INFERENCE ON UNSEEN DATA RELATED TO FUNCTION/NON-FUNCTIONAL REQUIREMENT CLASSIFICATION

  • Users can upload a csv file of functional and non-functional requirements in a format similar to benchmark datasets (see download section).
  • On successful activation of processing command, exploratory data analysis engine will process the data shortly in order to predict functional or non-functional class labels against requirement text.
  • User will be able to download the result file after data processing by clicking on the button.

TRAINING THE MODEL FROM SCRATCH

  • Users need to provide a csv file containing multi-class requirements in a format similar to benchmark datasets (see download section).
  • User has the freedom to choose data split method.
  • User has the freedom to choose number of folds for data split.
  • User has the freedom to choose number of epochs.
  • User has the freedom to choose batch size.
  • User has the freedom to choose learning rate.
  • Sign up preferably using an organizational email account with required data and purpose of experimentation.
  • After completing the Sign-Up process, users need to wait for account approval and training permission.
  • If the request is approved, users can log in for one-time training.
  • On successful activation of the processing command, the exploratory model training engine will process the data shortly to train the model.
  • At the end of training, users can download performance-related artifacts to analyze model behavior.