Data Mining Project (CSCI 5502)

Project for CU Boulder Data Mining class. Fall 2024. Daniel Ethridge, Atharva Patil, Deep Shukla, Sujith Battu.

Overview

This project involves performing an in-depth analysis of game data using the Steam API. We have gathered data on game names, images, trailers, user reviews, and other relevant information.

Goals:

• Analyze the impact of game trailers, soundtracks, and game art on user reviews.
• Explore how various factors influence game pricing.
• Utilize NLP for sentiment analysis on user reviews and image analysis for visual elements.

Progress:

• Completed data collection, cleaning, and initial visualizations.
• Moving towards deeper analysis using NLP and image analysis.
• Project is currently ongoing.

Getting started

1. Ensure Git Large File Storage is installed on your device
2. Clone the repo
   • HTTPS: git clone --recurse-submodules https://github.com/daniel-ethridge/Data-Mining-Project.git
   • SSH: git clone --recuse-submodules git@github.com:daniel-ethridge/Data-Mining-Project.git
3. If you have already cloned the repo without --recurse-submodules, run git submodule update --init.
4. Changes to the submodules can be retrieved with git pull --recurse-submodules
5. Open the Data Mining Project folder in a terminal.
6. Create a virtual environment: python -m venv .venv
7. Activate the virtual environment. How to do this varies depending on the operating system.
8. Run pip install -r requirements.txt

link to data

• dropbox
• Google Drive