add comments

Co-authored-by: Linlang Lv (iSoftStone Information) <v-lvlinlang@microsoft.com>

.github/labeler.yml

@@ -0,0 +1,6 @@
+documentation:
+- 'docs/**/*'
+- '**/*.md'
+
+waiting for triage:
+- any: ['**/*', '!docs/**/*', '!**/*.md']

.github/release-drafter.yml

@@ -14,6 +14,9 @@ categories:
     label: 
       - 'doc'
       - 'documentation'
+  - title: '🧹 Maintenance'
+    label: 
+      - 'maintenance'
 change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
 change-title-escapes: '\<*_&' # You can add # and @ to disable mentions, and add ` to disable code blocks.
 version-resolver:
@@ -30,4 +33,4 @@ version-resolver:
 template: |
   ## Changes
 
-  $CHANGES
+  $CHANGES

.github/workflows/labeler.yml

@@ -0,0 +1,14 @@
+name: "Add label automatically"
+on:
+- pull_request_target
+
+jobs:
+  triage:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/labeler@v4
+      with:
+        repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/python-publish.yml

@@ -19,7 +19,24 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python
+    #  This is because on macos systems you can install pyqlib using
+    # `pip install pyqlib` installs, it does not recognize the
+    # `pyqlib-<version>-cp38-cp38-macosx_11_0_x86_64.whl` and `pyqlib-<veresion>-cp38-cp37m-macosx_11_0_x86_64.whl`.
+    # So we limit the version of python, in order to generate a version of qlib that is usable for macos: `pyqlib-<veresion>-cp38-cp37m 
+    # `pyqlib-<version>-cp38-cp38-macosx_10_15_x86_64.whl` and `pyqlib-<veresion>-cp38-cp37m-macosx_10_15_x86_64.whl`.
+    # Python 3.7.16, 3.8.16  can build macosx_10_15.  But  Python 3.7.17, 3.8.17  can build macosx_11_0
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os == 'macos-11' && matrix.python-version == '3.7'
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.7.16"
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os == 'macos-11' && matrix.python-version == '3.8'
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.8.16"
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os != 'macos-11'
       uses: actions/setup-python@v2
       with:
         python-version: ${{ matrix.python-version }}
@@ -27,18 +44,18 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install setuptools wheel twine
-    - name: Build wheel on Windows
+    - name: Build wheel on ${{ matrix.os }}
       run: |
         pip install numpy
         pip install cython
         python setup.py bdist_wheel
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/*
-        
+
   deploy_with_manylinux:
     runs-on: ubuntu-latest
     steps:
@@ -55,10 +72,10 @@ jobs:
         python-version: 3.7
     - name: Install dependencies
       run: |
-        pip install twine  
+        pip install twine
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/pyqlib-*-manylinux*.whl

.github/workflows/release-drafter.yml

@@ -6,8 +6,14 @@ on:
     branches:
       - main
 
+permissions:
+  contents: read
+
 jobs:
   update_release_draft:
+    permissions:
+      contents: write
+      pull-requests: read
     runs-on: ubuntu-latest
     steps:
       # Drafts your next Release notes as Pull Requests are merged into "master"

.github/workflows/stale.yml

@@ -18,7 +18,8 @@ jobs:
         stale-issue-label: 'stale'
         stale-pr-label: 'stale'
         days-before-stale: 90
+        days-before-pr-stale: 365
         days-before-close: 5
         operations-per-run: 100
         exempt-issue-labels: 'bug,enhancement'
-        remove-stale-when-updated: true
+        remove-stale-when-updated: true

.github/workflows/test_qlib_from_pip.yml

@@ -13,16 +13,29 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
     steps:
     - name: Test qlib from pip
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -33,9 +46,6 @@ jobs:
     - name: Qlib installation test
       run: |
         python -m pip install pyqlib
-        # Specify the numpy version because the numpy upgrade caused the CI test to fail, 
-        # and this line of code will be removed when the next version of qlib is released.
-        python -m pip install "numpy<1.23"
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
@@ -50,7 +60,9 @@ jobs:
 
     - name: Downloads dependencies data
       run: |
-        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+        cd ..
+        python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+        cd qlib
 
     - name: Test workflow by config
       run: |

.github/workflows/test_qlib_from_source.yml

@@ -14,16 +14,29 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
     steps:
     - name: Test qlib from source
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -37,15 +50,13 @@ jobs:
         python -m pip install torch torchvision torchaudio
 
     - name: Installing pytorch for ubuntu
-      if: ${{ matrix.os == 'ubuntu-18.04' || matrix.os == 'ubuntu-20.04' }}
+      if: ${{ matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-22.04' }}
       run: |
-        python -m pip install --upgrade pip
         python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
 
     - name: Installing pytorch for windows
       if: ${{ matrix.os == 'windows-latest' }}
       run: |
-        python -m pip install --upgrade pip
         python -m pip install torch torchvision torchaudio
 
     - name: Set up Python tools
@@ -54,7 +65,10 @@ jobs:
         python -m pip install -e .[dev]
 
     - name: Lint with Black
+      # Python 3.7 will use a black with low level. So we use python with higher version for black check
+      if: (matrix.python-version != '3.7')
       run: |
+        pip install -U black  # follow the latest version of black, previous Qlib dependency will downgrade black
         black . -l 120 --check --diff
 
     - name: Make html with sphinx
@@ -91,6 +105,7 @@ jobs:
     - name: Check Qlib with pylint
       run: |
         pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0246,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' scripts --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
 
     # The following flake8 error codes were ignored:
       # E501 line too long
@@ -120,12 +135,16 @@ jobs:
       run: |
         mypy qlib --install-types --non-interactive || true
         mypy qlib --verbose
+    
+    - name: Check Qlib ipynb with nbqa
+      run: |
+        nbqa black . -l 120 --check --diff
+        nbqa pylint . --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136,W0719,W0104,W0404,C0412,W0611,C0410 --const-rgx='[a-z_][a-z0-9_]{2,30}$'
 
     - name: Test data downloads
       run: |
         python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        azcopy copy https://qlibpublic.blob.core.windows.net/data/rl /tmp/qlibpublic/data --recursive
-        mv /tmp/qlibpublic/data tests/.data
+        python scripts/get_data.py download_data --file_name rl_data.zip --target_dir tests/.data/rl
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
@@ -138,12 +157,15 @@ jobs:
         brew unlink libomp
         brew install libomp.rb
 
+    # Run after data downloads
+    - name: Check Qlib ipynb with nbconvert
+      run: |
+        # add more ipynb files in future
+        jupyter nbconvert --to notebook --execute examples/workflow_by_code.ipynb
+
     - name: Test workflow by config (install from source)
       run: |
-        # Version 0.52.0 of numba must be installed manually in CI, otherwise it will cause incompatibility with the latest version of numpy.
-        python -m pip install numba==0.52.0
-        # You must update numpy manually, because when installing python tools, it will try to uninstall numpy and cause CI to fail.
-        python -m pip install --upgrade numpy
+        python -m pip install numba
         python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
 
     - name: Unit tests with Pytest

.github/workflows/test_qlib_from_source_slow.yml

@@ -14,23 +14,35 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
     steps:
     - name: Test qlib from source slow
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
     - name: Set up Python tools
       run: |
         python -m pip install --upgrade pip
-        # python -m pip is necessary to upgrade pip.
         pip install --upgrade cython numpy
         pip install -e .[dev]
 

