mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 15:37:44 +00:00
chore: prepare repository for Predix public release
- Rebrand from RD-Agent to Predix for EUR/USD quantitative trading - Update all documentation to English - Remove Microsoft-specific references - Clean up temporary files and backups - Update LICENSE, README, and configuration for PredixAI organization Breaking changes: - Project name changed from 'rdagent' to 'predix' in pyproject.toml - All Microsoft and RD-Agent branding replaced with Predix - Documentation completely rewritten for EUR/USD focus Documentation: - README.md: Professional English documentation with installation, quick start, CLI reference - CHANGELOG.md: Cleaned up, references upstream RD-Agent for historical changes - CODE_OF_CONDUCT.md: Switched to Contributor Covenant v2.0 - SECURITY.md: Predix-specific vulnerability reporting process - SUPPORT.md: Updated support channels (nico@predix.io, GitHub Discussions) - CONTRIBUTING.md: Adapted for Predix project - docs/: Sphinx configuration updated for Predix branding Configuration: - pyproject.toml: Updated project metadata, keywords, URLs for PredixAI - .gitignore: Comprehensive Python/gitignore template - Makefile: Updated CI pages URL - setup_predix_eurusd.sh: Translated to English Cleanup: - Deleted log files, caches, __pycache__ directories - Removed backup files (*.backup_*) - Cleaned web/node_modules
This commit is contained in:
TPTBusiness
+62
-10
@@ -1,15 +1,67 @@
|
||||
# Environment
|
||||
.env
|
||||
.env.backup*
|
||||
*.backup*
|
||||
git_ignore_folder/
|
||||
fin_quant.log
|
||||
selector.log
|
||||
pickle_cache/
|
||||
log/
|
||||
.env.*
|
||||
!.env.example
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.pyc
|
||||
*.pyo
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
*.so
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
|
||||
# Virtual environments
|
||||
venv/
|
||||
ENV/
|
||||
env/
|
||||
.venv/
|
||||
|
||||
# IDE
|
||||
.idea/
|
||||
.vscode/
|
||||
*.swp
|
||||
*.swo
|
||||
*~
|
||||
|
||||
# Testing
|
||||
.pytest_cache/
|
||||
.coverage
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
log/
|
||||
|
||||
# Cache
|
||||
pickle_cache/
|
||||
prompt_cache.db
|
||||
.cache/
|
||||
|
||||
# Generated/processed data
|
||||
git_ignore_folder/
|
||||
data_raw/
|
||||
|
||||
# Build artifacts
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Local scripts (generated)
|
||||
convert_1min.py
|
||||
import_1min_qlib.py
|
||||
data_raw/
|
||||
|
||||
+14
-583
@@ -1,592 +1,23 @@
|
||||
# Changelog
|
||||
|
||||
## [0.8.0](https://github.com/microsoft/RD-Agent/compare/v0.7.0...v0.8.0) (2025-11-03)
|
||||
All notable changes to Predix will be documented in this file.
|
||||
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
### Features
|
||||
## [Unreleased]
|
||||
|
||||
* add a rag mcp in proposal ([#1267](https://github.com/microsoft/RD-Agent/issues/1267)) ([a0cd102](https://github.com/microsoft/RD-Agent/commit/a0cd1025c141aee6d4e6cb10286c77d827b89379))
|
||||
* add coder check and give more time ([#1127](https://github.com/microsoft/RD-Agent/issues/1127)) ([e32d229](https://github.com/microsoft/RD-Agent/commit/e32d229f2b722acac53f4e2f7d8a98e29cb19dc1))
|
||||
* add enable_cache toggle for UI data caching ([#1075](https://github.com/microsoft/RD-Agent/issues/1075)) ([0c9f193](https://github.com/microsoft/RD-Agent/commit/0c9f1930e8d5df1c00bfb32ee578da2dc53db1ec))
|
||||
* add extra_eval config and import_class for custom evaluators ([#1097](https://github.com/microsoft/RD-Agent/issues/1097)) ([5accec3](https://github.com/microsoft/RD-Agent/commit/5accec37c8828ac42005c2d12b815bef599b547e))
|
||||
* add hypo_critic and hypo_rewrite in proposal ([#1106](https://github.com/microsoft/RD-Agent/issues/1106)) ([71440f6](https://github.com/microsoft/RD-Agent/commit/71440f643fc9d952dfa064359c1945b729dbfd9f))
|
||||
* add improve_mode to MultiProcessEvolvingStrategy for selective task implementation ([#1273](https://github.com/microsoft/RD-Agent/issues/1273)) ([9344635](https://github.com/microsoft/RD-Agent/commit/93446356952803d8b1f1eb0c39da825c19274cb6))
|
||||
* add loop ID mapping to trace nodes and update UI labels ([#1098](https://github.com/microsoft/RD-Agent/issues/1098)) ([5437851](https://github.com/microsoft/RD-Agent/commit/54378518dadd6c38496eceda8ef5b33b375a5c97))
|
||||
* add mask inference in debug mode ([#1154](https://github.com/microsoft/RD-Agent/issues/1154)) ([ef749ab](https://github.com/microsoft/RD-Agent/commit/ef749ab744fb6fbafd1a8e6a3642cce20ce96069))
|
||||
* add only success filter toggle for traces ([#1047](https://github.com/microsoft/RD-Agent/issues/1047)) ([5e582cc](https://github.com/microsoft/RD-Agent/commit/5e582cc71d5c153666c465cb2d797dc71e43c501))
|
||||
* add option to enable hyperparameter tuning only in first eval loop ([#1211](https://github.com/microsoft/RD-Agent/issues/1211)) ([bc3fa17](https://github.com/microsoft/RD-Agent/commit/bc3fa170b029f50c8f7b1828cdf4ffd024e64b8b))
|
||||
* add previous runner loops to runner history ([#1142](https://github.com/microsoft/RD-Agent/issues/1142)) ([8de9f75](https://github.com/microsoft/RD-Agent/commit/8de9f757ea134b04cde0622c6225678d85a87862))
|
||||
* add reasoning attribute to DSRunnerFeedback for enhanced evaluation context ([#1162](https://github.com/microsoft/RD-Agent/issues/1162)) ([4e41c97](https://github.com/microsoft/RD-Agent/commit/4e41c9797cbafd35cc0d883fede4226398c573e1))
|
||||
* add sample submission file check ([#1053](https://github.com/microsoft/RD-Agent/issues/1053)) ([6a840d8](https://github.com/microsoft/RD-Agent/commit/6a840d819251e64d98daa40289592a05ac5fb369))
|
||||
* add show_hard_limit option and update time limit handling in DataScience settings ([#1144](https://github.com/microsoft/RD-Agent/issues/1144)) ([fe762cd](https://github.com/microsoft/RD-Agent/commit/fe762cd860a109b426e3d89a6fbc3c161d77b5e2))
|
||||
* add stdout into workspace for easier debugging ([#1236](https://github.com/microsoft/RD-Agent/issues/1236)) ([d3d4967](https://github.com/microsoft/RD-Agent/commit/d3d4967a129ad986d5087add4b101d913e1e14ba))
|
||||
* add time ratio limit for hyperparameter tuning in Kaggle settin… ([#1135](https://github.com/microsoft/RD-Agent/issues/1135)) ([e44bc83](https://github.com/microsoft/RD-Agent/commit/e44bc8356a93b63eb120e88336eaf4c5b05ccd97))
|
||||
* add user interaction in data science scenario ([#1251](https://github.com/microsoft/RD-Agent/issues/1251)) ([2afef70](https://github.com/microsoft/RD-Agent/commit/2afef703ca0e670197d02aab7f9c4f6e3e409872))
|
||||
* add ws CLI and support optional timeout/cache ([#1066](https://github.com/microsoft/RD-Agent/issues/1066)) ([fae3def](https://github.com/microsoft/RD-Agent/commit/fae3defefa38e91131d4e351d68f4484ca280956))
|
||||
* analyze feedback based on sota numbers ([#1116](https://github.com/microsoft/RD-Agent/issues/1116)) ([167f5e2](https://github.com/microsoft/RD-Agent/commit/167f5e2fe9a5679d5beca2f7d3093ac0fd17e664))
|
||||
* create Jupyter notebook pipeline file based on main.py file ([#1134](https://github.com/microsoft/RD-Agent/issues/1134)) ([2fa1790](https://github.com/microsoft/RD-Agent/commit/2fa1790cb3852d96a197fd7970af4063339dfa26))
|
||||
* enable drafting with knowledge ([#998](https://github.com/microsoft/RD-Agent/issues/998)) ([8e385eb](https://github.com/microsoft/RD-Agent/commit/8e385ebf422256d08f02c055ab64115872b69d94))
|
||||
* enable finetune llm ([#1055](https://github.com/microsoft/RD-Agent/issues/1055)) ([909c7d6](https://github.com/microsoft/RD-Agent/commit/909c7d6e8a35ce8c43d29201eccfe5cd2a21049d))
|
||||
* enable LLM‑based hypothesis selection with time‑aware prompt & colored logging ([#1122](https://github.com/microsoft/RD-Agent/issues/1122)) ([1c4ab89](https://github.com/microsoft/RD-Agent/commit/1c4ab89f52fbdff7cab68ee1b778703b20514a9b))
|
||||
* enable meta planner ([#1103](https://github.com/microsoft/RD-Agent/issues/1103)) ([c208209](https://github.com/microsoft/RD-Agent/commit/c20820929b7fcdd5c9fbb81e63bad0ba76239c50))
|
||||
* enable to inject diversity cross async multi-trace ([#1173](https://github.com/microsoft/RD-Agent/issues/1173)) ([bcdd957](https://github.com/microsoft/RD-Agent/commit/bcdd957c71b59d8664ecb1523b5fcf2179aa1138))
|
||||
* enhance timeout handling in CoSTEER and DataScience scenarios ([#1150](https://github.com/microsoft/RD-Agent/issues/1150)) ([06233cb](https://github.com/microsoft/RD-Agent/commit/06233cb95acb1df01ca71b1a554cf4a5f2c4d092))
|
||||
* enhance timeout management and knowledge base handling in CoSTEER components ([#1130](https://github.com/microsoft/RD-Agent/issues/1130)) ([963d260](https://github.com/microsoft/RD-Agent/commit/963d26001e346c05bcc540536f65d9a199ca6ac5))
|
||||
* fallback to acceptable results ([#1129](https://github.com/microsoft/RD-Agent/issues/1129)) ([3ce2bd4](https://github.com/microsoft/RD-Agent/commit/3ce2bd41c442c6b756810c7895b1e6a1df13dfbb))
|
||||
* improve fallback handling in CoSTEER and add GPU usage guidelin… ([#1165](https://github.com/microsoft/RD-Agent/issues/1165)) ([cec4240](https://github.com/microsoft/RD-Agent/commit/cec424046759f02735a6b49e3a9f615a403b62c9))
|
||||
* init pydantic ai agent & context 7 mcp ([#1240](https://github.com/microsoft/RD-Agent/issues/1240)) ([59af538](https://github.com/microsoft/RD-Agent/commit/59af5383d7d1d73a5e3630da9d1bbfed31111436))
|
||||
* **mcp:** cache with one-click toggle ([#1269](https://github.com/microsoft/RD-Agent/issues/1269)) ([6f86863](https://github.com/microsoft/RD-Agent/commit/6f86863b63ae331f9b7761eaf9ae0a85aca7ba42))
|
||||
* mcts policy based on trace scheduler ([#1203](https://github.com/microsoft/RD-Agent/issues/1203)) ([13890e0](https://github.com/microsoft/RD-Agent/commit/13890e0bbcaf5a7a87a7bff55e720b0c3bbbbfe9))
|
||||
* new prompt for auto-sota-selector ([#1109](https://github.com/microsoft/RD-Agent/issues/1109)) ([13c92a9](https://github.com/microsoft/RD-Agent/commit/13c92a90eee275e40a9a2fb0b853c8ecb2bd59fd))
|
||||
* offline selector ([#1231](https://github.com/microsoft/RD-Agent/issues/1231)) ([76b2e87](https://github.com/microsoft/RD-Agent/commit/76b2e87348cbeb983606691fdf343c4fc721c2bb))
|
||||
* prob-based trace scheduler ([#1131](https://github.com/microsoft/RD-Agent/issues/1131)) ([970561a](https://github.com/microsoft/RD-Agent/commit/970561a057ed5e56e29be3577b7c062aca4b49b6))
|
||||
* query & cache package_info ([#1083](https://github.com/microsoft/RD-Agent/issues/1083)) ([19869ea](https://github.com/microsoft/RD-Agent/commit/19869ea4752b67b62ffdcb8d54632a59661b5466))
|
||||
* refactor CoSTEER classes to use DSCoSTEER and update max seconds handling ([#1156](https://github.com/microsoft/RD-Agent/issues/1156)) ([6d01e3e](https://github.com/microsoft/RD-Agent/commit/6d01e3e1ca1eec281b52f461724bf63adefe5d81))
|
||||
* refine the logic of enabling hyperparameter tuning and add criteira ([#1175](https://github.com/microsoft/RD-Agent/issues/1175)) ([af071f5](https://github.com/microsoft/RD-Agent/commit/af071f5f45bfeb524a0f16da84d802e523478213))
|
||||
* show the summarized final difference between the final workspace and the base workspace ([#1281](https://github.com/microsoft/RD-Agent/issues/1281)) ([2bf8345](https://github.com/microsoft/RD-Agent/commit/2bf83453921457e44c802913a8e24b0de98611bd))
|
||||
* streamline hyperparameter tuning checks and update evaluation g… ([#1167](https://github.com/microsoft/RD-Agent/issues/1167)) ([383e5ed](https://github.com/microsoft/RD-Agent/commit/383e5ed488c73abedb41acb2ea27afd60738669f))
|
||||
* ui, support disable cache ([#1217](https://github.com/microsoft/RD-Agent/issues/1217)) ([92efe33](https://github.com/microsoft/RD-Agent/commit/92efe33fa9c8be54a71bf0840f867edc877236fe))
|
||||
* update README with latest paper acceptance to NeurIPS 2025 ([#1252](https://github.com/microsoft/RD-Agent/issues/1252)) ([8332960](https://github.com/microsoft/RD-Agent/commit/833296084f3b3d0fea15fd693e302c26b2d80762))
|
||||
### Changed
|
||||
- Rebranded from RD-Agent to Predix for EUR/USD quantitative trading
|
||||
- Updated project metadata for PredixAI organization
|
||||
|
||||
### Fixed
|
||||
- Removed all Chinese stock references, replaced with EUR/USD 1min FX data
|
||||
- Migrated to 1min EURUSD data (2020-2026)
|
||||
- Injected MultiIndex warning into factor interface prompt
|
||||
|
||||
### Bug Fixes
|
||||
---
|
||||
|
||||
* add a switch for ensemble_time_upper_bound and fix some bug in main ([#1226](https://github.com/microsoft/RD-Agent/issues/1226)) ([f00a538](https://github.com/microsoft/RD-Agent/commit/f00a5382b16379aaea2dfabf09a681be25e29d3e))
|
||||
* add gpu_info in research phase ([#1094](https://github.com/microsoft/RD-Agent/issues/1094)) ([58c9c1b](https://github.com/microsoft/RD-Agent/commit/58c9c1b9b62d6d25b9b6980e19959664ef7272d7))
|
||||
* add json format response fallback to prompt templates ([#1246](https://github.com/microsoft/RD-Agent/issues/1246)) ([4dfb8a1](https://github.com/microsoft/RD-Agent/commit/4dfb8a130b3970192d3a8da799152de492c79aec))
|
||||
* add metric in scores.csv and avoid reading sample_submission.csv ([#1152](https://github.com/microsoft/RD-Agent/issues/1152)) ([fd039f1](https://github.com/microsoft/RD-Agent/commit/fd039f1f8184c9107539f270735f227cf68c62c0))
|
||||
* add missing self parameter to instance methods in DSProposalV2ExpGen ([#1213](https://github.com/microsoft/RD-Agent/issues/1213)) ([68af035](https://github.com/microsoft/RD-Agent/commit/68af03517749cff4726acb016daad561148147bf))
|
||||
* add spec for hyperparameters in task design and coder ([#995](https://github.com/microsoft/RD-Agent/issues/995)) ([10246fd](https://github.com/microsoft/RD-Agent/commit/10246fd2491d48560d5f7055f78906e7a6a2882e))
|
||||
* align scenario descriptions and include debug timeout ([#1079](https://github.com/microsoft/RD-Agent/issues/1079)) ([13b6663](https://github.com/microsoft/RD-Agent/commit/13b66630ec17f1ed4f52a9d8ea0913722ca74483))
|
||||
* allow prev_out keys to be None in workspace cleanup assertion ([#1214](https://github.com/microsoft/RD-Agent/issues/1214)) ([1f4d190](https://github.com/microsoft/RD-Agent/commit/1f4d190a3209bbe4ec960f8dd79be59672cd0e7f))
|
||||
* based on response schema; not function calling ([#1038](https://github.com/microsoft/RD-Agent/issues/1038)) ([99da8c5](https://github.com/microsoft/RD-Agent/commit/99da8c58f0f779aa19edc2522d4cf143577811d8))
|
||||
* cancel tasks on resume and kill subprocesses on termination ([#1166](https://github.com/microsoft/RD-Agent/issues/1166)) ([cf6e418](https://github.com/microsoft/RD-Agent/commit/cf6e418eb8d899e22c93279055d42c185397fa2a))
|
||||
* change runner prompts ([#1223](https://github.com/microsoft/RD-Agent/issues/1223)) ([6d3e73d](https://github.com/microsoft/RD-Agent/commit/6d3e73d679a8ffe4a48923590a7c37b4fdcd207a))
|
||||
* clear ws_ckp after extraction to reduce workspace object size ([#1137](https://github.com/microsoft/RD-Agent/issues/1137)) ([783affe](https://github.com/microsoft/RD-Agent/commit/783affe0d513b2e9fbcbb11e0408cc79db19a274))
|
||||
* correct DS_LOCAL_DATA_PATH error in devcontainer ([#1063](https://github.com/microsoft/RD-Agent/issues/1063)) ([588fcfa](https://github.com/microsoft/RD-Agent/commit/588fcfa3ab0a4eca5afee766e3f56f094b28a999))
|
||||
* **dockerfile:** install coreutils to resolve timeout command error ([#1260](https://github.com/microsoft/RD-Agent/issues/1260)) ([07f89b0](https://github.com/microsoft/RD-Agent/commit/07f89b013ea99102f4875fda5704adde14cf9978))
|
||||
* **docs:** update rdagent ui with correct params ([#1249](https://github.com/microsoft/RD-Agent/issues/1249)) ([f360d0a](https://github.com/microsoft/RD-Agent/commit/f360d0a212793eb044c218b5e13b095e684a632d))
|
||||
* enable embedding truncation ([#1188](https://github.com/microsoft/RD-Agent/issues/1188)) ([2421fa4](https://github.com/microsoft/RD-Agent/commit/2421fa4493bd86c98ff672afc26ec71ba510e391))
|
||||
* enhance feedback handling in MultiProcessEvolvingStrategy for improved task evolution ([#1274](https://github.com/microsoft/RD-Agent/issues/1274)) ([961e561](https://github.com/microsoft/RD-Agent/commit/961e56102cddae3348af46a30f9085f353151890))
|
||||
* error in prompt template ([#1065](https://github.com/microsoft/RD-Agent/issues/1065)) ([a90e598](https://github.com/microsoft/RD-Agent/commit/a90e598e568c0339a5f29577fbf44e302bc0d96f))
|
||||
* filter log folders bug in ui ([#1073](https://github.com/microsoft/RD-Agent/issues/1073)) ([d0f33c5](https://github.com/microsoft/RD-Agent/commit/d0f33c56733bb28222c1f2c8f8a0ff5604ddf858))
|
||||
* fix a bug in return curve display ([#1042](https://github.com/microsoft/RD-Agent/issues/1042)) ([249f661](https://github.com/microsoft/RD-Agent/commit/249f6614a67d8b38e9ad2f0d95154db7071e8e3a))
|
||||
* fix a small bug in json_mode ([#1041](https://github.com/microsoft/RD-Agent/issues/1041)) ([8bc12ea](https://github.com/microsoft/RD-Agent/commit/8bc12eaaa7ecda69043ec781896299a6796c8140))
|
||||
* fix a small bug in response_schema ([#1043](https://github.com/microsoft/RD-Agent/issues/1043)) ([66cadcd](https://github.com/microsoft/RD-Agent/commit/66cadcd7b2a91bac416acd94196b96f43b572c2b))
|
||||
* fix bug for hypo_select_with_llm when not support response_schema ([#1208](https://github.com/microsoft/RD-Agent/issues/1208)) ([54cc2c4](https://github.com/microsoft/RD-Agent/commit/54cc2c492e3f6b22b3836899f2ddf83b1296f173))
|
||||
* fix chat_max_tokens calculation method to show true input_max_tokens ([#1241](https://github.com/microsoft/RD-Agent/issues/1241)) ([7d749b8](https://github.com/microsoft/RD-Agent/commit/7d749b819557f1abfca58189ae2abf2aec41fef5))
|
||||
* fix code diff bug ([#1115](https://github.com/microsoft/RD-Agent/issues/1115)) ([4603e88](https://github.com/microsoft/RD-Agent/commit/4603e88dbe910614f20a843f29463f17eebdda32))
|
||||
* fix mcts ([#1270](https://github.com/microsoft/RD-Agent/issues/1270)) ([c73f67a](https://github.com/microsoft/RD-Agent/commit/c73f67affee035def37474c66ebdd00dbc16c4ca))
|
||||
* fix some bugs in RD-Agent(Q) ([#1143](https://github.com/microsoft/RD-Agent/issues/1143)) ([44fd2ee](https://github.com/microsoft/RD-Agent/commit/44fd2ee68031599e106cbd99b8e86a110d8f2423))
|
||||
* **graph:** using assignment expression to avoid repeated function call ([#1174](https://github.com/microsoft/RD-Agent/issues/1174)) ([b4f57ce](https://github.com/microsoft/RD-Agent/commit/b4f57cec87bc61e8aa408319532cec055cb2d632))
|
||||
* handle mixed str and dict types in code_list ([#1279](https://github.com/microsoft/RD-Agent/issues/1279)) ([63ecb3b](https://github.com/microsoft/RD-Agent/commit/63ecb3bf26604d93f85595f6f6470c860be3c5ba))
|
||||
* handle None output and conditional step dump in LoopBase execution ([#1212](https://github.com/microsoft/RD-Agent/issues/1212)) ([68b6985](https://github.com/microsoft/RD-Agent/commit/68b69851916ed5bca42aab859ba7a9938bec4eb7))
|
||||
* handle the no-update case of root node in uncommited_rec_status ([#1062](https://github.com/microsoft/RD-Agent/issues/1062)) ([ead8dce](https://github.com/microsoft/RD-Agent/commit/ead8dced0e5b157b6e1bded380f440ee0b8a86f7))
|
||||
* handle ValueError in stdout shrinking and refactor shrink logic ([#1228](https://github.com/microsoft/RD-Agent/issues/1228)) ([bc7a3b4](https://github.com/microsoft/RD-Agent/commit/bc7a3b43b7cef45f036d508f95231b5885ad65f7))
|
||||
* ignore case when checking metric name ([#1160](https://github.com/microsoft/RD-Agent/issues/1160)) ([fc0df6e](https://github.com/microsoft/RD-Agent/commit/fc0df6e9fc7d8a9e7a0b4d4cb879cffbbcb9162f))
|
||||
* ignore class types when filtering workflow steps ([#1085](https://github.com/microsoft/RD-Agent/issues/1085)) ([64e3ec8](https://github.com/microsoft/RD-Agent/commit/64e3ec8f9afb5611814f9b64d50e6dc0685df8b2))
|
||||
* ignore RuntimeError for shared workspace double recovery ([#1140](https://github.com/microsoft/RD-Agent/issues/1140)) ([8fc1e9b](https://github.com/microsoft/RD-Agent/commit/8fc1e9bf8f5242e56d7bacf53cf58f9abe94e356))
|
||||
* improve the logic of json_schema and refine the reasoning extraction logic for reasoning model ([#1044](https://github.com/microsoft/RD-Agent/issues/1044)) ([12060b1](https://github.com/microsoft/RD-Agent/commit/12060b197ca618ca8901f93cde6bc2b42d79e4e9))
|
||||
* increase retry count in hypothesis_gen decorator to 10 ([#1230](https://github.com/microsoft/RD-Agent/issues/1230)) ([c4b8baa](https://github.com/microsoft/RD-Agent/commit/c4b8baaa5829567833ea2328fe89941423bf4cf2))
|
||||
* increase time default not controlled by LLM ([#1196](https://github.com/microsoft/RD-Agent/issues/1196)) ([8c62561](https://github.com/microsoft/RD-Agent/commit/8c62561d1c6bd3c8b3d354951cd154b08d567ef2))
|
||||
* insert await asyncio.sleep(0) to yield control in loop ([#1186](https://github.com/microsoft/RD-Agent/issues/1186)) ([5705be0](https://github.com/microsoft/RD-Agent/commit/5705be0512b788337c6798aea0bdf52791dd8e73))
|
||||
