How shambhujadhav4/tourist-destinations-recommendation works
Project type and purpose
• This is a data-driven, monolithic web-application built with Streamlit.
• Its purpose is to let end users select a city and category, then generate personalized tourist destination recommendations via a K-Nearest Neighbors (KNN) algorithm.
File structure
• Top-level files:
• .devcontainer/devcontainer.json – development container configuration
• LICENSE, README.md – documentation and license
• TouristRecommender/ directory:
• .streamlit/config.toml – Streamlit UI settings
• app.py – main Streamlit application entry point
• requirements.txt – Python dependencies (streamlit, pandas, scikit-learn, etc.)
• Tourist5.csv, Touristnew.csv – datasets stored as flat files
• Screenshots/ – UI and demo images (for documentation only)
README for additional insights
• Tech stack: Python 3.11, Streamlit, scikit-learn, pandas
• Core functionality: UI layer for input, ML layer for KNN recommendations, CSV-backed data layer
• No external microservices or databases—everything is self-contained
a. Main components
• User’s Web Browser (Client)
• Streamlit Application (app.py) – UI & controller
• Recommendation Engine – KNN implementation using scikit-learn
• Data Storage – CSV files loaded via pandas
• Development / Deployment Environment – Python interpreter & .devcontainer
• (Optional) Hosting Platform – Streamlit Cloud or Docker container
b. Relationships and data flow
1. User selects city & category in browser → HTTP request reaches Streamlit app
2. Streamlit app loads and preprocesses CSV data via pandas
3. Streamlit controller invokes scikit-learn KNN module to compute nearest neighbors
4. Recommendation results flow back to Streamlit frontend
5. Streamlit renders results to the user’s browser
c. Architectural patterns & design principles
• Monolithic single-process architecture
• Clear separation between UI (Streamlit), business logic (KNN engine), and data layer (pandas + CSV)
• Environment as code (requirements.txt + .devcontainer) for reproducibility
d. Key technologies
• Streamlit – frontend UI & simple web server
• pandas – data ingestion and preprocessing
• scikit-learn – KNN algorithm
• .devcontainer – standardize dev environment
• requirements.txt – dependency management