.gitignore

@@ -10,7 +10,6 @@ _build
 build/
 dist/
 
-
 *.pkl
 *.hd5
 *.csv
@@ -27,6 +26,8 @@ examples/estimator/estimator_example/
 examples/rl/data/
 examples/rl/checkpoints/
 examples/rl/outputs/
+examples/rl_order_execution/data/
+examples/rl_order_execution/outputs/
 
 *.egg-info/
 
@@ -47,4 +48,4 @@ tags
 *.swp
 
 ./pretrain
-.idea/
+.idea/

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.7.0
     hooks:
     -   id: black
         args: ["qlib", "-l 120"]
@@ -9,4 +9,4 @@ repos:
     rev: 4.0.1
     hooks:
         - id: flake8
-          args: ["--ignore=E501,F541,E266,E402,W503,E731,E203"]
+          args: ["--ignore=E501,F541,E266,E402,W503,E731,E203"]

.readthedocs.yaml

@@ -5,6 +5,12 @@
 # Required
 version: 2
 
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.7"
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py
@@ -14,7 +20,6 @@ formats: all
 
 # Optionally set the version of Python and requirements required to build your docs
 python:
-  version: 3.7
   install:
     - requirements: docs/requirements.txt
     - method: pip

README.md

@@ -11,6 +11,8 @@
 Recent released features
 | Feature | Status |
 | --                      | ------    |
+| KRNN and Sandwich models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1414/) on May 26, 2023 |
+| Release Qlib v0.9.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.9.0) on Dec 9, 2022 |
 | RL Learning Framework | :hammer: :chart_with_upwards_trend: Released on Nov 10, 2022. [#1332](https://github.com/microsoft/qlib/pull/1332), [#1322](https://github.com/microsoft/qlib/pull/1322), [#1316](https://github.com/microsoft/qlib/pull/1316),[#1299](https://github.com/microsoft/qlib/pull/1299),[#1263](https://github.com/microsoft/qlib/pull/1263), [#1244](https://github.com/microsoft/qlib/pull/1244), [#1169](https://github.com/microsoft/qlib/pull/1169), [#1125](https://github.com/microsoft/qlib/pull/1125), [#1076](https://github.com/microsoft/qlib/pull/1076)|
 | HIST and IGMTF models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1040) on Apr 10, 2022 |
 | Qlib [notebook tutorial](https://github.com/microsoft/qlib/tree/main/examples/tutorial) | 📖 [Released](https://github.com/microsoft/qlib/pull/1037) on Apr 7, 2022 | 
@@ -41,13 +43,11 @@ Features released before 2021 are not listed here.
   <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
 </p>
 
+Qlib is an open-source, AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms, including supervised learning, market dynamics modeling, and reinforcement learning.
 
-Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment.
+An increasing number of SOTA Quant research works/papers in diverse paradigms are being released in Qlib to collaboratively solve key challenges in quantitative investment. For example, 1) using supervised learning to mine the market's complex non-linear patterns from rich and heterogeneous financial data, 2) modeling the dynamic nature of the financial market using adaptive concept drift technology, and 3) using reinforcement learning to model continuous investment decisions and assist investors in optimizing their trading strategies.
 
 It contains the full ML pipeline of data processing, model training, back-testing; and covers the entire chain of quantitative investment: alpha seeking, risk modeling, portfolio optimization, and order execution. 
-
-With Qlib, users can easily try ideas to create better Quant investment strategies.
-
 For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative Investment Platform"](https://arxiv.org/abs/2009.11189).
 
 
@@ -91,6 +91,7 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
               </ul>
             </li>
           <li type="circle"><a href="#adapting-to-market-dynamics">Adapting to Market Dynamics</a></li>
+          <li type="circle"><a href="#reinforcement-learning-modeling-continuous-decisions">Reinforcement Learning: modeling continuous decisions</a></li>
           </ul>
         </li>
       </td>
@@ -138,7 +139,7 @@ This table demonstrates the supported Python version of `Qlib`:
 | Python 3.9    | :x:                   | :heavy_check_mark:   | :x: |
 
 **Note**: 
-1. **Conda** is suggested for managing your Python environment.
+1. **Conda** is suggested for managing your Python environment. In some cases, using Python outside of a `conda` environment may result in missing header files, causing the installation failure of certain packages.
 1. Please pay attention that installing cython in Python 3.6 will raise some error when installing ``Qlib`` from source. If users use Python 3.6 on their machines, it is recommended to *upgrade* Python to version 3.7 or use `conda`'s Python to install ``Qlib`` from source.
 1. For Python 3.9, `Qlib` supports running workflows such as training models, doing backtest and plot most of the related figures (those included in [notebook](examples/workflow_by_code.ipynb)). However, plotting for the *model performance* is not supported for now and we will fix this when the dependent packages are upgraded in the future.
 1. `Qlib`Requires `tables` package, `hdf5` in tables does not support python3.9. 
@@ -171,7 +172,23 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 
 **Tips**: If you fail to install `Qlib` or run the examples in your environment,  comparing your steps and the [CI workflow](.github/workflows/test_qlib_from_source.yml) may help you find the problem.
 
+**Tips for Mac**: If you are using Mac with M1, you might encounter issues in building the wheel for LightGBM, which is due to missing dependencies from OpenMP. To solve the problem, install openmp first with ``brew install libomp`` and then run ``pip install .`` to build it successfully. 
+
 ## Data Preparation
+❗ Due to more restrict data security policy. The offical dataset is disabled temporarily. You can try [this data source](https://github.com/chenditc/investment_data/releases) contributed by the community.
+Here is an example to download the data updated on 20220720.
+```bash
+wget https://github.com/chenditc/investment_data/releases/download/20220720/qlib_bin.tar.gz
+mkdir -p ~/.qlib/qlib_data/cn_data
+tar -zxvf qlib_bin.tar.gz -C ~/.qlib/qlib_data/cn_data --strip-components=2
+rm -f qlib_bin.tar.gz
+```
+
+The official dataset below will resume in short future.
+
+
+----
+
 Load and prepare data by running the following code:
 
 ### Get with module
@@ -320,7 +337,7 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
 The automatic workflow may not suit the research workflow of all Quant researchers. To support a flexible Quant research workflow, Qlib also provides a modularized interface to allow researchers to build their own workflow by code. [Here](examples/workflow_by_code.ipynb) is a demo for customized Quant research workflow by code.
 
 # Main Challenges & Solutions in Quant Research
-Quant investment is an very unique scenario with lots of key challenges to be solved.
+Quant investment is a very unique scenario with lots of key challenges to be solved.
 Currently, Qlib provides some solutions for several of them.
 
 ## Forecasting: Finding Valuable Signals/Patterns
@@ -354,10 +371,12 @@ Here is a list of models built on `Qlib`.
 - [ADD based on pytorch (Hongshun Tang, et al.2020)](examples/benchmarks/ADD/)
 - [IGMTF based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/IGMTF/)
 - [HIST based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/HIST/)
+- [KRNN based on pytorch](examples/benchmarks/KRNN/)
+- [Sandwich based on pytorch](examples/benchmarks/Sandwich/)
 
 Your PR of new Quant models is highly welcomed.
 
-The performance of each model on the `Alpha158` and `Alpha360` dataset can be found [here](examples/benchmarks/README.md).
+The performance of each model on the `Alpha158` and `Alpha360` datasets can be found [here](examples/benchmarks/README.md).
 
