Commit Graph

182 Commits

Author SHA1 Message Date
Xu Yang 00c76e0411 add inf evaluator to factor costeer and some minor improvement (#435) 2024-10-16 16:00:55 +08:00
Way2Learn 69fc1fd911 feat: supporting various Kaggle competitions & scenarios for RD-Agent (#409)
* Fixes on  kaggle output

* feat: add kaggle s3e14 template (#394)

* add s3e14 template

* fix CI

* Initialisation of a template of competition

* add kaggle s3e16 template (#396)

* get kaggle competition scores (#397)

* Adding a new competition s4e6

* feat: s4e5 (#400)

* init for s4e5

* edit s4e5

* ci issue

* feat: S4e3 (#402)

* Initialisation of a template of competition

* Adding a new competition s4e6

* Competition Initialised

* Fixed to make sure that now it runs

* Fixing for CI

* correct evaluation (#403)

* find rank in leaderboard (#405)

* fix: model templates for KG scenario (#408)

* fix feature selection for some models

* feat select template

* Updating the prompts for a more powerful model tuning

* refine the prompt

* fix: template error in s4e6

* feat: show simple execution time in demo (#410)

* show time in kaggle demo

* change color

* fix a small bug

* edit loop.py and proposal

* delete useless files

* CI issues

* ci issue

---------

Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com>
Co-authored-by: Haoran Pan <167847254+TPLin22@users.noreply.github.com>
Co-authored-by: Way2Learn <118058822+Xisen-Wang@users.noreply.github.com>
Co-authored-by: WinstonLiyt <1957922024@qq.com>
Co-authored-by: TPLin22 <tplin2@163.com>
2024-10-15 13:06:36 +08:00
Xu Yang 5ad3619492 force use_chat_cache False when facing error in evaluators (#432) 2024-10-15 12:21:33 +08:00
Xu Yang 768229427d feat: use unified pickle cacher & move llm config into a isolated config (#424)
* simplify RDAgent conf

* add unified cacher(untested)

* fix small bugs

* fix a bug

* fix a small bug in runner

* use hash_key = None to skip cache

* fix CI

* in factor execution, ignore cache when raise exception

* add file locker to avoid mp calling

* fix CI

* use function __module__ name as folder in cache
2024-10-14 17:34:09 +08:00
XianBW e7656883ba auto select content element in kaggle crawler now (#423) 2024-10-11 22:34:12 +08:00
Xu Yang a6ddf08e2a perf: some small upgrade to factor costeer to improve the performance (#420)
* 1. use dataframe.info instead of head
2. in former trace query, add the latest attempt to the last success execution

* fix CI
2024-10-10 20:29:17 +08:00
Xu Yang 19985c675e use main thread to get embedding to speed up cache (#415) 2024-10-08 19:34:19 +08:00
you-n-g d9c30f1488 refactor: refine util (#413)
* refine util

* lint
2024-10-08 02:07:20 +08:00
WinstonLiyt 80b392ce2f fix: fix a bug in competition metric evaluation (#407)
* fix a bug in competition metric evaluation

* fix a bug

* fix a bug in rag loading
2024-09-30 14:54:56 +08:00
WinstonLiyt 1cbaa4b15c fix: refine the ucb algorithm (#406)
* refine the ucb algorithm

* fix a ci error
2024-09-30 12:30:42 +08:00
WinstonLiyt 54109f62e4 feat: Add ranking in kaggle scenario (#401)
* fix some bugs in rag

* add ranking in kaggle scenario

* fix two mistouches

* fix two bugs

* fix a bug
2024-09-30 04:15:07 +08:00
WinstonLiyt 3020789ecf fix: fix some bugs in rag (#399)
* fix some bugs in rag

* fix a bug in costeer
2024-09-30 02:38:33 +08:00
XianBW 2359243b97 fix bug in feature selection (#398) 2024-09-30 01:21:45 +08:00
you-n-g ef641332fa feat: Dynamic scenario based on task (#392)
* OAI api

* more comments

* llm utils

* RD-Framework for dynamic scen

* remove useless code

* auto lint

* fix dynamic scennario

* Add parameter

* auto lint

* remove abstractmethod

* fix lint
2024-09-29 18:43:17 +08:00
Way2Learn d633d8ca5d feat: Revise to support better hypothesis proposal (#390)
* Revising for feedback

