📊 Data Visualization with Ollama (LLaMA 3.2 by Meta)

🔍 Overview

This project provides a powerful solution for sales data analysis and visualization. It supports data ingestion from CSV files and web scraping, enabling flexible data sourcing. Users can leverage Pandas and Streamlit for efficient data processing and exploration.

🚀 Key Highlights:

• AI-powered Chat 🤖: Ask natural language questions about your data.
• Dynamic Charting 📈: Generate interactive visualizations.
• Automated Table Structuring 📋: AI organizes web-scraped data into tables.
• Seamless Integration 🔄: Works with CSV and web sources.

✨ Features

✅ Flexible Data Ingestion: Import sales data from CSV or scrape from websites.

✅ Interactive Data Processing: Utilize Pandas and Streamlit for easy data transformation.

✅ AI-Powered Insights: Ask questions about your CSV data and receive instant responses.

✅ Visual Analytics: Generate insightful charts to identify trends and patterns.

✅ Web Data Structuring: Convert raw web data into structured tables for analysis.

🖥️ Demo

🔎 Web Scraping Example

📊 Data Analysis in Action

⚙️ Requirements

• Python 3.x 🐍
• Pandas 📊
• Streamlit 🌐
• Selenium 🕷️
• Ollama + LLaMA 3.2 Model 🧠

📥 Installation

1️⃣ Clone the repository:

git clone https://github.com/vy-phan/WebScraping.git

2️⃣ Navigate to the project directory:

cd datavis

3️⃣ Install dependencies:

pip install -r requirements.txt

🛠️ Installing Ollama & LLaMA 3.2

Step 1️⃣: Install Ollama

🔗 Download from: Ollama Official Site
📥 Run the installer and follow the setup instructions.

Step 2️⃣: Install LLaMA 3.2 Model

Run the following command:

ollama pull llama3.2

Step 3️⃣: Verify Installation

Check if the model is installed:

ollama list

✅ You should see llama3.2 in the list.

🚀 Running LLaMA 3.2

Start a chat session with:

ollama run llama3.2