https://github.com/prak112/document-wordcloud

Insights of commonly used words in the document represented through a word cloud
https://github.com/prak112/document-wordcloud

wordcloud-visualization

Last synced: 10 days ago
JSON representation

Insights of commonly used words in the document represented through a word cloud

• Host: GitHub
• URL: https://github.com/prak112/document-wordcloud
• Owner: prak112
• License: mit
• Created: 2021-04-27T15:37:45.000Z (about 5 years ago)
• Default Branch: main
• Last Pushed: 2023-06-14T20:13:37.000Z (about 3 years ago)
• Last Synced: 2025-01-15T01:41:55.763Z (over 1 year ago)
• Topics: wordcloud-visualization
• Language: Jupyter Notebook
• Homepage:
• Size: 4.28 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Approach

## Extraction of commonly used terms in the GYBN policy briefs

- Use PyPDF2 library to extract text from .pdf file

- Create a dictionary with counter for each identified word

- Filter common stop-words (based on context)

## Evaluation of the terms to identify meaning

- Load data into Dataframe

- Visualize wordcloud from Dataframe, learnt from this [Datacamp tutorial](https://www.datacamp.com/community/tutorials/wordcloud-python)

## Output

![Most commonly occuring words in the document](output/Nbs_wordcloud.png)