* jinja problem of enumerate ([#1216](https://github.com/microsoft/RD-Agent/issues/1216)) ([af9068c](https://github.com/microsoft/RD-Agent/commit/af9068c0b5263c5f58a43ccd13c19808020f77aa))
|
||||
* kaggle competition metric direction ([#1195](https://github.com/microsoft/RD-Agent/issues/1195)) ([a933b6c](https://github.com/microsoft/RD-Agent/commit/a933b6cabe6f6b673a30601f9b0974bc3ca806ae))
|
||||
* merge candidates ([#1254](https://github.com/microsoft/RD-Agent/issues/1254)) ([5a78c89](https://github.com/microsoft/RD-Agent/commit/5a78c89cee1fb593e3503bd4266042ba1e29569a))
|
||||
* minor conflict in prompts ([#1081](https://github.com/microsoft/RD-Agent/issues/1081)) ([f821e4c](https://github.com/microsoft/RD-Agent/commit/f821e4c1c56462c54d5fbe15dd797c147334b182))
|
||||
* minor fix to runtime_environment ([#1089](https://github.com/microsoft/RD-Agent/issues/1089)) ([bff82ef](https://github.com/microsoft/RD-Agent/commit/bff82ef93e225c43c6b55bb642c484d5b88f3cff))
|
||||
* model/factor experiment filtering in Qlib proposals ([#1257](https://github.com/microsoft/RD-Agent/issues/1257)) ([0f722e1](https://github.com/microsoft/RD-Agent/commit/0f722e1ce713d2010fe8b8181b905145a1186f95))
|
||||
* move snapshot saving after step index update in loop execution ([#1206](https://github.com/microsoft/RD-Agent/issues/1206)) ([0e3a9af](https://github.com/microsoft/RD-Agent/commit/0e3a9afd0a30b5a12ef3431043405f3314b4c635))
|
||||
* move task cancellation to finally block and fix subprocess kill typo ([#1234](https://github.com/microsoft/RD-Agent/issues/1234)) ([fb628e3](https://github.com/microsoft/RD-Agent/commit/fb628e3bcaded1f292e5827f258fa7d5f9ed74a9))
|
||||
* package and timer bug ([#1092](https://github.com/microsoft/RD-Agent/issues/1092)) ([7faf6d9](https://github.com/microsoft/RD-Agent/commit/7faf6d9b215d678b8cb146270a3e917a62ac1d88))
|
||||
* path traversal risk ([#1050](https://github.com/microsoft/RD-Agent/issues/1050)) ([2f78216](https://github.com/microsoft/RD-Agent/commit/2f782169ebeb0453422621ac8ace06353ca72615))
|
||||
* prevent JSON content from being added multiple times during retries ([#1255](https://github.com/microsoft/RD-Agent/issues/1255)) ([9d46a68](https://github.com/microsoft/RD-Agent/commit/9d46a68a36f237ef99bbc4a78668d71339fa9f91))
|
||||
* prevent parallelism in feedback and record steps ([#1046](https://github.com/microsoft/RD-Agent/issues/1046)) ([d0272a9](https://github.com/microsoft/RD-Agent/commit/d0272a9de104a629ccd2652b9e95c9bb58ac6cb1))
|
||||
* prompt yaml ([#1112](https://github.com/microsoft/RD-Agent/issues/1112)) ([1f2c9b1](https://github.com/microsoft/RD-Agent/commit/1f2c9b17b8d5250dc2ff81ad564139746d11a7c3))
|
||||
* properly assign sota_exp_fb before None comparison ([#1037](https://github.com/microsoft/RD-Agent/issues/1037)) ([5d6a927](https://github.com/microsoft/RD-Agent/commit/5d6a927501e95b6afa520294d23fcf9ca16c69ae))
|
||||
* refine DSCoSTEER_eval prompts ([#1157](https://github.com/microsoft/RD-Agent/issues/1157)) ([c62e5fc](https://github.com/microsoft/RD-Agent/commit/c62e5fcc871d4f88babc5a4c9cf8e4655e8ba437))
|
||||
* refine prompt, equal lightgbm, discourage over hypertuning ([#1072](https://github.com/microsoft/RD-Agent/issues/1072)) ([56ba15a](https://github.com/microsoft/RD-Agent/commit/56ba15a03fc278e7d701b40bbb5209411b27e561))
|
||||
* refine prompt; runner focus on low hanging fruit ([#1076](https://github.com/microsoft/RD-Agent/issues/1076)) ([1778b8c](https://github.com/microsoft/RD-Agent/commit/1778b8c953888e9b3b91d28483e0b64d126e3eb6))
|
||||
* refine prompts and add additional package info ([#1179](https://github.com/microsoft/RD-Agent/issues/1179)) ([22428a4](https://github.com/microsoft/RD-Agent/commit/22428a45053b6eefcfb805802b8bef4384a1ddda))
|
||||
* refine task scheduling logic in MultiProcessEvolvingStrategy for… ([#1275](https://github.com/microsoft/RD-Agent/issues/1275)) ([417766e](https://github.com/microsoft/RD-Agent/commit/417766ee366d1fdf4a54e297a93d05cb606d5144))
|
||||
* refine the prompt to force complete code & refine the logic of running ([#1069](https://github.com/microsoft/RD-Agent/issues/1069)) ([1e61de3](https://github.com/microsoft/RD-Agent/commit/1e61de3e60566029f1c89ca2c747bfbf3a354693))
|
||||
* remove refine decision & bug fix ([#1031](https://github.com/microsoft/RD-Agent/issues/1031)) ([0059a6a](https://github.com/microsoft/RD-Agent/commit/0059a6aeb658a76bdc28cd7741a2bc9e6569363f))
|
||||
* remove unused imports in data science scenario module ([#1136](https://github.com/microsoft/RD-Agent/issues/1136)) ([2307237](https://github.com/microsoft/RD-Agent/commit/23072377659da0bd206dc64dd858c9da75283f39))
|
||||
* replace hardcoded ChromeDriver path with webdriver-manager ([#1271](https://github.com/microsoft/RD-Agent/issues/1271)) ([40876e2](https://github.com/microsoft/RD-Agent/commit/40876e2085fb0e30e46b69fec34208d7e0dd1162))
|
||||
* revert 2 commits ([#1239](https://github.com/microsoft/RD-Agent/issues/1239)) ([1265ae9](https://github.com/microsoft/RD-Agent/commit/1265ae94e357190132fb2cd9ba3579d353ed6cee))
|
||||
* revert to v10 setting ([#1220](https://github.com/microsoft/RD-Agent/issues/1220)) ([d868188](https://github.com/microsoft/RD-Agent/commit/d868188f9a6fd451d1daf1b1cc14017a50232b0d))
|
||||
* scheduler next selection parallel disorder ([#1028](https://github.com/microsoft/RD-Agent/issues/1028)) ([f468595](https://github.com/microsoft/RD-Agent/commit/f468595169512b89f436396ee976404879e00d7a))
|
||||
* set requires_documentation_search to None to disable feature in eval ([#1245](https://github.com/microsoft/RD-Agent/issues/1245)) ([e117234](https://github.com/microsoft/RD-Agent/commit/e1172343e483638dc24715402048ec7116e8a429))
|
||||
* skip res_ratio check if timer or res_time is None ([#1189](https://github.com/microsoft/RD-Agent/issues/1189)) ([17400a3](https://github.com/microsoft/RD-Agent/commit/17400a3dc46ab987ef4670cf697a22c7145858be))
|
||||
* split then sample & remove simple model guide in ds proposal ([#1034](https://github.com/microsoft/RD-Agent/issues/1034)) ([2dde8b8](https://github.com/microsoft/RD-Agent/commit/2dde8b84a1d08cf0ca39b2f50de64d053fd73ba8))
|
||||
* stop evolve if global timer is timeout ([#1039](https://github.com/microsoft/RD-Agent/issues/1039)) ([ad37417](https://github.com/microsoft/RD-Agent/commit/ad374176a14be1fa5aac43fd8df48f89b2a81fe0))
|
||||
* summary page bug ([#1219](https://github.com/microsoft/RD-Agent/issues/1219)) ([36fec9a](https://github.com/microsoft/RD-Agent/commit/36fec9afa6d740a9f1ac32ac661cf7ec9fdaefc8))
|
||||
* TypeError: cannot unpack non-iterable bool object ([#1036](https://github.com/microsoft/RD-Agent/issues/1036)) ([f4370a4](https://github.com/microsoft/RD-Agent/commit/f4370a4265c84cefc4844d21b7f296929ca7638c))
|
||||
* ui bug ([#1192](https://github.com/microsoft/RD-Agent/issues/1192)) ([ad901aa](https://github.com/microsoft/RD-Agent/commit/ad901aaf4f7b344b8171b98ea753fde67b058a9b))
|
||||
* update fallback criterion ([#1210](https://github.com/microsoft/RD-Agent/issues/1210)) ([05fca1a](https://github.com/microsoft/RD-Agent/commit/05fca1acced3d3cfddbab3871d3dcee597b675bd))
|
||||
* update requirements.txt's streamlit ([#1133](https://github.com/microsoft/RD-Agent/issues/1133)) ([512d08f](https://github.com/microsoft/RD-Agent/commit/512d08f56c210edfa2ff45c71e53724909f10d8f))
|
||||
* use CoSTEERSettings for DSRunnerCoSTEERSettings ([#1096](https://github.com/microsoft/RD-Agent/issues/1096)) ([152a70f](https://github.com/microsoft/RD-Agent/commit/152a70f25a090e175e7b55c2285ca710954be9cc))
|
||||
## Historical Changes (from RD-Agent upstream)
|
||||
|
||||
## [0.7.0](https://github.com/microsoft/RD-Agent/compare/v0.6.1...v0.7.0) (2025-07-08)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add code change summary ([#1000](https://github.com/microsoft/RD-Agent/issues/1000)) ([937ec26](https://github.com/microsoft/RD-Agent/commit/937ec263b215928633822c4d76ad4e47442c8198))
|
||||
* add hide_base_name option and update data folder prompts ([#1004](https://github.com/microsoft/RD-Agent/issues/1004)) ([2f61fa8](https://github.com/microsoft/RD-Agent/commit/2f61fa8cd90c91ad29f320ce9ea6c49f49ac9111))
|
||||
* added running time statistics for the DS scenario experiment ([#1007](https://github.com/microsoft/RD-Agent/issues/1007)) ([030abd8](https://github.com/microsoft/RD-Agent/commit/030abd87191377641a678c80852f5ecad84e7a6e))
|
||||
* merge code summary and support more traces ([#1025](https://github.com/microsoft/RD-Agent/issues/1025)) ([48201e7](https://github.com/microsoft/RD-Agent/commit/48201e79b55ff5a98dad51702a7d0ac6b1ddc9eb))
|
||||
* show first evo round codes diff ([#1009](https://github.com/microsoft/RD-Agent/issues/1009)) ([4844622](https://github.com/microsoft/RD-Agent/commit/4844622e5fd28d7cbaabd9d7888f8204c60b76b3))
|
||||
* try coder on whole data ([#1017](https://github.com/microsoft/RD-Agent/issues/1017)) ([4973e05](https://github.com/microsoft/RD-Agent/commit/4973e0532248c6172eec3bb70dffda052af2d14f))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* fix a minor bug in DS eval ([#1012](https://github.com/microsoft/RD-Agent/issues/1012)) ([5a520e9](https://github.com/microsoft/RD-Agent/commit/5a520e9d44899d44fddc0f2e5571596223161b71))
|
||||
* fix some bugs in quant scen ([#1026](https://github.com/microsoft/RD-Agent/issues/1026)) ([7b34d41](https://github.com/microsoft/RD-Agent/commit/7b34d418642d1c0c2986db9ecf6a5d9bc22cc3da))
|
||||
* support experimental support for Deepseek models and update docs about configuration ([#1024](https://github.com/microsoft/RD-Agent/issues/1024)) ([35cfc19](https://github.com/microsoft/RD-Agent/commit/35cfc193f9b35d786aeb7585334427ad358c982f))
|
||||
|
||||
## [0.6.1](https://github.com/microsoft/RD-Agent/compare/v0.6.0...v0.6.1) (2025-06-28)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* fix mount ([#1001](https://github.com/microsoft/RD-Agent/issues/1001)) ([4ae2f13](https://github.com/microsoft/RD-Agent/commit/4ae2f1303dfcbaea53d459be7c8e85bf85ce5f4f))
|
||||
* handle the bug of wrong dag_parant index ([#996](https://github.com/microsoft/RD-Agent/issues/996)) ([bda12ff](https://github.com/microsoft/RD-Agent/commit/bda12ffecf9ae116e0d04eece0c6a1b61413d916))
|
||||
* improve log folder sorting and selection UX ([#993](https://github.com/microsoft/RD-Agent/issues/993)) ([b116807](https://github.com/microsoft/RD-Agent/commit/b11680777f116b6c40f9e535e0da10c186c95050))
|
||||
|
||||
## [0.6.0](https://github.com/microsoft/RD-Agent/compare/v0.5.0...v0.6.0) (2025-06-26)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* async mechanism for multi-trace ([#981](https://github.com/microsoft/RD-Agent/issues/981)) ([9e60c32](https://github.com/microsoft/RD-Agent/commit/9e60c32cf348481eb55617809c059c359d7603b8))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* add async to direct_exp_gen avoid infinite loop ([#992](https://github.com/microsoft/RD-Agent/issues/992)) ([78c203d](https://github.com/microsoft/RD-Agent/commit/78c203d8eefbba67fc120b35cb25e85b2200ac49))
|
||||
* docker container cleanup to prevent accumulation and system slowdown ([#975](https://github.com/microsoft/RD-Agent/issues/975)) ([05cf094](https://github.com/microsoft/RD-Agent/commit/05cf094913e48c903c8a4476d6c609d8bfa10681))
|
||||
* fix a bug and update the docs ([#978](https://github.com/microsoft/RD-Agent/issues/978)) ([d1ae9e1](https://github.com/microsoft/RD-Agent/commit/d1ae9e1dcc2ccd1ffe05cb1c6db3e905fa70425c))
|
||||
* merge datascience v3 and v2 ([#974](https://github.com/microsoft/RD-Agent/issues/974)) ([1ba7548](https://github.com/microsoft/RD-Agent/commit/1ba754853ce2010ce1cb0bbd217b67689fa1ebdf))
|
||||
* refine details ([#979](https://github.com/microsoft/RD-Agent/issues/979)) ([25caa3d](https://github.com/microsoft/RD-Agent/commit/25caa3d00c255286dce27915b9355987b87ed2e8))
|
||||
* refine prompt ([#987](https://github.com/microsoft/RD-Agent/issues/987)) ([76df96e](https://github.com/microsoft/RD-Agent/commit/76df96ee88212a8aee7f518b9cacf80591dc2939))
|
||||
|
||||
## [0.5.0](https://github.com/microsoft/RD-Agent/compare/v0.4.0...v0.5.0) (2025-06-18)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add a check for whether values in score_df are NaN ([#756](https://github.com/microsoft/RD-Agent/issues/756)) ([d9cc780](https://github.com/microsoft/RD-Agent/commit/d9cc78098beb27f3a1bf2f2d461302db177b7d41))
|
||||
* add competition level filter and extract constants to utils ([#869](https://github.com/microsoft/RD-Agent/issues/869)) ([b40b605](https://github.com/microsoft/RD-Agent/commit/b40b6055368e6c72d8435352104b1c281b06da7f))
|
||||
* add DocDev for auto-generating workspace documentation ([#781](https://github.com/microsoft/RD-Agent/issues/781)) ([bcba6ea](https://github.com/microsoft/RD-Agent/commit/bcba6eac32684ebb267c93b4e85dbfa9561d15d1))
|
||||
* add drafting pipeline ([#832](https://github.com/microsoft/RD-Agent/issues/832)) ([efedddf](https://github.com/microsoft/RD-Agent/commit/efedddf39bc19221fdffc2e39ee0a09097fc82b0))
|
||||
* add last_exp_fb to DSTrace and update feedback retrieval usage ([#910](https://github.com/microsoft/RD-Agent/issues/910)) ([10531fd](https://github.com/microsoft/RD-Agent/commit/10531fda9438c6915b26d5013bd2413e1333ceb9))
|
||||
* add mlflow logger in RD loop to log ([#815](https://github.com/microsoft/RD-Agent/issues/815)) ([b91b54f](https://github.com/microsoft/RD-Agent/commit/b91b54f355c26b751087d0c14774f466e82866de))
|
||||
* add naive experiment generator and update proposal configurations ([#759](https://github.com/microsoft/RD-Agent/issues/759)) ([75494f4](https://github.com/microsoft/RD-Agent/commit/75494f4fed5bc845acfd7f7bacef385f0f96c514))
|
||||
* add RD-Agent-Quant scenario ([#838](https://github.com/microsoft/RD-Agent/issues/838)) ([6e42d52](https://github.com/microsoft/RD-Agent/commit/6e42d523a85df67aa13927abbf0894564c71880e))
|
||||
* add reasoning_effort parameter to LiteLLMAPIBackend and LLMSett… ([#754](https://github.com/microsoft/RD-Agent/issues/754)) ([113889f](https://github.com/microsoft/RD-Agent/commit/113889fefe9b09aaea1b564704c81664b8f77ec5))
|
||||
* add reviewer in feedback ([#765](https://github.com/microsoft/RD-Agent/issues/765)) ([1a95bee](https://github.com/microsoft/RD-Agent/commit/1a95bee6aa6bc6f45fdeb484f3a6f81caa273038))
|
||||
* advanced checkpoint selectors ([#790](https://github.com/microsoft/RD-Agent/issues/790)) ([50ea033](https://github.com/microsoft/RD-Agent/commit/50ea0336e93d8cb39fb871e81a3f61abdf293bc7))
|
||||
* archive python and csv files in workspace to maintain results ([#814](https://github.com/microsoft/RD-Agent/issues/814)) ([67d0e01](https://github.com/microsoft/RD-Agent/commit/67d0e01e7c9237da1371d93cbf9d86f5f46faac4))
|
||||
* checkpoint selection ([#744](https://github.com/microsoft/RD-Agent/issues/744)) ([a15a06a](https://github.com/microsoft/RD-Agent/commit/a15a06ad643977db59d7cac9da52e637cf80395a))
|
||||
* custom data ([#810](https://github.com/microsoft/RD-Agent/issues/810)) ([6322916](https://github.com/microsoft/RD-Agent/commit/632291608cf605bd8bcfcab0017824823bdecdb8))
|
||||
* dump model ([#776](https://github.com/microsoft/RD-Agent/issues/776)) ([b49481e](https://github.com/microsoft/RD-Agent/commit/b49481e073e6f536d2b1b3bd2d01229ed05abdea))
|
||||
* enable to set different version of idea-proposal for multi traces ([#895](https://github.com/microsoft/RD-Agent/issues/895)) ([236c28f](https://github.com/microsoft/RD-Agent/commit/236c28f29c6bc5da62129632e464bbc32056ebdb))
|
||||
* enhance compatibility with more LLM models ([#905](https://github.com/microsoft/RD-Agent/issues/905)) ([8800624](https://github.com/microsoft/RD-Agent/commit/8800624ad4749d6e798785a082c9f94c306792ef))
|
||||
* idea pool integrated to exp_gen & add timer to RD-Agent & pause-resume to RD-loops ([#795](https://github.com/microsoft/RD-Agent/issues/795)) ([e62aefa](https://github.com/microsoft/RD-Agent/commit/e62aefa56e34ff45a8ed033f7bf28b95c8e63656))
|
||||
* joblib cache ([#749](https://github.com/microsoft/RD-Agent/issues/749)) ([83a0411](https://github.com/microsoft/RD-Agent/commit/83a041148ff908871b1906f9e6889d80ab513412))
|
||||
* log api status to mlflow ([#860](https://github.com/microsoft/RD-Agent/issues/860)) ([049921b](https://github.com/microsoft/RD-Agent/commit/049921beb0b4ed0ba1ab7508d9857d2c1e729349))
|
||||
* log reaching max time limit before breaking CoSTEER evolution ([#921](https://github.com/microsoft/RD-Agent/issues/921)) ([837fff2](https://github.com/microsoft/RD-Agent/commit/837fff29096fefe1369d386ef8a860395b737173))
|
||||
* merge failed and successful traces together ([#766](https://github.com/microsoft/RD-Agent/issues/766)) ([3a2aa8c](https://github.com/microsoft/RD-Agent/commit/3a2aa8cf0102647950b2dfc0007c118b0c799cd4))
|
||||
* merge selectively ([#888](https://github.com/microsoft/RD-Agent/issues/888)) ([06ba314](https://github.com/microsoft/RD-Agent/commit/06ba314ff0f91e7e78e8d456c719ac3194a8c774))
|
||||
* multi-trace online merge ([#886](https://github.com/microsoft/RD-Agent/issues/886)) ([2112d67](https://github.com/microsoft/RD-Agent/commit/2112d676d0938de6fea163b2e5eb9c36771e7041))
|
||||
* new proposal (structured outputs) prompts ([#887](https://github.com/microsoft/RD-Agent/issues/887)) ([150796a](https://github.com/microsoft/RD-Agent/commit/150796aaa72eaa5037fd7db8e785058fbc4d4967))
|
||||
* parallel loop running based on asyncio ([#932](https://github.com/microsoft/RD-Agent/issues/932)) ([c63e207](https://github.com/microsoft/RD-Agent/commit/c63e2071f3179feef69f88061c0172cb5c3157f2))
|
||||
* propose hypothesis across multiple parts in pipeline ([#827](https://github.com/microsoft/RD-Agent/issues/827)) ([acb0e21](https://github.com/microsoft/RD-Agent/commit/acb0e21a331410d044849e12e2887f41e5ff1c3a))
|
||||
* pull image with progress ([#777](https://github.com/microsoft/RD-Agent/issues/777)) ([5cad086](https://github.com/microsoft/RD-Agent/commit/5cad0860204ede974533dc7bdc9808cfd135fa24))
|
||||
* raise error when timeout in api call ([#793](https://github.com/microsoft/RD-Agent/issues/793)) ([eafd4df](https://github.com/microsoft/RD-Agent/commit/eafd4dfc6263f19a8cdaf27498a1d07b43815306))
|
||||
* raise policy violation ([#894](https://github.com/microsoft/RD-Agent/issues/894)) ([5b9d007](https://github.com/microsoft/RD-Agent/commit/5b9d0072aebe15369e9a0010af83e71684baeae7))
|
||||
* reanalyze competition info & pipeline coding evaluator prompt ([#837](https://github.com/microsoft/RD-Agent/issues/837)) ([f7b5258](https://github.com/microsoft/RD-Agent/commit/f7b52580080c75d311355bcc6193b49495801809))
|
||||
* refine merge ([#842](https://github.com/microsoft/RD-Agent/issues/842)) ([99463b4](https://github.com/microsoft/RD-Agent/commit/99463b46819b3a0dcb2bb12a823a9cdf7ec560b4))
|
||||
* refine prompt ([#760](https://github.com/microsoft/RD-Agent/issues/760)) ([a91b182](https://github.com/microsoft/RD-Agent/commit/a91b182c4c9510eb34e4aab956588e909fa5d70b))
|
||||
* replace hard-coded cache paths with dynamic cache_path config ([#952](https://github.com/microsoft/RD-Agent/issues/952)) ([db56894](https://github.com/microsoft/RD-Agent/commit/db568947f1084a80d603718f5a13fdbd72b90a47))
|
||||
* revert draft stage into a soft decay in hypothesis selection ([#849](https://github.com/microsoft/RD-Agent/issues/849)) ([d41db0c](https://github.com/microsoft/RD-Agent/commit/d41db0ca357b07091825ebd9d18c303b6db3cc6a))
|
||||
* trace merging ([#836](https://github.com/microsoft/RD-Agent/issues/836)) ([a3d5473](https://github.com/microsoft/RD-Agent/commit/a3d547369e408a05cff570c1239b6320be40418d))
|
||||
* truncate by time ([#863](https://github.com/microsoft/RD-Agent/issues/863)) ([2b9427a](https://github.com/microsoft/RD-Agent/commit/2b9427ae036ffe1e28a717502f45500fe91fe5ac))
|
||||
* update prompt to improve json respond format of some LLM models ([#928](https://github.com/microsoft/RD-Agent/issues/928)) ([0b84709](https://github.com/microsoft/RD-Agent/commit/0b84709e59c7abb9754961cd17cc9673fcf508aa))
|
||||
* using different chat model in different part ([#822](https://github.com/microsoft/RD-Agent/issues/822)) ([c052ea6](https://github.com/microsoft/RD-Agent/commit/c052ea6d1f8948183a4a6ebc873ec01b57373cce))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* 'DSProposalV2ExpGen' object has no attribute 'COMPONENT_TASK_MAP… ([#950](https://github.com/microsoft/RD-Agent/issues/950)) ([e353895](https://github.com/microsoft/RD-Agent/commit/e353895251f231fee85abdcb1b22b022a577af77))
|
||||
* adapting UI to mock trace ([#841](https://github.com/microsoft/RD-Agent/issues/841)) ([8a5754c](https://github.com/microsoft/RD-Agent/commit/8a5754c9b9c9410d0943aeed777a93c13422e54a))
|
||||
* add missing semicolon after chmod in env shell command ([#955](https://github.com/microsoft/RD-Agent/issues/955)) ([1128eaa](https://github.com/microsoft/RD-Agent/commit/1128eaa89ec1dcab4a05ef50d64c7f7e6aae88a8))
|
||||
