https://github.com/max0ne/twinkeydow

it recommends github repos
https://github.com/max0ne/twinkeydow

aws-lambda collaborative-filtering github mongodb numpy python react recommendation-system serverless typescript

Last synced: 10 months ago
JSON representation

it recommends github repos

• Host: GitHub
• URL: https://github.com/max0ne/twinkeydow
• Owner: max0ne
• License: mit
• Created: 2018-03-13T18:35:25.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2019-04-29T19:34:53.000Z (over 6 years ago)
• Last Synced: 2025-04-12T06:43:09.811Z (10 months ago)
• Topics: aws-lambda, collaborative-filtering, github, mongodb, numpy, python, react, recommendation-system, serverless, typescript
• Language: Jupyter Notebook
• Homepage: https://twinkeydow.mingfei.me
• Size: 13.2 MB
• Stars: 8
• Watchers: 3
• Forks: 0
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
[![Build Status](https://circleci.com/gh/max0ne/twinkeydow/tree/master.svg?style=shield

)](https://circleci.com/gh/max0ne/twinkeydow/tree/master) ![License](https://img.shields.io/github/license/mashape/apistatus.svg)

# Project Twinkeydow

It provides customized Github repo recommendations, based on your previous activities on Github. It works by pulling large number of public Github user data from [Github Public Event API](https://developer.github.com/v3/activity/events/), modeling each Github repo by [model based collaborative filtering](https://en.wikipedia.org/wiki/Collaborative_filtering#Model-based) and provide customized recommendations.

## Structure

The code mainly does 5 things

| wat | deployed to | tools | wat exactly |

| - |-|-|-|

| [Gathering Data](./github_repo_puller) | AWS EC2 | Node.js | Querying Github API for public activity |

| [Modeling](./als_thing/compute_feature_vector.ipynb) | AWS EMR | Python, Spark | CF modeling stuff given bunch of data to train with |

| [Predicting](./api/sim_repo) | AWS Lambda | Python, Serverless | KNN over repo feature vectors with NumPy |

| [API Hosting](./api/node) | AWS Lambda | TypeScript, Node.js, Serverless | generic web API services, handle misc stuff like OAuth, user authentication |

| [UI](./front) | Github Pages / S3 | React, CSS, Semantic UI | UI stuff |