Skip to content

NLP Based document visualiser. Creates word clouds and topic clouds based off input document. Created as part of University of Sydney Industry Project

Notifications You must be signed in to change notification settings

TabishB/NLP-Document-Visualiser

Repository files navigation

Forum Mind

ForumMind’s project primarily encapsulates the analysis of any given text body (JSON, PDF and so on), performing the categorisation, summation and relation of such in terms of topic analysis and prevalence in easy to view graphical formats.

Through heavy utilisation of NLTK/NLP text mining, database and front end web development the team has been able to analyse, store and graphically display large amounts of text to provide accurate and easily interpreted overviews. This enables users to determine context and relevance quickly, saving time on researching necessary resources or determining the relevance of any given text and providing a new level of understanding.

Getting Started

  • [Installation Instructions](Installation Instructions)
  • [User Walkthrough](User Walkthrough)
  • Demo Video
  • [Final Deployment Set up Manual](Final Deployment Set up Manual)
  • [Database Implementation](Database implementation)

Built With

Tools used

Tool Description Version
Project Management Tools
Bitbucket Version Control System N/A
Trello Task allocation and N/A
Google Drive Documentation Storage N/A
------------------------------------ -------------------------------------- ---------
Django Web App Tools
Django Web Framework 2.1.1
Bootstrap 4 CSS Framework 4.1
D3.JS Data visualization framework.
Django-cripsy-forms Bootstrap style css for Django Forms 1.7.2
Python 3 2018.5
------------------------------------ -------------------------------------- ---------
Django Database Tools
Mlab MongoDB cloud hosting service N/A
Django-rest-framework- mongoengine 3.3.1
Djongo 1.2.30
------------------------------------ -------------------------------------- ---------
LDA Tools
Nltk 3.3
Genism 3.6.0
Numpy 1.15.2
Pandas 0.23.4
Spacy 2.0.12
Mallet 2.0.8
Python 3 2018.5

Languages: • python

Frameworks: • Django • Bootstrap • D3.js

Libraries: • NLTK • pandas • scikit-learn • matplotlib • pyLDAvis • Gensim • spacy

Development Environments: • Jupyter • Atom • Visual Studio Code

Version Control: • Bitbucket • GitKraken • SourceTree

Databases: • MongoDB

Authors

  • Sam Higgs
  • Emma Muscat
  • Shenin Faizah
  • Thad Shattuck
  • Roy Gu
  • Tabish Bidiwale

About

NLP Based document visualiser. Creates word clouds and topic clouds based off input document. Created as part of University of Sydney Industry Project

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published