* add time to timer when api timeout bug ([#826](https://github.com/microsoft/RD-Agent/issues/826)) ([f45d6ae](https://github.com/microsoft/RD-Agent/commit/f45d6ae6595c1c39b389485b637a0ae53ffc8782))
|
||||
* add wait_retry to exp_gen v2 ([#783](https://github.com/microsoft/RD-Agent/issues/783)) ([b9fb7cf](https://github.com/microsoft/RD-Agent/commit/b9fb7cf4e3070062d91b5b67d0f10d6266b45142))
|
||||
* adjust ds_trace lookup and add stderr redirect to mlebench command ([#853](https://github.com/microsoft/RD-Agent/issues/853)) ([4e53108](https://github.com/microsoft/RD-Agent/commit/4e53108e020db719b39cba3a67e0c6dae3de19cf))
|
||||
* align competion_full_desc and scenario_all_desc, remove redundant info in problems proposal ([#808](https://github.com/microsoft/RD-Agent/issues/808)) ([76d8536](https://github.com/microsoft/RD-Agent/commit/76d8536d9ec53952383019306781d49cb3e9f75c))
|
||||
* bug fix in timer start ([#807](https://github.com/microsoft/RD-Agent/issues/807)) ([9af7161](https://github.com/microsoft/RD-Agent/commit/9af7161eb57bdd2e24b072335e9d185951c32472))
|
||||
* bug in problem identification ([#806](https://github.com/microsoft/RD-Agent/issues/806)) ([e1d5a29](https://github.com/microsoft/RD-Agent/commit/e1d5a2914046476f2f10d5884ed3c3ff956d65ff))
|
||||
* conda error information ([#941](https://github.com/microsoft/RD-Agent/issues/941)) ([fd39a94](https://github.com/microsoft/RD-Agent/commit/fd39a947763fb4a9be87b907c399bebe384df505))
|
||||
* default cost to NaN when calculation fails in LiteLLM backend ([#912](https://github.com/microsoft/RD-Agent/issues/912)) ([51a4048](https://github.com/microsoft/RD-Agent/commit/51a4048129cbfbc3b84bcf50fd8866fafb3e2da3))
|
||||
* ds trace ([#929](https://github.com/microsoft/RD-Agent/issues/929)) ([127e441](https://github.com/microsoft/RD-Agent/commit/127e441602e21a46d6313ff39133ab8ca841937e))
|
||||
* duplicate model names test in pipeline coder & runner ([#763](https://github.com/microsoft/RD-Agent/issues/763)) ([be3ee9d](https://github.com/microsoft/RD-Agent/commit/be3ee9da9882edda3c06ff7d1099d1bbda2203c3))
|
||||
* filter system metadata dirs and init missing DSTrace attribute ([#946](https://github.com/microsoft/RD-Agent/issues/946)) ([10050ef](https://github.com/microsoft/RD-Agent/commit/10050ef368ae7ec07cbf20ac4e52e21c2875eaab))
|
||||
* fix a bug in docker result extraction ([#824](https://github.com/microsoft/RD-Agent/issues/824)) ([e1c0f98](https://github.com/microsoft/RD-Agent/commit/e1c0f9826abcbc11dda215a600a2637c9ac6e984))
|
||||
* fix competition metric direction ([#784](https://github.com/microsoft/RD-Agent/issues/784)) ([3be0057](https://github.com/microsoft/RD-Agent/commit/3be0057556f46c899065ee1c7f9bafe33e79249c))
|
||||
* fix model input shape bug and costeer_model bug ([#821](https://github.com/microsoft/RD-Agent/issues/821)) ([b34bd89](https://github.com/microsoft/RD-Agent/commit/b34bd895d6d9c326aab85856a15be0cb72b2c4c8))
|
||||
* fix some minor bugs ([#758](https://github.com/microsoft/RD-Agent/issues/758)) ([963f96e](https://github.com/microsoft/RD-Agent/commit/963f96e5596bee04074135c2a0e31a8adc39ad8c))
|
||||
* fix some minor bugs in qlib scenario ([#817](https://github.com/microsoft/RD-Agent/issues/817)) ([79962a7](https://github.com/microsoft/RD-Agent/commit/79962a7ca40c77a3997a68da9ad1b5ab16728483))
|
||||
* fix the bug in the regular expression matching for stdout ([#890](https://github.com/microsoft/RD-Agent/issues/890)) ([ee57e37](https://github.com/microsoft/RD-Agent/commit/ee57e37a22af874b262c033d1606dbe7799706db))
|
||||
* fix the bug of Exceed-LLM-Context in online merge of multi-tarce ([#892](https://github.com/microsoft/RD-Agent/issues/892)) ([f760a3e](https://github.com/microsoft/RD-Agent/commit/f760a3eff7bd927a31e4958ed2f706312e83e3e3))
|
||||
* fix the problems weights bug ([#898](https://github.com/microsoft/RD-Agent/issues/898)) ([013d79f](https://github.com/microsoft/RD-Agent/commit/013d79f12060e908aeb57c3eb1bb56eea86df086))
|
||||
* fixed CI execution failures caused by document builds ([#857](https://github.com/microsoft/RD-Agent/issues/857)) ([5c116b2](https://github.com/microsoft/RD-Agent/commit/5c116b24ce727f6ed9ef39d5aa5b60442038c344))
|
||||
* get_metric_direction for aerial-cactus-identification ([#970](https://github.com/microsoft/RD-Agent/issues/970)) ([70dc62d](https://github.com/microsoft/RD-Agent/commit/70dc62de5fbd4272ecda1b6fcbcf898b3624a991))
|
||||
* import path of T ([#787](https://github.com/microsoft/RD-Agent/issues/787)) ([ac008a6](https://github.com/microsoft/RD-Agent/commit/ac008a61d03b4737ab3d994024e922839d8f3fe1))
|
||||
* improve eval alignment check (e.g. small-scale finetuning) ([#802](https://github.com/microsoft/RD-Agent/issues/802)) ([d391578](https://github.com/microsoft/RD-Agent/commit/d3915788082de640a4ce1eea6d2e607319b89c3e))
|
||||
* improve file tree and _walk symlink handling ([#877](https://github.com/microsoft/RD-Agent/issues/877)) ([516cb69](https://github.com/microsoft/RD-Agent/commit/516cb69357483ddd99f84b221a056d8491c34f9b))
|
||||
* log info ([#965](https://github.com/microsoft/RD-Agent/issues/965)) ([f1dbc21](https://github.com/microsoft/RD-Agent/commit/f1dbc2100498e22c8e5edbb2e4563c99c3d54775))
|
||||
* main bug ([#938](https://github.com/microsoft/RD-Agent/issues/938)) ([c6d34d6](https://github.com/microsoft/RD-Agent/commit/c6d34d67b8aedf5496bf6a875915ce657fc58448))
|
||||
* non-exist variable test_eval.py ([#847](https://github.com/microsoft/RD-Agent/issues/847)) ([4948c38](https://github.com/microsoft/RD-Agent/commit/4948c38560f4cf021d9354b201b22dfa5ccb9441))
|
||||
* refine feedback prompt ([#901](https://github.com/microsoft/RD-Agent/issues/901)) ([12bb2c4](https://github.com/microsoft/RD-Agent/commit/12bb2c4a1494b9aa29962905abb5e433a60eb716))
|
||||
* refine the time/memory constraints prompt in hypothesis proposal ([#856](https://github.com/microsoft/RD-Agent/issues/856)) ([51ce8ef](https://github.com/microsoft/RD-Agent/commit/51ce8ef84b4fe6590ce20599a56eee596f2f04e6))
|
||||
* Set PYTHONPATH in env.run_ret_code call in FBWorkspace class ([#755](https://github.com/microsoft/RD-Agent/issues/755)) ([68b5018](https://github.com/microsoft/RD-Agent/commit/68b501889caca754f27b57d9ab6f72184e93b15c))
|
||||
* task_gen for better understanding ([#752](https://github.com/microsoft/RD-Agent/issues/752)) ([6bfc1e5](https://github.com/microsoft/RD-Agent/commit/6bfc1e570449ee69ac110a4ced9a7cecbc0e6a73))
|
||||
* trace list but ([#852](https://github.com/microsoft/RD-Agent/issues/852)) ([32cdc57](https://github.com/microsoft/RD-Agent/commit/32cdc575bde103d71a358d4d99bd413076328ebd))
|
||||
* typo in workflow ([#861](https://github.com/microsoft/RD-Agent/issues/861)) ([0e54c9f](https://github.com/microsoft/RD-Agent/commit/0e54c9fe41d25a4cc45ab9e61bb2c2c01b854751))
|
||||
* update DS env setup with competition volume and timeout ([#878](https://github.com/microsoft/RD-Agent/issues/878)) ([816ada0](https://github.com/microsoft/RD-Agent/commit/816ada096afabe90578672b0e61b656802a30b62))
|
||||
* update feedback.py ([#772](https://github.com/microsoft/RD-Agent/issues/772)) ([133778c](https://github.com/microsoft/RD-Agent/commit/133778c67ee3349f1c2fe029bcf6a9ee14568efe))
|
||||
* update metric direction to return bool ([#791](https://github.com/microsoft/RD-Agent/issues/791)) ([0bf365e](https://github.com/microsoft/RD-Agent/commit/0bf365e7830aa86d2350b9d1c47410af46b3a7e8))
|
||||
* update runner max loop to 1 in DS scenario ([#820](https://github.com/microsoft/RD-Agent/issues/820)) ([3da378e](https://github.com/microsoft/RD-Agent/commit/3da378e986e8b776a17dbc694d29ef211192ed3e))
|
||||
* use fallback messages for missing submission and scores files ([#882](https://github.com/microsoft/RD-Agent/issues/882)) ([898fdea](https://github.com/microsoft/RD-Agent/commit/898fdeae80801d537ebc5c4a3b7df9de74c3403a))
|
||||
* use simple stdout and stderr ([#966](https://github.com/microsoft/RD-Agent/issues/966)) ([0b1c445](https://github.com/microsoft/RD-Agent/commit/0b1c445f1f0c212887ffff9f8fac44236df3607c))
|
||||
* use trace count as index ([#909](https://github.com/microsoft/RD-Agent/issues/909)) ([b87de56](https://github.com/microsoft/RD-Agent/commit/b87de56e54b206b3aada53850804474eff80b96d))
|
||||
* wrong variable test_eval.py ([#846](https://github.com/microsoft/RD-Agent/issues/846)) ([808ea6c](https://github.com/microsoft/RD-Agent/commit/808ea6cba541e60c35dd283cee9098ce46f2a59e))
|
||||
|
||||
## [0.4.0](https://github.com/microsoft/RD-Agent/compare/v0.3.0...v0.4.0) (2025-04-04)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* (Kaggle) add base template for competition: tabular-playground-series-may-2022 ([#481](https://github.com/microsoft/RD-Agent/issues/481)) ([f3405ca](https://github.com/microsoft/RD-Agent/commit/f3405ca732eb0ddca8e18ea72f69cbd86055c4ab))
|
||||
* a unified CoSTEER to fit more scenarios ([#491](https://github.com/microsoft/RD-Agent/issues/491)) ([cddbd02](https://github.com/microsoft/RD-Agent/commit/cddbd02e3ad3ccf6ad01443777319dc5c7eb08a7))
|
||||
* add a new competition ([#474](https://github.com/microsoft/RD-Agent/issues/474)) ([2fc0d77](https://github.com/microsoft/RD-Agent/commit/2fc0d77c485a31f647e21f4578e2e326f7032964))
|
||||
* add a tool to enable saving workspace files into a specific folder ([#728](https://github.com/microsoft/RD-Agent/issues/728)) ([bca864b](https://github.com/microsoft/RD-Agent/commit/bca864b7edeafe3f88405efb695ca8acad6252f8))
|
||||
* add baseline score stat ([#590](https://github.com/microsoft/RD-Agent/issues/590)) ([2948026](https://github.com/microsoft/RD-Agent/commit/2948026c390d067b643f8c8247c1447f1dc023e4))
|
||||
* add configurable volume mode for Docker volumes in env.py ([#537](https://github.com/microsoft/RD-Agent/issues/537)) ([642a022](https://github.com/microsoft/RD-Agent/commit/642a02239431411b91959f23e69b454997ca75d5))
|
||||
* add constraint labels for semantic search ([#680](https://github.com/microsoft/RD-Agent/issues/680)) ([0584cfc](https://github.com/microsoft/RD-Agent/commit/0584cfcd13ca1a62c85390ea2ee7574370748d31))
|
||||
* add cross validation to workflow ([#700](https://github.com/microsoft/RD-Agent/issues/700)) ([82e9b00](https://github.com/microsoft/RD-Agent/commit/82e9b00be62b01673353a7aaa3ab0e2e3ecaf3ca))
|
||||
* add describe_data_folder_v2 ([#738](https://github.com/microsoft/RD-Agent/issues/738)) ([bc8e846](https://github.com/microsoft/RD-Agent/commit/bc8e8460e0246321792ff3347b1b8905416ad075))
|
||||
* add do_truncate control for the load function ([#656](https://github.com/microsoft/RD-Agent/issues/656)) ([2b960a5](https://github.com/microsoft/RD-Agent/commit/2b960a58dfdeba69522a0f72ecf0975bb6ae87ee))
|
||||
* add do_truncate control for the load function ([#656](https://github.com/microsoft/RD-Agent/issues/656)) ([2b960a5](https://github.com/microsoft/RD-Agent/commit/2b960a58dfdeba69522a0f72ecf0975bb6ae87ee))
|
||||
* add eda to data science scenario ([#639](https://github.com/microsoft/RD-Agent/issues/639)) ([35aa479](https://github.com/microsoft/RD-Agent/commit/35aa479f00edf118d43ec228e0a84c155332957a))
|
||||
* add hypothesis guidelines and rule-based ranking ([#746](https://github.com/microsoft/RD-Agent/issues/746)) ([c077b82](https://github.com/microsoft/RD-Agent/commit/c077b8239cc72904c4bc450845ed2a11aa5445f0))
|
||||
* Add line length limit to shrink_text function and settings ([#715](https://github.com/microsoft/RD-Agent/issues/715)) ([75ed5e1](https://github.com/microsoft/RD-Agent/commit/75ed5e1c2ce1bf20bb55190c10a4134e04694d2b))
|
||||
* add loop_n parameter to the main loop ([#611](https://github.com/microsoft/RD-Agent/issues/611)) ([778c166](https://github.com/microsoft/RD-Agent/commit/778c166962250e3b9e7ad85de37f62297d370b45))
|
||||
* add max time config to costeer in data science ([#645](https://github.com/microsoft/RD-Agent/issues/645)) ([534686c](https://github.com/microsoft/RD-Agent/commit/534686c2ba7d9fa979c0762ad3177c36f6d7f4cb))
|
||||
* add mlebench submission validitor ([#545](https://github.com/microsoft/RD-Agent/issues/545)) ([712d94a](https://github.com/microsoft/RD-Agent/commit/712d94a7d6f22187fc3d18bd434e71ec6997aa9f))
|
||||
* add model removal and adjust some framework logic ([#681](https://github.com/microsoft/RD-Agent/issues/681)) ([1edf881](https://github.com/microsoft/RD-Agent/commit/1edf881c63512d351c0dd074d7a1c0965ff3119b))
|
||||
* add output_path to load function of LoopBase ([#628](https://github.com/microsoft/RD-Agent/issues/628)) ([dd33726](https://github.com/microsoft/RD-Agent/commit/dd33726ac5de75dc2030d193d457d59490b3361e))
|
||||
* add pipeline coder ([#742](https://github.com/microsoft/RD-Agent/issues/742)) ([759f295](https://github.com/microsoft/RD-Agent/commit/759f295dbf1224e177006e72d694e42dd6f372b6))
|
||||
* add rank into report (mle_summary) ([#665](https://github.com/microsoft/RD-Agent/issues/665)) ([13f7922](https://github.com/microsoft/RD-Agent/commit/13f7922aaae9e4143aac4ad08ec1c556c2faf04e))
|
||||
* add restart and fix unzip ([#538](https://github.com/microsoft/RD-Agent/issues/538)) ([ed2c7d1](https://github.com/microsoft/RD-Agent/commit/ed2c7d175f1f44ca06ad7a63b08da12f6c4df9ab))
|
||||
* add retry mechanism with wait_retry decorator and refactor diff generation ([#572](https://github.com/microsoft/RD-Agent/issues/572)) ([de1cd72](https://github.com/microsoft/RD-Agent/commit/de1cd72f068ebd1e1bd5bc2ad2b12ae484d54831))
|
||||
* add the shape of the CSV to the dataset description ([#561](https://github.com/microsoft/RD-Agent/issues/561)) ([a10c881](https://github.com/microsoft/RD-Agent/commit/a10c881bd86796e6167257ad26dd165f7e46d813))
|
||||
* add timeout settings and cleanup step in data science runner ([#539](https://github.com/microsoft/RD-Agent/issues/539)) ([295abd5](https://github.com/microsoft/RD-Agent/commit/295abd56f7b58055bd27b247dfed47eb85e9b0cd))
|
||||
* add type checker to api backend & align litellm and old backend ([#647](https://github.com/microsoft/RD-Agent/issues/647)) ([d38eae9](https://github.com/microsoft/RD-Agent/commit/d38eae986a0ba69d71288fa09fcc21e227551a02))
|
||||
* align mlebench data and evaluation & several fix on kaggle workflow ([#477](https://github.com/microsoft/RD-Agent/issues/477)) ([f6c522b](https://github.com/microsoft/RD-Agent/commit/f6c522b651db3c1f6af6815347589917f46e433a))
|
||||
* **backend:** integrate LiteLLM API Backend ([#564](https://github.com/microsoft/RD-Agent/issues/564)) ([f477687](https://github.com/microsoft/RD-Agent/commit/f4776879c76a213d53875b307c94be1ea5cfd9ba))
|
||||
* base data science scenario UI ([#525](https://github.com/microsoft/RD-Agent/issues/525)) ([39917b3](https://github.com/microsoft/RD-Agent/commit/39917b354b22a8488a17396fe2245cb41e3def03))
|
||||
* condaenv & full docker env ([#668](https://github.com/microsoft/RD-Agent/issues/668)) ([084dd6d](https://github.com/microsoft/RD-Agent/commit/084dd6d748a89492ea0888acb316b9bb9efeb62f))
|
||||
* diff mode fix ([#569](https://github.com/microsoft/RD-Agent/issues/569)) ([0c509f5](https://github.com/microsoft/RD-Agent/commit/0c509f599ce19303b44d8192ec3eb634c24992d6))
|
||||
* display LLM prompt ([#676](https://github.com/microsoft/RD-Agent/issues/676)) ([8c93bba](https://github.com/microsoft/RD-Agent/commit/8c93bba82e185edcf4204cc574df5f41bcdfa9d2))
|
||||
* Dynamically find and use sample submission file in eval tests ([#542](https://github.com/microsoft/RD-Agent/issues/542)) ([5f12b44](https://github.com/microsoft/RD-Agent/commit/5f12b44c89dd26b250e914192f9beb2da38fb3ab))
|
||||
* end-to-end optimization ([#473](https://github.com/microsoft/RD-Agent/issues/473)) ([d41343a](https://github.com/microsoft/RD-Agent/commit/d41343a63d87bf3479f5ec30745ea788580495bf))
|
||||
* Enhance eval script with file cleanup and detailed submission checks ([#529](https://github.com/microsoft/RD-Agent/issues/529)) ([cf2ff92](https://github.com/microsoft/RD-Agent/commit/cf2ff9213d3a8b0fad64df7cae0c35f996d72e27))
|
||||
* exclude invalid session log folder ([#554](https://github.com/microsoft/RD-Agent/issues/554)) ([fa86e4d](https://github.com/microsoft/RD-Agent/commit/fa86e4d1805000e0e5779c662ccbb5273fda623c))
|
||||
* improve the framework's ability to adaptively adjust the model ([#629](https://github.com/microsoft/RD-Agent/issues/629)) ([93806f3](https://github.com/microsoft/RD-Agent/commit/93806f33a1e0f29a125e29303d4b984a9817c3c0))
|
||||
* independent use_azure_token_provider on chat and embedding ([#452](https://github.com/microsoft/RD-Agent/issues/452)) ([d223004](https://github.com/microsoft/RD-Agent/commit/d223004917692e231b251330cbc8676081d5a10d))
|
||||
* integrate azure deepseek r1 ([#591](https://github.com/microsoft/RD-Agent/issues/591)) ([e79ce5c](https://github.com/microsoft/RD-Agent/commit/e79ce5c38539138abe04eb9809fbde437e97bbb7))
|
||||
* kaggle refactor ([#489](https://github.com/microsoft/RD-Agent/issues/489)) ([1b057d0](https://github.com/microsoft/RD-Agent/commit/1b057d0d63a861fba4b3cb59c6c5fc1a0e3da383))
|
||||
* **kaggle:** several update in kaggle scenarios ([#476](https://github.com/microsoft/RD-Agent/issues/476)) ([245d211](https://github.com/microsoft/RD-Agent/commit/245d211dcbfb18ebcc554247a0e3a8dbecf6f3bd))
|
||||
* loader prompt & simplify YAML loading and update data loader specifications ([#736](https://github.com/microsoft/RD-Agent/issues/736)) ([86f8bbf](https://github.com/microsoft/RD-Agent/commit/86f8bbf15895e7c198f9bc395d055ca5f02a5bb6))
|
||||
* make spec optional ([#719](https://github.com/microsoft/RD-Agent/issues/719)) ([a16b70f](https://github.com/microsoft/RD-Agent/commit/a16b70ff34c66d7e1c4c7ff5236eca8e7d8abea9))
|
||||
* Make system prompt role customizable in LLM settings ([#632](https://github.com/microsoft/RD-Agent/issues/632)) ([e4acd92](https://github.com/microsoft/RD-Agent/commit/e4acd92cc5eec6db5c29cb2d4788020fb89099b7))
|
||||
* multi log folder, replace "epxx" in workspace path ([#555](https://github.com/microsoft/RD-Agent/issues/555)) ([8a69c9c](https://github.com/microsoft/RD-Agent/commit/8a69c9c9630860c9b644356e1f71654aea222328))
|
||||
* new exp gen v2 implementation ([#725](https://github.com/microsoft/RD-Agent/issues/725)) ([5dcc2d5](https://github.com/microsoft/RD-Agent/commit/5dcc2d5fa63bbe9ae8c4817d9b40b77600440edb))
|
||||
* new-york-city-taxi-fare-prediction_template ([#488](https://github.com/microsoft/RD-Agent/issues/488)) ([a9caab7](https://github.com/microsoft/RD-Agent/commit/a9caab7bc5dc86f395a008e523355922137aef17))
|
||||
* out spec change for o1-preview ([#666](https://github.com/microsoft/RD-Agent/issues/666)) ([22894bd](https://github.com/microsoft/RD-Agent/commit/22894bdbee26b9cad73646d2975857787e515f75))
|
||||
* refactor for general data science ([#498](https://github.com/microsoft/RD-Agent/issues/498)) ([7002dc4](https://github.com/microsoft/RD-Agent/commit/7002dc4981a4f72096b438d2fe4fd9ff268c54f3))
|
||||
* refine logic for qlib_factor_from_report ([#463](https://github.com/microsoft/RD-Agent/issues/463)) ([21348d8](https://github.com/microsoft/RD-Agent/commit/21348d89e0e0eec1b4fab4e7a497f1eb34b8fe72))
|
||||
* run benchmark on gpt-4o & llama 3.1 ([#497](https://github.com/microsoft/RD-Agent/issues/497)) ([64af0b5](https://github.com/microsoft/RD-Agent/commit/64af0b5529b687cce8b5b7a1893946e15edca626))
|
||||
* summary and UI update ([#581](https://github.com/microsoft/RD-Agent/issues/581)) ([efa51f9](https://github.com/microsoft/RD-Agent/commit/efa51f9c259a06fe219f3137f0a1005e50d2bfdd))
|
||||
* template changes for some kaggle competitions ([#484](https://github.com/microsoft/RD-Agent/issues/484)) ([2e38000](https://github.com/microsoft/RD-Agent/commit/2e38000091030811fc081d72016c7bbadf7efd50))
|
||||
* track and log accumulated completion cost in LiteLLMAPIBackend ([#727](https://github.com/microsoft/RD-Agent/issues/727)) ([b294a95](https://github.com/microsoft/RD-Agent/commit/b294a95e0b7b2ef96af355cebac92d9c87f3acab))
|
||||
* update prompts and descriptions for data science components ([#731](https://github.com/microsoft/RD-Agent/issues/731)) ([c20e226](https://github.com/microsoft/RD-Agent/commit/c20e226c3e7771c9fcd1c879a8937e4694dc03eb))
|
||||
* variable printing tool of data_science coder testing ([#658](https://github.com/microsoft/RD-Agent/issues/658)) ([116c061](https://github.com/microsoft/RD-Agent/commit/116c06190b01f0b621c021726a1be23458ab1154))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* a default conf in scen qlib ([#503](https://github.com/microsoft/RD-Agent/issues/503)) ([d64a228](https://github.com/microsoft/RD-Agent/commit/d64a228525cbedd7687c1e06132eacd0d0647697))
|
||||
* a small bug in exp_gen ([#606](https://github.com/microsoft/RD-Agent/issues/606)) ([f734dde](https://github.com/microsoft/RD-Agent/commit/f734dde0b0101e13f38151468c8ddf9e23af26ac))
|
||||
* add check when retrying gen model codes ([#699](https://github.com/microsoft/RD-Agent/issues/699)) ([3b82f15](https://github.com/microsoft/RD-Agent/commit/3b82f159474087902d3c6007d370e3282b549015))
|
||||
