1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-01 01:51:18 +08:00
Commit Graph

1995 Commits

Author SHA1 Message Date
Fivele-Li
8c1905d1d7 Optimize KnowledgeBase to complete workflow (#1598)
* optimize KnowledgeBase to complete workflow;
* Update Knowledge methods of handle data IO;
* Update task to handle multi recorders;
* Integrate Knowledge to workflow;

* optimize KnowledgeBase to complete workflow
* Update TrainTask & AnalyseTask's recorder method;
* Update SummarizeTask;
* Update Workflow & Topic prompt;
2023-07-17 18:17:04 +08:00
you-n-g
1c9841b15e Connect TrainTask & Rolling & DDG-DA (#1599)
* Connect train task to ddg-da & rolling

* Pylint & black formatting

* Formatting
2023-07-17 09:58:58 +08:00
Xu Yang
5e0873ca81 Merge pull request #1592 from Fivele-Li/update_knowledge_module
update knowledge module;
2023-07-16 11:36:31 +08:00
Cadenza-Li
8a56cf69b4 add KnowledgeBase to workflow;
* Update CMDTask prompt example for Windows OS;
* Windows OS decode output of subprocess in gbk by default, specify encoding format explict;
* Add KnowledgeBase's 4 knowledge types to corresponding task;
2023-07-14 22:25:43 +08:00
you-n-g
a19e616bc3 Update test_utils.py 2023-07-14 16:43:43 +08:00
Cadenza-Li
025859acba Merge branch 'finco' into update_knowledge_module 2023-07-14 16:19:57 +08:00
Xu Yang
e5f685ce08 merge all commit (#1593)
Co-authored-by: Xu Yang <xuyang1@microsoft.com>
2023-07-14 16:17:24 +08:00
Cadenza-Li
b9b6938e71 Merge branch 'finco' into update_knowledge_module 2023-07-14 14:20:21 +08:00
Young
51a9403b15 Merge remote-tracking branch 'origin/main' into finco 2023-07-14 12:16:51 +08:00
you-n-g
be4646b4b7 Adjust rolling api (#1594)
* Intermediate version

* Fix yaml template & Successfully run rolling

* Be compatible with benchmark

* Get same results with previous linear model

* Black formatting

* Update black

* Update the placeholder mechanism

* Update CI

* Update CI

* Upgrade Black

* Fix CI and simplify code

* Fix CI

* Move the data processing caching mechanism into utils.

* Adjusting DDG-DA

* Organize import
2023-07-14 12:16:12 +08:00
Cadenza-Li
37d83fd747 update knowledge module;
* Knowledge.storage to storages list;
* optimize Knowledge & Storage save and load method;
* optimize Knowledge query prompt;
2023-07-13 17:20:22 +08:00
Cadenza-Li
d7ab6935dd update knowledge module;
* add storage class;
* new practice,execute,finance,infrastructure knowledge;
* add query method to KnowledgeBase;
2023-07-12 17:23:47 +08:00
you-n-g
8d3adf34ac Postpone PR stale. (#1591) 2023-07-12 09:59:09 +08:00
Fivele-Li
effed382e9 Optimize prompt for entire learn loop (#1589)
* Adjust prompt and fix cases
* adjust summarizeTask & learn prompts;
* fix typos & drop duplicate task method;

* adjust learn prompts;
2023-07-11 18:13:52 +08:00
Lewen Wang
b1dfc77ad7 Update qlibrl docs. (#1588)
* Update qlibrl docs.

* Update docs/component/rl/guidance.rst

* Update docs/component/rl/guidance.rst

* Update docs/component/rl/guidance.rst

---------

Co-authored-by: Litzy <litzy0619owned@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
2023-07-07 15:40:03 +08:00
Yang
3e074c8435 fix download token (#1577) 2023-07-06 12:38:52 +08:00
Fivele-Li
86ffd1799d Add knowledge module and tune summarizeTask (#1582)
* Add knowledge module
* add KnowledgeExperiment add KnowledgeBase;
* add knowledge associate prompts to template;

* Add Topic class
* add Topic to summarize knowledge;
* add recorder's metric to summarizeTask;

---------

Co-authored-by: Cadenza-Li <362237642@qq.com>
2023-07-06 11:39:36 +08:00
Linlang
b7e5f63a07 fix_pip_ci (#1584)
* fix_pip_ci

* fix_ci_get_data_error

---------

Co-authored-by: Linlang <v-linlanglv@microsoft.com>
2023-07-05 21:23:15 +08:00
Young
aef11536e3 rename & test 2023-07-04 20:28:08 +08:00
Xu Yang
8b0fdf1623 Merge pull request #1581 from microsoft/xuyang1/fix_singleton_bug
fix singleton bug
2023-07-04 16:51:51 +08:00
Xu Yang
9a36f8da20 fix singleton bug 2023-07-04 16:20:02 +08:00
Xu Yang
b7757d5008 Merge pull request #1580 from microsoft/xuyang1/refine_workflow_to_increase_success_rate
refine workflow to increase success rate
2023-07-03 17:59:54 +08:00
Xu Yang
ee5e5cfdd8 remove useless code 2023-07-03 17:57:13 +08:00
Xu Yang
6cb87ecfd1 refine code to use qrun 2023-07-03 17:56:22 +08:00
Xu Yang
9119bcdd3c Merge pull request #1576 from microsoft/xuyang1/add_config_and_code_dump_task
refine workflow and prompts
2023-06-30 14:43:49 +08:00
Xu Yang
4fccf8112d fix one workflow 2023-06-30 14:33:41 +08:00
Xu Yang
73bd79ca1a merge into one commit 2023-06-30 14:23:40 +08:00
Fivele-Li
7e84f3aae2 Add backtest and backforward task (#1568)
* * add TrainTask & BacktestTask;
* add BackForwardTask;
* adjust prompt_template.yaml which default config failed to backtest;
* run workflow in loop
* add update method to prompt_template.py

* remove debug code

* Adjust Learn Process
* add LearnManager class & use LearnManager to update system prompt;
* use qrun to replace recorder for training and backtesting;

* Adjust analyser
* analyser independent of recorder;
* rename analyser's workspace attribution;
* analyser load variable by recorder.

