https://github.com/1bk/gdelt_headline_analysis

News Headlines Analysis of (two) Websites - Using GDELT 2.0 Event Database
https://github.com/1bk/gdelt_headline_analysis

bokeh hacktoberfest headlines html-parser jupyter-notebook loading-bar nltk parsetree python sqlite

Last synced: about 1 month ago
JSON representation

News Headlines Analysis of (two) Websites - Using GDELT 2.0 Event Database

• Host: GitHub
• URL: https://github.com/1bk/gdelt_headline_analysis
• Owner: 1bk
• Created: 2018-08-01T17:28:31.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-10-25T21:42:38.000Z (about 5 years ago)
• Last Synced: 2023-12-09T17:40:47.432Z (11 months ago)
• Topics: bokeh, hacktoberfest, headlines, html-parser, jupyter-notebook, loading-bar, nltk, parsetree, python, sqlite
• Language: HTML
• Homepage:
• Size: 715 KB
• Stars: 3
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# gdelt_headline_analysis

News Headlines Analysis of (two) Websites - Using GDELT 2.0 Event Database

Main file to run: 

- analysis.ipynb (viewable on GitHub); or

- analysis.html (if charts won't load on GitHub); or

- analysis.pdf (if all the above fails to load chart)

`Note: 'download.py' has been limited to download only 50 files for demonstration purposes. Feel free to remove the limit in the script for "full experience".`

If run locally (only), the order of files to run:

1. download.py

2. process.py

3. extract.py

4. analysis.ipynb <- using Jupyter Notebook.