* add DSExperiment type check and directory validation in log proc… ([#535](https://github.com/microsoft/RD-Agent/issues/535)) ([f59b12c](https://github.com/microsoft/RD-Agent/commit/f59b12c9cc9afde82b74bc133797ff1396678627))
|
||||
* add ensemble test, change to "use cross-validation if possible" in workflow spec ([#634](https://github.com/microsoft/RD-Agent/issues/634)) ([acc97a8](https://github.com/microsoft/RD-Agent/commit/acc97a8217253497afedcfa829902b4432e1031e))
|
||||
* add force parameter for cache_with_pickle & using cache when get kaggle leaderboard ([#687](https://github.com/microsoft/RD-Agent/issues/687)) ([c8841e5](https://github.com/microsoft/RD-Agent/commit/c8841e590a925200859acba9fda4a17d4c3aa1c7))
|
||||
* add metric name check for valid scores ([#724](https://github.com/microsoft/RD-Agent/issues/724)) ([acc2ffb](https://github.com/microsoft/RD-Agent/commit/acc2ffbde4df3b53654559d14cd035ee6be6b35e))
|
||||
* add retry mechanism for GPU device check in DockerEnv ([#573](https://github.com/microsoft/RD-Agent/issues/573)) ([a780cfb](https://github.com/microsoft/RD-Agent/commit/a780cfb621dc487cc17072bfd4aedd7d581249ab))
|
||||
* add scores.csv checking in ensemble_test ([#567](https://github.com/microsoft/RD-Agent/issues/567)) ([01808b4](https://github.com/microsoft/RD-Agent/commit/01808b47c314d1daffacc0a65e0ab934a1c41d65))
|
||||
* add stdout context length setting and improve text shrinking logic ([#559](https://github.com/microsoft/RD-Agent/issues/559)) ([4ac26a6](https://github.com/microsoft/RD-Agent/commit/4ac26a65c1f18f7513480dd562566c8a96298aa7))
|
||||
* align components' name ([#701](https://github.com/microsoft/RD-Agent/issues/701)) ([295a114](https://github.com/microsoft/RD-Agent/commit/295a1148c53d00b716b2d540573a7f43e7e2d762))
|
||||
* auto continue small bug ([#598](https://github.com/microsoft/RD-Agent/issues/598)) ([75eaecf](https://github.com/microsoft/RD-Agent/commit/75eaecf36b9f70dfc2d7fedd35836acdb05f89d6))
|
||||
* avoid try-except in ensemble eval prompts ([#637](https://github.com/microsoft/RD-Agent/issues/637)) ([5c58d6e](https://github.com/microsoft/RD-Agent/commit/5c58d6e524ef848024578033ab6d47bc9b220822))
|
||||
* avoid warning for missing llama installation when not in use ([#509](https://github.com/microsoft/RD-Agent/issues/509)) ([5ec3422](https://github.com/microsoft/RD-Agent/commit/5ec342224c2c8c4cf591f1eae673e25b14218726))
|
||||
* change devault to default ([#688](https://github.com/microsoft/RD-Agent/issues/688)) ([7f401cd](https://github.com/microsoft/RD-Agent/commit/7f401cd1c3b333285acf6d6e57654f4b9f0cb6c5))
|
||||
* change ensemble test ([#622](https://github.com/microsoft/RD-Agent/issues/622)) ([5de3595](https://github.com/microsoft/RD-Agent/commit/5de35953ed0d3e2e1f4dff0e0522f2d6475079ec))
|
||||
* change summary info of log folder ([#552](https://github.com/microsoft/RD-Agent/issues/552)) ([0eb258d](https://github.com/microsoft/RD-Agent/commit/0eb258d734e9a1280a238b9a6f63eb33047ee0a7))
|
||||
* clarify an ambiguous explanation ([#705](https://github.com/microsoft/RD-Agent/issues/705)) ([5dbfc68](https://github.com/microsoft/RD-Agent/commit/5dbfc6859cbf6cc31932dae30cf05506108fc871))
|
||||
* clarify cross_validation ([#644](https://github.com/microsoft/RD-Agent/issues/644)) ([906993e](https://github.com/microsoft/RD-Agent/commit/906993ef6482f88131d1af46f5bc66a77034b549))
|
||||
* coder prompt & model test text ([#583](https://github.com/microsoft/RD-Agent/issues/583)) ([0a41227](https://github.com/microsoft/RD-Agent/commit/0a41227f267050feaeeb47ddd4d749643eb9f198))
|
||||
* correct the configuration inheritance relationship ([#671](https://github.com/microsoft/RD-Agent/issues/671)) ([30b1ff8](https://github.com/microsoft/RD-Agent/commit/30b1ff8e1ce59b741e0b81481962063014641c0b))
|
||||
* default emb model ([#702](https://github.com/microsoft/RD-Agent/issues/702)) ([4329a72](https://github.com/microsoft/RD-Agent/commit/4329a722832a201b3fa6f9d8f9d8d46f78110410))
|
||||
* direct_exp_gen to json_target_type in DSExpGen class ([#661](https://github.com/microsoft/RD-Agent/issues/661)) ([428b74a](https://github.com/microsoft/RD-Agent/commit/428b74a988157ea864ebb40e828bd9f67589c863))
|
||||
* docker error will trigger retry and data science runner loop set to 3 ([#602](https://github.com/microsoft/RD-Agent/issues/602)) ([ad785e0](https://github.com/microsoft/RD-Agent/commit/ad785e03d5db05d9191d5e772e184532835a787b))
|
||||
* ensure expected type ([#593](https://github.com/microsoft/RD-Agent/issues/593)) ([098a9a6](https://github.com/microsoft/RD-Agent/commit/098a9a6618f70fa8dd276b9014b9e7ba9621553b))
|
||||
* filter empty log traces in ds UI ([#533](https://github.com/microsoft/RD-Agent/issues/533)) ([1a2057c](https://github.com/microsoft/RD-Agent/commit/1a2057c9fc11edc4637f0baaa6dd226eb049c36e))
|
||||
* fix a bug in cross validation ([#618](https://github.com/microsoft/RD-Agent/issues/618)) ([05a4f10](https://github.com/microsoft/RD-Agent/commit/05a4f101e0b64b860ad03294619b2350004657e8))
|
||||
* fix a bug in ensemble test script ([#713](https://github.com/microsoft/RD-Agent/issues/713)) ([ad32100](https://github.com/microsoft/RD-Agent/commit/ad321000acbd9291d22fe03a9c60e57c70511c73))
|
||||
* fix a bug in initial tasks ([#635](https://github.com/microsoft/RD-Agent/issues/635)) ([edb552e](https://github.com/microsoft/RD-Agent/commit/edb552ed283119444f357fbd0b6170b2ad97712a))
|
||||
* fix a bug in kaggle conf ([#459](https://github.com/microsoft/RD-Agent/issues/459)) ([b4ed32b](https://github.com/microsoft/RD-Agent/commit/b4ed32b17ef07d8557450063765585a48d5fcd32))
|
||||
* fix a bug in progress_bar filter ([#712](https://github.com/microsoft/RD-Agent/issues/712)) ([ba5a84d](https://github.com/microsoft/RD-Agent/commit/ba5a84dee59c39cc2a8c0d428a82da1f899ce537))
|
||||
* fix a bug in proposal (add last loop's exception to last task desc) ([#596](https://github.com/microsoft/RD-Agent/issues/596)) ([419186f](https://github.com/microsoft/RD-Agent/commit/419186ffb985fe5a0aa0f7fe59c7a223e355492e))
|
||||
* fix a bug in regular expression exception processing ([#734](https://github.com/microsoft/RD-Agent/issues/734)) ([67d3702](https://github.com/microsoft/RD-Agent/commit/67d37027bbcd7294a5890a350fe16fe78e0dfa77))
|
||||
* fix a bug in threshold score display ([#592](https://github.com/microsoft/RD-Agent/issues/592)) ([0b0a2dc](https://github.com/microsoft/RD-Agent/commit/0b0a2dc512a5560a66464ad49de25d362d0dc17e))
|
||||
* fix a bug related to model_name in ensemble ([#692](https://github.com/microsoft/RD-Agent/issues/692)) ([c6ce473](https://github.com/microsoft/RD-Agent/commit/c6ce4733f32578298abe0b60f9d82611b793cc09))
|
||||
* fix a minor bug ([#694](https://github.com/microsoft/RD-Agent/issues/694)) ([1405d8d](https://github.com/microsoft/RD-Agent/commit/1405d8dafd99ecde6f3ba9dd76133d8830d03b47))
|
||||
* fix an error in model_coder prompt ([#690](https://github.com/microsoft/RD-Agent/issues/690)) ([4528826](https://github.com/microsoft/RD-Agent/commit/452882674e915dbd9e3399c26c70ce5bb86d012c))
|
||||
* fix combined_factors_df.pkl not loading in docker ([#697](https://github.com/microsoft/RD-Agent/issues/697)) ([3984b99](https://github.com/microsoft/RD-Agent/commit/3984b995aa74318b40de7712e100d4de5cc95b11))
|
||||
* fix docs build error ([#711](https://github.com/microsoft/RD-Agent/issues/711)) ([c9e1d32](https://github.com/microsoft/RD-Agent/commit/c9e1d32d6b63560350cc7cb799c3a908e2c04e42))
|
||||
* fix ExtendedSettingsConfigDict does not work ([#660](https://github.com/microsoft/RD-Agent/issues/660)) ([3a877f3](https://github.com/microsoft/RD-Agent/commit/3a877f383b908da8d027560714030b201946bb76))
|
||||
* fix kaggle templates path error ([#747](https://github.com/microsoft/RD-Agent/issues/747)) ([3b3f504](https://github.com/microsoft/RD-Agent/commit/3b3f5041514baf741fe2d4613fa651fb5d9c002d))
|
||||
* fix KeyError direct_exp_gen ([#735](https://github.com/microsoft/RD-Agent/issues/735)) ([7200682](https://github.com/microsoft/RD-Agent/commit/7200682ac4e60d3910c29a4f7c4a37b3d24e4224))
|
||||
* fix some bugs (ensemble output, HPO, model tuning) ([#648](https://github.com/microsoft/RD-Agent/issues/648)) ([818ee29](https://github.com/microsoft/RD-Agent/commit/818ee29f8e5d4765b9801463b85b42ee9516ec33))
|
||||
* fix some bugs in the ensemble component ([#595](https://github.com/microsoft/RD-Agent/issues/595)) ([c0990ab](https://github.com/microsoft/RD-Agent/commit/c0990abb06c73ae062d9a50f50cdfd6d04aded22))
|
||||
* fix some bugs in workflow unit test ([#624](https://github.com/microsoft/RD-Agent/issues/624)) ([f845dcc](https://github.com/microsoft/RD-Agent/commit/f845dcc0ee1b059b8b32485ad46bb90c7ae0fa78))
|
||||
* fix some description errors in direct_exp_gen ([#698](https://github.com/microsoft/RD-Agent/issues/698)) ([dfaacb6](https://github.com/microsoft/RD-Agent/commit/dfaacb6d06e5d5f55e950d7177570d1efebf958f))
|
||||
* fix some minor bugs and add AutoML & cross-validation ([#604](https://github.com/microsoft/RD-Agent/issues/604)) ([18c5ef2](https://github.com/microsoft/RD-Agent/commit/18c5ef268d40efe7bb9ee18aa0d250732bdda6fa))
|
||||
* fix submission file search and add TODO in env.py ([#544](https://github.com/microsoft/RD-Agent/issues/544)) ([54d930e](https://github.com/microsoft/RD-Agent/commit/54d930e91e629f0fc2f8bdd0d0d62fcad1e99a9c))
|
||||
* fix task return dict with wrong format ([#558](https://github.com/microsoft/RD-Agent/issues/558)) ([2008244](https://github.com/microsoft/RD-Agent/commit/20082440a249dd0e5a7026c2d98c9de0288dd400))
|
||||
* fix the errors in the coder and evaluator of the five components ([#576](https://github.com/microsoft/RD-Agent/issues/576)) ([c487f83](https://github.com/microsoft/RD-Agent/commit/c487f835b651cdc40b95bbbe4efcb9a617be9e40))
|
||||
* handle division by zero in percentage calculations ([#550](https://github.com/microsoft/RD-Agent/issues/550)) ([de16c91](https://github.com/microsoft/RD-Agent/commit/de16c915e1716ef8cee43ce41069ea1a09cf1f24))
|
||||
* handle invalid regex patterns in filter_progress_bar function ([#579](https://github.com/microsoft/RD-Agent/issues/579)) ([b0daee0](https://github.com/microsoft/RD-Agent/commit/b0daee0d90e193ca1d028e01c31ebf368af89601))
|
||||
* Handle ValueError when resolving relative path for uri ([#585](https://github.com/microsoft/RD-Agent/issues/585)) ([4c7765a](https://github.com/microsoft/RD-Agent/commit/4c7765a12bda5dcfd9af72b292853d9bc28c5baf))
|
||||
* include data information in cache key generation ([#566](https://github.com/microsoft/RD-Agent/issues/566)) ([26dda46](https://github.com/microsoft/RD-Agent/commit/26dda4682b7b643c164589057cb568a4d9e55e17))
|
||||
* keep some txt files ([#557](https://github.com/microsoft/RD-Agent/issues/557)) ([54aba85](https://github.com/microsoft/RD-Agent/commit/54aba851c9fa194e318d37700307df59e06c6c84))
|
||||
* mle_score save problem ([#674](https://github.com/microsoft/RD-Agent/issues/674)) ([ca2e478](https://github.com/microsoft/RD-Agent/commit/ca2e478cf25c2c8511d5f027e32f8a98fc8e3a07))
|
||||
* move docker timeout message to __run() ([#620](https://github.com/microsoft/RD-Agent/issues/620)) ([585f4f9](https://github.com/microsoft/RD-Agent/commit/585f4f96e09f70d00eb397c10bf49c09973111df))
|
||||
* move mlebench check into runner ([#556](https://github.com/microsoft/RD-Agent/issues/556)) ([b0f7965](https://github.com/microsoft/RD-Agent/commit/b0f7965f650638273710302efee2e5da037368a2))
|
||||
* move next_component_required logic to DSTrace class and accurate implement ([#612](https://github.com/microsoft/RD-Agent/issues/612)) ([c20d311](https://github.com/microsoft/RD-Agent/commit/c20d311792f33b2ccccb466c6ec3155ff8be3213))
|
||||
* patching weird azure deployment ([#494](https://github.com/microsoft/RD-Agent/issues/494)) ([89c50ae](https://github.com/microsoft/RD-Agent/commit/89c50aee2ec8bfd1cb23767ddf7dcdd023daac8b))
|
||||
* qlib and other scenario bugs ([#636](https://github.com/microsoft/RD-Agent/issues/636)) ([98de31d](https://github.com/microsoft/RD-Agent/commit/98de31d4e577c8c450c9694f73a755c19af571f7))
|
||||
* refine prompt to generate the most simple task in init stage ([#546](https://github.com/microsoft/RD-Agent/issues/546)) ([9d6feed](https://github.com/microsoft/RD-Agent/commit/9d6feed28ce034db48482d8d9741ef8c72f4bddc))
|
||||
* replace API call with build_cls_from_json_with_retry function ([#548](https://github.com/microsoft/RD-Agent/issues/548)) ([eb72a47](https://github.com/microsoft/RD-Agent/commit/eb72a47fbf9c88dacea9691b8d7e92610492d190))
|
||||
* replace func "len()" in ensemble test code to support various data type ([#739](https://github.com/microsoft/RD-Agent/issues/739)) ([ab9c7b9](https://github.com/microsoft/RD-Agent/commit/ab9c7b955f78c5de7ec08a6c1a012a76badbdd0e))
|
||||
* return 1D embedding if create_embedding receive a string input ([#670](https://github.com/microsoft/RD-Agent/issues/670)) ([4a9c318](https://github.com/microsoft/RD-Agent/commit/4a9c3180ae4a4b043b1b4a89f51ee69cb6843142))
|
||||
* rich.print error when some control char in output ([#684](https://github.com/microsoft/RD-Agent/issues/684)) ([ec0cb2a](https://github.com/microsoft/RD-Agent/commit/ec0cb2a032824023dcd04a3acc93202471d1f90a))
|
||||
* Runnable on first complete & Rename method to next_incomplete_component for clarity ([#615](https://github.com/microsoft/RD-Agent/issues/615)) ([93d9f63](https://github.com/microsoft/RD-Agent/commit/93d9f63369a78f78e1a67ab548923bb994d1d3b4))
|
||||
* runner COSTEER evaluator ([#693](https://github.com/microsoft/RD-Agent/issues/693)) ([6a379ec](https://github.com/microsoft/RD-Agent/commit/6a379ec9b84d4e4944f1e412347aae4f5a93d476))
|
||||
* save only one mle_score pkl for a running exp ([#675](https://github.com/microsoft/RD-Agent/issues/675)) ([f87ab67](https://github.com/microsoft/RD-Agent/commit/f87ab676b73cce82bd9f997ac779e31c571b53c4))
|
||||
* Set default value for 'entry' parameter in Env.run method ([#643](https://github.com/microsoft/RD-Agent/issues/643)) ([e50d242](https://github.com/microsoft/RD-Agent/commit/e50d2424b849e4181d6ca02e9cace90236665924))
|
||||
* sort file name for cache reproduction ([#588](https://github.com/microsoft/RD-Agent/issues/588)) ([7158410](https://github.com/microsoft/RD-Agent/commit/7158410fbfdd84052f9a69cf1e04e09ac07ca598))
|
||||
* sota comparison logic ([#608](https://github.com/microsoft/RD-Agent/issues/608)) ([3575372](https://github.com/microsoft/RD-Agent/commit/35753722c0800d62855faeab996d513e62cfe7de))
|
||||
* target json type & round ([#662](https://github.com/microsoft/RD-Agent/issues/662)) ([58cb58f](https://github.com/microsoft/RD-Agent/commit/58cb58f966a1db26f5ea9662a54ba12bc921ee24))
|
||||
* templates bug ([#456](https://github.com/microsoft/RD-Agent/issues/456)) ([434a868](https://github.com/microsoft/RD-Agent/commit/434a8687eeda77e27b4938fb19694c15858ee446))
|
||||
* trace summary df showing in dsapp ([#551](https://github.com/microsoft/RD-Agent/issues/551)) ([177096d](https://github.com/microsoft/RD-Agent/commit/177096d55fecb8c7dab9650ef8f5a31024cd4c1c))
|
||||
* unzip kaggle data ([#464](https://github.com/microsoft/RD-Agent/issues/464)) ([3a9fc8e](https://github.com/microsoft/RD-Agent/commit/3a9fc8e73337d3757267b6f4482499499a1b6792))
|
||||
|
||||
## [0.3.0](https://github.com/microsoft/RD-Agent/compare/v0.2.1...v0.3.0) (2024-10-21)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add a new template for kaggle ([#289](https://github.com/microsoft/RD-Agent/issues/289)) ([eee3ab5](https://github.com/microsoft/RD-Agent/commit/eee3ab5b25198224826cb7a8a17eab28bd5d1f7d))
|
||||
* add download submission.csv button for kaggle scenario ([#317](https://github.com/microsoft/RD-Agent/issues/317)) ([dcdcbe4](https://github.com/microsoft/RD-Agent/commit/dcdcbe46b4858bfb133ae3cca056e7f602d5cf63))
|
||||
* add kaggle command ([#271](https://github.com/microsoft/RD-Agent/issues/271)) ([0938394](https://github.com/microsoft/RD-Agent/commit/0938394b7084ffbf3294d8c23d2d34bf7322ca0b))
|
||||
* add kaggle tpl: feedback-prize ([#331](https://github.com/microsoft/RD-Agent/issues/331)) ([a288e39](https://github.com/microsoft/RD-Agent/commit/a288e399e6b0beec62729bd7d46b98a55de5ab79))
|
||||
* add more templates for kaggle ([#291](https://github.com/microsoft/RD-Agent/issues/291)) ([da752ec](https://github.com/microsoft/RD-Agent/commit/da752ec806e6f5f5679bc27ac1c072ed9a319251))
|
||||
* add normal rag into framework ([#360](https://github.com/microsoft/RD-Agent/issues/360)) ([91b0b1f](https://github.com/microsoft/RD-Agent/commit/91b0b1f66c3c1bf757cb64c4cfbdcaafe59eab74))
|
||||
* add qlib_factor_strategy ([#307](https://github.com/microsoft/RD-Agent/issues/307)) ([f8f59ff](https://github.com/microsoft/RD-Agent/commit/f8f59ff0a1be4428a68c8c27f220aabad0b6c9f0))
|
||||
* Add ranking in kaggle scenario ([#401](https://github.com/microsoft/RD-Agent/issues/401)) ([b16b4be](https://github.com/microsoft/RD-Agent/commit/b16b4beb402e0c27dfb39ee9d2a120f1b56d447c))
|
||||
* Add runtime measurement for each step and loop in RDLoop. ([#281](https://github.com/microsoft/RD-Agent/issues/281)) ([83058c8](https://github.com/microsoft/RD-Agent/commit/83058c864ceeec413dd29bf501030d5a7bd34679))
|
||||
* add s3e11 kaggle template ([#324](https://github.com/microsoft/RD-Agent/issues/324)) ([8c57524](https://github.com/microsoft/RD-Agent/commit/8c57524bead1c8f655a08763d608eb7a6dd5975e))
|
||||
* Added RepoAnalyzer to empower auto-summary of a workspace ([#264](https://github.com/microsoft/RD-Agent/issues/264)) ([0bd349a](https://github.com/microsoft/RD-Agent/commit/0bd349af50b9b881ba1774bdeb4d723529ef2aa9))
|
||||
* Added support for loading and storing RAG in Kaggle scenarios. ([#269](https://github.com/microsoft/RD-Agent/issues/269)) ([c4895de](https://github.com/microsoft/RD-Agent/commit/c4895de83f1ed000e563d42b3468a6bd9e5a4965))
|
||||
* announce Discord and WeChat ([#367](https://github.com/microsoft/RD-Agent/issues/367)) ([acac507](https://github.com/microsoft/RD-Agent/commit/acac5078a103b71afa6bd6c053b0766a6a7e609d))
|
||||
* auto submit result after one kaggle RDLoop ([#345](https://github.com/microsoft/RD-Agent/issues/345)) ([ab55d70](https://github.com/microsoft/RD-Agent/commit/ab55d7052b53a928b84dc5d5d0d2999d90ca9056))
|
||||
* better feedback & evaluation ([#346](https://github.com/microsoft/RD-Agent/issues/346)) ([cc9a8c1](https://github.com/microsoft/RD-Agent/commit/cc9a8c1eab3ca89f8c1e5de4a2bb4e7fcc0cc615))
|
||||
* Dynamic scenario based on task ([#392](https://github.com/microsoft/RD-Agent/issues/392)) ([665a037](https://github.com/microsoft/RD-Agent/commit/665a037e4fd7326c450e3fa0d0605eea26fd9ef3))
|
||||
* Factor Implement Search Enhancement ([#294](https://github.com/microsoft/RD-Agent/issues/294)) ([4ecf25f](https://github.com/microsoft/RD-Agent/commit/4ecf25f0acf2389a172b14d3dab20895daf2ab89))
|
||||
* Feature selection v3 to support all actions ([#280](https://github.com/microsoft/RD-Agent/issues/280)) ([0047641](https://github.com/microsoft/RD-Agent/commit/00476413fbf00e36e71ab3ccb48d4e766b6ccf4d))
|
||||
* fix some bugs and add original features' description ([#259](https://github.com/microsoft/RD-Agent/issues/259)) ([1a5f45a](https://github.com/microsoft/RD-Agent/commit/1a5f45a40d821c017bdba14af8c93710707c5ea5))
|
||||
* get kaggle notebooks & disscussion text for RAG ([#371](https://github.com/microsoft/RD-Agent/issues/371)) ([cead345](https://github.com/microsoft/RD-Agent/commit/cead3450a14bf4b142ac988c27fa098c7656a95c))
|
||||
* Iceberge competition ([#372](https://github.com/microsoft/RD-Agent/issues/372)) ([c10ea4f](https://github.com/microsoft/RD-Agent/commit/c10ea4f5d4cc56a75b47cf23c7084ee189ba1a25))
|
||||
* implement isolated model feature selection loop ([#370](https://github.com/microsoft/RD-Agent/issues/370)) ([cf1292d](https://github.com/microsoft/RD-Agent/commit/cf1292de1a0153ca14ea64971e73a1c93f7d89e3))
|
||||
* Initial version if Graph RAG in KAGGLE scenario ([#301](https://github.com/microsoft/RD-Agent/issues/301)) ([fd3c0fd](https://github.com/microsoft/RD-Agent/commit/fd3c0fd26eff7d3be72fa4f2a234e33b9f796627))
|
||||
* Integrate RAG into the Kaggle scenarios. ([#262](https://github.com/microsoft/RD-Agent/issues/262)) ([be0e48a](https://github.com/microsoft/RD-Agent/commit/be0e48a7dfbee2b5d2947d09115db5db2e5266f1))
|
||||
* Kaggle loop update (Feature & Model) ([#241](https://github.com/microsoft/RD-Agent/issues/241)) ([4cf22a6](https://github.com/microsoft/RD-Agent/commit/4cf22a65c964123b4267569ee02c0c7094c54ca4))
|
||||
* kaggle templates related ([#287](https://github.com/microsoft/RD-Agent/issues/287)) ([785fdc1](https://github.com/microsoft/RD-Agent/commit/785fdc144d16fa8454b7c9d2e53e78fe7f22a29a))
|
||||
* Model context for tuning and selection ([#284](https://github.com/microsoft/RD-Agent/issues/284)) ([f2831e7](https://github.com/microsoft/RD-Agent/commit/f2831e7442510668b0ca75953b3359894803ef3c))
|
||||