 ### Run a single model
 All the models listed above are runnable with ``Qlib``. Users can find the config files we provide and some details about the model through the [benchmarks](examples/benchmarks) folder. More information can be retrieved at the model files listed above.
@@ -390,6 +409,17 @@ Here is a list of solutions built on `Qlib`.
 - [Rolling Retraining](examples/benchmarks_dynamic/baseline/)
 - [DDG-DA on pytorch (Wendi, et al. AAAI 2022)](examples/benchmarks_dynamic/DDG-DA/)
 
+##  Reinforcement Learning: modeling continuous decisions
+Qlib now supports reinforcement learning, a feature designed to model continuous investment decisions. This functionality assists investors in optimizing their trading strategies by learning from interactions with the environment to maximize some notion of cumulative reward.
+
+Here is a list of solutions built on `Qlib` categorized by scenarios.
+
+### [RL for order execution](examples/rl_order_execution)
+[Here](https://qlib.readthedocs.io/en/latest/component/rl/overall.html#order-execution) is the introduction of this scenario.  All the methods below are compared [here](examples/rl_order_execution).
+- [TWAP](examples/rl_order_execution/exp_configs/backtest_twap.yml)
+- [PPO: "An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization", IJCAL 2020](examples/rl_order_execution/exp_configs/backtest_ppo.yml)
+- [OPDS: "Universal Trading for Order Execution with Oracle Policy Distillation", AAAI 2021](examples/rl_order_execution/exp_configs/backtest_opds.yml)
+
 # Quant Dataset Zoo
 Dataset plays a very important role in Quant. Here is a list of the datasets built on `Qlib`:
 

docs/component/data.rst

@@ -52,7 +52,7 @@ Also, ``Qlib`` provides a high-frequency dataset. Users can run a high-frequency
 Qlib Format Dataset
 -------------------
 ``Qlib`` has provided an off-the-shelf dataset in `.bin` format, users could use the script ``scripts/get_data.py`` to download the China-Stock dataset as follows. User can also use numpy to load `.bin` file to validate data.
-The price volume data look different from the actual dealling price because of they are **adjusted** (`adjusted price <https://www.investopedia.com/terms/a/adjusted_closing_price.asp>`_).  And then you may find that the adjusted price may be different from different data sources. This is because different data sources may vary in the way of adjusting prices. Qlib normalize the price on first trading day of each stock to 1 when adjusting them.
+The price volume data look different from the actual dealing price because of they are **adjusted** (`adjusted price <https://www.investopedia.com/terms/a/adjusted_closing_price.asp>`_).  And then you may find that the adjusted price may be different from different data sources. This is because different data sources may vary in the way of adjusting prices. Qlib normalize the price on first trading day of each stock to 1 when adjusting them.
 Users can leverage `$factor` to get the original trading price (e.g. `$close / $factor` to get the original close price).
 
 Here are some discussions about the price adjusting of Qlib. 
@@ -119,7 +119,7 @@ Here are some example:
 for daily data:
   .. code-block:: bash
 
-    python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
+    python scripts/get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
 
 for 1min data:
   .. code-block:: bash
@@ -140,12 +140,13 @@ Users can also provide their own data in CSV format. However, the CSV data **mus
 
         where the data are in the following format:
 
-        .. code-block::
+            +-----------+-------+
+            | symbol    | close |
+            +===========+=======+
+            | SH600000  | 120   |
+            +-----------+-------+
 
-            symbol,close
-            SH600000,120
-
-- CSV file **must** includes a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
+- CSV file **must** include a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
 
     .. code-block:: bash
 
@@ -153,11 +154,13 @@ Users can also provide their own data in CSV format. However, the CSV data **mus
 
     where the data are in the following format:
 
-    .. code-block::
-
-        symbol,date,close,open,volume
-        SH600000,2020-11-01,120,121,12300000
-        SH600000,2020-11-02,123,120,12300000
+        +---------+------------+-------+------+----------+
+        | symbol  | date       | close | open | volume   |
+        +=========+============+=======+======+==========+
+        | SH600000| 2020-11-01 | 120   | 121  | 12300000 |
+        +---------+------------+-------+------+----------+
+        | SH600000| 2020-11-02 | 123   | 120  | 12300000 |
+        +---------+------------+-------+------+----------+
 
 
 Supposed that users prepare their CSV format data in the directory ``~/.qlib/csv_data/my_data``, they can run the following command to start the conversion.

docs/component/rl/framework.rst

@@ -42,4 +42,8 @@ As you may have noticed, a training vessel itself holds all the required compone
 
 With a training vessel, the trainer could finally launch the training pipeline by simple, Scikit-learn-like interfaces (i.e., ``trainer.fit()``).
 
-The API for Trainer and TrainingVessel and can be found `here <../../reference/api.html#module-qlib.rl.trainer>`__.
+The API for Trainer and TrainingVessel and can be found `here <../../reference/api.html#module-qlib.rl.trainer>`__.
+
+The RL module is designed in a loosely-coupled way. Currently, RL examples are integrated with concrete business logic.
+But the core part of RL is much simpler than what you see.
+To demonstrate the simple core of RL, `a dedicated notebook <https://github.com/microsoft/qlib/tree/main/examples/rl/simple_example.ipynb>`__ for RL without business loss is created.

docs/component/rl/guidance.rst

@@ -0,0 +1,32 @@
+
+========
+Guidance
+========
+.. currentmodule:: qlib
+
+QlibRL can help users quickly get started and conveniently implement quantitative strategies based on reinforcement learning(RL) algorithms. For different user groups, we recommend the following guidance to use QlibRL.
+
+Beginners to Reinforcement Learning Algorithms
+==============================================
+Whether you are a quantitative researcher who wants to understand what RL can do in trading or a learner who wants to get started with RL algorithms in trading scenarios, if you have limited knowledge of RL and want to shield various detailed settings to quickly get started with RL algorithms, we recommend the following sequence to learn qlibrl:
+ - Learn the fundamentals of RL in `part1 <https://qlib.readthedocs.io/en/latest/component/rl/overall.html#reinforcement-learning>`_.
+ - Understand the trading scenarios where RL methods can be applied in `part2 <https://qlib.readthedocs.io/en/latest/component/rl/overall.html#potential-application-scenarios-in-quantitative-trading>`_.
+ - Run the examples in `part3 <https://qlib.readthedocs.io/en/latest/component/rl/quickstart.html>`_ to solve trading problems using RL.
+ - If you want to further explore QlibRL and make some customizations, you need to first understand the framework of QlibRL in `part4 <https://qlib.readthedocs.io/en/latest/component/rl/framework.html>`_ and rewrite specific components according to your needs.
+
+Reinforcement Learning Algorithm Researcher
+==============================================
+If you are already familiar with existing RL algorithms and dedicated to researching RL algorithms but lack domain knowledge in the financial field, and you want to validate the effectiveness of your algorithms in financial trading scenarios, we recommend the following steps to get started with QlibRL:
+ - Understand the trading scenarios where RL methods can be applied in `part2 <https://qlib.readthedocs.io/en/latest/component/rl/overall.html#potential-application-scenarios-in-quantitative-trading>`_.
+ - Choose an RL application scenario (currently, QlibRL has implemented two scenario examples: order execution and algorithmic trading). Run the example in `part3 <https://qlib.readthedocs.io/en/latest/component/rl/quickstart.html>`_ to get it working.
+ - Modify the `policy <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/policy.py>`_ part to incorporate your own RL algorithm.
+
+Quantitative Researcher
+=======================
+If you have a certain level of financial domain knowledge and coding skills, and you want to explore the application of RL algorithms in the investment field, we recommend the following steps to explore QlibRL:
+ - Learn the fundamentals of RL in `part1 <https://qlib.readthedocs.io/en/latest/component/rl/overall.html#reinforcement-learning>`_.
+ - Understand the trading scenarios where RL methods can be applied in `part2 <https://qlib.readthedocs.io/en/latest/component/rl/overall.html#potential-application-scenarios-in-quantitative-trading>`_.
+ - Run the examples in `part3 <https://qlib.readthedocs.io/en/latest/component/rl/quickstart.html>`_ to solve trading problems using RL.
+ - Understand the framework of QlibRL in `part4 <https://qlib.readthedocs.io/en/latest/component/rl/framework.html>`_.
+ - Choose a suitable RL algorithm based on the characteristics of the problem you want to solve (currently, QlibRL supports PPO and DQN algorithms based on tianshou).
+ - Design the MDP (Markov Decision Process) process based on market trading rules and the problem you want to solve. Refer to the example in order execution and make corresponding modifications to the following modules: `State <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/state.py#L70>`_, `Metrics <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/state.py#L18>`_, `ActionInterpreter <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/interpreter.py#L199>`_, `StateInterpreter <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/interpreter.py#L68>`_, `Reward <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/reward.py>`_, `Observation <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/interpreter.py#L44>`_, `Simulator <https://github.com/microsoft/qlib/blob/main/qlib/rl/order_execution/simulator_simple.py>`_.

