choropleth maps.	`geoprocessing-brazil`
Premium Documentation	Mermaid diagrams, markdown standards, document structure.	`document-mastery`
Format Conversion	Import (PDF→MD) and Export (MD→PDF/DOCX).	`document-converter`
High-Performance SQL	Local SQL on CSV/Parquet without a server.	`duckdb-sql-master`
Auto-Mapping	Variable standardization and dictionary mapping.	`datapro setup`

📦 Installation

# Clone and Install
git clone https://github.com/pablodiegoo/Data-Pro-Skill
cd Data-Pro-Skill
pip install -e .

# Full Feature Suite (OCR, Stats, Advanced PDF)
pip install "datapro[full,docs] @ git+https://github.com/pablodiegoo/Data-Pro-Skill"

[!IMPORTANT]
For the Advanced PDF Engine, system dependencies are required:
sudo apt install pandoc texlive-xetex texlive-fonts-extra

🚀 Quick Start

1. Project Initialization

datapro setup

Initializes the Source of Truth and prepares the agent environment.

2. High-Speed Analysis

datapro analyze data.csv --goal "nps drivers"

3. Premium Reporting

datapro report results.md --theme executive --logo ./logo.png

📂 Project Structure

Following the Unified Structure Reference (structure.json):

scripts/: Implementation scripts (utils, notebooks).
database/: Raw, processed, and final datasets.
docs/: Studies, reports, and project plans.
assets/: Images, final docs, and project context.
.agent/: AI Agent "Brain" (Rules, Skills, Workflows).

🤝 Contributing

We follow a strict English-only policy for code and documentation. Please refer to CONTRIBUTING.md before submitting pull requests.

⚖️ License

Distributed under the MIT License. See LICENSE for more information.

Built with ❤️ for the Data Science Community