* Modify FactorRowCountEvaluator and FactorIndexEvaluator to return the ratio ([#328](https://github.com/microsoft/RD-Agent/issues/328)) ([8f43f8e](https://github.com/microsoft/RD-Agent/commit/8f43f8e87a92e05b541e925910608606ec8f6c4b))
|
||||
* New competition - Optiver ([#356](https://github.com/microsoft/RD-Agent/issues/356)) ([3705efe](https://github.com/microsoft/RD-Agent/commit/3705efe3b923748655a57d76b7a236e54d361831))
|
||||
* random forest for s3e11 ([#347](https://github.com/microsoft/RD-Agent/issues/347)) ([b57846d](https://github.com/microsoft/RD-Agent/commit/b57846d29314e9a5967945d1b4895f0f48c0f5ce))
|
||||
* refine the code in model description and fix some bugs in feedback.py ([#288](https://github.com/microsoft/RD-Agent/issues/288)) ([5b124d7](https://github.com/microsoft/RD-Agent/commit/5b124d7372137e4c613eb2749ddcc773922cc7b6))
|
||||
* refine the template in several Kaggle competitions ([#343](https://github.com/microsoft/RD-Agent/issues/343)) ([034f238](https://github.com/microsoft/RD-Agent/commit/034f238ed5ec351486b21250eabc75114961936c))
|
||||
* Revise to support better hypothesis proposal ([#390](https://github.com/microsoft/RD-Agent/issues/390)) ([c55ec0a](https://github.com/microsoft/RD-Agent/commit/c55ec0a0f577bbf7fc6228f7b87d2089ded83b31))
|
||||
* show workspace in demo ([#348](https://github.com/microsoft/RD-Agent/issues/348)) ([ddf567c](https://github.com/microsoft/RD-Agent/commit/ddf567c551b553788be022e9312c209ef6137d64))
|
||||
* support Multi output ([#330](https://github.com/microsoft/RD-Agent/issues/330)) ([3d36c45](https://github.com/microsoft/RD-Agent/commit/3d36c452ff0983800e5343834cc69f24a508ea70))
|
||||
* Supporting COVID-19 competition ([#374](https://github.com/microsoft/RD-Agent/issues/374)) ([a1b63db](https://github.com/microsoft/RD-Agent/commit/a1b63db79600edc9a74ba713c9d0be290214a592))
|
||||
* supporting Mnist competition ([#375](https://github.com/microsoft/RD-Agent/issues/375)) ([e958a34](https://github.com/microsoft/RD-Agent/commit/e958a34f5632a46ac43bff8e0d07d6ed020fdfc2))
|
||||
* Supporting Model Specifications ([#319](https://github.com/microsoft/RD-Agent/issues/319)) ([e126471](https://github.com/microsoft/RD-Agent/commit/e1264719e10b76158a91cd0ef331848e7c2de7c7))
|
||||
* supporting various Kaggle competitions & scenarios for RD-Agent ([#409](https://github.com/microsoft/RD-Agent/issues/409)) ([75eea22](https://github.com/microsoft/RD-Agent/commit/75eea22cc3d4e6f5a94c88cce915e27c507f8c50))
|
||||
* template for kaggle ([#308](https://github.com/microsoft/RD-Agent/issues/308)) ([ff97cf0](https://github.com/microsoft/RD-Agent/commit/ff97cf0155ab6941e4b5cf7d103575f934b70dc9))
|
||||
* use auto gen seed when using LLM cache ([#441](https://github.com/microsoft/RD-Agent/issues/441)) ([ca15365](https://github.com/microsoft/RD-Agent/commit/ca15365d23eeb094f42cf3dc8f5269b2f1c42bd3))
|
||||
* use unified pickle cacher & move llm config into a isolated config ([#424](https://github.com/microsoft/RD-Agent/issues/424)) ([2879ecf](https://github.com/microsoft/RD-Agent/commit/2879ecff816d97688b60909a79c7e568d42608a1))
|
||||
* xgboost gpu accelerate ([#359](https://github.com/microsoft/RD-Agent/issues/359)) ([56a5b8f](https://github.com/microsoft/RD-Agent/commit/56a5b8f9b2c6726cc64ec5b04b4ce7935d59b572))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* a bug of developer& edit s4e8 template ([#338](https://github.com/microsoft/RD-Agent/issues/338)) ([f12ce72](https://github.com/microsoft/RD-Agent/commit/f12ce726e7de96d478a232a3c27f92439820f8b4))
|
||||
* actively raised errors aer also considered as negative feedback. ([#268](https://github.com/microsoft/RD-Agent/issues/268)) ([46ec908](https://github.com/microsoft/RD-Agent/commit/46ec908e3594ac5e4cdc4057268e2f8800f5ed1f))
|
||||
* bug of saving preprocess cache files ([#310](https://github.com/microsoft/RD-Agent/issues/310)) ([5fb0608](https://github.com/microsoft/RD-Agent/commit/5fb0608f39f113cc9807fb1f381284a0bd4da318))
|
||||
* cache ([#383](https://github.com/microsoft/RD-Agent/issues/383)) ([f2a6e75](https://github.com/microsoft/RD-Agent/commit/f2a6e75b36ca96f7733b9c2a7154ac67bd2d7c6f))
|
||||
* change css tag of kaggle competition info crawler ([#306](https://github.com/microsoft/RD-Agent/issues/306)) ([1e3d38b](https://github.com/microsoft/RD-Agent/commit/1e3d38bf1ca3654f3a90ff392ecba1dbb4e80224))
|
||||
* debug dsagent ([#387](https://github.com/microsoft/RD-Agent/issues/387)) ([8fe9511](https://github.com/microsoft/RD-Agent/commit/8fe9511e606ba148c66f384add6ab94857079541))
|
||||
* eval_method cannot catch run factor error ([#260](https://github.com/microsoft/RD-Agent/issues/260)) ([2aaab31](https://github.com/microsoft/RD-Agent/commit/2aaab317ccb7a0121063bcd85fc36c21c7b8a391))
|
||||
* fix a bug in competition metric evaluation ([#407](https://github.com/microsoft/RD-Agent/issues/407)) ([94c47d6](https://github.com/microsoft/RD-Agent/commit/94c47d6fd5c3e38fc786a83e6d0d05e8d04498f3))
|
||||
* fix a bug in mini case ([#389](https://github.com/microsoft/RD-Agent/issues/389)) ([e75bb57](https://github.com/microsoft/RD-Agent/commit/e75bb5746f63933b750406bbd34ee63c5ba76b9f))
|
||||
* fix a bug in model tuning feedback ([#316](https://github.com/microsoft/RD-Agent/issues/316)) ([8aa088d](https://github.com/microsoft/RD-Agent/commit/8aa088da2dc7525a3970c01d01987246f47d6238))
|
||||
* fix a bug in scenario.py ([#388](https://github.com/microsoft/RD-Agent/issues/388)) ([999a1eb](https://github.com/microsoft/RD-Agent/commit/999a1eb0eff9088e1b02419db741db4acf8d9ff7))
|
||||
* fix a bug in the format of the model input ([#327](https://github.com/microsoft/RD-Agent/issues/327)) ([8f0574e](https://github.com/microsoft/RD-Agent/commit/8f0574eaaadb245b8c38e09ad4821306996d926f))
|
||||
* fix a small bug in cache using module name and function name as unique folder name ([#429](https://github.com/microsoft/RD-Agent/issues/429)) ([4f8134a](https://github.com/microsoft/RD-Agent/commit/4f8134a697d952f7ac824d7ebeec64bbc4545ab3))
|
||||
* fix a typo ([#362](https://github.com/microsoft/RD-Agent/issues/362)) ([9fafabd](https://github.com/microsoft/RD-Agent/commit/9fafabdf321b818bdd2211a2324d50cd0ebe1c1f))
|
||||
* fix cache result logic ([#430](https://github.com/microsoft/RD-Agent/issues/430)) ([5e34263](https://github.com/microsoft/RD-Agent/commit/5e342637dcc862679fd0642c6ba9ef048c984845))
|
||||
* fix command injection ([#421](https://github.com/microsoft/RD-Agent/issues/421)) ([52f30a6](https://github.com/microsoft/RD-Agent/commit/52f30a6184af1295be15e855a80b84bc424fc75d))
|
||||
* fix json load error ([#386](https://github.com/microsoft/RD-Agent/issues/386)) ([bba55fb](https://github.com/microsoft/RD-Agent/commit/bba55fb48fe105f4847c1b9c476eedc80835f523))
|
||||
* fix some bugs in feedback.py and refine the prompt ([#292](https://github.com/microsoft/RD-Agent/issues/292)) ([d834052](https://github.com/microsoft/RD-Agent/commit/d8340527f133dcc649d599d90d6402eddd37859e))
|
||||
* fix some bugs in knowledge base ([#378](https://github.com/microsoft/RD-Agent/issues/378)) ([fa6ff8e](https://github.com/microsoft/RD-Agent/commit/fa6ff8e591cf1847df77d73116649c5623161573))
|
||||
* fix some bugs in rag ([#399](https://github.com/microsoft/RD-Agent/issues/399)) ([194215c](https://github.com/microsoft/RD-Agent/commit/194215c4559aee5b6ece18d65c95fb30968e2db6))
|
||||
* fix some bugs in the entire loop ([#274](https://github.com/microsoft/RD-Agent/issues/274)) ([8a564ec](https://github.com/microsoft/RD-Agent/commit/8a564ece1d87b27ee98b76db317935e802468965))
|
||||
* fix some errors in scenario.py, proposal.py and runner.py and several complex competition scenarios([#365](https://github.com/microsoft/RD-Agent/issues/365)) ([2e383b1](https://github.com/microsoft/RD-Agent/commit/2e383b175d8448a67cb470f4e3ae8977d8ec6b5b))
|
||||
* improve_execution_time_in_kaggle_loop ([#279](https://github.com/microsoft/RD-Agent/issues/279)) ([4c8f998](https://github.com/microsoft/RD-Agent/commit/4c8f998c76f1e983a5687d2c65d3251750f2a9a0))
|
||||
* kaggle data mount problem ([#297](https://github.com/microsoft/RD-Agent/issues/297)) ([795df31](https://github.com/microsoft/RD-Agent/commit/795df311e3f93cd2f3fb51ba5698adaf10f6bd62))
|
||||
* Optiver fixes ([#357](https://github.com/microsoft/RD-Agent/issues/357)) ([b054017](https://github.com/microsoft/RD-Agent/commit/b054017463af0d1784407030f2477d212118f341))
|
||||
* partial bug in bench ([#368](https://github.com/microsoft/RD-Agent/issues/368)) ([af9808f](https://github.com/microsoft/RD-Agent/commit/af9808f98736a2df07e121c2f6d7bfeb7b7d3581))
|
||||
* preprocess output format & some mistake in spelling ([#358](https://github.com/microsoft/RD-Agent/issues/358)) ([b8b2cd6](https://github.com/microsoft/RD-Agent/commit/b8b2cd6ccd3b27aa73de847e50899a8a53b71b8f))
|
||||
* rag save file ([#385](https://github.com/microsoft/RD-Agent/issues/385)) ([1cb01dd](https://github.com/microsoft/RD-Agent/commit/1cb01dd6fe595f2f5fb86487601326611dd1a57a))
|
||||
* raise error in demo when no Metric in a Loop ([#313](https://github.com/microsoft/RD-Agent/issues/313)) ([e46a78e](https://github.com/microsoft/RD-Agent/commit/e46a78eb69271cb19978aab2f3b976c2870ca082))
|
||||
* refactor Bench ([#302](https://github.com/microsoft/RD-Agent/issues/302)) ([78a87f6](https://github.com/microsoft/RD-Agent/commit/78a87f624780ff67c0fa995ae4692678a120f99c))
|
||||
* refine some codes ([#353](https://github.com/microsoft/RD-Agent/issues/353)) ([866c2e6](https://github.com/microsoft/RD-Agent/commit/866c2e63ffa3876a3d16ad37f96da41d0558b714))
|
||||
* refine the prompt ([#286](https://github.com/microsoft/RD-Agent/issues/286)) ([77966c4](https://github.com/microsoft/RD-Agent/commit/77966c4f5e9f492c437c5b4b78d89c0f875ef0d8))
|
||||
* refine the ucb algorithm ([#406](https://github.com/microsoft/RD-Agent/issues/406)) ([14f7d97](https://github.com/microsoft/RD-Agent/commit/14f7d976e03c92d6e727524e0cdad8a03b585016))
|
||||
* revert model and make SOTA model available to COSTEER ([#351](https://github.com/microsoft/RD-Agent/issues/351)) ([3b7437b](https://github.com/microsoft/RD-Agent/commit/3b7437b87e685188259779cd85a78a0b592de9de))
|
||||
* stop using markup in docker env print ([#336](https://github.com/microsoft/RD-Agent/issues/336)) ([3009889](https://github.com/microsoft/RD-Agent/commit/3009889b5e2605b5427c76f3084e0e58026bb5ae))
|
||||
* support seed and fix absolute path ([#278](https://github.com/microsoft/RD-Agent/issues/278)) ([26352e1](https://github.com/microsoft/RD-Agent/commit/26352e13121cad5be95c0de78bb9f5dda4330614))
|
||||
* template for kaggle foreset & s4e9 ([#334](https://github.com/microsoft/RD-Agent/issues/334)) ([2393a41](https://github.com/microsoft/RD-Agent/commit/2393a41e7237615ced2c3fdd5c49308236b9f276))
|
||||
* test kaggle method ([#296](https://github.com/microsoft/RD-Agent/issues/296)) ([91a6196](https://github.com/microsoft/RD-Agent/commit/91a619618be1d7db660ea2b413a78dfaba9417a1))
|
||||
* update code to fix a small bug in model cache md5 hash ([#303](https://github.com/microsoft/RD-Agent/issues/303)) ([b00e4dc](https://github.com/microsoft/RD-Agent/commit/b00e4dc2eff5b16029a2a12a6589eadac5cfd148))
|
||||
* update new feature engineering code format ([#272](https://github.com/microsoft/RD-Agent/issues/272)) ([7850b80](https://github.com/microsoft/RD-Agent/commit/7850b8006a7c89d22629b345b4f361b0f35bc60d))
|
||||
* Update prompts.yaml to constrain only one model type ([#341](https://github.com/microsoft/RD-Agent/issues/341)) ([5b5dfee](https://github.com/microsoft/RD-Agent/commit/5b5dfeefbc7eb9dcbd9923544005c5d281262c03))
|
||||
* Update runner.py to fix a small bug ([#282](https://github.com/microsoft/RD-Agent/issues/282)) ([8aef3ab](https://github.com/microsoft/RD-Agent/commit/8aef3abcecd6002bd4bfeedcbe2c786d8bbfe2be))
|
||||
* Use fixed file name in model costeer & fixing cache ([#311](https://github.com/microsoft/RD-Agent/issues/311)) ([1f910a5](https://github.com/microsoft/RD-Agent/commit/1f910a5248bc576895ed66c2f7b2c3e046a2bc28))
|
||||
|
||||
|
||||
### Performance Improvements
|
||||
|
||||
* some small upgrade to factor costeer to improve the performance ([#420](https://github.com/microsoft/RD-Agent/issues/420)) ([9eb931f](https://github.com/microsoft/RD-Agent/commit/9eb931ffd971f252380dbd33ad1db259a4f229fd))
|
||||
|
||||
|
||||
### Reverts
|
||||
|
||||
* Revert feat: Factor Implement Search Enhancement ([#294](https://github.com/microsoft/RD-Agent/issues/294)) ([#305](https://github.com/microsoft/RD-Agent/issues/305)) ([f663cf4](https://github.com/microsoft/RD-Agent/commit/f663cf42a2f75cd52aef1c6b18be7c27f0641fed))
|
||||
|
||||
## [0.2.1](https://github.com/microsoft/RD-Agent/compare/v0.2.0...v0.2.1) (2024-09-10)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* default model value in config ([#256](https://github.com/microsoft/RD-Agent/issues/256)) ([c097585](https://github.com/microsoft/RD-Agent/commit/c097585f631f401c2c0966f6ad4c17286924f011))
|
||||
* fix_dotenv_error ([#257](https://github.com/microsoft/RD-Agent/issues/257)) ([923063c](https://github.com/microsoft/RD-Agent/commit/923063c1fd957c4ed42e97272c72b5e9545451dc))
|
||||
* readme ([#248](https://github.com/microsoft/RD-Agent/issues/248)) ([8cede22](https://github.com/microsoft/RD-Agent/commit/8cede2209922876490148459e1134da828e1fda0))
|
||||
|
||||
## [0.2.0](https://github.com/microsoft/RD-Agent/compare/v0.1.0...v0.2.0) (2024-09-07)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add collect info ([#233](https://github.com/microsoft/RD-Agent/issues/233)) ([89f4af9](https://github.com/microsoft/RD-Agent/commit/89f4af90fb4d95a0689bf9efc8ffd9326469c0aa))
|
||||
* add cross validation for kaggle scenario ([#236](https://github.com/microsoft/RD-Agent/issues/236)) ([e0b03ba](https://github.com/microsoft/RD-Agent/commit/e0b03ba6b5c3d9aa552b99d470e106d4e348e64d))
|
||||
* add progress status for docker env ([#215](https://github.com/microsoft/RD-Agent/issues/215)) ([538d4ef](https://github.com/microsoft/RD-Agent/commit/538d4ef2e52de795b90d3f75b2e1e877ab85c18d))
|
||||
* Added loop code for Kaggle scene. ([#211](https://github.com/microsoft/RD-Agent/issues/211)) ([975c327](https://github.com/microsoft/RD-Agent/commit/975c32715e51aec6b49537401f5fc59115e04a01))
|
||||
* Demo display effect and usage ([#162](https://github.com/microsoft/RD-Agent/issues/162)) ([8cf122a](https://github.com/microsoft/RD-Agent/commit/8cf122a0155f434fa4477ae7a6d616b5caecd3e0))
|
||||
* piloting of the framework ([#227](https://github.com/microsoft/RD-Agent/issues/227)) ([e9b103e](https://github.com/microsoft/RD-Agent/commit/e9b103e684fdd2b98cd1a89971a3fce2d6e884a1))
|
||||
* support more models for kaggle scenario ([#223](https://github.com/microsoft/RD-Agent/issues/223)) ([e3a9659](https://github.com/microsoft/RD-Agent/commit/e3a96598c0720fe092ec86d7ca8c195c7d6bcc72))
|
||||
* update model_experiment.py to support basic EDA ([#220](https://github.com/microsoft/RD-Agent/issues/220)) ([bf2684c](https://github.com/microsoft/RD-Agent/commit/bf2684c4d55ab8e1048ac0291695475ad53b0cd6))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* fix some bugs in llm calling ([#217](https://github.com/microsoft/RD-Agent/issues/217)) ([7b010f8](https://github.com/microsoft/RD-Agent/commit/7b010f8b5940aba65a58f1d78192aa80bcd0e654))
|
||||
* package dependency. ([#234](https://github.com/microsoft/RD-Agent/issues/234)) ([46be295](https://github.com/microsoft/RD-Agent/commit/46be2952952af534fd8d98a656c704c688d7cbdd))
|
||||
* remove useless line ([#177](https://github.com/microsoft/RD-Agent/issues/177)) ([64e9a8e](https://github.com/microsoft/RD-Agent/commit/64e9a8e39a2072a962111db18f5b9565df5b0176))
|
||||
|
||||
## [0.1.0](https://github.com/microsoft/RD-Agent/compare/v0.0.1...v0.1.0) (2024-08-09)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add entry for rdagent. ([#187](https://github.com/microsoft/RD-Agent/issues/187)) ([121b6d9](https://github.com/microsoft/RD-Agent/commit/121b6d98de38cd03be30cbee47b40baf39a2b60b))
|
||||
* change ui entry ([#197](https://github.com/microsoft/RD-Agent/issues/197)) ([fa5d335](https://github.com/microsoft/RD-Agent/commit/fa5d3354d22240888f4fc4007d9834f7424632aa))
|
||||
* remove pdfs and enable online pdf readings ([#183](https://github.com/microsoft/RD-Agent/issues/183)) ([18c0501](https://github.com/microsoft/RD-Agent/commit/18c05016a23d694c7b12759cf1322562dcffc56a))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* Fix a fail href in readme ([#189](https://github.com/microsoft/RD-Agent/issues/189)) ([1b89218](https://github.com/microsoft/RD-Agent/commit/1b89218f6bc697494f4a1b8a42ad18963002714f))
|
||||
* fix quick start problem ([#191](https://github.com/microsoft/RD-Agent/issues/191)) ([44f61bf](https://github.com/microsoft/RD-Agent/commit/44f61bfa1058a8efb59ca48b7f1417765aeea33e))
|
||||
* update command line in readme.md ([#192](https://github.com/microsoft/RD-Agent/issues/192)) ([9c45d24](https://github.com/microsoft/RD-Agent/commit/9c45d24a192da02f7d9765cb001097da1bc36c61))
|
||||
|
||||
## 0.0.1 (2024-08-08)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* Add description for scenario experiments. ([#174](https://github.com/microsoft/RD-Agent/issues/174)) ([fbd8c6d](https://github.com/microsoft/RD-Agent/commit/fbd8c6d87e1424c08997103b8e8fbf264858c4ed))
|
||||
* Added QlibFactorFromReportScenario and improved the report-factor loop. ([#161](https://github.com/microsoft/RD-Agent/issues/161)) ([882c79b](https://github.com/microsoft/RD-Agent/commit/882c79bf11583980e646b130f71cfa20201ffc7b))
|
||||
* filter feature which is high correlation to former implemented features ([#145](https://github.com/microsoft/RD-Agent/issues/145)) ([e818326](https://github.com/microsoft/RD-Agent/commit/e818326422740e04a4863f7c3c18744dde2ad98f))
|
||||
* Remove redundant 'key steps' section in frontend scene display. ([#169](https://github.com/microsoft/RD-Agent/issues/169)) ([e767005](https://github.com/microsoft/RD-Agent/commit/e76700513bee29232c93b97414419df330d9be8d))
|
||||
* streamlit webapp demo for different scenarios ([#135](https://github.com/microsoft/RD-Agent/issues/135)) ([d8da7db](https://github.com/microsoft/RD-Agent/commit/d8da7db865e6653fc4740efee9a843b69bd79699))
|
||||
* Uploaded Documentation, Updated Prompts & Some Code for model demo ([#144](https://github.com/microsoft/RD-Agent/issues/144)) ([529f935](https://github.com/microsoft/RD-Agent/commit/529f935aa98623f0dc1dda29eecee3ef738dd446))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* Add framework handling for task coding failure. ([#176](https://github.com/microsoft/RD-Agent/issues/176)) ([5e14fa5](https://github.com/microsoft/RD-Agent/commit/5e14fa54a9dd30a94aebe2643b8c9a3b85517a11))
|
||||
* Comprehensive update to factor extraction. ([#143](https://github.com/microsoft/RD-Agent/issues/143)) ([b5ea040](https://github.com/microsoft/RD-Agent/commit/b5ea04019fd5fa15c0f8b9a7e4f18f490f7057d4))
|
||||
* first round app folder cleaning ([#166](https://github.com/microsoft/RD-Agent/issues/166)) ([6a5a750](https://github.com/microsoft/RD-Agent/commit/6a5a75021912927deb5e8e4c7ad3ec4b51bfc788))
|
||||
* fix pickle problem ([#140](https://github.com/microsoft/RD-Agent/issues/140)) ([7ee4258](https://github.com/microsoft/RD-Agent/commit/7ee42587b60d94417f34332cee395cf210dc8a0e))
|
||||
* fix release CI ([#165](https://github.com/microsoft/RD-Agent/issues/165)) ([85d6a5e](https://github.com/microsoft/RD-Agent/commit/85d6a5ed91113fda34ae079b23c89aa24acd2cb2))
|
||||
* fix release CI error ([#160](https://github.com/microsoft/RD-Agent/issues/160)) ([1c9f8ef](https://github.com/microsoft/RD-Agent/commit/1c9f8ef287961731944acc9008496b4dddeddca7))
|
||||
* fix several bugs in data mining scenario ([#147](https://github.com/microsoft/RD-Agent/issues/147)) ([b233380](https://github.com/microsoft/RD-Agent/commit/b233380e2c66fb030db39424f0f040c86e37f5c4))
|
||||
* fix some small bugs in report-factor loop ([#152](https://github.com/microsoft/RD-Agent/issues/152)) ([a79f9f9](https://github.com/microsoft/RD-Agent/commit/a79f9f93406aff6305a76e6a6abd3852642e4c62))
|
||||
* fix_release_ci_error ([#150](https://github.com/microsoft/RD-Agent/issues/150)) ([4f82e99](https://github.com/microsoft/RD-Agent/commit/4f82e9960a2638af9d831581185ddd3bac5711fc))
|
||||
* Fixed some bugs introduced during refactoring. ([#167](https://github.com/microsoft/RD-Agent/issues/167)) ([f8f1445](https://github.com/microsoft/RD-Agent/commit/f8f1445283fb89aefeb2918243c35a219a51a56c))
|
||||
* optimize some prompts in factor loop. ([#158](https://github.com/microsoft/RD-Agent/issues/158)) ([c2c1330](https://github.com/microsoft/RD-Agent/commit/c2c13300b9ad315a663ec2d0eada414e56c6f54f))
|
||||
|
||||
|
||||
### Miscellaneous Chores
|
||||
|
||||
* release 0.0.1 ([1feacd3](https://github.com/microsoft/RD-Agent/commit/1feacd39b21193de11e9bbecf880ddf96d7c261c))
|
||||
For earlier changes inherited from the RD-Agent project, see the [upstream changelog](https://github.com/microsoft/RD-Agent/blob/main/CHANGELOG.md).
