aboutsummaryrefslogtreecommitdiffhomepage
path: root/src
Commit message (Expand)AuthorAgeFilesLines
...
* | add link to formal codebookadamjanovsky2024-01-191-0/+2
|/
* refactoring here and thereadamjanovsky2023-11-243-60/+78
* revert hyperparams on segment extractionadamjanovsky2023-11-231-1/+1
* hardcode hyperparams for all stagesadamjanovsky2023-11-233-25/+83
* hardcode optimal hyperparams for embeddingsadamjanovsky2023-11-231-4/+4
* continue refactoring the notebookAdam Janovsky2023-11-143-3/+6
* Merge branch 'bump-req-python-to-3-10' into reference-analysisAdam Janovsky2023-11-1424-40/+51
|\
| * bump required python to 3.8Adam Janovsky2023-11-1424-40/+51
* | fix some ruff errorsAdam Janovsky2023-11-141-1/+1
* | merge fresh mainAdam Janovsky2023-11-1419-90/+248
|\|
| * fix new ruff errorsAdam Janovsky2023-11-1010-20/+22
| * Merge pull request #369 from crocs-muni/fix/better-log-filename-and-requireme...adamjanovsky2023-10-261-1/+1
| |\
| | * add .log suffix to default log filenameadamjanovsky2023-10-181-1/+1
| * | Wrap CC scheme download in try-except and continue on fail.J08nY2023-10-231-1/+4
| * | Revert "feat: Initial implementation of tool/dataset version check"GeorgeFI2023-10-221-8/+0
| * | feat: Initial implementation of tool/dataset version checkGeorgeFI2023-10-221-0/+8
| |/
| * Merge pull request #357 from crocs-muni/feat-pytesseract-wrapperadamjanovsky2023-10-121-5/+10
| |\
| | * fix: Fixed calling method on NoneTypeGeorgeFI2023-10-011-1/+1
| | * fix: OCR with Pytesseract fixed nowGeorgeFI2023-09-251-1/+2
| | * feat: Added pytesseract wrapperGeorgeFI2023-09-201-5/+9
| * | Fix Australian scheme in-eval.J08nY2023-10-102-2/+2
| |/
| * style: Fix of mypy typing - calling methods on potential None objectGeorgeFI2023-09-011-0/+7
| * Merge branch 'main' into feat-fips-referencesGeorgeFI2023-09-016-51/+104
| |\
| | * Fix CC scheme certificate matching.J08nY2023-08-242-0/+11
| | * Add rudimentary profiling.J08nY2023-08-244-49/+93
| | * Do not rerun pdf to text conversion, it is pointless.J08nY2023-08-241-2/+0
| * | fix: Fixing of typesGeorgeFI2023-08-251-4/+6
| * | refactor: Refactored graph building functionsGeorgeFI2023-08-251-0/+83
| * | Merge branch 'main' into feat-fips-referencesGeorgeFI2023-08-202-4/+10
| |\|
| | * Fix Canada CC scheme download.J08nY2023-08-142-4/+10
| * | refactor: Light refactor of fips returns statementsGeorgeFI2023-06-101-6/+3
| |/
* | bump referencesadamjanovsky2023-11-1413-190/+759
* | recertification -> reevaluation in codeAdam Janovsky2023-10-201-4/+4
* | rename recertification: re-evaluationAdam Janovsky2023-10-2013-198/+198
* | improve write-up of reference annotation methodologyAdam Janovsky2023-10-201-31/+30
* | add inter-annotator agreementAdam Janovsky2023-10-201-0/+39
* | finalize annotation labelsAdam Janovsky2023-10-1917-1493/+1321
* | ditch lang, fix groupbyadamjanovsky2023-09-292-10/+13
* | minor refactoring segment extractorAdam Janovsky2023-09-221-13/+10
* | fix sentence extractionAdam Janovsky2023-09-221-22/+25
* | clean labels when loading dataframesadamjanovsky2023-09-211-0/+2
* | revert pydanticadamjanovsky2023-09-211-2/+1
* | fixes and bump reqsAdam Janovsky2023-09-212-5/+14
* | multiple fixes segment extractoradamjanovsky2023-09-174-67/+138
* | fix anssi cert_id normalizationadamjanovsky2023-09-171-3/+5
* | WiP: introduce actually extracted cert_id_keywords instead of canonicalAdam Janovsky2023-09-175-20/+72
* | delete nonexisting cert from test splitadamjanovsky2023-09-151-2/+1
* | delete one test annotation for which we dont have certAdam Janovsky2023-09-141-1/+0
* | sort values in train.csv annotationsAdam Janovsky2023-09-141-197/+197
* | enrich train dataset with some samples from testadamjanovsky2023-09-083-1251/+1347