https://github.com/subhadarship/text-clustering

Clustering text data (data mining fall 2019)
https://github.com/subhadarship/text-clustering

bert clustering glove-embeddings lda nlp roberta topic-modeling visualization

Last synced: 7 months ago
JSON representation

Clustering text data (data mining fall 2019)

• Host: GitHub
• URL: https://github.com/subhadarship/text-clustering
• Owner: subhadarship
• License: mit
• Created: 2019-11-15T04:57:23.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-11-14T02:35:05.000Z (almost 4 years ago)
• Last Synced: 2025-01-24T11:28:43.040Z (9 months ago)
• Topics: bert, clustering, glove-embeddings, lda, nlp, roberta, topic-modeling, visualization
• Language: Jupyter Notebook
• Homepage:
• Size: 25.6 MB
• Stars: 2
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Text Clustering

![Alt Text](https://media.giphy.com/media/VSYyrK0MzKSyI/giphy.gif)

clustering text data (data mining fall 2019)

## Notes

- [`present.html`](https://github.com/subhadarship/text-clustering/blob/master/present.html) is created using revel.js

- [`topic_modeling_big.ipynb`](https://github.com/subhadarship/text-clustering/blob/master/topic_modeling_big.ipynb) uses more data for LDA than [`topic_modeling.ipynb`](https://github.com/subhadarship/text-clustering/blob/master/topic_modeling.ipynb). But it still cannot handle very large data (e.g. 1M)

## TODO

- [x] big data LDA (still less than a million samples)

- [x] visualize results LDA

- [x] big data neural models (check k-means time)

- [x] find optimum number of clusters for neural models

- [x] visualize results neural models

## Write-up

see [`text_clustering.pdf`](https://github.com/subhadarship/text-clustering/blob/master/text_clustering.pdf)

## LICENSE

[MIT](https://github.com/subhadarship/text-clustering/tree/master/LICENSE)