|
||||
|
||||
+68
-6
@@ -1,9 +1,71 @@
|
||||
# Microsoft Open Source Code of Conduct
|
||||
# Contributor Covenant Code of Conduct
|
||||
|
||||
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
|
||||
## Our Pledge
|
||||
|
||||
Resources:
|
||||
We as members, contributors, and leaders pledge to make participation in our
|
||||
community a harassment-free experience for everyone, regardless of age, body
|
||||
size, visible or invisible disability, ethnicity, sex characteristics, gender
|
||||
identity and expression, level of experience, education, socio-economic status,
|
||||
nationality, personal appearance, race, religion, or sexual identity
|
||||
and orientation.
|
||||
|
||||
- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
|
||||
- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
|
||||
- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns
|
||||
We pledge to act and interact in ways that contribute to an open, welcoming,
|
||||
diverse, inclusive, and healthy community.
|
||||
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to a positive environment for our
|
||||
community include:
|
||||
|
||||
* Demonstrating empathy and kindness toward other people
|
||||
* Being respectful of differing opinions, viewpoints, and experiences
|
||||
* Giving and gracefully accepting constructive feedback
|
||||
* Accepting responsibility and apologizing to those affected by our mistakes,
|
||||
and learning from the experience
|
||||
* Focusing on what is best not just for us as individuals, but for the
|
||||
overall community
|
||||
|
||||
Examples of unacceptable behavior include:
|
||||
|
||||
* The use of sexualized language or imagery, and sexual attention or
|
||||
advances of any kind
|
||||
* Trolling, insulting or derogatory comments, and personal or political attacks
|
||||
* Public or private harassment
|
||||
* Publishing others' private information, such as a physical or email
|
||||
address, without their explicit permission
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Enforcement Responsibilities
|
||||
|
||||
Community leaders are responsible for clarifying and enforcing our standards of
|
||||
acceptable behavior and will take appropriate and fair corrective action in
|
||||
response to any behavior that they deem inappropriate, threatening, offensive,
|
||||
or harmful.
|
||||
|
||||
## Scope
|
||||
|
||||
This Code of Conduct applies within all community spaces, and also applies when
|
||||
an individual is officially representing the community in public spaces.
|
||||
|
||||
## Enforcement
|
||||
|
||||
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
||||
reported to the community leaders responsible for enforcement at
|
||||
nico@predix.io.
|
||||
All complaints will be reviewed and investigated promptly and fairly.
|
||||
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
||||
version 2.0, available at
|
||||
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
|
||||
|
||||
Community Impact Guidelines were inspired by [Mozilla's code of conduct
|
||||
enforcement ladder](https://github.com/mozilla/diversity).
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
|
||||
For answers to common questions about this code of conduct, see the FAQ at
|
||||
https://www.contributor-covenant.org/faq. Translations are available at
|
||||
https://www.contributor-covenant.org/translations.
|
||||
|
||||
+5
-5
@@ -1,10 +1,10 @@
|
||||
# Contributing to RD-Agent
|
||||
# Contributing to Predix
|
||||
|
||||
We welcome contributions and suggestions to improve RD-Agent. Whether it's solving an issue, addressing a bug, enhancing documentation, or even correcting a typo, every contribution is valuable and helps improve the project.
|
||||
We welcome contributions and suggestions to improve Predix. Whether it's solving an issue, addressing a bug, enhancing documentation, or even correcting a typo, every contribution is valuable and helps improve the project.
|
||||
|
||||
## Getting Started
|
||||
|
||||
To get started, you can explore the issues list or search for `TODO:` comments in the codebase by running the command:
|
||||
To get started, you can explore the issues list or search for `TODO:` comments in the codebase by running:
|
||||
```sh
|
||||
grep -r "TODO:"
|
||||
```
|
||||
@@ -14,7 +14,7 @@ grep -r "TODO:"
|
||||
1. **Fork the Repository**: Create a fork of the repository on GitHub.
|
||||
2. **Clone the Repository**: Clone your forked repository to your local machine.
|
||||
```sh
|
||||
git clone https://github.com/your-username/RD-Agent.git
|
||||
git clone https://github.com/your-username/predix.git
|
||||
```
|
||||
3. **Create a Branch**: Create a new branch for your changes.
|
||||
```sh
|
||||
@@ -47,4 +47,4 @@ If you encounter any issues or have suggestions for improvements, please open an
|
||||
- Update documentation as needed.
|
||||
- Test your changes thoroughly before submitting a pull request.
|
||||
|
||||
Thank you for contributing to RD-Agent!
|
||||
Thank you for contributing to Predix!
|
||||
|
||||
@@ -19,7 +19,7 @@ CONSTRAINTS_FILE := constraints/$(PYTHON_VERSION).txt
|
||||
PUBLIC_DIR := $(shell [ "$$READTHEDOCS" = "True" ] && echo "$$READTHEDOCS_OUTPUT/html" || echo "public")
|
||||
|
||||
# URL and Path of changelog source code.
|
||||
CHANGELOG_URL := $(shell echo $${CI_PAGES_URL:-https://microsoft.github.io/rdagent}/_sources/changelog.md.txt)
|
||||
CHANGELOG_URL := $(shell echo $${CI_PAGES_URL:-https://predixai.github.io/predix}/_sources/changelog.md.txt)
|
||||
CHANGELOG_PATH := docs/changelog.md
|
||||
|
||||
########################################################################################
|
||||
|
||||
@@ -1,538 +1,313 @@
|
||||
# Predix
|
||||
|
||||
<h4 align="center">
|
||||
<img src="docs/_static/logo.png" alt="RA-Agent logo" style="width:70%; ">
|
||||
|
||||
<a href="https://rdagent.azurewebsites.net" target="_blank">🖥️ Live Demo</a> |
|
||||
<a href="https://rdagent.azurewebsites.net/factor_loop" target="_blank">🎥 Demo Video</a> <a href="https://www.youtube.com/watch?v=JJ4JYO3HscM&list=PLALmKB0_N3_i52fhUmPQiL4jsO354uopR" target="_blank">▶️YouTube</a> |
|
||||
<a href="https://rdagent.readthedocs.io/en/latest/index.html" target="_blank">📖 Documentation</a> |
|
||||
<a href="https://aka.ms/RD-Agent-Tech-Report" target="_blank">📄 Tech Report</a> |
|
||||
<a href="#-paperwork-list"> 📃 Papers </a>
|
||||
</h3>
|
||||
<strong>AI-powered Quantitative Trading Agent for EUR/USD Forex</strong>
|
||||
</h4>
|
||||
|
||||
<p align="center">
|
||||
<a href="#installation">Installation</a> •
|
||||
<a href="#quick-start">Quick Start</a> •
|
||||
<a href="#configuration">Configuration</a> •
|
||||
<a href="#features">Features</a>
|
||||
</p>
|
||||
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/ci.yml)
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/github-code-scanning/codeql)
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/dependabot/dependabot-updates)
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/pr.yml)
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/release.yml)
|
||||
[](https://pypi.org/project/rdagent/#files)
|
||||
[](https://pypi.org/project/rdagent/)
|
||||
[](https://pypi.org/project/rdagent/)
|
||||
[](https://github.com/microsoft/RD-Agent/releases)
|
||||
[](https://github.com/microsoft/RD-Agent/blob/main/LICENSE)
|
||||
[](https://github.com/pre-commit/pre-commit)
|
||||
[](http://mypy-lang.org/)
|
||||
[](https://github.com/astral-sh/ruff)
|
||||
[](https://discord.gg/ybQ97B6Jjy)
|
||||
[](https://rdagent.readthedocs.io/en/latest/?badge=latest)
|
||||
[](https://github.com/microsoft/RD-Agent/actions/workflows/readthedocs-preview.yml) <!-- this badge is too long, please place it in the last one to make it pretty -->
|
||||
[](https://arxiv.org/abs/2505.14738)
|
||||
<p align="center">
|
||||
<a href="https://github.com/PredixAI/predix/blob/main/LICENSE"><img src="https://img.shields.io/github/license/PredixAI/predix" alt="License"></a>
|
||||
<a href="https://pypi.org/project/predix/"><img src="https://img.shields.io/pypi/v/predix" alt="PyPI"></a>
|
||||
<a href="https://github.com/PredixAI/predix/actions/workflows/ci.yml"><img src="https://github.com/PredixAI/predix/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
|
||||
<a href="https://github.com/astral-sh/ruff"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff"></a>
|
||||
</p>
|
||||
|
||||
---
|
||||
|
||||
# 📰 News
|
||||
| 🗞️ News | 📝 Description |
|
||||
| -- | ------ |
|
||||
| Web UI Release | We release a new frontend that can be built and served by `rdagent server_ui` for real-time interaction and trace viewing, currently excluding the `data_science` scenario. |
|
||||
| NeurIPS 2025 Acceptance | We are thrilled to announce that our paper [R&D-Agent-Quant](https://arxiv.org/abs/2505.15155) has been accepted to NeurIPS 2025 |
|
||||
| [Technical Report Release](#overall-technical-report) | Overall framework description and results on MLE-bench |
|
||||
| [R&D-Agent-Quant Release](#deep-application-in-diverse-scenarios) | Apply R&D-Agent to quant trading |
|
||||
| MLE-Bench Results Released | R&D-Agent currently leads as the [top-performing machine learning engineering agent](#-the-best-machine-learning-engineering-agent) on MLE-bench |
|
||||
| Support LiteLLM Backend | We now fully support **[LiteLLM](https://github.com/BerriAI/litellm)** as our default backend for integration with multiple LLM providers. |
|
||||
| General Data Science Agent | [Data Science Agent](https://rdagent.readthedocs.io/en/latest/scens/data_science.html) |
|
||||
| Kaggle Scenario release | We release **[Kaggle Agent](https://rdagent.readthedocs.io/en/latest/scens/data_science.html)**, try the new features! |
|
||||
| Official WeChat group release | We created a WeChat group, welcome to join! (🗪[QR Code](https://github.com/microsoft/RD-Agent/issues/880)) |
|
||||
| Official Discord release | We launch our first chatting channel in Discord (🗪[](https://discord.gg/ybQ97B6Jjy)) |
|
||||
| First release | **R&D-Agent** is released on GitHub |
|
||||
## Overview
|
||||
|
||||
**Predix** is an autonomous AI agent for quantitative trading strategies in the EUR/USD forex market. Built on a multi-agent framework, Predix automates the full research and development cycle:
|
||||
|
||||
- 📊 **Data Analysis** – Automatically analyzes market patterns and microstructure
|
||||
- 💡 **Strategy Discovery** – Proposes novel trading factors and signals
|
||||
- 🧠 **Model Evolution** – Iteratively improves predictive models
|
||||
- 📈 **Backtesting** – Validates strategies on historical 1-minute data
|
||||
|
||||
# 🏆 The Best Machine Learning Engineering Agent!
|
||||
Predix is optimized for **1-minute EUR/USD FX data** (2020–2026) and uses Qlib as the underlying backtesting engine.
|
||||
|
||||
[MLE-bench](https://github.com/openai/mle-bench) is a comprehensive benchmark evaluating the performance of AI agents on machine learning engineering tasks. Utilizing datasets from 75 Kaggle competitions, MLE-bench provides robust assessments of AI systems' capabilities in real-world ML engineering scenarios.
|
||||
---
|
||||
|
||||
R&D-Agent currently leads as the top-performing machine learning engineering agent on MLE-bench:
|
||||
## Installation
|
||||
|
||||
| Agent | Low == Lite (%) | Medium (%) | High (%) | All (%) |
|
||||
|---------|--------|-----------|---------|----------|
|
||||
| R&D-Agent o3(R)+GPT-4.1(D) | 51.52 ± 6.9 | 19.3 ± 5.5 | 26.67 ± 0 | 30.22 ± 1.5 |
|
||||
| R&D-Agent o1-preview | 48.18 ± 2.49 | 8.95 ± 2.36 | 18.67 ± 2.98 | 22.4 ± 1.1 |
|
||||
| AIDE o1-preview | 34.3 ± 2.4 | 8.8 ± 1.1 | 10.0 ± 1.9 | 16.9 ± 1.1 |
|
||||
### Prerequisites
|
||||
|
||||
**Notes:**
|
||||
- **O3(R)+GPT-4.1(D)**: This version is designed to both reduce average time per loop and leverage a cost-effective combination of backend LLMs by seamlessly integrating Research Agent (o3) with Development Agent (GPT-4.1).
|
||||
- **AIDE o1-preview**: Represents the previously best public result on MLE-bench as reported in the original MLE-bench paper.
|
||||
- Average and standard deviation results for R&D-Agent o1-preview is based on a independent of 5 seeds and for R&D-Agent o3(R)+GPT-4.1(D) is based on 6 seeds.
|
||||
- According to MLE-Bench, the 75 competitions are categorized into three levels of complexity: **Low==Lite** if we estimate that an experienced ML engineer can produce a sensible solution in under 2 hours, excluding the time taken to train any models; **Medium** if it takes between 2 and 10 hours; and **High** if it takes more than 10 hours.
|
||||
- **Python 3.10 or 3.11**
|
||||
- **Docker** (required for sandboxed code execution)
|
||||
- **Linux** (officially supported; macOS/Windows may work with adjustments)
|
||||
|
||||
You can inspect the detailed runs of the above results online.
|
||||
- [R&D-Agent o1-preview detailed runs](https://aka.ms/RD-Agent_MLE-Bench_O1-preview)
|
||||
- [R&D-Agent o3(R)+GPT-4.1(D) detailed runs](https://aka.ms/RD-Agent_MLE-Bench_O3_GPT41)
|
||||
### Quick Install
|
||||
|
||||
For running R&D-Agent on MLE-bench, refer to **[MLE-bench Guide: Running ML Engineering via MLE-bench](https://rdagent.readthedocs.io/en/latest/scens/data_science.html)**
|
||||
```bash
|
||||
# Install from PyPI
|
||||
pip install predix
|
||||
|
||||
# 🥇 The First Data-Centric Quant Multi-Agent Framework!
|
||||
|
||||
R&D-Agent for Quantitative Finance, in short **RD-Agent(Q)**, is the first data-centric, multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization.
|
||||
|
||||
|
||||
|
||||
Extensive experiments in real stock markets show that, at a cost under $10, RD-Agent(Q) achieves approximately 2× higher ARR than benchmark factor libraries while using over 70% fewer factors. It also surpasses state-of-the-art deep time-series models under smaller resource budgets. Its alternating factor–model optimization further delivers excellent trade-off between predictive accuracy and strategy robustness.
|
||||
|
||||
You can learn more details about **RD-Agent(Q)** through the [paper](https://arxiv.org/abs/2505.15155) and reproduce it through the [documentation](https://rdagent.readthedocs.io/en/latest/scens/quant_agent_fin.html).
|
||||
|
||||
# Data Science Agent Preview
|
||||
Check out our demo video showcasing the current progress of our Data Science Agent under development:
|
||||
|
||||
https://github.com/user-attachments/assets/3eccbecb-34a4-4c81-bce4-d3f8862f7305
|
||||
|
||||
# 🌟 Introduction
|
||||
<div align="center">
|
||||
<img src="docs/_static/scen.png" alt="Our focused scenario" style="width:80%; ">
|
||||
</div>
|
||||
|
||||
R&D-Agent aims to automate the most critical and valuable aspects of the industrial R&D process, and we begin with focusing on the data-driven scenarios to streamline the development of models and data.
|
||||
Methodologically, we have identified a framework with two key components: 'R' for proposing new ideas and 'D' for implementing them.
|
||||
We believe that the automatic evolution of R&D will lead to solutions of significant industrial value.
|
||||
|
||||
|
||||
<!-- Tag Cloud -->
|
||||
R&D is a very general scenario. The advent of R&D-Agent can be your
|
||||
- 💰 **Automatic Quant Factory** ([🎥Demo Video](https://rdagent.azurewebsites.net/factor_loop)|[▶️YouTube](https://www.youtube.com/watch?v=X4DK2QZKaKY&t=6s))
|
||||
- 🤖 **Data Mining Agent:** Iteratively proposing data & models ([🎥Demo Video 1](https://rdagent.azurewebsites.net/model_loop)|[▶️YouTube](https://www.youtube.com/watch?v=dm0dWL49Bc0&t=104s)) ([🎥Demo Video 2](https://rdagent.azurewebsites.net/dmm)|[▶️YouTube](https://www.youtube.com/watch?v=VIaSTZuoZg4)) and implementing them by gaining knowledge from data.
|
||||
- 🦾 **Research Copilot:** Auto read research papers ([🎥Demo Video](https://rdagent.azurewebsites.net/report_model)|[▶️YouTube](https://www.youtube.com/watch?v=BiA2SfdKQ7o)) / financial reports ([🎥Demo Video](https://rdagent.azurewebsites.net/report_factor)|[▶️YouTube](https://www.youtube.com/watch?v=ECLTXVcSx-c)) and implement model structures or building datasets.
|
||||
- 🤖 **Kaggle Agent:** Auto Model Tuning and Feature Engineering([🎥Demo Video Coming Soon...]()) and implementing them to achieve more in competitions.
|
||||
- ...
|
||||
|
||||
You can click the links above to view the demo. We're continuously adding more methods and scenarios to the project to enhance your R&D processes and boost productivity.
|
||||
|
||||
Additionally, you can take a closer look at the examples in our **[🖥️ Live Demo](https://rdagent.azurewebsites.net/)**.
|
||||
|
||||
<div align="center">
|
||||
<a href="https://rdagent.azurewebsites.net/" target="_blank">
|
||||
<img src="docs/_static/demo.png" alt="Watch the demo" width="80%">
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
# ⚡ Quick start
|
||||
|
||||
### RD-Agent currently only supports Linux.
|
||||
|
||||
You can try above demos by running the following command:
|
||||
|
||||
### 🐳 Docker installation.
|
||||
Users must ensure Docker is installed before attempting most scenarios. Please refer to the [official 🐳Docker page](https://docs.docker.com/engine/install/) for installation instructions.
|
||||
Ensure the current user can run Docker commands **without using sudo**. You can verify this by executing `docker run hello-world`.
|
||||
|
||||
### 🐍 Create a Conda Environment
|
||||
- Create a new conda environment with Python (3.10 and 3.11 are well-tested in our CI):
|
||||
```sh
|
||||
conda create -n rdagent python=3.10
|
||||
```
|
||||
- Activate the environment:
|
||||
```sh
|
||||
conda activate rdagent
|
||||
```
|
||||
|
||||
### 🛠️ Install the R&D-Agent
|
||||
|
||||
#### For Users
|
||||
- You can directly install the R&D-Agent package from PyPI:
|
||||
```sh
|
||||
pip install rdagent
|
||||
```
|
||||
|
||||
#### For Developers
|
||||
- If you want to try the latest version or contribute to RD-Agent, you can install it from the source and follow the development setup:
|
||||
```sh
|
||||
git clone https://github.com/microsoft/RD-Agent
|
||||
cd RD-Agent
|
||||
make dev
|
||||
```
|
||||
|
||||
More details can be found in the [development setup](https://rdagent.readthedocs.io/en/latest/development.html).
|
||||
|
||||
### 💊 Health check
|
||||
- rdagent provides a health check that currently checks two things.
|
||||
- whether the docker installation was successful.
|
||||
- whether the default port used by the [rdagent ui](https://github.com/microsoft/RD-Agent?tab=readme-ov-file#%EF%B8%8F-monitor-the-application-results) is occupied.
|
||||
```sh
|
||||
rdagent health_check --no-check-env
|
||||
```
|
||||
|
||||
|
||||
### ⚙️ Configuration
|
||||
- The demos requires following ability:
|
||||
- ChatCompletion
|
||||
- json_mode
|
||||
- embedding query
|
||||
|
||||
You can set your Chat Model and Embedding Model in the following ways:
|
||||
|
||||
> **🔥 Attention**: We now provide experimental support for **DeepSeek** models! You can use DeepSeek's official API for cost-effective and high-performance inference. See the configuration example below for DeepSeek setup.
|
||||
|
||||
- **Using LiteLLM (Default)**: We now support LiteLLM as a backend for integration with multiple LLM providers. You can configure in multiple ways:
|
||||
|
||||
**Option 1: Unified API base for both models**
|
||||
|
||||
*Configuration Example: `OpenAI` Setup :*
|
||||
|
||||
```bash
|
||||
cat << EOF > .env
|
||||
# Set to any model supported by LiteLLM.
|
||||
CHAT_MODEL=gpt-4o
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
# Configure unified API base
|
||||
OPENAI_API_BASE=<your_unified_api_base>
|
||||
OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
```
|
||||
|
||||
*Configuration Example: `Azure OpenAI` Setup :*
|
||||
|
||||
> Before using this configuration, please confirm in advance that your `Azure OpenAI API key` supports `embedded models`.
|
||||
|
||||
```bash
|
||||
cat << EOF > .env
|
||||
EMBEDDING_MODEL=azure/<Model deployment supporting embedding>
|
||||
CHAT_MODEL=azure/<your deployment name>
|
||||
AZURE_API_KEY=<replace_with_your_openai_api_key>
|
||||
AZURE_API_BASE=<your_unified_api_base>
|
||||
AZURE_API_VERSION=<azure api version>
|
||||
```
|
||||
|
||||
**Option 2: Separate API bases for Chat and Embedding models**
|
||||
```bash
|
||||
cat << EOF > .env
|
||||
# Set to any model supported by LiteLLM.
|
||||
# Configure separate API bases for chat and embedding
|
||||
|
||||
# CHAT MODEL:
|
||||
CHAT_MODEL=gpt-4o
|
||||
OPENAI_API_BASE=<your_chat_api_base>
|
||||
OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
|
||||
# EMBEDDING MODEL:
|
||||
# TAKE siliconflow as an example, you can use other providers.
|
||||
# Note: embedding requires litellm_proxy prefix
|
||||
EMBEDDING_MODEL=litellm_proxy/BAAI/bge-large-en-v1.5
|
||||
LITELLM_PROXY_API_KEY=<replace_with_your_siliconflow_api_key>
|
||||
LITELLM_PROXY_API_BASE=https://api.siliconflow.cn/v1
|
||||
```
|
||||
|
||||
*Configuration Example: `DeepSeek` Setup :*
|
||||
|
||||
>Since many users encounter configuration errors when setting up DeepSeek. Here's a complete working example for DeepSeek Setup:
|
||||
```bash
|
||||
cat << EOF > .env
|
||||
# CHAT MODEL: Using DeepSeek Official API
|
||||
CHAT_MODEL=deepseek/deepseek-chat
|
||||
DEEPSEEK_API_KEY=<replace_with_your_deepseek_api_key>
|
||||
|
||||
# EMBEDDING MODEL: Using SiliconFlow for embedding since deepseek has no embedding model.
|
||||
# Note: embedding requires litellm_proxy prefix
|
||||
EMBEDDING_MODEL=litellm_proxy/BAAI/bge-m3
|
||||
LITELLM_PROXY_API_KEY=<replace_with_your_siliconflow_api_key>
|
||||
LITELLM_PROXY_API_BASE=https://api.siliconflow.cn/v1
|
||||
```
|
||||
|
||||
Notice: If you are using reasoning models that include thought processes in their responses (such as \<think> tags), you need to set the following environment variable:
|
||||
```bash
|
||||
REASONING_THINK_RM=True
|
||||
```
|
||||
|
||||
You can also use a deprecated backend if you only use `OpenAI API` or `Azure OpenAI` directly. For this deprecated setting and more configuration information, please refer to the [documentation](https://rdagent.readthedocs.io/en/latest/installation_and_configuration.html).
