0.4.0 (2025-04-04)
Features
- (Kaggle) add base template for competition: tabular-playground-series-may-2022 (#481) (f3405ca)
- a unified CoSTEER to fit more scenarios (#491) (cddbd02)
- add a new competition (#474) (2fc0d77)
- add a tool to enable saving workspace files into a specific folder (#728) (bca864b)
- add baseline score stat (#590) (2948026)
- add configurable volume mode for Docker volumes in env.py (#537) (642a022)
- add constraint labels for semantic search (#680) (0584cfc)
- add cross validation to workflow (#700) (82e9b00)
- add describe_data_folder_v2 (#738) (bc8e846)
- add do_truncate control for the load function (#656) (2b960a5)
- add do_truncate control for the load function (#656) (2b960a5)
- add eda to data science scenario (#639) (35aa479)
- add hypothesis guidelines and rule-based ranking (#746) (c077b82)
- Add line length limit to shrink_text function and settings (#715) (75ed5e1)
- add loop_n parameter to the main loop (#611) (778c166)
- add max time config to costeer in data science (#645) (534686c)
- add mlebench submission validitor (#545) (712d94a)
- add model removal and adjust some framework logic (#681) (1edf881)
- add output_path to load function of LoopBase (#628) (dd33726)
- add pipeline coder (#742) (759f295)
- add rank into report (mle_summary) (#665) (13f7922)
- add restart and fix unzip (#538) (ed2c7d1)
- add retry mechanism with wait_retry decorator and refactor diff generation (#572) (de1cd72)
- add the shape of the CSV to the dataset description (#561) (a10c881)
- add timeout settings and cleanup step in data science runner (#539) (295abd5)
- add type checker to api backend & align litellm and old backend (#647) (d38eae9)
- align mlebench data and evaluation & several fix on kaggle workflow (#477) (f6c522b)
- backend: integrate LiteLLM API Backend (#564) (f477687)
- base data science scenario UI (#525) (39917b3)
- condaenv & full docker env (#668) (084dd6d)
- diff mode fix (#569) (0c509f5)
- display LLM prompt (#676) (8c93bba)
- Dynamically find and use sample submission file in eval tests (#542) (5f12b44)
- end-to-end optimization (#473) (d41343a)
- Enhance eval script with file cleanup and detailed submission checks (#529) (cf2ff92)
- exclude invalid session log folder (#554) (fa86e4d)
- improve the framework's ability to adaptively adjust the model (#629) (93806f3)
- independent use_azure_token_provider on chat and embedding (#452) (d223004)
- integrate azure deepseek r1 (#591) (e79ce5c)
- kaggle refactor (#489) (1b057d0)
- kaggle: several update in kaggle scenarios (#476) (245d211)
- loader prompt & simplify YAML loading and update data loader specifications (#736) (86f8bbf)
- make spec optional (#719) (a16b70f)
- Make system prompt role customizable in LLM settings (#632) (e4acd92)
- multi log folder, replace "epxx" in workspace path (#555) (8a69c9c)
- new exp gen v2 implementation (#725) (5dcc2d5)
- new-york-city-taxi-fare-prediction_template (#488) (a9caab7)
- out spec change for o1-preview (#666) (22894bd)
- refactor for general data science (#498) (7002dc4)
- refine logic for qlib_factor_from_report (#463) (21348d8)
- run benchmark on gpt-4o & llama 3.1 (#497) (64af0b5)
- summary and UI update (#581) (efa51f9)
- template changes for some kaggle competitions (#484) (2e38000)
- track and log accumulated completion cost in LiteLLMAPIBackend (#727) (b294a95)
- update prompts and descriptions for data science components (#731) (c20e226)
- variable printing tool of data_science coder testing (#658) (116c061)
Bug Fixes
- a default conf in scen qlib (#503) (d64a228)
- a small bug in exp_gen (#606) (f734dde)
- add check when retrying gen model codes (#699) (3b82f15)
- add DSExperiment type check and directory validation in log proc… (#535) (f59b12c)
- add ensemble test, change to "use cross-validation if possible" in workflow spec (#634) (acc97a8)
- add force parameter for cache_with_pickle & using cache when get kaggle leaderboard (#687) (c8841e5)
- add metric name check for valid scores (#724) (acc2ffb)
- add retry mechanism for GPU device check in DockerEnv (#573) (a780cfb)
