could you please tell me how can i get the data?

[GuangyuanWang]

i cant find it anywhere

[franticnerd]

Sorry for the late reply. You can get the DBLP data used in the experiments here:

https://drive.google.com/file/d/1GbxKrxrmFrKt5vgDHP1xe1Qr_rfvR1jh/view?usp=sharing

[GuangyuanWang]

a great help to me, thanks.

[nstfk]

Hi I was wondering if the seed_keywords.text and doc_ids.txt are supposed to be created before running and what is their content?

[fracivilization]

I've run the code. Probably, seed_keywords.text and doc_ids.txt is made by the preprocess code "cluster-preprocess.py", but the error message is hidden because of "time" command in "run.sh". So, I recommend checking your error message after remove "time" in "run.sh".

[jsw-zorro]

Does anyone know that how can I get the raw dataset?

[mortezamsp]

i downloaded that data, and fixed the path, but the problem is 'run.sh' gets errors, it says that: /seed_keywords.txt and doc_ids.txt are missing. actually they doesnt exist in the link you shared in gogle drive.

[mortezamsp]

Does anyone know that how can I get the raw dataset?

https://drive.google.com/file/d/1GbxKrxrmFrKt5vgDHP1xe1Qr_rfvR1jh/view?usp=sharing
isn't it?

[SasCezar]

In the 'dblp' folder, duplicate the 'input' folder and rename it to 'raw'.

[Aravindkumar-Rajendran]

How to create 'embeddings.txt' file in a custom dataset?

[mortezamsp]

salam i dont remember that project, but your question seems to have a genral answer: change code to accept a string instead of text file.

On Wed, Apr 13, 2022, 7:28 AM Aravind Kumar @.***> wrote:

How to create 'embeddings.txt' file in a custom dataset?

— Reply to this email directly, view it on GitHub https://github.com/franticnerd/taxogen/issues/1#issuecomment-1097500321, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHFQE7HZFGTGWUDZEIJGIJTVEYZ5ZANCNFSM4ESRUGNA . You are receiving this because you commented.Message ID: @.***>