docs/component/rl/overall.rst

@@ -4,7 +4,7 @@ Reinforcement Learning in Quantitative Trading
 
 Reinforcement Learning
 ======================
-Different from supervised learning tasks such as classification tasks and regression tasks. Another important paradigm in machine learning is Reinforcement Learning, 
+Different from supervised learning tasks such as classification tasks and regression tasks. Another important paradigm in machine learning is Reinforcement Learning(RL), 
 which attempts to optimize an accumulative numerical reward signal by directly interacting with the environment under a few assumptions such as Markov Decision Process(MDP).
 
 As demonstrated in the following figure, an RL system consists of four elements, 1)the agent 2) the environment the agent interacts with 3) the policy that the agent follows to take actions on the environment and 4)the reward signal from the environment to the agent. 
@@ -25,26 +25,46 @@ The Qlib Reinforcement Learning toolkit (QlibRL) is an RL platform for quantitat
 
 Potential Application Scenarios in Quantitative Trading
 =======================================================
-RL methods have already achieved outstanding achievement in many applications, such as game playing, resource allocating, recommendation, marketing and advertising, etc.
-Investment is always a continuous process, taking the stock market as an example, investors need to control their positions and stock holdings by one or more buying and selling behaviors, to maximize the investment returns.
-Besides, each buy and sell decision is made by investors after fully considering the overall market information and stock information. 
-From the view of an investor, the process could be described as a continuous decision-making process generated according to interaction with the market, such problems could be solved by the RL algorithms. 
-Following are some scenarios where RL can potentially be used in quantitative investment.
-
-Portfolio Construction
-----------------------
-Portfolio construction is a process of selecting securities optimally by taking a minimum risk to achieve maximum returns. With an RL-based solution, an agent allocates stocks at every time step by obtaining information for each stock and the market. The key is to develop of policy for building a portfolio and make the policy able to pick the optimal portfolio. 
+RL methods have demonstrated remarkable achievements in various applications, including game playing, resource allocation, recommendation systems, marketing, and advertising.
+In the context of investment, which involves continuous decision-making, let's consider the example of the stock market. Investors strive to optimize their investment returns by effectively managing their positions and stock holdings through various buying and selling behaviors.
+Furthermore, investors carefully evaluate market conditions and stock-specific information before making each buying or selling decision. From an investor's perspective, this process can be viewed as a continuous decision-making process driven by interactions with the market. RL algorithms offer a promising approach to tackle such challenges.
+Here are several scenarios where RL holds potential for application in quantitative investment.
 
 Order Execution
 ---------------
-As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument. Essentially, the goal of order execution is twofold: it not only requires to fulfill the whole order but also targets a more economical execution with maximizing profit gain (or minimizing capital loss). The order execution with only one order of liquidation or acquirement is called single-asset order execution.
+The order execution task is to execute orders efficiently while considering multiple factors, including optimal prices, minimizing trading costs, reducing market impact, maximizing order fullfill rates, and achieving execution within a specified time frame. RL can be applied to such tasks by incorporating these objectives into the reward function and action selection process. Specifically, the RL agent interacts with the market environment, observes the state from market information, and makes decisions on next step execution. The RL algorithm learns an optimal execution strategy through trial and error, aiming to maximize the expected cumulative reward, which incorporates the desired objectives.
 
-Considering stock investment always aim to pursue long-term maximized profits, it usually manifests as a sequential process of continuously adjusting the asset portfolios, execution for multiple orders, including order of liquidation and acquirement, brings more constraints and makes the sequence of execution for different orders should be considered, e.g. before executing an order to buy some stocks, we have to sell at least one stock. The order execution with multiple assets is called multi-asset order execution. 
+ - General Setting
+    - Environment: The environment represents the financial market where order execution takes place. It encompasses variables such as the order book dynamics, liquidity, price movements, and market conditions.
 
-According to the order execution’s trait of sequential decision-making, an RL-based solution could be applied to solve the order execution. With an RL-based solution, an agent optimizes execution strategy by interacting with the market environment. 
+    - State: The state refers to the information available to the RL agent at a given time step. It typically includes features such as the current order book state (bid-ask spread, order depth), historical price data, historical trading volume, market volatility, and any other relevant information that can aid in decision-making.
 
-With QlibRL, the RL algorithm in the above scenarios can be easily implemented.
+    - Action: The action is the decision made by the RL agent based on the observed state. In order execution, actions can include selecting the order size, price, and timing of execution.
 
