Topic modeling for Persian using linear embedding features

requirement

• sklearn
• matplotlib
• plot
• numpy
• collections

Dataset

There are 7 topics(folders) each of which contains 10 documents.
3 documents are used for testing in each topic.

How to use

all the data is already in the 'data' folder. all you need to do is to run the main.py file.

documentation

a full documentation in Persian is available in the report folder

result

accuracy report:

learning curve: