Skip to content

In this project I used NLP to analyze a dataset containing each episode from the hit show "The Office" with my findings I used TF-IDF and the Cosine Similarity to build a recommendation engine based on whether or not 'Micheal' and 'Dwight' appeared in the episode.

Notifications You must be signed in to change notification settings

JacobJ215/The-Office-Recommendation-Engine

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

97 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Era of Ratings

Ever wonder why you kept watching that show that you weren't all that interested in? What truly causes a cult-like audience? In this repo we will analyze the following:

  • Whether environmental ratings such as IMDB play a role on what you binge next
  • If you as the audience is more likely to skip around between episodes if your ride or die character has a special storyline
  • Prediction of the next big binge on Netflix

Please see Tables of Contents below:

  1. Resources- The datasets that were used to analyze Netflix, ratings and specific TV shows
  2. Images- A compilation of the visualizations created to interpret results
  3. Models - Contains the models created by the team
  4. AWS Predictor - AWS model suggesting what movie to watch next
  5. Presentation- Slide deck presenting final conclusions

About

In this project I used NLP to analyze a dataset containing each episode from the hit show "The Office" with my findings I used TF-IDF and the Cosine Similarity to build a recommendation engine based on whether or not 'Micheal' and 'Dwight' appeared in the episode.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 96.6%
  • Python 3.4%