-Nested Portfolio Construction and Order Executor
-------------------------------------------------
-QlibRL makes it possible to jointly optimize different levels of strategies/models/agents. Take `Nested Decision Execution Framework <https://github.com/microsoft/qlib/blob/main/examples/nested_decision_execution>`_ as an example, the optimization of order execution strategy and portfolio management strategies can interact with each other to maximize returns.
+    - Reward: The reward is a scalar signal that indicates the performance of the RL agent's action in the environment. The reward function is designed to encourage actions that lead to efficient and cost-effective order execution. It typically considers multiple objectives, such as maximizing price advantages, minimizing trading costs (including transaction fees and slippage), reducing market impact (the effect of the order on the market price) and maximizing order fullfill rates. 
+
+ - Scenarios
+    - Single-asset order execution: Single-asset order execution focuses on the task of executing a single order for a specific asset, such as a stock or a cryptocurrency. The primary objective is to execute the order efficiently while considering factors such as maximizing price advantages, minimizing trading costs, reducing market impact, and achieving a high fullfill rate. The RL agent interacts with the market environment and makes decisions on order size, price, and timing of execution for that particular asset. The goal is to learn an optimal execution strategy for the single asset, maximizing the expected cumulative reward while considering the specific dynamics and characteristics of that asset.
+
+    - Multi-asset order execution: Multi-asset order execution expands the order execution task to involve multiple assets or securities. It typically involves executing a portfolio of orders across different assets simultaneously or sequentially. Unlike single-asset order execution, the focus is not only on the execution of individual orders but also on managing the interactions and dependencies between different assets within the portfolio. The RL agent needs to make decisions on the order sizes, prices, and timings for each asset in the portfolio, considering their interdependencies, cash constraints, market conditions, and transaction costs. The goal is to learn an optimal execution strategy that balances the execution efficiency for each asset while considering the overall performance and objectives of the portfolio as a whole.
+   
+The choice of settings and RL algorithm depends on the specific requirements of the task, available data, and desired performance objectives. 
+
+Portfolio Construction
+----------------------
+Portfolio construction is a process of selecting and allocating assets in an investment portfolio. RL provides a framework to optimize portfolio management decisions by learning from interactions with the market environment and maximizing long-term returns while considering risk management.
+ - General Setting
+    - State: The state represents the current information about the market and the portfolio. It typically includes historical prices and volumes, technical indicators, and other relevant data.
+
+    - Action: The action corresponds to the decision of allocating capital to different assets in the portfolio. It determines the weights or proportions of investments in each asset.
+
+    - Reward: The reward is a metric that evaluates the performance of the portfolio. It can be defined in various ways, such as total return, risk-adjusted return, or other objectives like maximizing Sharpe ratio or minimizing drawdown.
+
+ - Scenarios
+    - Stock market: RL can be used to construct portfolios of stocks, where the agent learns to allocate capital among different stocks.
+
+    - Cryptocurrency market: RL can be applied to construct portfolios of cryptocurrencies, where the agent learns to make allocation decisions.
+
+    - Foreign exchange (Forex) market: RL can be used to construct portfolios of currency pairs, where the agent learns to allocate capital across different currencies based on exchange rate data, economic indicators, and other factors.
+
+Similarly, the choice of basic setting and algorithm depends on the specific requirements of the problem and the characteristics of the market.

docs/component/rl/toctree.rst

@@ -5,6 +5,7 @@ Reinforcement Learning in Quantitative Trading
 ========================================================================
 
 .. toctree::
+    Guidance <guidance>
     Overall <overall>
     Quick Start <quickstart>
     Framework <framework>

docs/component/workflow.rst

@@ -53,9 +53,7 @@ Below is a typical config file of ``qrun``.
             kwargs:
                 topk: 50
                 n_drop: 5
-                signal:
-                    - <MODEL>
-                    - <DATASET>
+                signal: <PRED>
         backtest:
             limit_threshold: 0.095
             account: 100000000
@@ -281,9 +279,7 @@ The following script is the configuration of `backtest` and the `strategy` used
             kwargs:
                 topk: 50
                 n_drop: 5
-                signal:
-                    - <MODEL>
-                    - <DATASET>
+                signal: <PRED>
         backtest:
             limit_threshold: 0.095
             account: 100000000

docs/introduction/introduction.rst

@@ -36,7 +36,7 @@ Name                         Description
                              the training process of models which enable algorithms controlling the
                              training process.
 
-`Learning Framework` layer   The `Forecast Model` and `Trading Agent` are learnable. They are learned
+`Learning Framework` layer   The `Forecast Model` and `Trading Agent` are trainable. They are trained
                              based on the `Learning Framework` layer and then applied to multiple scenarios
                              in `Workflow` layer. The supported learning paradigms can be categorized into
                              reinforcement learning and supervised learning.  The learning framework
@@ -51,7 +51,7 @@ Name                         Description
                              modules.  With these signals `Decision Generator` will generate the target
                              trading decisions(i.e. portfolio, orders)
                              If RL-based Strategies are adopted, the `Policy` is learned in a end-to-end way,
-                             the trading deicsions are generated directly.
+                             the trading decisions are generated directly.
                              Decisions will be executed by `Execution Env`
                              (i.e. the trading market).  There may be multiple levels of `Strategy`
                              and `Executor` (e.g. an *order executor trading strategy and intraday order executor*

docs/introduction/quick.rst

@@ -16,7 +16,7 @@ This ``Quick Start`` guide tries to demonstrate
 Installation
 ============
 
-Users can easily intsall ``Qlib`` according to the following steps:
+Users can easily install ``Qlib`` according to the following steps:
 
 - Before installing ``Qlib`` from source, users need to install some dependencies:
 

docs/requirements.txt

@@ -5,3 +5,4 @@ scipy
 scikit-learn
 pandas
 tianshou
+sphinx_rtd_theme

examples/benchmarks/ADARNN/workflow_config_adarnn_Alpha360.yaml

@@ -28,8 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL>
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/ADD/workflow_config_add_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL>
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml

@@ -36,9 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158_csi500.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360_csi500.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158_csi500.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360_csi500.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_early_stop_Alpha158.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/GATs/workflow_config_gats_Alpha158.yaml

@@ -35,9 +35,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/GATs/workflow_config_gats_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/GRU/workflow_config_gru_Alpha158.yaml

@@ -36,9 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/GRU/workflow_config_gru_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/HIST/workflow_config_hist_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -89,4 +87,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/IGMTF/workflow_config_igmtf_Alpha360.yaml

@@ -28,8 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL>
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/KRNN/README.md

@@ -0,0 +1,8 @@
+# KRNN
+* Code: [https://github.com/microsoft/FOST/blob/main/fostool/model/krnn.py](https://github.com/microsoft/FOST/blob/main/fostool/model/krnn.py)
+
+
+# Introductions about the settings/configs.
+* Torch_geometric is used in the original model in FOST, but we didn't use it.
+* make use your CUDA version matches the torch version to allow the usage of GPU, we use CUDA==10.2 and torch.__version__==1.12.1
+

examples/benchmarks/KRNN/requirements.txt

@@ -0,0 +1,2 @@
+numpy==1.23.4
+pandas==1.5.2

examples/benchmarks/KRNN/workflow_config_krnn_Alpha360.yaml

@@ -0,0 +1,89 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: KRNN
+        module_path: qlib.contrib.model.pytorch_krnn
+        kwargs:
+            fea_dim: 6
+            cnn_dim: 8
+            cnn_kernel_size: 3
+            rnn_dim: 8
+            rnn_dups: 2
+            rnn_layers: 2
+            n_epochs: 200
+            lr: 0.001
+            early_stop: 20
+            batch_size: 2000
+            metric: loss
+            GPU: 0
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config
+

examples/benchmarks/LSTM/workflow_config_lstm_Alpha158.yaml

@@ -36,9 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LSTM/workflow_config_lstm_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/multi_freq_handler.py

@@ -29,13 +29,13 @@ class Avg15minHandler(DataHandlerLP):
         fit_end_time=None,
         process_type=DataHandlerLP.PTYPE_A,
         filter_pipe=None,
-        inst_processor=None,
+        inst_processors=None,
         **kwargs,
     ):
         infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
         learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
         data_loader = Avg15minLoader(
-            config=self.loader_config(), filter_pipe=filter_pipe, freq=freq, inst_processor=inst_processor
+            config=self.loader_config(), filter_pipe=filter_pipe, freq=freq, inst_processors=inst_processors
         )
         super().__init__(
             instruments=instruments,
@@ -48,7 +48,6 @@ class Avg15minHandler(DataHandlerLP):
         )
 
     def loader_config(self):
-
         # Results for dataset: df: pd.DataFrame
         #   len(df.columns) == 6 + 6 * 16, len(df.index.get_level_values(level="datetime").unique()) == T
         #   df.columns: close0, close1, ..., close16, open0, ..., open16, ..., vwap16

