6818ada2cf
fix: fix some minor bugs ( #758 )
2025-04-04 23:54:54 +08:00
11e8acc88b
feat: add a check for whether values in score_df are NaN ( #756 )
...
* add a check for whether values in score_df are NaN
* fix ci
* change raise to assert
2025-04-04 22:44:55 +08:00
9415113e01
feat: add reasoning_effort parameter to LiteLLMAPIBackend and LLMSett… ( #754 )
...
* feat: Add reasoning_effort parameter to LiteLLMAPIBackend and LLMSettings
* style: Use consistent quotation marks for reasoning_effort literals
2025-04-04 19:37:40 +08:00
d3414ea07d
fix: task_gen for better understanding ( #752 )
2025-04-04 17:09:26 +08:00
8bd2714814
feat: joblib cache ( #749 )
...
* cache function
* fix test
* bin cache
* fix test
* fix test
* fix test
* cache for different source
* cache for localenv
* remove unnecessary log
* reformat
* remove unrelated modify
2025-04-04 12:08:18 +08:00
200764d38b
workflow entrypoint check ( #748 )
2025-04-04 12:07:46 +08:00
756dfba53f
fix: fix kaggle templates path error ( #747 )
...
* fix kaggle templates path error
* add env.py dependence
* reformat with lint
2025-04-04 11:20:33 +08:00
1f0032bc50
fix when score is a string ( #750 )
2025-04-03 23:48:38 +08:00
9eded6faa8
feat: add hypothesis guidelines and rule-based ranking ( #746 )
...
* 1. add hypothesis guidelines 2. add weighted scoring
* fix CI & speed up exp_gen
* random but reproduciable choice on hypothesis
---------
Co-authored-by: Xu <v-xuminrui@microsoft.com >
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-04-03 18:48:28 +08:00
8783781daa
refactor: Improve data handling and representation in eval tests and prompts ( #740 )
2025-04-03 13:53:25 +08:00
da8fbcf4ee
feat: add pipeline coder ( #742 )
...
* init commit
* limit problem numbers
* ensemble lower case
* add runtime and spec to coder
* submission check notice
* sub EDA in sample execution
* avoid lightgbm
* add time limit to scenario
* rephrase the submission check
* give positive feedback when facing warning in check
* ENABLE FEEDBACK
* fix feedback bug
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2025-04-03 13:00:11 +08:00
22ed8b522b
fix: fix KeyError direct_exp_gen ( #735 )
...
* fix KeyError direct_exp_gen
* fix KeyError direct_exp_gen
* fix fin_factor fetch data error
2025-04-03 12:01:10 +08:00
7fc5e73f76
fix: replace func "len()" in ensemble test code to support various data type ( #739 )
...
* replace len with def get_length
* update get_length implementation
2025-04-02 19:52:54 +08:00
e30768969d
feat: add describe_data_folder_v2 ( #738 )
...
* add describe_data_folder_v2
* fix ci
* fix
* add packages
2025-04-02 19:38:43 +08:00
bc8e9dc23a
costeer max loop as hyperp & skip workflow in eval ( #737 )
2025-04-02 14:18:42 +08:00
1474478768
feat: new exp gen v2 implementation ( #725 )
...
* first framework commit
* idea proposal v2
Co-authored-by: Roland Minrui <RolandMinrui@users.noreply.github.com >
* fix a small bug in v1
* fix a small bug
* add problem to DShypothesis
* use exp gen as unified interface
* merge yuante's code into pr
* fix a small bug in draft
* update all minrui's code
* small update
* fix small bug & remove useless code
* fix return type
* fix CI
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
Co-authored-by: Roland Minrui <RolandMinrui@users.noreply.github.com >
Co-authored-by: Xu <v-xuminrui@microsoft.com >
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-04-02 13:37:47 +08:00
260b563710
feat: loader prompt & simplify YAML loading and update data loader specifications ( #736 )
...
* refactor: Simplify YAML loading and update data loader specifications
* docs: Add comment explaining FunctionLoader usage in tpl.py
* lint
* lint
2025-04-01 22:36:25 +08:00
3ef0b21350
chore: split dsapp to pages & add llm_logs showing ( #733 )
...
* split dsapp to pages & add llm_logs showing
* some changes
* small bug
* add time info
* do not test UI in test_import
* cache stdout
2025-04-01 20:55:10 +08:00
473b9000b9
feat: update prompts and descriptions for data science components ( #731 )
...
* docs: Update prompts and descriptions for data science components
* chore: Remove outdated comments from conf.py
* feat: Add metric_name attribute to DataScienceScen class
* style: Update description in prompts.yaml and reorder metric_name init
* docs: Update prompts.yaml with feature engineering guidelines
2025-04-01 20:54:42 +08:00
00b31fa752
fix: fix a bug in regular expression exception processing ( #734 )
...
* fix a bug in regular expression exception precessing
* fix ci
* fix
2025-04-01 16:54:05 +08:00
752de9dc67
feat: add a tool to enable saving workspace files into a specific folder ( #728 )
...
* add a tool to enable saving workspace files into a specific folder
* fix
* fix
2025-03-28 16:22:27 +08:00
a99276d59b
feat: track and log accumulated completion cost in LiteLLMAPIBackend ( #727 )
...
* feat: Track and log accumulated completion cost in LiteLLMAPIBackend
* refactor: Use variable for retry count and update import formatting
* lint
* fix: Allow chat_max_tokens to be None in LLMSettings
* feat: Add logging for LiteLLM settings and finish reason in cost calculation
2025-03-28 12:24:19 +08:00
450571e86e
fix: add metric name check for valid scores ( #724 )
...
