Commit Graph

140 Commits

Author SHA1 Message Date
WinstonLiyt 60e09c3a53 fix: Add framework handling for task coding failure. (#176)
* Add framework handling for task coding failure.

* fix a ci bug
2024-08-07 19:01:46 +08:00
Xisen Wang 087c1c4b66 doc: Update General Model Scenario Documentation (#173)
* Init todo

* Evaluation & dataset

* Generate new data

* dataset generation

* add the result

* Analysis

* Factor update

* Updates

* Reformat analysis.py

* CI fix

* Revised General Model Doc & Layout

* Update model_copilot_general.rst

* Update eval.py

* Update eval.py

* Update analysis.py

* Update eval_method.py

* Update model_copilot_general.rst to add configurations

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Taozhi Wang <taozhi.mark.wang@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: cyncyw <47289405+taozhiwang@users.noreply.github.com>
Co-authored-by: WinstonLiyt <104308117+WinstonLiyt@users.noreply.github.com>
2024-08-06 17:44:10 +08:00
Xu Yang 9c0d3df8f6 put all the property in scenarios into local attribute to enable static scenario content (#175) 2024-08-06 17:07:01 +08:00
WinstonLiyt ba78a87dcb feat: Add description for scenario experiments. (#174)
* Fixed some bugs introduced during refactoring.

* Add description for scenario experiments.

* Update factor_from_report_w_sc.py

* fix some ci bugs.

* add @property to get_experiment_setting

* fix a ci error.
2024-08-06 16:03:40 +08:00
WinstonLiyt abcf7d913b doc: Improved documentation for two factor scenarios. (#172)
* Fixed some bugs introduced during refactoring.

* Improved documentation for two factor scenarios.

* Update factor_from_report_w_sc.py

* Improved some details.
2024-08-06 14:28:48 +08:00
WinstonLiyt 4771e5b644 feat: Remove redundant 'key steps' section in frontend scene display. (#169)
* Fixed some bugs introduced during refactoring.

* fix a minor bug

* build factor source data (price and volumns) from qlib if no source data is provided by the user (#168)

* Fixed some bugs introduced during refactoring.

* fix a small bug

* fix a small bug

* Remove redundant 'key steps' section in frontend scene display.

---------

Co-authored-by: Xu Yang <peteryang@vip.qq.com>
2024-08-06 11:07:10 +08:00
Tim 7e4820cabf doc: add benchmark.rst (#153)
* add benchmark png

* Create benchmark.rst

* Update benchmark.rst

* Draft

* rename file

* add autopydantic_settings

* remove ignored file

* add example

* sort imports

* sort imports

* format code with black

---------

Co-authored-by: Young <afe.young@gmail.com>
2024-08-06 09:29:22 +08:00
WinstonLiyt db68a28c1b fix: Fixed some bugs introduced during refactoring. (#167)
* Fixed some bugs introduced during refactoring.

* fix a minor bug

* build factor source data (price and volumns) from qlib if no source data is provided by the user (#168)

* Fixed some bugs introduced during refactoring.

* fix a small bug

* fix a small bug

---------

Co-authored-by: Xu Yang <peteryang@vip.qq.com>
2024-08-05 21:48:24 +08:00
Xu Yang 0933eb2948 build factor source data (price and volumns) from qlib if no source data is provided by the user (#168) 2024-08-05 21:01:59 +08:00
Xu Yang 987cfc723e fix: first round app folder cleaning (#166)
* first round app folder cleaning

* fix CI
2024-08-05 18:11:23 +08:00
WinstonLiyt 420dbbe584 feat: Added QlibFactorFromReportScenario and improved the report-factor loop. (#161)
* Optimize factor hypothesis prompt

* Optimize the factor feedback prompt.

* Improve the prompts in feedback(factor).

* change some prompts

* Added QlibFactorFromReportScenario and improved the report-factor loop.

* reformat

* reformat

* reformat

* reformat
2024-08-05 14:12:05 +08:00
Suhan Cui 319ed40961 fix: fix several bugs in data mining scenario (#147)
* fix

* ci

* demo
2024-08-05 13:28:50 +08:00
WinstonLiyt b1ae3e113c fix: optimize some prompts in factor loop. (#158)
* Optimize factor hypothesis prompt

* Optimize the factor feedback prompt.