* Revised for better hypothesis proposal

* revise for CI

* typo-fix
2024-09-29 16:18:18 +08:00
WinstonLiyt 4954f08484 fix: fix a bug in mini case (#389)
* fix: fix a bug in mini case

* fix a bug
2024-09-29 15:51:51 +08:00
Haoran Pan 0467ba03a8 fix: fix a bug in scenario.py (#388)
* fix: fix a bug in scenario.py

* Update scenario.py
2024-09-29 14:46:00 +08:00
cyncyw 26cc2b580d fix: debug dsagent (#387)
* basic dsagent & debug

debug dsagent

change dsagent conf

* Refine changes

* Update vector_base.py
2024-09-29 01:15:33 -04:00
cyncyw 152effac32 fix: rag save file (#385)
* debug vector base
2024-09-28 23:43:11 -04:00
cyncyw 5b646b93df debug vector base (#380) 2024-09-28 17:58:51 -04:00
WinstonLiyt 5b4828ed9a fix: fix some bugs in knowledge base (#378)
* fix a bug in dig_recognizer

* fix some bug in rag

* fix a ci error
2024-09-29 00:23:38 +08:00
WinstonLiyt 674729475f fix two template (#376) 2024-09-28 06:12:06 +08:00
XianBW ad75ea2681 feat: get kaggle notebooks & disscussion text for RAG (#371)
* crawl notebooks & change to DS-Agent format text

* give one function in kaggle_crawler to collect kaggle knowledge texts

* fix CI

* add tool for merge .py files to one py file

* fix CI

* delete files

* changes for select function

* add nbformat

* jump crawler import test

* del test code

* CI

* change

* change

* change
2024-09-28 05:42:47 +08:00
Way2Learn 82054363ff feat: Supporting COVID-19 competition (#374)
* Uploading the initially runnable template

* CI Fixes

* edit params

* change the template

* fix a bug in rag

---------

Co-authored-by: TPLin22 <tplin2@163.com>
Co-authored-by: WinstonLiye <1957922024@qq.com>
2024-09-28 05:33:44 +08:00
Way2Learn 0a262c8a1d feat: supporting Mnist competition (#375)
* Initialised a version

* Fixes

* feat mnist & fix some bugs(with TODO)

---------

Co-authored-by: TPLin22 <tplin2@163.com>
2024-09-28 05:14:03 +08:00
Way2Learn 5b41352e6d feat: Iceberge competition (#372)
* Relevant files fixed

* Make the entire system run

* Fix CI

* refine the template

---------

Co-authored-by: WinstonLiye <1957922024@qq.com>
2024-09-28 01:32:35 +08:00
Xu Yang 1d2b8b9867 feat: implement isolated model feature selection loop (#370)
* rename meta_tpl

* use a isolated coder to deal with model feature selection and refine the structure

* fix CI

* fix: fix some errors in scenario.py, proposal.py and runner.py and several complex competition scenarios(#365)

* fix several bugs in proposal and runner

* fix a bug in feedback-prize-english-language-learning

* fix some bugs and templates

* fix the bug in optiver and nlp problem

* delete unnecessary codes

* remove unnecessary codes

* complete forest and s4e8

* push

* feedback & s4e8 &  forest

* optiver finished

* s3e11 & s3e26

* s4e9 finished

* sf-crime finished

* the last one finished

---------

Co-authored-by: WinstonLiyt <104308117+WinstonLiyt@users.noreply.github.com>
Co-authored-by: WinstonLiyte <1957922024@qq.com>
2024-09-28 00:40:25 +08:00
WinstonLiyt 46fe590d54 fix: fix some errors in scenario.py, proposal.py and runner.py and several complex competition scenarios(#365)
* fix several bugs in proposal and runner

* fix a bug in feedback-prize-english-language-learning

* fix some bugs and templates

* fix the bug in optiver and nlp problem
2024-09-27 20:26:51 +08:00
WinstonLiyt 377b56ff20 fix: fix a typo (#362) 2024-09-27 02:15:28 +08:00
WinstonLiyt bc5e779d5b feat: add normal rag into framework (#360)
* add normal rag into framework

* fix a typo

* fix a bug
2024-09-27 01:36:12 +08:00
Haoran Pan aa4803496b feat: xgboost gpu accelerate (#359)
* gpu accelerate

* delete nn of sf-crime
2024-09-27 00:40:53 +08:00
WinstonLiyt 11b342b3e6 fix: refine some codes (#353)
* refine some codes

