Skip to content

laumaxim/movie_recommender

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Getting started with Flask and Heroku

Instruction for deploying this small web application written in Flask to a Heroku cloud. The app asks the user for a list of movies, then asks to rate those movies as "Top" or "Flop", good or bad movies respectively. The app utilizes a dataset of movies and movie ratings made by humans on an online website. The user has a choice of two methods of recommendation: simply a list of top-rated, but unwatched movies or a list of recommended movies created by collaborative filtering. Cosine similarity is used to compare the user rating to the ratings in the dataset and the most similiar movies are then recommended.

Follow the steps below to run the app.

Requirements

  • free heroku account
  • heroku cli installed and set up locally

Instructions

  1. clone the repository

  2. create a new heroku app

heroku create <my-app-name>
  1. test the app locally
heroku local web

on windows use

heroku local web -f Procfile.windows
  1. push code to heroku
git push heroku master
  1. open website in browser
heroku open

Further Ressources

The dataset:

F. Maxwell Harper and Joseph A. Konstan. 2015. The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems (TiiS) 5, 4: 19:1–19:19. https://doi.org/10.1145/2827872

Releases

No releases published

Packages

 
 
 

Contributors