|
||||
|
||||
|
||||
|
||||
- If your environment configuration is complete, please execute the following commands to check if your configuration is valid. This step is necessary.
|
||||
|
||||
```bash
|
||||
rdagent health_check
|
||||
```
|
||||
|
||||
### 🚀 Run the Application
|
||||
|
||||
The **[🖥️ Live Demo](https://rdagent.azurewebsites.net/)** is implemented by the following commands(each item represents one demo, you can select the one you prefer):
|
||||
|
||||
- Run the **Automated Quantitative Trading & Iterative Factors Model Joint Evolution**: [Qlib](http://github.com/microsoft/qlib) self-loop factor & model proposal and implementation application
|
||||
```sh
|
||||
rdagent fin_quant
|
||||
```
|
||||
|
||||
- Run the **Automated Quantitative Trading & Iterative Factors Evolution**: [Qlib](http://github.com/microsoft/qlib) self-loop factor proposal and implementation application
|
||||
```sh
|
||||
rdagent fin_factor
|
||||
```
|
||||
|
||||
- Run the **Automated Quantitative Trading & Iterative Model Evolution**: [Qlib](http://github.com/microsoft/qlib) self-loop model proposal and implementation application
|
||||
```sh
|
||||
rdagent fin_model
|
||||
```
|
||||
|
||||
- Run the **Automated Quantitative Trading & Factors Extraction from Financial Reports**: Run the [Qlib](http://github.com/microsoft/qlib) factor extraction and implementation application based on financial reports
|
||||
```sh
|
||||
# 1. Generally, you can run this scenario using the following command:
|
||||
rdagent fin_factor_report --report-folder=<Your financial reports folder path>
|
||||
|
||||
# 2. Specifically, you need to prepare some financial reports first. You can follow this concrete example:
|
||||
wget https://github.com/SunsetWolf/rdagent_resource/releases/download/reports/all_reports.zip
|
||||
unzip all_reports.zip -d git_ignore_folder/reports
|
||||
rdagent fin_factor_report --report-folder=git_ignore_folder/reports
|
||||
```
|
||||
|
||||
- Run the **Automated Model Research & Development Copilot**: model extraction and implementation application
|
||||
```sh
|
||||
# 1. Generally, you can run your own papers/reports with the following command:
|
||||
rdagent general_model <Your paper URL>
|
||||
|
||||
# 2. Specifically, you can do it like this. For more details and additional paper examples, use `rdagent general_model -h`:
|
||||
rdagent general_model "https://arxiv.org/pdf/2210.09789"
|
||||
```
|
||||
|
||||
- Run the **Automated Medical Prediction Model Evolution**: Medical self-loop model proposal and implementation application
|
||||
|
||||
```bash
|
||||
# Generally, you can run the data science program with the following command:
|
||||
rdagent data_science --competition <your competition name>
|
||||
|
||||
# Specifically, you need to create a folder for storing competition files (e.g., competition description file, competition datasets, etc.), and configure the path to the folder in your environment. In addition, you need to use chromedriver when you download the competition descriptors, which you can follow for this specific example:
|
||||
|
||||
# 1. Download the dataset, extract it to the target folder.
|
||||
wget https://github.com/SunsetWolf/rdagent_resource/releases/download/ds_data/arf-12-hours-prediction-task.zip
|
||||
unzip arf-12-hours-prediction-task.zip -d ./git_ignore_folder/ds_data/
|
||||
|
||||
# 2. Configure environment variables in the `.env` file
|
||||
dotenv set DS_LOCAL_DATA_PATH "$(pwd)/git_ignore_folder/ds_data"
|
||||
dotenv set DS_CODER_ON_WHOLE_PIPELINE True
|
||||
dotenv set DS_IF_USING_MLE_DATA False
|
||||
dotenv set DS_SAMPLE_DATA_BY_LLM False
|
||||
dotenv set DS_SCEN rdagent.scenarios.data_science.scen.DataScienceScen
|
||||
|
||||
# 3. run the application
|
||||
rdagent data_science --competition arf-12-hours-prediction-task
|
||||
```
|
||||
|
||||
**NOTE:** For more information about the dataset, please refer to the [documentation](https://rdagent.readthedocs.io/en/latest/scens/data_science.html).
|
||||
|
||||
- Run the **Automated Kaggle Model Tuning & Feature Engineering**: self-loop model proposal and feature engineering implementation application <br />
|
||||
> Using **tabular-playground-series-dec-2021** as an example. <br />
|
||||
> 1. Register and login on the [Kaggle](https://www.kaggle.com/) website. <br />
|
||||
> 2. Configuring the Kaggle API. <br />
|
||||
> (1) Click on the avatar (usually in the top right corner of the page) -> `Settings` -> `Create New Token`, A file called `kaggle.json` will be downloaded. <br />
|
||||
> (2) Move `kaggle.json` to `~/.config/kaggle/` <br />
|
||||
> (3) Modify the permissions of the kaggle.json file. Reference command: `chmod 600 ~/.config/kaggle/kaggle.json` <br />
|
||||
> 3. Join the competition: Click `Join the competition` -> `I Understand and Accept` at the bottom of the [competition details page](https://www.kaggle.com/competitions/tabular-playground-series-dec-2021/data).
|
||||
```bash
|
||||
# Generally, you can run the Kaggle competition program with the following command:
|
||||
rdagent data_science --competition <your competition name>
|
||||
|
||||
# 1. Configure environment variables in the `.env` file
|
||||
mkdir -p ./git_ignore_folder/ds_data
|
||||
dotenv set DS_LOCAL_DATA_PATH "$(pwd)/git_ignore_folder/ds_data"
|
||||
dotenv set DS_CODER_ON_WHOLE_PIPELINE True
|
||||
dotenv set DS_IF_USING_MLE_DATA True
|
||||
dotenv set DS_SAMPLE_DATA_BY_LLM True
|
||||
dotenv set DS_SCEN rdagent.scenarios.data_science.scen.KaggleScen
|
||||
|
||||
# 2. run the application
|
||||
rdagent data_science --competition tabular-playground-series-dec-2021
|
||||
```
|
||||
|
||||
### 🖥️ Monitor the Application Results
|
||||
#### Streamlit UI
|
||||
|
||||
Use the Streamlit UI to view run logs, especially for the `data_science` scenario.
|
||||
|
||||
```sh
|
||||
rdagent ui --port 19899 --log-dir <your log folder like "log/"> --data-science
|
||||
# Or install from source
|
||||
git clone https://github.com/PredixAI/predix
|
||||
cd predix
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
About the `data_science` parameter: If you want to see the logs of the data science scenario, set the `data_science` parameter to `True`; otherwise set it to `False`.
|
||||
### Development Setup
|
||||
|
||||
#### Web UI
|
||||
```bash
|
||||
# Create conda environment
|
||||
conda create -n predix python=3.10
|
||||
conda activate predix
|
||||
|
||||
We also provide a separate web frontend in `web/` for the Flask backend started by `server_ui`.
|
||||
|
||||
**NOTE:** This web UI is different from `rdagent ui`. The current web UI does not support the `data_science` scenario yet. For the `data_science` scenario, please continue to use `rdagent ui --data-science`.
|
||||
|
||||
```sh
|
||||
cd web
|
||||
npm install
|
||||
# Install in editable mode with dev dependencies
|
||||
make dev
|
||||
```
|
||||
|
||||
To build the frontend for the Flask backend, generate the static assets into the default directory used by `server_ui`:
|
||||
---
|
||||
|
||||
```sh
|
||||
cd web
|
||||
npm run build:flask
|
||||
## Quick Start
|
||||
|
||||
### 1. Health Check
|
||||
|
||||
Verify your environment is properly configured:
|
||||
|
||||
```bash
|
||||
rdagent health_check --no-check-env
|
||||
```
|
||||
|
||||
By default, `server_ui` serves static files from `./git_ignore_folder/static`. If you need a different location, set the `UI_STATIC_PATH` environment variable before starting the backend.
|
||||
### 2. Configure LLM Backend
|
||||
|
||||
Start the Flask backend and serve the built frontend together with the real-time APIs:
|
||||
Create a `.env` file in your project root:
|
||||
|
||||
```sh
|
||||
rdagent server_ui --port 19899
|
||||
```bash
|
||||
# Example: OpenAI configuration
|
||||
cat << EOF > .env
|
||||
CHAT_MODEL=gpt-4o
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
OPENAI_API_BASE=https://api.openai.com/v1
|
||||
OPENAI_API_KEY=your-api-key-here
|
||||
EOF
|
||||
```
|
||||
|
||||
After that, open `http://127.0.0.1:19899` in your browser.
|
||||
**Alternative providers:**
|
||||
|
||||
#### Common Notes
|
||||
- **Azure OpenAI**: Set `AZURE_API_KEY`, `AZURE_API_BASE`, `AZURE_API_VERSION`
|
||||
- **DeepSeek**: Use `CHAT_MODEL=deepseek/deepseek-chat` with `DEEPSEEK_API_KEY`
|
||||
- **SiliconFlow (embedding)**: Use `EMBEDDING_MODEL=litellm_proxy/BAAI/bge-m3`
|
||||
|
||||
Port `19899` is used in the examples above. Before starting either UI, check whether this port is already occupied. If it is, please change it to another available port.
|
||||
### 3. Run Quantitative Trading Loop
|
||||
|
||||
You can check whether the port is occupied by running:
|
||||
```bash
|
||||
# Full factor & model co-evolution
|
||||
rdagent fin_quant
|
||||
|
||||
```sh
|
||||
rdagent health_check --no-check-env --no-check-docker
|
||||
# Factor-only evolution
|
||||
rdagent fin_factor
|
||||
|
||||
# Model-only evolution
|
||||
rdagent fin_model
|
||||
```
|
||||
|
||||
# 🏭 Scenarios
|
||||
### 4. Monitor Results
|
||||
|
||||
We have applied R&D-Agent to multiple valuable data-driven industrial scenarios.
|
||||
```bash
|
||||
# Start the UI dashboard
|
||||
rdagent ui --port 19899 --log-dir log/ --data-science
|
||||
```
|
||||
|
||||
Then open `http://127.0.0.1:19899` in your browser.
|
||||
|
||||
## 🎯 Goal: Agent for Data-driven R&D
|
||||
---
|
||||
|
||||
In this project, we are aiming to build an Agent to automate Data-Driven R\&D that can
|
||||
+ 📄 Read real-world material (reports, papers, etc.) and **extract** key formulas, descriptions of interested **features** and **models**, which are the key components of data-driven R&D .
|
||||
+ 🛠️ **Implement** the extracted formulas (e.g., features, factors, and models) in runnable codes.
|
||||
+ Due to the limited ability of LLM in implementing at once, build an evolving process for the agent to improve performance by learning from feedback and knowledge.
|
||||
+ 💡 Propose **new ideas** based on current knowledge and observations.
|
||||
## Configuration
|
||||
|
||||
<!--  -->
|
||||
### Data Configuration
|
||||
|
||||
## 📈 Scenarios/Demos
|
||||
Edit [`data_config.yaml`](data_config.yaml) to customize:
|
||||
|
||||
In the two key areas of data-driven scenarios, model implementation and data building, our system aims to serve two main roles: 🦾Copilot and 🤖Agent.
|
||||
- The 🦾Copilot follows human instructions to automate repetitive tasks.
|
||||
- The 🤖Agent, being more autonomous, actively proposes ideas for better results in the future.
|
||||
```yaml
|
||||
instrument: EURUSD
|
||||
frequency: 1min
|
||||
data_path: ~/.qlib/qlib_data/eurusd_1min_data
|
||||
|
||||
The supported scenarios are listed below:
|
||||
# Walk-forward split
|
||||
train_start: "2022-03-14"
|
||||
train_end: "2024-06-30"
|
||||
valid_start: "2024-07-01"
|
||||
valid_end: "2024-12-31"
|
||||
test_start: "2025-01-01"
|
||||
test_end: "2026-03-20"
|
||||
|
||||
| Scenario/Target | Model Implementation | Data Building |
|
||||
| -- | -- | -- |
|
||||
| **💹 Finance** | 🤖 [Iteratively Proposing Ideas & Evolving](https://rdagent.azurewebsites.net/model_loop)[▶️YouTube](https://www.youtube.com/watch?v=dm0dWL49Bc0&t=104s) | 🤖 [Iteratively Proposing Ideas & Evolving](https://rdagent.azurewebsites.net/factor_loop) [▶️YouTube](https://www.youtube.com/watch?v=X4DK2QZKaKY&t=6s) <br/> 🦾 [Auto reports reading & implementation](https://rdagent.azurewebsites.net/report_factor)[▶️YouTube](https://www.youtube.com/watch?v=ECLTXVcSx-c) |
|
||||
| **🩺 Medical** | 🤖 [Iteratively Proposing Ideas & Evolving](https://rdagent.azurewebsites.net/dmm)[▶️YouTube](https://www.youtube.com/watch?v=VIaSTZuoZg4) | - |
|
||||
| **🏭 General** | 🦾 [Auto paper reading & implementation](https://rdagent.azurewebsites.net/report_model)[▶️YouTube](https://www.youtube.com/watch?v=BiA2SfdKQ7o) <br/> 🤖 Auto Kaggle Model Tuning | 🤖Auto Kaggle feature Engineering |
|
||||
# Market context for LLM prompts
|
||||
market_context:
|
||||
spread_bps: 1.5
|
||||
target_arr: 9.62 # Target annual return (%)
|
||||
max_drawdown: 20 # Max drawdown (%)
|
||||
```
|
||||
|
||||
- **[RoadMap](https://rdagent.readthedocs.io/en/latest/scens/data_science.html#roadmap)**: Currently, we are working hard to add new features to the Kaggle scenario.
|
||||
### Environment Variables
|
||||
|
||||
Different scenarios vary in entrance and configuration. Please check the detailed setup tutorial in the scenarios documents.
|
||||
| Variable | Description | Example |
|
||||
|----------|-------------|---------|
|
||||
| `CHAT_MODEL` | LLM for reasoning | `gpt-4o`, `deepseek-chat` |
|
||||
| `EMBEDDING_MODEL` | Embedding model | `text-embedding-3-small` |
|
||||
| `OPENAI_API_KEY` | API key for OpenAI | `sk-...` |
|
||||
| `DEEPSEEK_API_KEY` | API key for DeepSeek | `sk-...` |
|
||||
| `DS_LOCAL_DATA_PATH` | Local data directory | `./data` |
|
||||
|
||||
Here is a gallery of [successful explorations](https://github.com/SunsetWolf/rdagent_resource/releases/download/demo_traces/demo_traces.zip) (5 traces showed in **[🖥️ Live Demo](https://rdagent.azurewebsites.net/)**). You can download and view the execution trace using [this command](https://github.com/microsoft/RD-Agent?tab=readme-ov-file#%EF%B8%8F-monitor-the-application-results) from the documentation.
|
||||
---
|
||||
|
||||
Please refer to **[📖readthedocs_scen](https://rdagent.readthedocs.io/en/latest/scens/catalog.html)** for more details of the scenarios.
|
||||
## Features
|
||||
|
||||
# ⚙️ Framework
|
||||
### 🔄 Iterative Factor Evolution
|
||||
|
||||
<div align="center">
|
||||
<img src="docs/_static/Framework-RDAgent.png" alt="Framework-RDAgent" width="85%">
|
||||
</div>
|
||||
Predix continuously proposes, implements, and validates new alpha factors:
|
||||
|
||||
- Learns from backtest feedback
|
||||
- Avoids overfitting through walk-forward validation
|
||||
- Discovers non-obvious patterns in order flow, volatility, and session dynamics
|
||||
|
||||
Automating the R&D process in data science is a highly valuable yet underexplored area in industry. We propose a framework to push the boundaries of this important research field.
|
||||
### 🧠 Model Architecture Search
|
||||
|
||||
The research questions within this framework can be divided into three main categories:
|
||||
| Research Area | Paper/Work List |
|
||||
|--------------------|-----------------|
|
||||
| **Benchmark the R&D abilities** | [Benchmark](#benchmark) |
|
||||
| **Idea proposal:** Explore new ideas or refine existing ones | [Research](#research) |
|
||||
| **Ability to realize ideas:** Implement and execute ideas | [Development](#development) |
|
||||
Automatically explores and refines predictive models:
|
||||
|
||||
We believe that the key to delivering high-quality solutions lies in the ability to evolve R&D capabilities. Agents should learn like human experts, continuously improving their R&D skills.
|
||||
- Linear baselines (LightGBM, XGBoost)
|
||||
- Deep learning (LSTM, Transformer, Temporal CNN)
|
||||
- Ensemble methods
|
||||
|
||||
More documents can be found in the **[📖 readthedocs](https://rdagent.readthedocs.io/)**.
|
||||
### 📚 Knowledge Base
|
||||
|
||||
# 📃 Paper/Work list
|
||||
Built-in knowledge accumulation across loops:
|
||||
|
||||
## Overall Technical Report
|
||||
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://arxiv.org/abs/2505.14738)
|
||||
```BibTeX
|
||||
- Successful factors are archived
|
||||
- Failed attempts inform future proposals
|
||||
- Cross-loop learning improves robustness
|
||||
|
||||
### 🖥️ Interactive UI
|
||||
|
||||
Real-time dashboard for monitoring:
|
||||
|
||||
- Factor performance metrics
|
||||
- Model architecture evolution
|
||||
- Cumulative returns and drawdowns
|
||||
- Code diffs and implementation history
|
||||
|
||||
---
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
predix/
|
||||
├── rdagent/ # Core agent framework
|
||||
│ ├── app/ # CLI and scenario apps
|
||||
│ ├── components/ # Reusable agent components
|
||||
│ ├── core/ # Core abstractions
|
||||
│ ├── scenarios/ # Domain-specific scenarios
|
||||
│ └── utils/ # Utilities
|
||||
├── constraints/ # Constraint definitions
|
||||
├── docs/ # Documentation
|
||||
├── web/ # Web UI frontend
|
||||
├── data_config.yaml # Data configuration
|
||||
├── pyproject.toml # Project metadata
|
||||
└── requirements.txt # Dependencies
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Data Setup
|
||||
|
||||
Predix uses 1-minute EUR/USD data. To prepare your dataset:
|
||||
|
||||
```bash
|
||||
# Run the data setup script (if provided)
|
||||
./setup_predix_eurusd.sh
|
||||
|
||||
# Or manually place data in:
|
||||
# ~/.qlib/qlib_data/eurusd_1min_data/
|
||||
```
|
||||
|
||||
Expected data columns: `$open`, `$close`, `$high`, `$low`, `$volume`
|
||||
|
||||
---
|
||||
|
||||
## CLI Commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `rdagent fin_quant` | Full factor & model co-evolution |
|
||||
| `rdagent fin_factor` | Factor-only evolution |
|
||||
| `rdagent fin_model` | Model-only evolution |
|
||||
| `rdagent fin_factor_report --report-folder=<path>` | Extract factors from financial reports |
|
||||
| `rdagent general_model <paper-url>` | Extract model from research paper |
|
||||
| `rdagent data_science --competition <name>` | Kaggle/data science competition mode |
|
||||
| `rdagent ui --port 19899 --log-dir <path>` | Start monitoring dashboard |
|
||||
| `rdagent health_check` | Validate environment setup |
|
||||
|
||||
---
|
||||
|
||||
## Requirements
|
||||
|
||||
Core dependencies (see [`requirements.txt`](requirements.txt) for full list):
|
||||
|
||||
- **LLM**: `openai`, `litellm`
|
||||
- **Data**: `pandas`, `numpy`, `pyarrow`
|
||||
- **ML**: `scikit-learn`, `lightgbm`, `xgboost`
|
||||
- **Backtesting**: `qlib` (via Docker)
|
||||
- **UI**: `streamlit`, `plotly`, `flask`
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
This project is licensed under the **MIT License** – see the [`LICENSE`](LICENSE) file for details.
|
||||
|
||||
---
|
||||
|
||||
## Contributing
|
||||
|
||||
Contributions are welcome! Please:
|
||||
|
||||
1. Fork the repository
|
||||
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
|
||||
3. Commit your changes (`git commit -m 'Add amazing feature'`)
|
||||
4. Push to the branch (`git push origin feature/amazing-feature`)
|
||||
5. Open a Pull Request
|
||||
|
||||
For major changes, please open an issue first to discuss your approach.
|
||||
|
||||
---
|
||||
|
||||
## Citation
|
||||
|
||||
If you use Predix in your research, please cite the underlying framework:
|
||||
|
||||
```bibtex
|
||||
@misc{yang2025rdagentllmagentframeworkautonomous,
|
||||
title={R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science},
|
||||
author={Xu Yang and Xiao Yang and Shikai Fang and Yifei Zhang and Jian Wang and Bowen Xian and Qizheng Li and Jingyuan Li and Minrui Xu and Yuante Li and Haoran Pan and Yuge Zhang and Weiqing Liu and Yelong Shen and Weizhu Chen and Jiang Bian},
|
||||
year={2025},
|
||||
eprint={2505.14738},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI},
|
||||
url={https://arxiv.org/abs/2505.14738},
|
||||
title={R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science},
|
||||
author={Yang, Xu and Yang, Xiao and Fang, Shikai and Zhang, Yifei and Wang, Jian and Xian, Bowen and Li, Qizheng and Li, Jingyuan and Xu, Minrui and Li, Yuante and others},
|
||||
year={2025},
|
||||
eprint={2505.14738},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
## 📊 Benchmark
|
||||
- [Towards Data-Centric Automatic R&D](https://arxiv.org/abs/2404.11276)
|
||||
```BibTeX
|
||||
@misc{chen2024datacentric,
|
||||
title={Towards Data-Centric Automatic R&D},
|
||||
author={Haotian Chen and Xinjie Shen and Zeqi Ye and Wenjun Feng and Haoxue Wang and Xiao Yang and Xu Yang and Weiqing Liu and Jiang Bian},
|
||||
year={2024},
|
||||
eprint={2404.11276},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🔍 Research
|
||||
## Support
|
||||
|
||||
In a data mining expert's daily research and development process, they propose a hypothesis (e.g., a model structure like RNN can capture patterns in time-series data), design experiments (e.g., finance data contains time-series and we can verify the hypothesis in this scenario), implement the experiment as code (e.g., Pytorch model structure), and then execute the code to get feedback (e.g., metrics, loss curve, etc.). The experts learn from the feedback and improve in the next iteration.
|
||||
- **Issues**: [GitHub Issues](https://github.com/PredixAI/predix/issues)
|
||||
- **Documentation**: [Read the Docs](https://rdagent.readthedocs.io/)
|
||||
|
||||
Based on the principles above, we have established a basic method framework that continuously proposes hypotheses, verifies them, and gets feedback from the real-world practice. This is the first scientific research automation framework that supports linking with real-world verification.
|
||||
---
|
||||
|
||||
For more detail, please refer to our **[🖥️ Live Demo page](https://rdagent.azurewebsites.net)**.
|
||||
## Disclaimer
|
||||
|
||||
## 🛠️ Development
|
||||
Predix is provided "as is" for **research and educational purposes only**. It is **not** intended for:
|
||||
|
||||
- [Collaborative Evolving Strategy for Automatic Data-Centric Development](https://arxiv.org/abs/2407.18690)
|
||||
```BibTeX
|
||||
@misc{yang2024collaborative,
|
||||
title={Collaborative Evolving Strategy for Automatic Data-Centric Development},
|
||||
author={Xu Yang and Haotian Chen and Wenjun Feng and Haoxue Wang and Zeqi Ye and Xinjie Shen and Xiao Yang and Shizhao Sun and Weiqing Liu and Jiang Bian},
|
||||
year={2024},
|
||||
eprint={2407.18690},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI}
|
||||
}
|
||||
```
|
||||
|
||||
- Live trading or financial advice
|
||||
- Production use without thorough testing
|
||||
- Replacement of qualified financial professionals
|
||||
|
||||
## Deep Application in Diverse Scenarios
|
||||
|
||||
- [R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization](https://arxiv.org/abs/2505.15155)
|
||||
```BibTeX
|
||||
@misc{li2025rdagentquantmultiagentframeworkdatacentric,
|
||||
title={R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization},
|
||||
author={Yuante Li and Xu Yang and Xiao Yang and Minrui Xu and Xisen Wang and Weiqing Liu and Jiang Bian},
|
||||
year={2025},
|
||||
eprint={2505.15155},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={q-fin.CP},
|
||||
url={https://arxiv.org/abs/2505.15155},
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
|
||||
# 🤝 Contributing
|
||||
|
||||
We welcome contributions and suggestions to improve R&D-Agent. Please refer to the [Contributing Guide](CONTRIBUTING.md) for more details on how to contribute.