* fix ci errors

* update

* update advanced rag
2024-09-27 00:17:28 +08:00
Haoran Pan 885ef7a982 fix: preprocess output format & some mistake in spelling (#358)
* spaceship: format type of y = pd.series; fix a wrong spelling in xgb

* s3e11: format of y -- pd.series

* spaceship: format of y & fit nn

* spaceship: wrong spelling in xgb

* ci issue
2024-09-26 23:17:27 +08:00
Way2Learn 5ff03c6ac7 fix: Optiver fixes (#357)
* Adding the competition: Optiver Volatility Prediction

* Fixing for CI

* Updating a new competition @ Optiver

* re-writing the optiver competition

* Revise for better commit

* Further fixes

* Further fixes

* Fixes

* Further Fixing Optiver Template

* Fix further to pass the test

* Fixing for CI

* Fixing for CI
2024-09-26 23:11:05 +08:00
Way2Learn cb9b695e34 feat: New competition - Optiver (#356)
* Adding the competition: Optiver Volatility Prediction

* Fixing for CI

* Updating a new competition @ Optiver

* re-writing the optiver competition

* Revise for better commit

* Further fixes

* Further fixes

* Fixes
2024-09-26 22:06:42 +08:00
Xu Yang 2724ab4dac remove temp debug prompt (#352) 2024-09-26 18:00:56 +08:00
Xu Yang f3210f3baa fix: revert model and make SOTA model available to COSTEER (#351)
* revert model and make SOTA model available to COSTEER

* fix CI

* fix CI

* fix CI
2024-09-26 17:54:45 +08:00
Way2Learn 66db69e104 feat: better feedback & evaluation (#346)
* Updated new keys for evaluation

* fix the bug in feedback

---------

Co-authored-by: WinstonLiye <1957922024@qq.com>
2024-09-26 16:15:47 +08:00
XianBW 1f28c887f1 feat: show workspace in demo (#348)
* change id name in s4e8 tpl

* add workspace in demo

* add workspace in demo

* fix CI

* change workspace path color
2024-09-26 14:35:22 +08:00
Haoran Pan 5300d9345c feat: random forest for s3e11 (#347) 2024-09-26 13:43:50 +08:00
XianBW 45ffc70414 feat: add kaggle tpl: feedback-prize (#331)
* change feedback tpl

* feedback tpl changes

* fix feedback tpl

* fix train.py of feedback tpl

* add rf model for feedback tpl

* fix CI
2024-09-26 09:08:25 +08:00
WinstonLiyt 773c5fdfd7 feat: refine the template in several Kaggle competitions (#343)
* add an error catching in model runner

* check forest & s3e11 & s4e8 & spaceship, change params of forest & s3e26 & spaceship

* fix ci errors

---------

Co-authored-by: TPLin22 <tplin2@163.com>
2024-09-26 02:12:07 +08:00
WinstonLiyt d0adee2c51 add a button to control feature selection (#342) 2024-09-26 01:11:42 +08:00
Way2Learn 77e4d4b850 fix: Update prompts.yaml to constrain only one model type (#341)
* Update prompts.yaml

* Update prompts.yaml

* fix a bug

---------

Co-authored-by: WinstonLiyt <104308117+WinstonLiyt@users.noreply.github.com>
Co-authored-by: WinstonLiye <1957922024@qq.com>
2024-09-25 23:25:14 +08:00
Haoran Pan 5c92bb0456 fix: a bug of developer& edit s4e8 template (#338)
* s4e8 preprocess remove onehot & fix a bug

* Update runner.py

* Update fea_share_preprocess.py

* Update runner.py

---------

Co-authored-by: WinstonLiyt <104308117+WinstonLiyt@users.noreply.github.com>
2024-09-25 20:09:52 +08:00
WinstonLiyt 41003efbc3 fix a bug in model tuning feedback (#339) 2024-09-25 19:42:37 +08:00
Xu Yang 7fc0c64358 multi channel support in kaggle scenario (#337) 2024-09-25 19:15:31 +08:00
WinstonLiyt 861cd2eaf1 fix a bug in the definition of source data shape (#335) 2024-09-25 18:14:59 +08:00
Haoran Pan 2d4bb7f3b6 fix: template for kaggle foreset & s4e9 (#334)
* s4e9: remove onehot, reshape output

* forest-cover-type-prediction: cross validation
2024-09-25 17:52:11 +08:00
WinstonLiyt c5025cdb08 fix a bug in feature selection prompt (#333) 2024-09-25 17:14:58 +08:00