• Setup python envoirnment and run given .ipynb files in juypter notebook.
• Extract corpus in twitter-gender-corpus folder according to structure.
• Every file is already setup so all you need to do is to sequentionly run those files to generate all datasets and models.
• Assignment 3 - Stylometry Based Method.ipyub generate own csv file and then use it to generate model.
• Assignment 3 - Content Based Method.ipyub generate all files for word and char n-gram and use them it generate model.
• Assignment 3 - Clustering Based Method.ipyub use csv files generated by Content Based Method.ipyub so run content based before running clustering