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

@@ -14,8 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL> 
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_csi500.yaml

@@ -14,8 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL> 
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_multi_freq.yaml

@@ -18,7 +18,7 @@ data_handler_config: &data_handler_config
         label: day
         feature: 1min
     # with label as reference
-    inst_processor:
+    inst_processors:
         feature:
             - class: Resample1minProcessor
               module_path: features_sample.py
@@ -33,9 +33,7 @@ port_analysis_config: &port_analysis_config
         kwargs:
             topk: 50
             n_drop: 5
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
     backtest:
         verbose: False
         limit_threshold: 0.095

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360_csi500.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/workflow_config_lightgbm_configurable_dataset.yaml

@@ -29,9 +29,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/LightGBM/workflow_config_lightgbm_multi_freq.yaml

@@ -19,7 +19,7 @@ data_handler_config: &data_handler_config
         feature_15min: 1min
         feature_day: day
     # with label as reference
-    inst_processor:
+    inst_processors:
         feature_15min:
             - class: ResampleNProcessor
               module_path: features_resample_N.py
@@ -31,9 +31,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Linear/workflow_config_linear_Alpha158.yaml

@@ -27,9 +27,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Linear/workflow_config_linear_Alpha158_csi500.yaml

@@ -27,9 +27,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Linear/workflow_config_linear_Alpha158_multi_pass_bt.yaml

@@ -0,0 +1,78 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: LinearModel
+        module_path: qlib.contrib.model.linear
+        kwargs:
+            estimator: ols
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: True
+            ann_scaler: 252
+        - class: MultiPassPortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/Localformer/workflow_config_localformer_Alpha158.yaml

@@ -36,9 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Localformer/workflow_config_localformer_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/MLP/workflow_config_mlp_Alpha158.yaml

@@ -41,9 +41,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -64,8 +62,6 @@ task:
         kwargs:
             loss: mse
             lr: 0.002
-            lr_decay: 0.96
-            lr_decay_steps: 100
             optimizer: adam
             max_steps: 8000
             batch_size: 8192

examples/benchmarks/MLP/workflow_config_mlp_Alpha158_csi500.yaml

@@ -41,9 +41,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -64,8 +62,6 @@ task:
         kwargs:
             loss: mse
             lr: 0.002
-            lr_decay: 0.96
-            lr_decay_steps: 100
             optimizer: adam
             max_steps: 8000
             batch_size: 8192

examples/benchmarks/MLP/workflow_config_mlp_Alpha360.yaml

@@ -29,9 +29,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -52,8 +50,6 @@ task:
         kwargs:
             loss: mse
             lr: 0.002
-            lr_decay: 0.96
-            lr_decay_steps: 100
             optimizer: adam
             max_steps: 8000
             batch_size: 4096

examples/benchmarks/MLP/workflow_config_mlp_Alpha360_csi500.yaml

@@ -29,9 +29,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -52,8 +50,6 @@ task:
         kwargs:
             loss: mse
             lr: 0.002
-            lr_decay: 0.96
-            lr_decay_steps: 100
             optimizer: adam
             max_steps: 8000
             batch_size: 4096

examples/benchmarks/README.md

@@ -26,7 +26,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
 
 | Model Name                               | Dataset                             | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
 |------------------------------------------|-------------------------------------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
-| TCN(Shaojie Bai, et al.)                 | Alpha158                            | 0.0275±0.00 | 0.2157±0.01 | 0.0411±0.00 | 0.3379±0.01 | 0.0190±0.02       | 0.2887±0.27       | -0.1202±0.03 |
+| TCN(Shaojie Bai, et al.)                 | Alpha158                            | 0.0279±0.00 | 0.2181±0.01 | 0.0421±0.00 | 0.3429±0.01 | 0.0262±0.02       | 0.4133±0.25       | -0.1090±0.03 |
 | TabNet(Sercan O. Arik, et al.)           | Alpha158                            | 0.0204±0.01 | 0.1554±0.07 | 0.0333±0.00 | 0.2552±0.05 | 0.0227±0.04       | 0.3676±0.54       | -0.1089±0.08 |
 | Transformer(Ashish Vaswani, et al.)      | Alpha158                            | 0.0264±0.00 | 0.2053±0.02 | 0.0407±0.00 | 0.3273±0.02 | 0.0273±0.02       | 0.3970±0.26       | -0.1101±0.02 |
 | GRU(Kyunghyun Cho, et al.)               | Alpha158(with selected 20 features) | 0.0315±0.00 | 0.2450±0.04 | 0.0428±0.00 | 0.3440±0.03 | 0.0344±0.02       | 0.5160±0.25       | -0.1017±0.02 |
@@ -68,6 +68,8 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
 | TRA(Hengxu Lin, et al.)                   | Alpha360 | 0.0485±0.00 | 0.3787±0.03 | 0.0587±0.00 | 0.4756±0.03 | 0.0920±0.03       | 1.2789±0.42       | -0.0834±0.02 |
 | IGMTF(Wentao Xu, et al.)                  | Alpha360 | 0.0480±0.00 | 0.3589±0.02 | 0.0606±0.00 | 0.4773±0.01 | 0.0946±0.02       | 1.3509±0.25       | -0.0716±0.02 |
 | HIST(Wentao Xu, et al.)                   | Alpha360 | 0.0522±0.00 | 0.3530±0.01 | 0.0667±0.00 | 0.4576±0.01 | 0.0987±0.02       | 1.3726±0.27       | -0.0681±0.01 |
+| KRNN                                      | Alpha360 | 0.0173±0.01 | 0.1210±0.06 | 0.0270±0.01 | 0.2018±0.04 | -0.0465±0.05      | -0.5415±0.62      | -0.2919±0.13 |
+| Sandwich                                  | Alpha360 | 0.0258±0.00 | 0.1924±0.04 | 0.0337±0.00 | 0.2624±0.03 | 0.0005±0.03       | 0.0001±0.33       | -0.1752±0.05 |
 
 
 - The selected 20 features are based on the feature importance of a lightgbm-based model.
@@ -134,7 +136,7 @@ If you want to contribute your new models, you can follow the steps below.
     - `README.md`: a brief introduction to your models
     - `workflow_config_<model name>_<dataset>.yaml`: a configuration which can read by `qrun`. You are encouraged to run your model in all datasets.
 3. You can integrate your model as a module [in this folder](https://github.com/microsoft/qlib/tree/main/qlib/contrib/model).
-4. Please updated your results in the benchmark tables, e.g. [Alpha360](#alpha158-dataset), [Alpha158](#alpha158-dataset)(the values of each metric are the mean and std calculated based on 20 runs with different random seeds, if you don't have enough computational resource, you can ask for help in the PR).
+4. Please update your results in the above **Benchmark Tables**, e.g. [Alpha360](#alpha158-dataset), [Alpha158](#alpha158-dataset)(the values of each metric are the mean and std calculated based on **20 Runs** with different random seeds. You can accomplish the above operations through the automated [script](https://github.com/microsoft/qlib/blob/main/examples/run_all_model.py) provided by Qlib, and get the final result in the .md file. if you don't have enough computational resource, you can ask for help in the PR).
 5. Update the info in the index page in the [news list](https://github.com/microsoft/qlib#newspaper-whats-new----sparkling_heart) and [model list](https://github.com/microsoft/qlib#quant-model-paper-zoo).
 
