search

MaartenGr / BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.
https://maartengr.github.io/BERTopic/
MIT License
6.19k stars 765 forks source link

Not showing Topic after topic_model.get_topic_info() #2205

Open hari-chalise opened 2 weeks ago

hari-chalise commented 2 weeks ago

Discussed in https://github.com/MaartenGr/BERTopic/discussions/2199

Originally posted by **hari-chalise** October 26, 2024 Hi Maarten, I am trying to Topic modelling BY using BERTopic for Nepali News Article . And now i am just use 1000 Rows of data of news article with two column. But After complete all step embedding, dimensionality reduction, clustering and representation but after running topic_model.get_topic_info() i get nan nan and so on what is my mistake i can't figure out. ![issue_topic_Modelling](https://github.com/user-attachments/assets/d37da367-c093-4987-9bbf-36fc68a43cb0)
hari-chalise commented 2 weeks ago

I it required to add whole code here to better clarification?

MaartenGr commented 2 weeks ago

@hari-chalise Yes, please fill in all the information. Which version of BERTopic are you using? What code are you running? Are you running into any errors? If there is an error in the code, I would first need to see it for example.

hari-chalise commented 3 days ago

I mean , Can I used BERTopic For Topic Modelling for Nepali News Article ? I was recently tried to do but i encountered error such as Blank in Topic. Currently i am unable to include all error with details code because of my system error so please reply me on my question as much as possible i will provide details @MaartenGr

MaartenGr commented 2 days ago

@hari-chalise

I mean , Can I used BERTopic For Topic Modelling for Nepali News Article

Yes, that should be possible!

To help you, I will need more information. I need to know how you instantiate the BERTopic class. So, what's in the following?

topic_model = BERTopic(
  ...
)

I will also need to know which version of BERTopic you are using.

I can only help you if you provide me that information and then I'll be happy to help you!