- add scores.csv checking in ensemble_test (#567) (01808b4)
- add stdout context length setting and improve text shrinking logic (#559) (4ac26a6)
- align components' name (#701) (295a114)
- auto continue small bug (#598) (75eaecf)
- avoid try-except in ensemble eval prompts (#637) (5c58d6e)
- avoid warning for missing llama installation when not in use (#509) (5ec3422)
- change devault to default (#688) (7f401cd)
- change ensemble test (#622) (5de3595)
- change summary info of log folder (#552) (0eb258d)
- clarify an ambiguous explanation (#705) (5dbfc68)
- clarify cross_validation (#644) (906993e)
- coder prompt & model test text (#583) (0a41227)
- correct the configuration inheritance relationship (#671) (30b1ff8)
- default emb model (#702) (4329a72)
- direct_exp_gen to json_target_type in DSExpGen class (#661) (428b74a)
- docker error will trigger retry and data science runner loop set to 3 (#602) (ad785e0)
- ensure expected type (#593) (098a9a6)
- filter empty log traces in ds UI (#533) (1a2057c)
- fix a bug in cross validation (#618) (05a4f10)
- fix a bug in ensemble test script (#713) (ad32100)
- fix a bug in initial tasks (#635) (edb552e)
- fix a bug in kaggle conf (#459) (b4ed32b)
- fix a bug in progress_bar filter (#712) (ba5a84d)
- fix a bug in proposal (add last loop's exception to last task desc) (#596) (419186f)
- fix a bug in regular expression exception processing (#734) (67d3702)
- fix a bug in threshold score display (#592) (0b0a2dc)
- fix a bug related to model_name in ensemble (#692) (c6ce473)
- fix a minor bug (#694) (1405d8d)
- fix an error in model_coder prompt (#690) (4528826)
- fix combined_factors_df.pkl not loading in docker (#697) (3984b99)
- fix docs build error (#711) (c9e1d32)
- fix ExtendedSettingsConfigDict does not work (#660) (3a877f3)
- fix kaggle templates path error (#747) (3b3f504)
- fix KeyError direct_exp_gen (#735) (7200682)
- fix some bugs (ensemble output, HPO, model tuning) (#648) (818ee29)
- fix some bugs in the ensemble component (#595) (c0990ab)
- fix some bugs in workflow unit test (#624) (f845dcc)
- fix some description errors in direct_exp_gen (#698) (dfaacb6)
- fix some minor bugs and add AutoML & cross-validation (#604) (18c5ef2)
- fix submission file search and add TODO in env.py (#544) (54d930e)
- fix task return dict with wrong format (#558) (2008244)
- fix the errors in the coder and evaluator of the five components (#576) (c487f83)
- handle division by zero in percentage calculations (#550) (de16c91)
- handle invalid regex patterns in filter_progress_bar function (#579) (b0daee0)
- Handle ValueError when resolving relative path for uri (#585) (4c7765a)
- include data information in cache key generation (#566) (26dda46)
- keep some txt files (#557) (54aba85)
- mle_score save problem (#674) (ca2e478)
- move docker timeout message to __run() (#620) (585f4f9)
- move mlebench check into runner (#556) (b0f7965)
- move next_component_required logic to DSTrace class and accurate implement (#612) (c20d311)
- patching weird azure deployment (#494) (89c50ae)
- qlib and other scenario bugs (#636) (98de31d)
- refine prompt to generate the most simple task in init stage (#546) (9d6feed)
- replace API call with build_cls_from_json_with_retry function (#548) (eb72a47)
- replace func "len()" in ensemble test code to support various data type (#739) (ab9c7b9)
- return 1D embedding if create_embedding receive a string input (#670) (4a9c318)
- rich.print error when some control char in output (#684) (ec0cb2a)
- Runnable on first complete & Rename method to next_incomplete_component for clarity (#615) (93d9f63)
- runner COSTEER evaluator (#693) (6a379ec)
- save only one mle_score pkl for a running exp (#675) (f87ab67)
- Set default value for 'entry' parameter in Env.run method (#643) (e50d242)
- sort file name for cache reproduction (#588) (7158410)
- sota comparison logic (#608) (3575372)
- target json type & round (#662) (58cb58f)
- templates bug (#456) (434a868)
- trace summary df showing in dsapp (#551) (177096d)
- unzip kaggle data (#464) (3a9fc8e)