Edustudio

⚡️New

- The paper of EduStudio is accepted by Frontiers of Computer Science! [paper](https://journal.hep.com.cn/fcs/EN/10.1007/s11704-024-40372-3)
Highly recommend reading the paper to further understand the design philosophy and usage of EduStudio!

🔧 Bug Fixes
- issue 19 on MGCD
- issue 20 on CL4KT
- issue 21 on SAKT and CT_NCM
- issue 23 and issue 24 on CNCD
- issue 33 on Fair_NCDM
- issue 31 on InterpretabilityEvalTPL
- issue 32 on IdentifiabilityEvalTPL
- issue 22 on cachedata
- miscs raise in issue 28, 29

⚡️ New
- add `IdentifiablityEvalTPL` including `Identifiability Score (IDS)` metric that is proposed in [[WWW 2024] IC-IDM](https://arxiv.org/pdf/2309.00300)
- add `Matrix Factorization (MF)` model in the CD model section
⬆️ Improvements
- [optimize] `get_stu_status` API is iterative in TrainTPL

⬆️ Improvements
- change the dataset download source from GitLab to [HuggingFace](https://huggingface.co/datasets/lmcRS/edustudio-datasets/tree/main)
- add external [datasets.yaml](https://huggingface.co/datasets/lmcRS/edustudio-datasets/blob/main/datasets.yaml) support for downloading datasets automatically

🔧 Bug Fixes
- fix `DT_INFO_DICT` option in frame_cfg (specified in settings.py) not working bug

⚡️New Features
- Add `DCD` model: [NeurIPS 2023] [Disentangling Cognitive Diagnosis with Limited Exercise Labels](https://openreview.net/pdf?id=ogPBujRhiN)
- Add `FairCD` model: [SCIS 2023] [Understanding and Improving Fairness in Cognitive Diagnosis](https://www.sciengine.com/SCIS/doi/10.1007/s11432-022-3852-0;JSESSIONID=90890fc0-d1be-4694-ac0d-0b12a450f9ad)
- Add `AdversarialTrainTPL` for adverarial training
- Add `FairnessEvalTPL` for fairness evaluation, including DP, EO and FCD metrics.
- Add R2M operations of `SLP_Math` and `SLP_English` datasets, which are from [SLP](https://aic-fe.bnu.edu.cn/en/data/index.html) dataset.
- Add `EDUSTUDIO_VERSION` option in settings.py (i.e., frame_cfg)

⬆️ Improvements
- Divide functionality of `M2C_BuildSeqInterFeats` ➡️ `M2C_RandomDataSplit4KT` & `M2C_BuildSeqInterFeats`
- Rename `EduTrainTPL` ➡️ `GeneralTrainTPL`
- Rename `BinaryClassificationEvalTPL` ➡️ `PredictionEvalTPL`
- Rename `CognitiveDiagnosisEvalTPL` ➡️`InterpretabilityEvalTPL`
- Rename some atomic operations: `Cpt` ➡️ `KC `
- Enrich [Docs](https://edustudio.readthedocs.org)

🔧 Bug Fixes
- K-fold split for KT

This release is meant to fix bugs:
- Fix bugs in IRT、MIRT
- Fix bugs in DeepIRT、DKVMN、DKT+、QIKT、QDKT

- Fixed Data Cache bug
- Fixed UnifyConfig Bug
- Add fixed random seed for each fold training