Skip to content

Web Application to get estimation of affinity between you and your twitter friends/followers using Machine Learning and IBM Watson.

Notifications You must be signed in to change notification settings

gary1998/ibm-hackathon-2019

Repository files navigation

Icon

FRIEND AFFINITY FINDER v1.0 (2019)

By Team EDGE

For IBM HackChallenge 2019


Steps to setup using Docker Containers:

 docker pull gary29198/faf-frontend:latest 
 docker pull gary29198/faf-backend:latest 
 docker run -d -p 8000:8000 gary29198/faf-frontend 
 docker run -d -p 5000:5000 gary29198/faf-backend 

Steps to setup using GitHub Repository:

1) Clone the repository, ofcourse:

git clone https://github.com/gary1998/ibm-hackathon-2019.git

2) Install all the dependencies on your system:

cd source_code
pip install -r requirements.txt

(In case you don't have pip installed on your system: Install pip v19.1.1)

3) Start the backend server by following commands:

python source_code/backend.py

4) Start the frontend UI on server by following command: If you're using Python v2.7

python -m SimpleHTTPServer 8000

If you're using Python v3.7

python -m http.server 8000

Steps to use:

1) Access the UI on any web-browser

In case, you used GitHub Repository:

http://localhost:8000/source_code/

In case, you used Docker Images:

http://localhost:8000/

Dashboard

2) Login to UI using Twitter Developer Credentials

Login

3) Select any friend, follower, text or your own tweets to analyze

Analysis

4) Visualize 27 different properties of every friend, follower, text, or own tweets you analyzed in Card and Progress Bar form

Cards

5) Estimate affinity in friends, followers, text, or own tweets in 3D graph

3D Affinity Graph


Steps to install pip v19.1.1:
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
python get-pip.py

Copyright EDGE © 2019

About

Web Application to get estimation of affinity between you and your twitter friends/followers using Machine Learning and IBM Watson.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published