 Finally, you can send PR for review. ([here is an example](https://github.com/microsoft/qlib/pull/1040))

examples/benchmarks/SFM/workflow_config_sfm_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Sandwich/README.md

@@ -0,0 +1,8 @@
+# Sandwich
+* Code: [https://github.com/microsoft/FOST/blob/main/fostool/model/sandwich.py](https://github.com/microsoft/FOST/blob/main/fostool/model/sandwich.py)
+
+
+# Introductions about the settings/configs.
+* Torch_geometric is used in the original model in FOST, but we didn't use it.
+make use your CUDA version matches the torch version to allow the usage of GPU, we use CUDA==10.2 and torch.version==1.12.1
+

examples/benchmarks/Sandwich/requirements.txt

@@ -0,0 +1,2 @@
+numpy==1.23.4
+pandas==1.5.2

examples/benchmarks/Sandwich/workflow_config_sandwich_Alpha360.yaml

@@ -0,0 +1,91 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: Sandwich
+        module_path: qlib.contrib.model.pytorch_sandwich
+        kwargs:
+            fea_dim: 6
+            cnn_dim_1: 16
+            cnn_dim_2: 16
+            cnn_kernel_size: 3
+            rnn_dim_1: 8
+            rnn_dim_2: 8
+            rnn_dups: 2
+            rnn_layers: 2
+            n_epochs: 200
+            lr: 0.001
+            early_stop: 20
+            batch_size: 2000
+            metric: loss
+            GPU: 0
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config
+

examples/benchmarks/TCN/workflow_config_tcn_Alpha158.yaml

@@ -36,8 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL>
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TCN/workflow_config_tcn_Alpha360.yaml

@@ -28,8 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            model: <MODEL>
-            dataset: <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TCTS/workflow_config_tcts_Alpha360.yaml

@@ -30,9 +30,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:
@@ -95,4 +93,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/TFT/data_formatters/base.py

@@ -139,7 +139,6 @@ class GenericDataFormatter(abc.ABC):
         # Sanity checks first.
         # Ensure only one ID and time column exist
         def _check_single_column(input_type):
-
             length = len([tup for tup in column_definition if tup[2] == input_type])
 
             if length != 1:

examples/benchmarks/TFT/expt_settings/configs.py

@@ -78,7 +78,6 @@ class ExperimentConfig:
 
     @property
     def hyperparam_iterations(self):
-
         return 240 if self.experiment == "volatility" else 60
 
     def make_data_formatter(self):

examples/benchmarks/TFT/libs/hyperparam_opt.py

@@ -88,7 +88,6 @@ class HyperparamOptManager:
         params_file = os.path.join(self.hyperparam_folder, "params.csv")
 
         if os.path.exists(results_file) and os.path.exists(params_file):
-
             self.results = pd.read_csv(results_file, index_col=0)
             self.saved_params = pd.read_csv(params_file, index_col=0)
 
@@ -178,7 +177,6 @@ class HyperparamOptManager:
             return parameters
 
         for _ in range(self._max_tries):
-
             parameters = _get_next()
             name = self._get_name(parameters)
 

examples/benchmarks/TFT/libs/tft_model.py

@@ -475,7 +475,6 @@ class TemporalFusionTransformer:
 
         embeddings = []
         for i in range(num_categorical_variables):
-
             embedding = tf.keras.Sequential(
                 [
                     tf.keras.layers.InputLayer([time_steps]),
@@ -680,7 +679,6 @@ class TemporalFusionTransformer:
 
         data_map = {}
         for _, sliced in data.groupby(id_col):
-
             col_mappings = {"identifier": [id_col], "time": [time_col], "outputs": [target_col], "inputs": input_cols}
 
             for k in col_mappings:
@@ -954,7 +952,6 @@ class TemporalFusionTransformer:
         """
 
         with tf.variable_scope(self.name):
-
             transformer_layer, all_inputs, attention_components = self._build_base_graph()
 
             outputs = tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(self.output_size * len(self.quantiles)))(

examples/benchmarks/TFT/workflow_config_tft_Alpha158.yaml

@@ -16,9 +16,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TRA/Reports.ipynb

