cf93b769ff
feat: end-to-end optimization ( #473 )
...
* fix
* refine the code
* aligned data with MLE Kaggle competition dataset
* fix ci error
* fix ci
2024-11-05 15:41:50 +08:00
9bea9a6d1f
fix a bug ( #470 )
2024-11-04 15:05:05 +08:00
2e2e75a043
fix: unzip kaggle data ( #464 )
...
* unzip kaggle data
* read local_data_path from .env file
* fix build docs error
* recover azure-identity packages
* optimize code logic
* add error when downloading data from kaggle
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2024-11-04 14:57:10 +08:00
437fbcb577
fix a bug in kaggle runner cache and kaggle costeer execute template ( #467 )
2024-11-04 11:16:16 +08:00
44271ecfd4
feat: refine logic for qlib_factor_from_report ( #463 )
...
* fix a bug in kaggle conf
* fix a ci error
* refine logic for qlib_factor_from_report
2024-10-31 16:04:32 +08:00
30a5061012
docs: some changes in kaggle doc ( #461 )
...
* add kaggle scenario description for webapp
* catch download button error
* change kaggle auto_submit to False default
* Added guidance for custom templates in kaggle doc
* CI
* CI
* add kaggle data set instruction(NOTE)
* delete repeated description for kaggle scenario
---------
Co-authored-by: TPLin22 <tplin2@163.com >
2024-10-30 17:00:56 +08:00
1d50ffd9ac
fix: fix a bug in kaggle conf ( #459 )
...
* fix a bug in kaggle conf
* fix a ci error
2024-10-29 15:13:18 +08:00
1fe8bdfd6a
fix: templates bug ( #456 )
...
* Update model_nn.py
* ci issue
2024-10-28 14:22:04 +08:00
7672eaeaaa
chore: remove package ( #449 )
...
* remove package
* reformat with black
* fix pytest error
* fix pytest error
* fix pytest error
* add packages
* change code
2024-10-24 20:38:13 +08:00
c71fd1fba2
feat: independent use_azure_token_provider on chat and embedding ( #452 )
...
* independent use_azure_token_provider
* fix CI
* fix doc format
2024-10-23 18:22:58 +08:00
eace48a054
always return str ( #453 )
2024-10-23 16:47:36 +08:00
4f36115d37
fix KGFactorRunner cache system bug ( #451 )
2024-10-23 15:17:38 +08:00
9d7e1b8b49
docs: add documentation for kaggle scen ( #448 )
...
* init for bg & quickstart for kaggle docs
* Add documentation for the environment configuration in the Kaggle scenario.
* add some descriptions in documents
* remove useless docs
* ci issue
---------
Co-authored-by: TPLin22 <tplin2@163.com >
2024-10-23 13:26:57 +08:00
33684cafe4
chore: remove torch in main code ( #439 )
...
* use np.ndarray in costeer model evaluators
* remove package
* fix test error
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com >
2024-10-21 15:56:04 +08:00
671d4f0600
chore: move use_auto_chat_cache_seed_gen and init_chat_cache_seed to LLMSett… ( #444 )
...
* move use_auto_chat_cache_seed_gen and init_chat_cache_seed to LLMSettings
* remove RD_AGENT_SETTINGS in llm_utils.py
2024-10-21 12:03:59 +08:00
64df9bec37
feat: use auto gen seed when using LLM cache ( #441 )
...
* initial version
* test requirements
* fix bugs
* fix bugs
* add annotation
* fix ruff error
* fix CI
* fix CI
* fix CI
* fix CI
* change random usage
* move cache_seed_gen to core/utils.py
* fix CI
* change cache_seed_gen name
---------
Co-authored-by: Young <afe.young@gmail.com >
2024-10-21 11:32:20 +08:00
5ff09b6a2d
fix display bug in webapp ( #440 )
2024-10-18 17:07:25 +08:00
75d35bf447
fix problem of reading log file tags on Windows ( #437 )
...
Co-authored-by: Bowen Xian (Shanghai Wicresoft Co Ltd) <v-bxian@microsoft.com >
2024-10-17 20:22:39 +08:00
00c76e0411
add inf evaluator to factor costeer and some minor improvement ( #435 )
2024-10-16 16:00:55 +08:00
d615c0e31b
number of subprocesses <= number of tasks ( #434 )
2024-10-16 14:13:20 +08:00
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
b9a36e1b25
chore: more optional parameters for running benchmark analysis ( #431 )
...
* set title and round
* decision from multiple types
* check if decision is true
* reformat
* remove unused file
2024-10-15 12:41:32 +08:00
5ad3619492
force use_chat_cache False when facing error in evaluators ( #432 )
2024-10-15 12:21:33 +08:00
41eb482621
fix: fix cache result logic ( #430 )
...
* make cache logic more tidy
* update WeChat QR code
2024-10-14 19:35:21 +08:00
3a44e715ad
fix: fix a small bug in cache using module name and function name as unique folder name ( #429 )
2024-10-14 17:53:04 +08:00
f3b3e4acb7
convert str to bool ( #428 )
2024-10-14 17:44:33 +08:00
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
e7656883ba
auto select content element in kaggle crawler now ( #423 )
2024-10-11 22:34:12 +08:00
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
5402c00165
fix: fix json load error ( #386 )
...
* fix json load error
* fix os.symlink error
* reformat with black
* fix os.symlink error
* reformat with isort
2024-10-10 11:58:15 +08:00
9f6b457aa5
improve factor costeer: ( #417 )
...
1. when facing odd v2_query_component_limit, make from gt bigger than without gt
2. do code evaluator even value does not pass
3. provide the value header to value failed evaluators
2024-10-09 18:56:37 +08:00
19985c675e
use main thread to get embedding to speed up cache ( #415 )
2024-10-08 19:34:19 +08:00
d9c30f1488
refactor: refine util ( #413 )
...
* refine util
* lint
2024-10-08 02:07:20 +08:00
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
1cbaa4b15c
fix: refine the ucb algorithm ( #406 )
...
* refine the ucb algorithm
* fix a ci error
2024-09-30 12:30:42 +08:00
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
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
a34761a52d
chore: update web.py ( #395 )
...
seperate -> separate
2024-09-30 01:36:26 +08:00
2359243b97
fix bug in feature selection ( #398 )
2024-09-30 01:21:45 +08:00
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
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
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
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
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
33c912281f
fix: cache ( #383 )
...
* fix: cache
* update cache
* fix
* Fix lint
2024-09-29 12:07:36 +08:00
152effac32
fix: rag save file ( #385 )
...
* debug vector base
2024-09-28 23:43:11 -04:00
d0a9648e22
convert covid workspace to merged.py for submission ( #384 )
2024-09-29 11:29:40 +08:00
47940f6589
fix: partial bug in bench ( #368 )
...
* Add more log
* Fix eval
* update
* keep ratio <= 1
* feat: cache exception (#369 )
* 0 instead of NaN
* remove unused evaluators
* save gen_factor_l_all_rounds
* black reformat
* cache exception
---------
Co-authored-by: Tim <illking@foxmail.com >
2024-09-29 09:59:54 +08:00
5b646b93df
debug vector base ( #380 )
2024-09-28 17:58:51 -04:00
8654c3689b
Quick fixes for logging ( #379 )
2024-09-29 01:36:57 +08:00
Yuante Li