Box_Office_Success

Linear Regression project predicting box office success using data scraped from Box Office Mojo.

In this repo you will find the following files:

• My powerpoint presentation on this project going over each step of the process as well as my results. This is the best place to start.
• The jupyter notebook I used for scraping Box Office Mojo.
• The jupyter notebook I used for feature engineering.
• The juptyer notebook I used for modeling.
• The CSV file of all Hollywood Blacklist films from 2008 through 2017

The data is a combination of data I scraped along with a kaggle dataset containing all of the films featured on the "Hollywood Blacklist" of promising scripts.

Deployment with Streamlit App via an AWS EC2 Instance

I successfully deployed this model to the web by creating a python file containing the pickled model results and the code necessary to input variables needed for a prediction via the user-friendly Streamlit library! The code for this deployment can be found in the 'box_office_stream_deploy.py' file.

This app was first deployed via a detatched TMUX session on an AWS free tier server. It now lives on Streamlit Share! Find it here