{"id":28323718,"url":"https://github.com/zhijiexiong/dlkt","last_synced_at":"2025-06-24T00:30:29.984Z","repository":{"id":222961693,"uuid":"702116496","full_name":"ZhijieXiong/dlkt","owner":"ZhijieXiong","description":"Migrated to pyedmine","archived":false,"fork":false,"pushed_at":"2025-05-08T10:41:27.000Z","size":11997,"stargazers_count":16,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"release","last_synced_at":"2025-06-02T01:06:38.611Z","etag":null,"topics":["cognitive-diagnosis","dataset-collection","dataset-info","deep-knowledge-tracing","deep-learning","dkt","exercise-recommendation","knowledge-tracing","model-ranking-list","ncd","neural-cognitive-diagnosis","paper-collection"],"latest_commit_sha":null,"homepage":"https://github.com/ZhijieXiong/pyedmine","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ZhijieXiong.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2023-10-08T14:44:11.000Z","updated_at":"2025-05-08T10:41:31.000Z","dependencies_parsed_at":"2024-04-13T18:48:14.886Z","dependency_job_id":null,"html_url":"https://github.com/ZhijieXiong/dlkt","commit_stats":null,"previous_names":["zhijiexiong/dlkt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ZhijieXiong/dlkt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhijieXiong%2Fdlkt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhijieXiong%2Fdlkt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhijieXiong%2Fdlkt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhijieXiong%2Fdlkt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZhijieXiong","download_url":"https://codeload.github.com/ZhijieXiong/dlkt/tar.gz/refs/heads/release","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZhijieXiong%2Fdlkt/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261582295,"owners_count":23180566,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cognitive-diagnosis","dataset-collection","dataset-info","deep-knowledge-tracing","deep-learning","dkt","exercise-recommendation","knowledge-tracing","model-ranking-list","ncd","neural-cognitive-diagnosis","paper-collection"],"created_at":"2025-05-25T16:14:42.506Z","updated_at":"2025-06-24T00:30:29.978Z","avatar_url":"https://github.com/ZhijieXiong.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[Document] | [DatasetInfo] | [PaperCollection] | [Experiment] | [RankingList]\n\n[Document]: md_doc/DOC.md\n[DatasetInfo]: https://zhijiexiong.github.io/sub-page/pyedmine/datasetInfo.html\n[PaperCollection]: https://zhijiexiong.github.io/sub-page/pyedmine/paperCollection.html\n[Experiment]: md_doc/Experiement.md\n[RankingList]: https://zhijiexiong.github.io/sub-page/pyedmine/rankingList.html\n# Important News!!!\n\nWe have migrated all code to **[PyEdmine](https://github.com/ZhijieXiong/pyedmine)**, which significantly refactors and optimizes the framework while introducing a unified experimental pipeline for **Knowledge Tracing (KT), Cognitive Diagnosis (CD), and Exercise Recommendation (ER)**. Additionally, PyEdmine open-sources all **pre-trained model weights and parameters** from the benchmark rankings.\n\n# Introduction\n\nA library of algorithms for reproducing knowledge tracing, cognitive diagnosis, and exercise recommendation models.\n\n# Quick-Start\n\n## Prepare\n\n1. Initialize project\n\n   - Create file `settings.json` in the root directory.\n\n   - Modify the environment configuration file `settings.json`\n\n     ```python\n     {\n       \"LIB_PATH\": \".../dlkt-main\",  # Change to the project root path\n       \"FILE_MANAGER_ROOT\": \"any_dir\"  # Any path used to store data and models\n     }\n     ```\n\n   - Run `set_up.py`\n\n     ```shell\n     python set_up.py\n     ```\n\n2. Place the original files of the dataset in the corresponding directory (Please refer to [Document (Section 1.3)](md_doc/DOC.md) for details)\n\n3. Data Preprocessing: Run ` example/preprocess.py`, for example\n\n   ```shell\n   python preprocess.py --dataset_name assist2009\n   ```\n\n## Knowledge Tracing\n\n1. Divide the dataset according to the specified experimental settings: Run `example4knowledge_racing/prepare_dataset/akt_setting.py`. For example, \n\n   ```shell\n   python akt_setting.py\n   ```\n\n   - For details on dataset partitioning, please refer to [Document (Section 1.6)](md_doc/DOC.md)\n\n2. Train model: Run the file under `example/train`. For example, train a DKT model\n\n   ```shell\n   python dkt.py\n   ```\n\n   - Regarding the meaning of parameters, please refer to [Document (Section 2)](Doc.md)\n\n## Cognitive Diagnosis\n\n1. Divide the dataset according to the specified experimental settings: Run `example4cognitive_diagnosis/prepare_dataset/akt_setting.py`. For example, \n\n   ```shell\n   python ncd_setting.py\n   ```\n\n2. Train model: Run the file under `example4cognitive_diagnosis/train`. For example, train a NCD model\n\n   ```shell\n   python ncd.py\n   ```\n\n## Exercise Recommendation\n\n1. Divide the dataset according to the specified experimental settings: Run `example4exercise_recommendation/prepare_dataset/kg4ex_setting.py`. For example, \n\n   ```\n   python kg4ex_setting.py\n   ```\n\n2. Train or evaluate different model or method\n\n   1. KG4EX\n      - step 1, train a `DKT` model to get mlkc\n      - step 2, train a `DKT_KG4EX` model to get pkc\n      - step 3, run `example4exercise_recommendation/kg4ex/get_mlkc_pkc.py`\n      - step 4, run `example4exercise_recommendation/kg4ex/get_efr.py`\n      - step 5, run `example4exercise_recommendation/kg4ex/get_triples.py`\n      - step 6, run `example4exercise_recommendation/train/kg4ex.py`\n\n   2. EB-CF (Exercise-based collaborative filtering)\n      - step1, change `example4exercise_recommendation/eb_cf/load_data` to get users' history data\n      - step2, run `example4exercise_recommendation/eb_cf/get_que_sim_mat.py` to get questions' similarity matrix\n      - step3, run `example4exercise_recommendation/eb_cf/evaluate.py`\n   3. SB-CF (Student-based collaborative filtering)\n      - Similar to EB-CF, run the code in `example4exercise_recommendation/sb_cf`\n\n# Contributing\n\nPlease let us know if you encounter a bug or have any suggestions by [filing an issue](https://github.com/ZhijieXiong/dlkt/issuesWe) \n\nWe welcome all contributions from bug fixes to new features and extensions.\n\nWe expect all contributions discussed in the issue tracker and going through PRs.\n\n# Contributors\n\n- https://github.com/ZhijieXiong\n- https://github.com/kingofpop625\n- https://github.com/shshen-closer\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhijiexiong%2Fdlkt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhijiexiong%2Fdlkt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhijiexiong%2Fdlkt/lists"}