---------

Co-authored-by: Cadenza-Li <362237642@qq.com>
2023-06-30 10:04:43 +08:00
you-n-g
4db30b1225 Update README.md for RL (#1573)
* Update README.md

* Update README.md
2023-06-28 10:53:58 +08:00
you-n-g
b1e7b19a3d Update __init__.py 2023-06-27 11:55:40 +08:00
you-n-g
27f476b311 Update __init__.py v0.9.2 2023-06-26 00:00:46 +08:00
you-n-g
0e61cac6a8 Update release-drafter.yml (#1569)
* Update release-drafter.yml

* Update release-drafter.yml
2023-06-25 23:48:37 +08:00
Linlang
21f0b394e7 change get_data url (#1558)
* change_url

* fix_CI

* fix_CI_2

* fix_CI_3

* fix_CI_4

* fix_CI_5

* fix_CI_6

* fix_CI_7

* fix_CI_8

* fix_CI_9

* fix_CI_10

* fix_CI_11

* fix_CI_12

* fix_CI_13

* fix_CI_13

* fix_CI_14

* fix_CI_15

* fix_CI_16

* fix_CI_17

* fix_CI_18

* fix_CI_19

* fix_CI_20

* fix_CI_21

* fix_CI_22

* fix_CI_23

* fix_CI_24

* fix_CI_25

* fix_CI_26

* fix_CI_27

* fix_get_data_error

* fix_get_data_error2

* modify_get_data

* modify_get_data2

* modify_get_data3

* modify_get_data4

* fix_CI_28

* fix_CI_29

* fix_CI_30

---------

Co-authored-by: Linlang <v-linlanglv@microsoft.com>
2023-06-25 23:39:11 +08:00
Fivele-Li
1326ac614d Add docs to context and retrieve (#1566)
* add analyser docstring to context;
* add retrieve method to context manager;

* add notes to retrieve
2023-06-24 21:47:27 +08:00
Fivele-Li
f12184cc0f Add analyser task and optimize interact (#1552)
* * optimize interact
* add AnalyserTask
* optimize logger format and add render feature

* format optimize
2023-06-16 11:42:45 +08:00
Xu Yang
a70386ad52 Merge pull request #1550 from microsoft/xuyang1/refine_task_prompts
add datahandler and design action task according to component
2023-06-14 14:52:42 +08:00
Xu Yang
74619ed8d8 fix using defaut in record strategy and backtest 2023-06-14 14:52:16 +08:00
Fivele-Li
1a523df007 Optimize log and interact of FinCo (#1549)
* use FinCoLog for a better interact experience

* addition file changes

* optimize format

* optimize format
2023-06-14 14:48:17 +08:00
Xu Yang
f9cc8a5aaa remove useless prompt 2023-06-14 10:46:38 +08:00
Xu Yang
7762c5a1fd add datahandler and design action task according to component 2023-06-13 23:28:27 +08:00
Xu Yang
fa7ef29281 Merge pull request #1548 from microsoft/xuyang1/add_dump_to_file_task
add simple readme & move prompt templates to outer yaml file to make the code clean
2023-06-13 15:29:13 +08:00
Xu Yang
429c9a7c66 format 2023-06-13 15:27:59 +08:00
Xu Yang
80fbc00792 move prompt templates to yaml file to make code clean 2023-06-13 15:21:19 +08:00
Xu Yang
01accec24c update code 2023-06-12 16:25:16 +08:00
Fivele-Li
1d88830b0d Add recorder task and visualize (#1542)
* add recorder task

* add batch generate summarize report unittest.

* * add recorder to RecorderTask;
* add matplot figure to analyzer.py

* add image to markdown;

* Add some log

* update figure path.

---------

Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Cadenza-Li <362237642@qq.com>
2023-06-12 15:48:00 +08:00
Wendi Li
cd4ab998fb Update on Dynamic Benchmark (#1539)
* move config file to benchmark_dynamic & switch default sim task model to GBDT

* Update benchmark_dynamic results

* Change the default value of alpha of DDG-DA
2023-06-03 08:42:24 +08:00
you-n-g
ad7498e287 Edit yaml task (#1538)
* Edit yaml task

* update comments
2023-06-02 00:44:41 +08:00
you-n-g
73d51f05b4 Init workspace and CMDTask (#1537)
* Update setup.py and config

* WIP

* init_workspace and CMDTask

* Delete test_sumarize.py
2023-06-01 23:32:35 +08:00
Fivele-Li
3b56b8e6c0 Optimize summarize task prompt and others (#1533)
* 1.update prompt;
2.update fetch information method.

* 1.update prompt;
2.save result to markdown;

* 1.get context info from context_manager;
2.run the entire process successfully.
2023-06-01 21:22:24 +08:00
you-n-g
40e0c329ba Add configurable dataset (#1535) 2023-06-01 20:05:02 +08:00