* update metric_name
* fix some bugs
* add an evaluation in workflow
* add an evalution in runner
* fix ci
* test change
* fix CI
---------
Co-authored-by: TPLin22 <tplin2@163.com >
Co-authored-by: yuanteli <1957922024@qq.com >
2025-03-27 19:36:57 +08:00
7fc9e18a71
feat: make spec optional ( #719 )
...
* feat: Add spec_enabled configuration for data science settings
* make spec alternative
* change spec logic in exp_gen
* remove some general texts
* align
---------
Co-authored-by: Young <afe.young@gmail.com >
Co-authored-by: yuanteli <1957922024@qq.com >
2025-03-27 17:17:41 +08:00
6da6fb5ee5
refactor: remove unused code and update documentation in CoSTEER module ( #720 )
...
* refactor: Remove unused code and update documentation in CoSTEER module
* fix mypy error
* fix black error
---------
Co-authored-by: Young <afe.young@gmail.com >
2025-03-26 22:48:01 +08:00
61813cba67
chore: update data science scenario UI ( #717 )
...
* UI changes
* remove hardcode
* fix CI
2025-03-21 18:11:06 +08:00
9a43e15bf4
feat: Add line length limit to shrink_text function and settings ( #715 )
2025-03-21 00:41:52 +08:00
251800396d
add task type logger tag in coding ( #714 )
2025-03-20 19:15:37 +08:00
5f3e382248
fix: fix a bug in ensemble test script ( #713 )
...
* fix a bug in ensemble test script
* fix
* add a comment
2025-03-20 17:35:39 +08:00
fa0dbb69fe
fix: fix a bug in progress_bar filter ( #712 )
...
* fix a bug in progress_bar filter
* fix
2025-03-20 16:02:09 +08:00
f1e4e9900c
fix docs build error ( #709 )
2025-03-20 11:39:19 +08:00
60b66aa6c9
change only model codes in model coder ( #707 )
2025-03-19 19:37:26 +08:00
b91471181c
fix coverage using method ( #706 )
2025-03-19 19:00:53 +08:00
a48abf4a84
fix: clarify an ambiguous explanation ( #705 )
2025-03-19 17:57:04 +08:00
5b14779f69
feat: add cross validation to workflow ( #700 )
2025-03-19 17:56:42 +08:00
8ea8817e7d
fix: default emb model ( #702 )
...
* fix: Remove incorrect prefix from default embedding model name
* refactor: Consolidate model settings in LLMSettings class
2025-03-19 12:27:45 +08:00
fd747fe741
fix: align components' name ( #701 )
2025-03-19 11:27:43 +08:00
b666397786
fix: fix combined_factors_df.pkl not loading in docker ( #697 )
...
* Fix combined_factors_df.pkl not loading in docker
* change combined factors file type
* change qlib commit id
2025-03-18 18:36:21 +08:00
31381743f7
feat: out spec change for o1-preview ( #666 )
...
* add not_json batcheditout
* ensemble out_spec change
* feature out_spec change
* model out_spec change
* workflow out_spec change
* runner debugger out_spec change
* filter_progress_bar return format fix
* data_loader and spec out_spec change
* show finish_reason in llm log
* json_mode fix
* remove hardcode
* fix CI
* fix grammer
* complete PythonBatchEditOut logic
---------
Co-authored-by: yuanteli <1957922024@qq.com >
2025-03-18 17:43:44 +08:00
e564b418e1
fix: fix some description errors in direct_exp_gen ( #698 )
...
* fix some description errors in direct_exp_gen
* delete an unused module
2025-03-18 16:21:59 +08:00
d1031ed24d
refactor: update evolving_strategy.py ( #686 )
...
implmentation -> implementation
2025-03-18 16:15:08 +08:00
d66c045115
fix: add check when retrying gen model codes ( #699 )
...
* add check when retrying gen model codes
* fix CI
2025-03-18 15:59:34 +08:00
7b3473cf30
feat: add model removal and adjust some framework logic ( #681 )
...
* prune model task
* add component_description
* add model removal logic to component, hypo, and task gen
* fix ci
* adjust coder to meet the requirement of model removal
* fix and refine the logic of model removal
* add model removal logic in model_eval
* fix ci
* fix ci
* prune some unnecessary codes
2025-03-18 14:42:53 +08:00
1d6e97cb99
fix preds_dict's keys ( #695 )
2025-03-17 23:33:17 +08:00
3d7b2b4567
fix: runner COSTEER evaluator ( #693 )
...
* fix scores.csv and submission.csv check in runner eval
* add coverage check info in running COSTEER feedback
* feedback value fix
2025-03-17 23:12:59 +08:00
b8a699a0df
fix: fix a minor bug ( #694 )
2025-03-17 21:43:26 +08:00
bb91201dd2
fix: fix a bug related to model_name in ensemble ( #692 )
...
* fix a bug related to model_name in ensemble
* refine
2025-03-17 21:23:57 +08:00
e0ae91b497
validate and update 'final_decision' before init CosTeerFeedback ( #691 )
2025-03-17 19:53:09 +08:00
b20692cbd4
fix: fix an error in model_coder prompt ( #690 )
2025-03-17 15:38:39 +08:00
b033215ca9
fix: add force parameter for cache_with_pickle & using cache when get kaggle leaderboard ( #687 )
...
* use kaggleApi latest edition
* add 'force' for cache_with_pickle, use cache when getting kaggle leaderboard
2025-03-16 00:50:17 +08:00
Yuante Li