A1 - Recommendation System

Setup and Running

Backend Setup

1. Navigate to backend directory:

   cd backend
   

2. Create and activate virtual environment:

   python3 -m venv venv
   source venv/bin/activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Run the backend server:

   uvicorn app.main:app --reload --port 8000
   

Backend API will be available at http://localhost:8000

Frontend Setup

1. Navigate to frontend directory:

   cd frontend
   

2. Install dependencies:

   npm install
   

3. Run the development server:

   npm run dev
   

Frontend will be available at http://localhost:5173

Datasets

The datasets are located in backend/data/:

• movies_example/ - Small example dataset for testing
• movies_large/ - Larger dataset for production use

Each dataset contains:

• users.csv - User IDs and names
• movies.csv - Movie IDs, titles, and years
• ratings.csv - User ratings for movies

Implementation

Backend (Python + FastAPI)

• Data Loader (backend/app/data_loader.py) - Loads and parses CSV files
• Similarity Functions (backend/app/similarity.py) - Euclidean distance and Pearson correlation
• Recommender (backend/app/recommender.py) - Generates recommendations using collaborative filtering
• API (backend/app/main.py) - REST endpoints for frontend communication

Frontend (Svelte)

• API Client (frontend/src/lib/api.js) - Communicates with backend
• App (frontend/src/App.svelte) - Main application component
• Controls (frontend/src/lib/Controls.svelte) - User and algorithm selection
• SimilarUsers (frontend/src/lib/SimilarUsers.svelte) - Displays similar users
• MovieRecommendations (frontend/src/lib/MovieRecommendations.svelte) - Displays movie recommendations

API Endpoints

• GET /api/users?dataset=movies_example - List all users
• GET /api/recommendations?user=Mike&algorithm=euclidean&dataset=movies_example - Get movie recommendations
• GET /api/similar-users?user=Mike&algorithm=euclidean&dataset=movies_example - Get similar users