* Improve the prompts in feedback(factor).

* change some prompts
2024-08-03 21:34:15 +08:00
Xu Yang 4eca5fd8c0 use mp to execute all feature and fix a small bug in config (#157) 2024-08-03 10:17:01 +08:00
Xu Yang 38e97dbd81 some small refinement (#156) 2024-08-02 19:06:21 +08:00
XianBW 4ea5fefad8 feat: streamlit webapp demo for different scenarios (#135)
add streamlit webapp demo & docs
2024-08-02 18:37:15 +08:00
WinstonLiyt 317ad89599 fix: fix some small bugs in report-factor loop (#152)
* Init todo

* update all code

* update

* Extract factors from financial reports loop finished

* Fix two small bugs.

* Delete rdagent/app/qlib_rd_loop/run_script.sh

* Minor mod

* Delete rdagent/app/qlib_rd_loop/nohup.out

* Fix a small bug in file reading.

* some updates

* Update the detailed process and prompt of factor loop.

* Evaluation & dataset

* Optimize the prompt for generating hypotheses and feedback in the factor loop.

* Generate new data

* dataset generation

* Performed further optimizations on the factor loop and report extraction loop, added log handling for both processes, and implemented a screenshot feature for report extraction.

* Update rdagent/components/coder/factor_coder/CoSTEER/evaluators.py

* Update package.txt for fitz.

* add the result

* Performed further optimizations on the factor loop and report extraction loop, added log handling for both processes, and implemented a screenshot feature for report extraction. (#100) (#102)

- Performed further optimizations on the factor loop and report extraction loop.
- Added log handling for both processes.
- Implemented a screenshot feature for report extraction.

* Analysis

* Optimized log output.

* Factor update

* A draft of the "Quick Start" section for README

* Add scenario descriptions.

* Updates

* Adjust content

* Enable logging of backtesting in Qlib and store rich-text descriptions in Trace. Support one-step debugging for factor extraction.

* Reformat analysis.py

* CI fix

* Refactor

* remove useless code

* fix bugs (#111)

* Fix two small bugs.

* Fix a merge bug.

* Fix two small bugs.

* fix some bugs.

* Fix some format bugs.

* Restore a file.

* Fix a format bug.

* draft renew of evaluators

* fix a small bug.

* fix a small bug

* Support Factor Report Loop

* Update framework for extracting factors from research reports.

* Refactor report-based factor extraction and fix minor bugs.

* fix a small bug of log.

* change some prompts

* improve factor_runner

* fix a small bug

* change some prompts

* cancel some comments

* cancel some comments and fix some bugs

* fix some bugs in factor from reports loop

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: Taozhi Wang <taozhi.mark.wang@gmail.com>
Co-authored-by: Suhan Cui <51844791+SH-Src@users.noreply.github.com>
2024-08-02 17:14:12 +08:00
Xisen Wang 84d957a615 feat: Uploaded Documentation, Updated Prompts & Some Code for model demo (#144)
* Added three new keys on hypothesis reasoning

* Updated two scenario rich text

* Uploaded Documentation & Further Improved Demo of Models

* Add docs

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2024-08-02 16:22:06 +08:00
cyncyw 7adade22bf docs: Config Docs Update (#148)
* Add a table & factor debug

* Congfig setting

* Update env example and configuration list.

Also change api priority

* Add a TODO for the rst

* CI: shorter line

* Update docs/installation_and_configuration.rst

* Update docs/installation_and_configuration.rst

* Update links & standard config

* Add TODO

* Fix bug

* Update rdagent/oai/llm_utils.py

---------

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2024-08-02 15:49:58 +08:00
WinstonLiyt c6bf4e5015 fix: Comprehensive update to factor extraction. (#143)
* Init todo

* update all code

* update

* Extract factors from financial reports loop finished

* Fix two small bugs.

* Delete rdagent/app/qlib_rd_loop/run_script.sh

* Minor mod

* Delete rdagent/app/qlib_rd_loop/nohup.out

* Fix a small bug in file reading.

