A comprehensive web application built with Streamlit that provides interactive analytics, AI-powered game recommendations, and an intelligent chatbot for exploring Steam's vast gaming library.

• Comprehensive Analytics: Visualize 15,000+ Steam games with interactive charts
• Price Analysis: Distribution of game prices and discount patterns
• Genre Insights: Top 15 game genres with detailed breakdowns
• Platform Support: Cross-platform availability statistics (Windows, macOS, Linux, SteamOS)
• Release Trends: Monthly and yearly game release patterns
• Developer Statistics: Top developers and publishers by game count
• Review Analysis: User review distribution and sentiment
• Word Cloud: Visual representation of game descriptions and themes

• Smart Recommendations: Content-based filtering using cosine similarity
• Personalized Results: Get 1-15 similar game suggestions
• Rich Game Cards: Beautiful UI with game images, pricing, and discounts
• Detailed Information: Full game details including:
  • Release dates
  • Developer and publisher info
  • Original pricing and current discounts
  • Direct Steam store links
• Responsive Design: Mobile-friendly interface with modern aesthetics

• Conversational AI: Powered by Llama 3 (8B parameters) via Groq
• RAG Architecture: Retrieval-Augmented Generation using FAISS vector database
• Natural Language Understanding: Ask questions in plain English
• Game Discovery: Get personalized recommendations through conversation
• Context-Aware: Remembers chat history for coherent dialogues
• Rich Responses: Detailed game information and suggestions

• Python 3.8 or higher
• pip package manager
• Git

1. Clone the repository

git https://github.com/HaFares/Game-Recommendation-System-.git
cd Game-Recommendation-System

2. Create a virtual environment

python -m venv venv

# On Windows
venv\Scripts\activate

# On macOS/Linux
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Set up API keys

Create a .env file in the root directory or set environment variables:

export HUGGINGFACEHUB_API_TOKEN="your_huggingface_token"
export GROQ_API_KEY="your_groq_api_key"

5. Prepare data files

Ensure the following files are in your project directory:

• game_data_for_dashboard.csv - Main dataset for analytics
• games_data_recomendation.csv - Dataset for recommendations
• similarity_finale.pkl - Pre-computed similarity matrix
• faiss_index/ - FAISS vector database directory

steam-games-analytics/
│
├── app.py                          # Main Streamlit application
├── requirements.txt                # Python dependencies
├── README.md                       # Project documentation
│
├── data/
│   ├── game_data_for_dashboard.csv
│   ├── games_data_recomendation.csv
│   └── similarity_finale.pkl
│
├── faiss_index/                    # Vector database for chatbot
│   ├── index.faiss
│   └── index.pkl
│
└── assets/                         # Images and static files

streamlit run app.py

The application will open in your default browser at http://localhost:8501

Use the sidebar to switch between three main sections:

1. Dashboard - Explore comprehensive game analytics
2. Recommendation System - Find similar games based on your preferences
3. Chatbot - Chat with AI to discover new games

• Streamlit - Web application framework
• Python 3.8+ - Programming language

• Pandas - Data manipulation and analysis
• NumPy - Numerical computing
• Plotly - Interactive visualizations
• Matplotlib & Seaborn - Statistical graphics
• WordCloud - Text visualization

• LangChain - LLM application framework
• Groq - Fast LLM inference (Llama 3)
• HuggingFace - Embeddings (all-MiniLM-L6-v2)
• FAISS - Vector similarity search
• Sentence Transformers - Text embeddings

• streamlit-shadcn-ui - Enhanced UI components

The application uses Steam game data including:

• Game titles and descriptions
• Pricing information and discounts
• Release dates
• Developer and publisher details
• Platform compatibility
• User reviews and ratings
• Genre classifications
• Game images and Steam store links

• Steam for providing the gaming data
• Groq for fast LLM inference
• HuggingFace for embedding models
• The Streamlit team for the amazing framework
• The open-source community for various libraries used

⭐ If you find this project useful, please consider giving it a star!

Made with ❤️ and ☕