/hn-favorites-topic-modelling

Hacker News Favorites Topic Modelling with Selenium, spaCy and Gensim

Primary LanguageJupyter NotebookMIT LicenseMIT

Hacker News Favorites NLP Analysis

Introduction

If you are reading this probably you know Hacker News, an aggregation platform for computer science, start-ups, etc. It was created and maintained by Y Combinator Startup Accelerator.

Installation and usage

  1. Python environment
git clone ...
cd ...
virtualenv .venv
. .venv/bin/activate
pip install -r requirements.txt
  1. Selenium Chrome webdriver

We use Chrome backend for Selenium in headless mode. https://sites.google.com/a/chromium.org/chromedriver/downloads the chromedriver version for your Chrome and install in "contrib" subfolder.

  1. Just execute jupyter-lab
jupyter-lab

License

MIT License