* some updates

* Update the detailed process and prompt of factor loop.

* Evaluation & dataset

* Optimize the prompt for generating hypotheses and feedback in the factor loop.

* Generate new data

* dataset generation

* Performed further optimizations on the factor loop and report extraction loop, added log handling for both processes, and implemented a screenshot feature for report extraction.

* Update rdagent/components/coder/factor_coder/CoSTEER/evaluators.py

* Update package.txt for fitz.

* add the result

* Performed further optimizations on the factor loop and report extraction loop, added log handling for both processes, and implemented a screenshot feature for report extraction. (#100) (#102)

- Performed further optimizations on the factor loop and report extraction loop.
- Added log handling for both processes.
- Implemented a screenshot feature for report extraction.

* Analysis

* Optimized log output.

* Factor update

* A draft of the "Quick Start" section for README

* Add scenario descriptions.

* Updates

* Adjust content

* Enable logging of backtesting in Qlib and store rich-text descriptions in Trace. Support one-step debugging for factor extraction.

* Reformat analysis.py

* CI fix

* Refactor

* remove useless code

* fix bugs (#111)

* Fix two small bugs.

* Fix a merge bug.

* Fix two small bugs.

* fix some bugs.

* Fix some format bugs.

* Restore a file.

* Fix a format bug.

* draft renew of evaluators

* fix a small bug.

* fix a small bug

* Support Factor Report Loop

* Update framework for extracting factors from research reports.

* Refactor report-based factor extraction and fix minor bugs.

* fix a small bug of log.

* change some prompts

* improve factor_runner

* fix a small bug

* change some prompts

* cancel some comments

* cancel some comments and fix some bugs

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: Taozhi Wang <taozhi.mark.wang@gmail.com>
Co-authored-by: Suhan Cui <51844791+SH-Src@users.noreply.github.com>
2024-08-02 15:04:49 +08:00
Xu Yang 060f569720 feat: filter feature which is high correlation to former implemented features (#145)
* filter feature which is high correlation to former implemented features

* use multiprocessing to calculate IC and some minor fix
2024-08-02 14:41:17 +08:00
Xu Yang bb18db0a24 Fix a small bug in model value evaluation (#142)
* Value evaluation feedback not correct. We should give different feedback when target tensor or gt tensor is not available.

* fix CI
2024-08-01 18:08:23 +08:00
Suhan Cui 145c446eab Dm2 (#137)
* template

* train

* prompts

* ci

* ci

* ci
2024-08-01 15:00:40 +08:00
you-n-g dd4f46e209 fix: fix pickle problem (#140)
* fix pickle problem

* CI

* CI

* CI

* CI

* CI
2024-08-01 14:56:03 +08:00
WinstonLiyt abe923ea84 Fix a small bug in the hypothesis prompts. 2024-08-01 14:15:43 +08:00
Xisen Wang 0accbe258b Added three new keys on hypothesis reasoning (#138)
* Added three new keys on hypothesis reasoning

* Updated two scenario rich text
2024-08-01 10:53:37 +08:00
Xu Yang 345f91b708 refine the graph model interface (#136) 2024-07-30 19:38:37 +08:00
cyncyw 6e8f912968 Openai api & eval debug (#124)
* Openai api & eval debug


---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2024-07-30 18:06:48 +08:00
XianBW dbbec2ffaf New Structure Demo (#120)
better demo
---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Taozhi Wang <taozhi.mark.wang@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: cyncyw <47289405+taozhiwang@users.noreply.github.com>
2024-07-30 17:23:05 +08:00
Xisen Wang 1b4e98a752 Checking general demo (#126)
* Init todo

* Evaluation & dataset

* Generate new data

* dataset generation

* add the result

* Analysis

* Factor update

* Updates

* Reformat analysis.py

* CI fix

* Further Optimised Model Workflow by Incorporating Feedbacks on Exp Task Card

* Rebasing To build the extraction & implementation demo

* Revised for clean code

* Revised further to show "Knowledge"

* Revised to make model_research_copilot better

* Further Optimised Model Workflow by Incorporating Feedbacks on Exp Task Card

* Rebasing To build the extraction & implementation demo

* Revised for clean code

* Revised further to show "Knowledge"

