It is a question categorization classifier to differentiate different categorize of questions, the test data set is provided, just mold your data set according to the example files and you are good to go
It uses logistic regression model for the natural language processing,the LR model is one of the most better performed model specially when it comes to NLP.
Set your labels schema as 'labels' and your questions schema as 'Answers', it includes cleaning of data. The data is also visualized just to help you out, the number of words build for dictionary is also printed.
Important: Use jupyter notebook to open the files, python3 is used to code, Enjoy :)