Skip to content

Notebooks containing analyses of Untappd user data & models predicting beer ratings

Notifications You must be signed in to change notification settings

jasperkuller/untappd_beer_analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Bacchus ex machina: Tapping into beer ratings

1. Installation

All necesary libraries are indicated at the beginning of the notebook. The code should run with no issues using Python versions 3.*.

2. Project motivation

This project is part of an assignment for the Udacity Data Scientist nanodegree course. In it, students can practice their data science (CRISP-DM) skills on a real-world problem and communicate their findings in a blogpost. For my assignment, I chose to analyze data from Untappd, a geosocial network app that allows users to check-in beers and share reviews with their friends and other users. I'll try to answer three questions:

  1. What contributes to the way people rate beer?
  2. Is there a way to predict if you'll like a certain beer?
  3. How could data further enhance the Untappd experience?

3. File Descriptions

Files include two jupyter notebooks: the main one analyses an Untappd dataset that a user put on Kaggle, the second one repeats the analysis with my own Untappd data.

4. Results

I wrote a blogpost about my findings on Medium.

5. Acknowledgements, Licensing

I'd like to thank Theun van Vliet for providing feedback and inspiration. Gratitude to Nikita Gruntov who provided his Untappd data to the public on Kaggle, and to fellow authors analyzing beer data and writing about it. Feel free to use the code provided here and analyze your own Untappd data!

About

Notebooks containing analyses of Untappd user data & models predicting beer ratings

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published