|
||||
|
||||
Before submitting a pull request, ensure that your code passes the automatic CI checks.
|
||||
|
||||
## 📝 Guidelines
|
||||
This project welcomes contributions and suggestions.
|
||||
Contributing to this project is straightforward and rewarding. Whether it's solving an issue, addressing a bug, enhancing documentation, or even correcting a typo, every contribution is valuable and helps improve R&D-Agent.
|
||||
|
||||
To get started, you can explore the issues list, or search for `TODO:` comments in the codebase by running the command `grep -r "TODO:"`.
|
||||
|
||||
<img src="https://img.shields.io/github/contributors-anon/microsoft/RD-Agent"/>
|
||||
|
||||
<a href="https://github.com/microsoft/RD-Agent/graphs/contributors">
|
||||
<img src="https://contrib.rocks/image?repo=microsoft/RD-Agent&max=100&columns=15" />
|
||||
</a>
|
||||
|
||||
Before we released R&D-Agent as an open-source project on GitHub, it was an internal project within our group. Unfortunately, the internal commit history was not preserved when we removed some confidential code. As a result, some contributions from our group members, including Haotian Chen, Wenjun Feng, Haoxue Wang, Zeqi Ye, Xinjie Shen, and Jinhui Li, were not included in the public commits.
|
||||
|
||||
# ⚖️ Legal disclaimer
|
||||
<p style="line-height: 1; font-style: italic;">The RD-agent is provided “as is”, without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. The RD-agent is aimed to facilitate research and development process in the financial industry and not ready-to-use for any financial investment or advice. Users shall independently assess and test the risks of the RD-agent in a specific use scenario, ensure the responsible use of AI technology, including but not limited to developing and integrating risk mitigation measures, and comply with all applicable laws and regulations in all applicable jurisdictions. The RD-agent does not provide financial opinions or reflect the opinions of Microsoft, nor is it designed to replace the role of qualified financial professionals in formulating, assessing, and approving finance products. The inputs and outputs of the RD-agent belong to the users and users shall assume all liability under any theory of liability, whether in contract, torts, regulatory, negligence, products liability, or otherwise, associated with use of the RD-agent and any inputs and outputs thereof.</p>
|
||||
Users assume all liability and should comply with applicable laws and regulations in their jurisdiction. Past performance does not guarantee future results.
|
||||
|
||||
+8
-29
@@ -1,41 +1,20 @@
|
||||
<!-- BEGIN MICROSOFT SECURITY.MD V0.0.9 BLOCK -->
|
||||
# Security Policy
|
||||
|
||||
## Security
|
||||
## Reporting a Vulnerability
|
||||
|
||||
Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet) and [Xamarin](https://github.com/xamarin).
|
||||
|
||||
If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/security.md/definition), please report it to us as described below.
|
||||
|
||||
## Reporting Security Issues
|
||||
We take the security of Predix seriously. If you believe you have found a security vulnerability, please report it to us as described below.
|
||||
|
||||
**Please do not report security vulnerabilities through public GitHub issues.**
|
||||
|
||||
Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/security.md/msrc/create-report).
|
||||
Instead, please report them via email to:
|
||||
- **Email**: nico@predix.io
|
||||
|
||||
If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/security.md/msrc/pgp).
|
||||
|
||||
You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
|
||||
|
||||
Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
|
||||
|
||||
* Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
|
||||
* Full paths of source file(s) related to the manifestation of the issue
|
||||
* The location of the affected source code (tag/branch/commit or direct URL)
|
||||
* Any special configuration required to reproduce the issue
|
||||
* Step-by-step instructions to reproduce the issue
|
||||
* Proof-of-concept or exploit code (if possible)
|
||||
* Impact of the issue, including how an attacker might exploit the issue
|
||||
|
||||
This information will help us triage your report more quickly.
|
||||
|
||||
If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/security.md/msrc/bounty) page for more details about our active programs.
|
||||
You should receive a response within 48 hours. If for some reason you do not, please follow up via email to ensure we received your original message.
|
||||
|
||||
## Preferred Languages
|
||||
|
||||
We prefer all communications to be in English.
|
||||
|
||||
## Policy
|
||||
## Security Updates
|
||||
|
||||
Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/security.md/cvd).
|
||||
|
||||
<!-- END MICROSOFT SECURITY.MD BLOCK -->
|
||||
Security updates will be released as patch versions. Please ensure you are using the latest version of Predix to benefit from security fixes.
|
||||
|
||||
+25
-25
@@ -1,25 +1,25 @@
|
||||
# TODO: The maintainer of this repo has not yet edited this file
|
||||
|
||||
**REPO OWNER**: Do you want Customer Service & Support (CSS) support for this product/project?
|
||||
|
||||
- **No CSS support:** Fill out this template with information about how to file issues and get help.
|
||||
- **Yes CSS support:** Fill out an intake form at [aka.ms/onboardsupport](https://aka.ms/onboardsupport). CSS will work with/help you to determine next steps.
|
||||
- **Not sure?** Fill out an intake as though the answer were "Yes". CSS will help you decide.
|
||||
|
||||
*Then remove this first heading from this SUPPORT.MD file before publishing your repo.*
|
||||
|
||||
# Support
|
||||
|
||||
## How to file issues and get help
|
||||
|
||||
This project uses GitHub Issues to track bugs and feature requests. Please search the existing
|
||||
issues before filing new issues to avoid duplicates. For new issues, file your bug or
|
||||
feature request as a new Issue.
|
||||
|
||||
For help and questions about using this project, please **REPO MAINTAINER: INSERT INSTRUCTIONS HERE
|
||||
FOR HOW TO ENGAGE REPO OWNERS OR COMMUNITY FOR HELP. COULD BE A STACK OVERFLOW TAG OR OTHER
|
||||
CHANNEL. WHERE WILL YOU HELP PEOPLE?**.
|
||||
|
||||
## Microsoft Support Policy
|
||||
|
||||
Support for this **PROJECT or PRODUCT** is limited to the resources listed above.
|
||||
# Support
|
||||
|
||||
## How to file issues and get help
|
||||
|
||||
This project uses GitHub Issues to track bugs and feature requests. Please search the existing
|
||||
issues before filing new issues to avoid duplicates. For new issues, file your bug or
|
||||
feature request as a new Issue.
|
||||
|
||||
- **Issues**: [https://github.com/PredixAI/predix/issues](https://github.com/PredixAI/predix/issues)
|
||||
|
||||
For help and questions about using this project, please reach out via:
|
||||
|
||||
- **Email**: nico@predix.io
|
||||
- **GitHub Discussions**: [https://github.com/PredixAI/predix/discussions](https://github.com/PredixAI/predix/discussions)
|
||||
|
||||
## Community Support
|
||||
|
||||
We encourage users to help each other through GitHub Discussions or by contributing
|
||||
answers to issues. If you find a solution to a problem, please consider sharing it
|
||||
publicly to help others.
|
||||
|
||||
## Support Policy
|
||||
|
||||
Support is provided on a best-effort basis by the maintainers and community.
|
||||
For critical issues or commercial support needs, please contact the maintainers directly.
|
||||
|
||||
@@ -1,10 +1,16 @@
|
||||
We encourage to set the TODOs in code. But some TODOs are more global.
|
||||
So we place it here.
|
||||
# TODOs
|
||||
|
||||
This file tracks global TODOs for the Predix project. Individual TODOs in code should be addressed in their respective modules.
|
||||
|
||||
- [ ] Aligning the naming of files in components & scenarios.
|
||||
- We would like to have the same logic for naming convention in components(reusable components for all scenarios) and scenarios (componets for specific scenario).
|
||||
- But now we have following mismatch
|
||||
- `coder` in `components` & `developer` in `components`
|
||||
- [ ] The name of the folders mismatch with the content in them.
|
||||
- Why are scenarios in experiments?
|
||||
## Current Global TODOs
|
||||
|
||||
- [ ] Align naming conventions for files in `components/` and `scenarios/` directories
|
||||
- Current mismatch: `coder` in `components/` vs `developer` in `scenarios/`
|
||||
- [ ] Clean up folder naming inconsistencies
|
||||
- Investigate why some scenario-related code is in `experiments/` folders
|
||||
|
||||
## Completed
|
||||
|
||||
- [x] Rebrand from RD-Agent to Predix for EUR/USD focus
|
||||
- [x] Remove Microsoft-specific references
|
||||
- [x] Update documentation for PredixAI organization
|
||||
|
||||
+4
-4
@@ -10,9 +10,9 @@ import subprocess
|
||||
|
||||
latest_tag = subprocess.check_output(["git", "describe", "--tags", "--abbrev=0"], text=True).strip()
|
||||
|
||||
project = "RDAgent"
|
||||
copyright = "2024, Microsoft"
|
||||
author = "Microsoft"
|
||||
project = "Predix"
|
||||
copyright = "2025, Predix Team"
|
||||
author = "Predix Team"
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
|
||||
@@ -66,7 +66,7 @@ html_static_path = ["_static"]
|
||||
html_favicon = "_static/favicon.ico"
|
||||
|
||||
html_theme_options = {
|
||||
"source_repository": "https://github.com/microsoft/RD-Agent",
|
||||
"source_repository": "https://github.com/PredixAI/predix",
|
||||
"source_branch": "main",
|
||||
"source_directory": "docs/",
|
||||
}
|
||||
|
||||
+4
-4
@@ -1,13 +1,13 @@
|
||||
.. RDAgent documentation master file, created by
|
||||
.. Predix documentation master file, created by
|
||||
sphinx-quickstart on Mon Jul 15 04:27:50 2024.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
Welcome to RDAgent's documentation!
|
||||
Welcome to Predix's documentation!
|
||||
===================================
|
||||
|
||||
.. image:: _static/logo.png
|
||||
:alt: RD-Agent Logo
|
||||
:alt: Predix Logo
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 3
|
||||
@@ -23,7 +23,7 @@ Welcome to RDAgent's documentation!
|
||||
api_reference
|
||||
policy
|
||||
|
||||
GitHub <https://github.com/microsoft/RD-Agent>
|
||||
GitHub <https://github.com/PredixAI/predix>
|
||||
|
||||
|
||||
Indices and tables
|
||||
|
||||
+8
-6
@@ -7,7 +7,7 @@ requires = [
|
||||
|
||||
[project]
|
||||
authors = [
|
||||
{email = "xuyang1@microsoft.com", name = "MSRA-MIIC"},
|
||||
{email = "nico@predix.io", name = "Predix Team"},
|
||||
]
|
||||
classifiers = [
|
||||
"Development Status :: 3 - Alpha",
|
||||
@@ -16,18 +16,20 @@ classifiers = [
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
]
|
||||
description = "Research & Development Agent"
|
||||
description = "Predix - AI-gestützter Quantitative Trading Agent für EUR/USD"
|
||||
dynamic = [
|
||||
"dependencies",
|
||||
"optional-dependencies",
|
||||
"version",
|
||||
]
|
||||
keywords = [
|
||||
"Quantitative Trading",
|
||||
"Autonomous Agents",
|
||||
"Large Language Models",
|
||||
"Research and Development",
|
||||
"EUR/USD",
|
||||
"Forex",
|
||||
]
|
||||
name = "rdagent"
|
||||
name = "predix"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
|
||||
@@ -35,8 +37,8 @@ requires-python = ">=3.10"
|
||||
rdagent = "rdagent.app.cli:app"
|
||||
|
||||
[project.urls]
|
||||
homepage = "https://github.com/microsoft/RD-Agent/"
|
||||
issue = "https://github.com/microsoft/RD-Agent/issues"
|
||||
homepage = "https://github.com/PredixAI/predix/"
|
||||
issue = "https://github.com/PredixAI/predix/issues"
|
||||
|
||||
[tool.coverage.report]
|
||||
fail_under = 80
|
||||
|
||||
+47
-47
@@ -1,11 +1,11 @@
|
||||
#!/bin/bash
|
||||
# =============================================================================
|
||||
# setup_predix_eurusd.sh
|
||||
# Richtet Predix für EURUSD 15min Trading ein
|
||||
# Ausführen: bash setup_predix_eurusd.sh
|
||||
# Sets up Predix for EURUSD 15min trading
|
||||
# Usage: bash setup_predix_eurusd.sh
|
||||
# =============================================================================
|
||||
|
||||
set -e # Abbruch bei Fehler
|
||||
set -e # Exit on error
|
||||
|
||||
PREDIX_DIR="$HOME/Predix"
|
||||
CSV_SOURCE="$HOME/Downloads/eurusd_data.csv"
|
||||
@@ -16,27 +16,27 @@ echo "========================================"
|
||||
echo " Predix EURUSD Setup"
|
||||
echo "========================================"
|
||||
|
||||
# ─── 1. Prüfen ob alles da ist ───────────────────────────────────────────────
|
||||
# ─── 1. Check prerequisites ───────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[1/7] Prüfe Voraussetzungen..."
|
||||
echo "[1/7] Checking prerequisites..."
|
||||
|
||||
if [ ! -d "$PREDIX_DIR" ]; then
|
||||
echo "FEHLER: $PREDIX_DIR nicht gefunden!"
|
||||
echo "ERROR: $PREDIX_DIR not found!"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ ! -f "$CSV_SOURCE" ]; then
|
||||
echo "FEHLER: $CSV_SOURCE nicht gefunden!"
|
||||
echo "Bitte eurusd_data.csv in ~/Downloads/ legen"
|
||||
echo "ERROR: $CSV_SOURCE not found!"
|
||||
echo "Please place eurusd_data.csv in ~/Downloads/"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Predix gefunden: $PREDIX_DIR"
|
||||
echo "✓ CSV gefunden: $CSV_SOURCE"
|
||||
echo "✓ Predix found: $PREDIX_DIR"
|
||||
echo "✓ CSV found: $CSV_SOURCE"
|
||||
|
||||
# ─── 2. Ordner anlegen ───────────────────────────────────────────────────────
|
||||
# ─── 2. Create directory structure ─────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[2/7] Erstelle Ordnerstruktur..."
|
||||
echo "[2/7] Creating directory structure..."
|
||||
|
||||
mkdir -p "$DATA_DIR"
|
||||
mkdir -p "$QLIB_DIR/calendars"
|
||||
@@ -45,11 +45,11 @@ mkdir -p "$QLIB_DIR/features/eurusd"
|
||||
mkdir -p "$PREDIX_DIR/git_ignore_folder/log"
|
||||
|
||||
cp "$CSV_SOURCE" "$DATA_DIR/eurusd_data.csv"
|
||||
echo "✓ CSV kopiert nach $DATA_DIR"
|
||||
echo "✓ CSV copied to $DATA_DIR"
|
||||
|
||||
# ─── 3. CSV → Qlib Format konvertieren ───────────────────────────────────────
|
||||
# ─── 3. Convert CSV to Qlib format ─────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[3/7] Konvertiere CSV zu Qlib-Format..."
|
||||
echo "[3/7] Converting CSV to Qlib format..."
|
||||
|
||||
python3 << 'PYEOF'
|
||||
import pandas as pd
|
||||
@@ -60,20 +60,20 @@ import os
|
||||
QLIB_DIR = Path(os.path.expanduser("~/.qlib/qlib_data/eurusd_data"))
|
||||
CSV_PATH = Path(os.path.expanduser("~/Downloads/eurusd_data.csv"))
|
||||
|
||||
# Laden + sortieren
|
||||
# Load + sort
|
||||
df = pd.read_csv(CSV_PATH, parse_dates=["datetime"])
|
||||
df = df.sort_values("datetime").reset_index(drop=True)
|
||||
df.columns = [c.lower() for c in df.columns]
|
||||
|
||||
print(f" Rows: {len(df):,} | Range: {df['datetime'].min().date()} -> {df['datetime'].max().date()}")
|
||||
|
||||
# ── Kalender (alle 15min Timestamps) ────────────────────────────────────────
|
||||
# ── Calendar (all 15min timestamps) ────────────────────────────────────────
|
||||
cal = df["datetime"].dt.strftime("%Y-%m-%d %H:%M:%S")
|
||||
cal_path = QLIB_DIR / "calendars" / "15min.txt"
|
||||
cal.to_csv(cal_path, index=False, header=False)
|
||||
print(f" ✓ Kalender: {len(cal)} Einträge -> {cal_path}")
|
||||
print(f" ✓ Calendar: {len(cal)} entries -> {cal_path}")
|
||||
|
||||
# ── Instruments (nur EURUSD) ─────────────────────────────────────────────────
|
||||
# ── Instruments (only EURUSD) ──────────────────────────────────────────────
|
||||
inst_path = QLIB_DIR / "instruments" / "all.txt"
|
||||
start = df["datetime"].min().strftime("%Y-%m-%d")
|
||||
end = df["datetime"].max().strftime("%Y-%m-%d")
|
||||
@@ -81,22 +81,22 @@ with open(inst_path, "w") as f:
|
||||
f.write(f"EURUSD\t{start}\t{end}\n")
|
||||
print(f" ✓ Instruments -> {inst_path}")
|
||||
|
||||
# ── Features (Qlib binary format via CSV) ───────────────────────────────────
|
||||
# ── Features (Qlib binary format via CSV) ──────────────────────────────────
|
||||
feat_dir = QLIB_DIR / "features" / "eurusd"
|
||||
feat_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Qlib erwartet: $open, $high, $low, $close, $volume
|
||||
# Qlib expects: $open, $high, $low, $close, $volume
|
||||
for col in ["open", "high", "low", "close", "volume"]:
|
||||
out = feat_dir / f"{col}.day.bin"
|
||||
# Qlib binary: float32 array
|
||||
arr = df[col].astype("float32").values
|
||||
arr.tofile(str(out).replace(".day.bin", f"_15min.bin"))
|
||||
|
||||
# Auch als einfache CSV für direkten Zugriff
|
||||
# Also as simple CSV for direct access
|
||||
df.to_csv(QLIB_DIR / "eurusd_15min.csv", index=False)
|
||||
print(f" ✓ Features + CSV -> {feat_dir}")
|
||||
|
||||
# ── Returns + technische Features vorberechnen ───────────────────────────────
|
||||
# ── Returns + technical features precomputation ────────────────────────────
|
||||
def ema(s, p): return s.ewm(span=p, adjust=False).mean()
|
||||
def rsi(c, p=14):
|
||||
d = c.diff()
|
||||
@@ -118,28 +118,28 @@ feat["adx_proxy"] = df["close"].rolling(14).std() / df["close"].rolling(96).std(
|
||||
|
||||
feat.dropna(inplace=True)
|
||||
feat.to_csv(QLIB_DIR / "eurusd_features.csv", index=False)
|
||||
print(f" ✓ Features CSV: {len(feat):,} Zeilen, {len(feat.columns)} Spalten")
|
||||
print(" Fertig!")
|
||||
print(f" ✓ Features CSV: {len(feat):,} rows, {len(feat.columns)} columns")
|
||||
print(" Done!")
|
||||
PYEOF
|
||||
|
||||
echo "✓ Qlib-Daten konvertiert"
|
||||
echo "✓ Qlib data converted"
|
||||
|
||||
# ─── 4. .env updaten ─────────────────────────────────────────────────────────
|
||||
# ─── 4. Update .env ────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[4/7] Update .env..."
|
||||
echo "[4/7] Updating .env..."
|
||||
|
||||
ENV_FILE="$PREDIX_DIR/.env"
|
||||
|
||||
# Backup
|
||||
cp "$ENV_FILE" "$ENV_FILE.backup_$(date +%Y%m%d_%H%M%S)"
|
||||
|
||||
# QLIB_DATA_DIR auf EURUSD umbiegen
|
||||
# Update QLIB_DATA_DIR to EURUSD
|
||||
sed -i "s|QLIB_DATA_DIR=.*|QLIB_DATA_DIR=$QLIB_DIR|" "$ENV_FILE"
|
||||
|
||||
# LOG_PATH korrigieren (war /home/nico/RD-Agent-Local/log)
|
||||
# Fix LOG_PATH (was /home/nico/RD-Agent-Local/log)
|
||||
sed -i "s|LOG_PATH=.*|LOG_PATH=$PREDIX_DIR/git_ignore_folder/log|" "$ENV_FILE"
|
||||
|
||||
# EURUSD-spezifische Vars hinzufügen (falls noch nicht da)
|
||||
# Add EURUSD-specific vars (if not already present)
|
||||
grep -q "EURUSD_DATA_PATH" "$ENV_FILE" || cat >> "$ENV_FILE" << 'ENVEOF'
|
||||
|
||||
# ---------- EURUSD ----------
|
||||
@@ -151,11 +151,11 @@ BACKTEST_END_TIME=2026-03-20
|
||||
COST_RATE=0.00015
|
||||
ENVEOF
|
||||
|
||||
echo "✓ .env aktualisiert (Backup erstellt)"
|
||||
echo "✓ .env updated (backup created)"
|
||||
|
||||
# ─── 5. Prompts für EURUSD anpassen ──────────────────────────────────────────
|
||||
# ─── 5. Adjust prompts for EURUSD ──────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[5/7] Passe Qlib-Prompts für EURUSD an..."
|
||||
echo "[5/7] Adjusting Qlib prompts for EURUSD..."
|
||||
|
||||
PROMPT_FILE="$PREDIX_DIR/rdagent/app/qlib_rd_loop/prompts.yaml"
|
||||
cp "$PROMPT_FILE" "${PROMPT_FILE}.backup_$(date +%Y%m%d_%H%M%S)"
|
||||
@@ -218,16 +218,16 @@ hypothesis_generation:
|
||||
Target: beat current best ARR of 9.62%.
|
||||
YAMLEOF
|
||||
|
||||
echo "✓ prompts.yaml aktualisiert (Backup erstellt)"
|
||||
echo "✓ prompts.yaml updated (backup created)"
|
||||
|
||||
# ─── 6. Model Coder Prompt erweitern ─────────────────────────────────────────
|
||||
# ─── 6. Extend Model Coder Prompt ──────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[6/7] Erweitere Model Coder Prompts..."
|
||||
echo "[6/7] Extending Model Coder prompts..."
|
||||
|
||||
MODEL_PROMPT="$PREDIX_DIR/rdagent/components/coder/model_coder/prompts.yaml"
|
||||
cp "$MODEL_PROMPT" "${MODEL_PROMPT}.backup_$(date +%Y%m%d_%H%M%S)"
|
||||
|
||||
# EURUSD session filter als Kommentar in den evolving_strategy Block injizieren
|
||||
# Inject EURUSD session filter as comment in evolving_strategy block
|
||||
python3 << 'PYEOF'
|
||||
import re
|
||||
from pathlib import Path
|
||||
@@ -251,12 +251,12 @@ content = content.replace(
|
||||
eurusd_note + "\n Your code is expected to align the scenario in any form"
|
||||
)
|
||||
path.write_text(content)
|
||||
print(" ✓ Model coder prompt erweitert")
|
||||
print(" ✓ Model coder prompt extended")
|
||||
PYEOF
|
||||
|
||||
echo "✓ Model coder Prompt angepasst"
|
||||
echo "✓ Model coder prompt adjusted"
|
||||
|
||||
# ─── 7. Git Commits ──────────────────────────────────────────────────────────
|
||||
# ─── 7. Git Commits ────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "[7/7] Git Commits..."
|
||||
|
||||
@@ -279,23 +279,23 @@ git commit -m "feat: inject EURUSD trading rules into model coder
|
||||
- Max trade frequency guidance"
|
||||
|
||||
git add .env 2>/dev/null || true
|
||||
echo " (Note: .env nicht committed - enthält API Keys)"
|
||||
echo " (Note: .env not committed - contains API keys)"
|
||||
|
||||
echo ""
|
||||
echo "========================================"
|
||||
echo " Setup abgeschlossen!"
|
||||
echo " Setup completed!"
|
||||
echo "========================================"
|
||||
echo ""
|
||||
echo "Nächste Schritte:"
|
||||
echo "Next steps:"
|
||||
echo ""
|
||||
echo " 1. Starten:"
|
||||
echo " 1. Start:"
|
||||
echo " cd ~/Predix && rdagent fin_quant"
|
||||
echo ""
|
||||
echo " 2. Dashboard (in zweitem Terminal):"
|
||||
echo " 2. Dashboard (in second terminal):"
|
||||
echo " cd ~/Predix && rdagent server_ui --port 19899"
|
||||
echo " → http://localhost:19899"
|
||||
echo ""
|
||||
echo " 3. Logs:"
|
||||
echo " tail -f $PREDIX_DIR/git_ignore_folder/log/*.log"
|
||||
echo ""
|
||||
echo "Backup-Dateien (.backup_*) können nach erfolgreichem Test gelöscht werden."
|
||||
echo "Backup files (.backup_*) can be deleted after successful testing."
|
||||
|
||||
Reference in New Issue
Block a user