Home
DATA 515A Project - Spring 2019
Finding new books to read isn’t always easy. Looking at the size of libraries and some bookstores, it’s hardly surprising that there’s a lot of bad stuff circulating as well. Until recently, we limited ourselves to word of mouth and the tedious business of reading the back of every book on the shelves.
This project aims to build a recommendation engine to help you find your next best book.
Amazon Dataset: http://jmcauley.ucsd.edu/data/amazon/index.html
Goodreads Dataset: https://sites.google.com/eng.ucsd.edu/ucsdbookgraph/home
Before setting up the components, install all necessary dependencies
From the root directory of the project run
pip install -r requirements.txtthenextbestbook has five components. Architecture below:
The following links details the setup process for each component