Inference on Unseen Data Related to Requirements Multi-Label Classification:
- Users can upload a CSV file of test multi-label requirements in a format similar to benchmark datasets (see download section).
- Exploratory data analysis engine will process the data shortly to predict multiple labels against requirement text.
- Users can download the result file after data processing by clicking a button.
Training the Model from Scratch
- Provide a CSV file containing multi-label requirements in a format similar to benchmark datasets (see download section).
- Choose encoder, data split method, number of folds, machine learning classifier, and multi-label data transformation method.
- Before training, sign up using an organizational email and provide the required data and purpose of experimentation.
- After approval, users can log in for one-time training and download performance artifacts.
- At the end of training, users can download performance-related artifacts to analyze the model behavior.