hfut-lec / edustudio

EduStudio is a Unified Library for Student Cognitive Modeling including Cognitive Diagnosis (CD) and Knowledge Tracing (KT).

EduStudio is a Unified Library for Student Cognitive Modeling including Cognitive Diagnosis(CD) and Knowledge Tracing(KT) based on Pytorch.

Navigation

Resource Name	Description
Eco-Repository	A repository containing resources about student cognitive modeling: papers, datasets, conferences&journals
Eco-Leaderboard	A leaderboard demonstrating performance of implemented models
EduStudio Documentation	The document for EduStudio usage
Reference Table	The reference table demonstrating the corresponding templates of each model

Description

EduStudio first decomposes the general algorithmic workflow into six steps: configuration reading, data prepration, model implementation, training control, model evaluation, and Log Storage. Subsequently, to enhance the reusability and scalability of each step, we extract the commonalities of each algorithm at each step into individual templates for templatization.

Figure: Overall Architecture of EduStudio

Quick Start

Install EduStudio:

pip install -U edustudio

Example: Run NCDM model:

from edustudio.quickstart import run_edustudio

run_edustudio(
    dataset='FrcSub',
    cfg_file_name=None,
    traintpl_cfg_dict={
        'cls': 'GeneralTrainTPL',
    },
    datatpl_cfg_dict={
        'cls': 'CDInterExtendsQDataTPL'
    },
    modeltpl_cfg_dict={
        'cls': 'NCDM',
    },
    evaltpl_cfg_dict={
        'clses': ['PredictionEvalTPL', 'InterpretabilityEvalTPL'],
    }
)

To find out which templates are used for a model, we can find in the Reference Table

License

EduStudio uses MIT License.