oentaryorj / smu.softeng.crossact Goto Github PK

Python Boilerplate contains all the boilerplate you need to create a Python package.

• Free software: BSD license
• Documentation: https://crossact.readthedocs.io

• Full Dataset
• Toy Dataset (100users)

• KEEN MODEL

  • Running the code to save the data

    • We need to create three files for each Github or StackOverflow dataset (i.e., interactions_non_activities.pickle, i_features_non_activities.pickle, and u_features_CO.pickle)

      • interactions_non_activities.pickle: interaction between users and items
      • i_features_non_activities.pickle: item features
      • u_features_CO.pickle: user features

  • Training KEEN model

    • We have two steps to train KEEN model:

      • Training interaction model (See step 1a in the KEEN model)
      • Training threshold model (See step 1b in the KEEN model)

• ACT MODEL

  • Running the code to save the data

    • We need to create two files for each Github or StackOverflow dataset (i.e., interactions_with_first_activities_for_ACT.pickle, interactions_with_second_activities_for_ACT.pickle)

      • interactions_with_first_activities_for_ACT.pickle: interaction between users and items for the first activity
      • interactions_with_second_activities_for_ACT.pickle: interaction between users and items for the second activity

  • Training ACT model

    • We have two steps to train ACT model:

      • Training interaction model (See in the ACT model)
      • Training threshold model (See in the ACT model)

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.