* Revised to make model_research_copilot better

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Taozhi Wang <taozhi.mark.wang@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: cyncyw <47289405+taozhiwang@users.noreply.github.com>
2024-07-30 15:47:21 +08:00
Suhan Cui 6896f3f82b Dm (#132) 2024-07-30 12:14:48 +08:00
Suhan Cui 38a84a0765 Dm (#131)
* template

* a
2024-07-30 11:38:02 +08:00
WinstonLiyt 7ec13c4087 Fix some minor bugs caused by version changes. (#128)
Fix some minor bugs caused by version changes.
2024-07-29 18:02:17 +08:00
SH-Src 02bee7ecdf update 2024-07-29 09:35:56 +00:00
you-n-g 45c9726133 Support special step customization (#123)
* Support special step customization

* lint
2024-07-26 14:29:19 +08:00
you-n-g 38ac4cffcd Fix loop bug (#122) 2024-07-26 13:47:50 +08:00
Linlang faa2fb03ad CI checks that can be automatically repaired (#119)
* fix isort & black & toml-sort & sphinx error

* fix ci error

* fix ci error

* add comments

* Update Makefile

* change sphinx build command

* add auto-lint

* add black args

* format with black

* Auto Linting document

* fix ci error

---------

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: Young <afe.young@gmail.com>
2024-07-26 12:12:16 +08:00
WinstonLiyt a4fa000862 Fix two small bugs. (#121)
* Fix two small bugs.
2024-07-26 11:00:21 +08:00
you-n-g 080f5e6a60 loguru mypy error (#118) 2024-07-25 23:12:42 +08:00
cyncyw a82222d077 Benchmark (#114)
* Init todo

* Evaluation & dataset

* Generate new data

* dataset generation

* add the result

* Analysis

* Factor update

* Updates

* Reformat analysis.py

* CI fix

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2024-07-25 18:22:57 +08:00
you-n-g 30827f2ae7 fix record (#113)
* fix record

* fix type

* add loguru-mypy
2024-07-25 18:14:51 +08:00
WinstonLiyt 25fb571a0f A draft of the "Quick Start" section for your README. Enable logging of backtesting in Qlib and store rich-text descriptions in Trace. Support one-step debugging for factor extraction. (#105)
- A draft of the "Quick Start" section for your README. 
- Enable logging of backtesting in Qlib and store rich-text descriptions in Trace. 
- Support one-step debugging for factor extraction.
2024-07-25 08:43:13 +00:00
Suhan Cui e10e7f0e59 fix bugs (#111) 2024-07-25 08:42:46 +00:00
bowen xian 055bffcbf3 fix new demo bugs 2024-07-25 08:06:15 +00:00
Xisen Wang 33a3e3b1af Update model_experiment.py by adding scenario rich-text description
- Updated relevant description
2024-07-25 15:45:26 +08:00
Linlang 571b5304cb fix mypy error (#91)
* fix mypy error

* fix mypy error

* fix ruff error

* change command

* delete python 3.8&3.9 from CI

* change command

* Some modifications according to the comments

* Add literal type

* Update .github/workflows/ci.yml

* Some modifications according to the comments

* fix ruff error

* fix meta dict

* Fix type

* Some modifications according to the comments

* merge latest code

* Some modifications according to the comments

* Some modifications according to the comments

* fix ci error

* fix ruff error

* Update Makefile

* Update Makefile

---------

Co-authored-by: Ubuntu <debug@debug.qjtqi00gqezu1eqs55bqdrf51f.px.internal.cloudapp.net>
Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2024-07-25 15:20:04 +08:00
XianBW ec22f7f02f Demo (#101)
New demo windows structure
2024-07-25 14:14:12 +08:00
you-n-g 0a4ac992e2 Agent Infra (#107)
* Agent Infra

* Update test/utils/test_agent_infra.py
2024-07-25 11:15:22 +08:00
Xisen Wang 3205975d61 Merge branch 'main' into Continous-Update-Branch 2024-07-25 11:00:55 +08:00
Xisen Wang c4046b388f Update model_extraction_and_implementation.py 2024-07-24 19:36:37 +08:00