🎲 Board Games Analysis & Recommendation Engine

Project Overview

This project analyzes a board games dataset to uncover trends and build useful tools for players and enthusiasts.

• The data was cleaned, organized, and stored in a SQL database for efficient querying.

• A filtering-based recommendation engine (Python + Streamlit) helps users discover games based on:

  • Ratings

  • Playtime

  • Number of players

  • Complexity

• Visual charts highlight:

  • Top-rated games

  • Most-played games

  • Most-wishlisted games

Overall, this project combines data engineering, analysis, and visualization to deliver practical insights and personalized recommendations.

📑 Presentation: Board Game Database

---

Data Sources

• Board Game CSV file: Dataset with ~2000 rows

• YAML configuration: Used to dynamically manage file paths and input/output references

---

Figures

• ER Diagram: A visual representation of the database logical structure

---

Libraries Used

• pandas

• streamlit

• seaborn

• matplotlib

• PyYAML

---

Jupyter Notebooks

code_recommendation_engine.ipynb

• Load the database

• Drop irrelevant columns and clean age column

• Export cleaned database to CSV

• Build recommendation engine based on:

  • Minimum age

  • Number of players

  • Level of complexity

  • Playing time

• Order results by average rating

code_for_graphs.ipynb

Exploratory Data Analysis (EDA) with visualizations:

• Top 10 most played games

• Top 10 trending/wishlisted games

• Top 10 rated games

• Correlation matrix

importing_csv_sql.ipynb

• Create and import tables based on the ER diagram

---

SQL Scripts

• boardsgames_schema_V2.sql: Defines table creation, primary keys, and foreign key relationships

• Data imported using the SQL Data Import Wizard

---

App

• app.py: Contains the Streamlit app with the recommendation engine

Run locally with:

streamlit run app.py

---

How to Run the Project

Clone the repository

git clone <repo_url>

cd <repo_name>

Create a virtual environment (recommended)

python -m venv venv

source venv/bin/activate # Mac/Linux

venv\Scripts\activate # Windows

Install dependencies

pip install -r requirements.txt

Run the Streamlit app

streamlit run app.py

Open the localhost URL in your browser to interact with the app.

---

Contributors

Julia • Ricardo • Mauricio • Priyanka