@@ -25,59 +25,65 @@
     "import seaborn as sns\n",
     "import matplotlib.pyplot as plt\n",
     "import matplotlib\n",
-    "sns.set(style='white')\n",
-    "matplotlib.rcParams['pdf.fonttype'] = 42\n",
-    "matplotlib.rcParams['ps.fonttype'] = 42\n",
+    "\n",
+    "sns.set(style=\"white\")\n",
+    "matplotlib.rcParams[\"pdf.fonttype\"] = 42\n",
+    "matplotlib.rcParams[\"ps.fonttype\"] = 42\n",
     "\n",
     "from tqdm.auto import tqdm\n",
     "from joblib import Parallel, delayed\n",
     "\n",
+    "\n",
     "def func(x, N=80):\n",
     "    ret = x.ret.copy()\n",
     "    x = x.rank(pct=True)\n",
-    "    x['ret'] = ret\n",
+    "    x[\"ret\"] = ret\n",
     "    diff = x.score.sub(x.label)\n",
-    "    r = x.nlargest(N, columns='score').ret.mean()\n",
-    "    r -= x.nsmallest(N, columns='score').ret.mean()\n",
-    "    return pd.Series({\n",
-    "        'MSE': diff.pow(2).mean(), \n",
-    "        'MAE': diff.abs().mean(), \n",
-    "        'IC': x.score.corr(x.label),\n",
-    "        'R': r\n",
-    "    })\n",
-    "    \n",
+    "    r = x.nlargest(N, columns=\"score\").ret.mean()\n",
+    "    r -= x.nsmallest(N, columns=\"score\").ret.mean()\n",
+    "    return pd.Series(\n",
+    "        {\n",
+    "            \"MSE\": diff.pow(2).mean(),\n",
+    "            \"MAE\": diff.abs().mean(),\n",
+    "            \"IC\": x.score.corr(x.label),\n",
+    "            \"R\": r,\n",
+    "        }\n",
+    "    )\n",
+    "\n",
+    "\n",
     "ret = pd.read_pickle(\"data/ret.pkl\").clip(-0.1, 0.1)\n",
+    "\n",
+    "\n",
     "def backtest(fname, **kwargs):\n",
-    "    pred = pd.read_pickle(fname).loc['2018-09-21':'2020-06-30']  # test period\n",
-    "    pred['ret'] = ret\n",
+    "    pred = pd.read_pickle(fname).loc[\"2018-09-21\":\"2020-06-30\"]  # test period\n",
+    "    pred[\"ret\"] = ret\n",
     "    dates = pred.index.unique(level=0)\n",
     "    res = Parallel(n_jobs=-1)(delayed(func)(pred.loc[d], **kwargs) for d in dates)\n",
-    "    res = {\n",
-    "       dates[i]: res[i]\n",
-    "       for i in range(len(dates))\n",
-    "    }\n",
+    "    res = {dates[i]: res[i] for i in range(len(dates))}\n",
     "    res = pd.DataFrame(res).T\n",
-    "    r = res['R'].copy()\n",
+    "    r = res[\"R\"].copy()\n",
     "    r.index = pd.to_datetime(r.index)\n",
     "    r = r.reindex(pd.date_range(r.index[0], r.index[-1])).fillna(0)  # paper use 365 days\n",
     "    return {\n",
-    "        'MSE': res['MSE'].mean(),\n",
-    "        'MAE': res['MAE'].mean(),\n",
-    "        'IC': res['IC'].mean(),\n",
-    "        'ICIR': res['IC'].mean()/res['IC'].std(),\n",
-    "        'AR': r.mean()*365,\n",
-    "        'AV': r.std()*365**0.5,\n",
-    "        'SR': r.mean()/r.std()*365**0.5,\n",
-    "        'MDD': (r.cumsum().cummax() - r.cumsum()).max()\n",
+    "        \"MSE\": res[\"MSE\"].mean(),\n",
+    "        \"MAE\": res[\"MAE\"].mean(),\n",
+    "        \"IC\": res[\"IC\"].mean(),\n",
+    "        \"ICIR\": res[\"IC\"].mean() / res[\"IC\"].std(),\n",
+    "        \"AR\": r.mean() * 365,\n",
+    "        \"AV\": r.std() * 365**0.5,\n",
+    "        \"SR\": r.mean() / r.std() * 365**0.5,\n",
+    "        \"MDD\": (r.cumsum().cummax() - r.cumsum()).max(),\n",
     "    }, r\n",
     "\n",
+    "\n",
     "def fmt(x, p=3, scale=1, std=False):\n",
-    "    _fmt = '{:.%df}'%p\n",
+    "    _fmt = \"{:.%df}\" % p\n",
     "    string = _fmt.format((x.mean() if not isinstance(x, (float, np.floating)) else x) * scale)\n",
     "    if std and len(x) > 1:\n",
-    "        string += ' ('+_fmt.format(x.std()*scale)+')'\n",
+    "        string += \" (\" + _fmt.format(x.std() * scale) + \")\"\n",
     "    return string\n",
     "\n",
+    "\n",
     "def backtest_multi(files, **kwargs):\n",
     "    res = []\n",
     "    pnl = []\n",
@@ -88,14 +94,14 @@
     "    res = pd.DataFrame(res)\n",
     "    pnl = pd.concat(pnl, axis=1)\n",
     "    return {\n",
-    "        'MSE': fmt(res['MSE'], std=True),\n",
-    "        'MAE': fmt(res['MAE'], std=True),\n",
-    "        'IC': fmt(res['IC']),\n",
-    "        'ICIR': fmt(res['ICIR']),\n",
-    "        'AR': fmt(res['AR'], scale=100, p=1)+'%',\n",
-    "        'VR': fmt(res['AV'], scale=100, p=1)+'%',\n",
-    "        'SR': fmt(res['SR']),\n",
-    "        'MDD': fmt(res['MDD'], scale=100, p=1)+'%'\n",
+    "        \"MSE\": fmt(res[\"MSE\"], std=True),\n",
+    "        \"MAE\": fmt(res[\"MAE\"], std=True),\n",
+    "        \"IC\": fmt(res[\"IC\"]),\n",
+    "        \"ICIR\": fmt(res[\"ICIR\"]),\n",
+    "        \"AR\": fmt(res[\"AR\"], scale=100, p=1) + \"%\",\n",
+    "        \"VR\": fmt(res[\"AV\"], scale=100, p=1) + \"%\",\n",
+    "        \"SR\": fmt(res[\"SR\"]),\n",
+    "        \"MDD\": fmt(res[\"MDD\"], scale=100, p=1) + \"%\",\n",
     "    }, pnl"
    ]
   },
@@ -124,16 +130,20 @@
    "outputs": [],
    "source": [
     "exps = {\n",
-    "    'Linear': ['output/Linear/pred.pkl'],\n",
-    "    'LightGBM': ['output/GBDT/lr0.05_leaves128/pred.pkl'],\n",
-    "    'MLP': glob.glob('output/search/MLP/hs128_bs512_do0.3_lr0.001_seed*/pred.pkl'),\n",
-    "    'SFM': glob.glob('output/search/SFM/hs32_bs512_do0.5_lr0.001_seed*/pred.pkl'),\n",
-    "    'ALSTM': glob.glob('output/search/LSTM_Attn/hs256_bs1024_do0.1_lr0.0002_seed*/pred.pkl'),\n",
-    "    'Trans.': glob.glob('output/search/Transformer/head4_hs64_bs1024_do0.1_lr0.0002_seed*/pred.pkl'),\n",
-    "    'ALSTM+TS':glob.glob('output/LSTM_Attn_TS/hs256_bs1024_do0.1_lr0.0002_seed*/pred.pkl'),\n",
-    "    'Trans.+TS':glob.glob('output/Transformer_TS/head4_hs64_bs1024_do0.1_lr0.0002_seed*/pred.pkl'),\n",
-    "    'ALSTM+TRA(Ours)': glob.glob('output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl'),\n",
-    "    'Trans.+TRA(Ours)': glob.glob('output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb1.0_head4_hs64_bs512_do0.1_lr0.0005_seed*/pred.pkl')\n",
+    "    \"Linear\": [\"output/Linear/pred.pkl\"],\n",
+    "    \"LightGBM\": [\"output/GBDT/lr0.05_leaves128/pred.pkl\"],\n",
+    "    \"MLP\": glob.glob(\"output/search/MLP/hs128_bs512_do0.3_lr0.001_seed*/pred.pkl\"),\n",
+    "    \"SFM\": glob.glob(\"output/search/SFM/hs32_bs512_do0.5_lr0.001_seed*/pred.pkl\"),\n",
+    "    \"ALSTM\": glob.glob(\"output/search/LSTM_Attn/hs256_bs1024_do0.1_lr0.0002_seed*/pred.pkl\"),\n",
+    "    \"Trans.\": glob.glob(\"output/search/Transformer/head4_hs64_bs1024_do0.1_lr0.0002_seed*/pred.pkl\"),\n",
+    "    \"ALSTM+TS\": glob.glob(\"output/LSTM_Attn_TS/hs256_bs1024_do0.1_lr0.0002_seed*/pred.pkl\"),\n",
+    "    \"Trans.+TS\": glob.glob(\"output/Transformer_TS/head4_hs64_bs1024_do0.1_lr0.0002_seed*/pred.pkl\"),\n",
+    "    \"ALSTM+TRA(Ours)\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl\"\n",
+    "    ),\n",
+    "    \"Trans.+TRA(Ours)\": glob.glob(\n",
+    "        \"output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb1.0_head4_hs64_bs512_do0.1_lr0.0005_seed*/pred.pkl\"\n",
+    "    ),\n",
     "}"
    ]
   },
@@ -160,14 +170,8 @@
     }
    ],
    "source": [
-    "res = {\n",
-    "    name: backtest_multi(exps[name])\n",
-    "    for name in tqdm(exps)\n",
-    "}\n",
-    "report = pd.DataFrame({\n",
-    "    k: v[0]\n",
-    "    for k, v in res.items()\n",
-    "}).T"
+    "res = {name: backtest_multi(exps[name]) for name in tqdm(exps)}\n",
+    "report = pd.DataFrame({k: v[0] for k, v in res.items()}).T"
    ]
   },
   {
@@ -385,24 +389,40 @@
     }
    ],
    "source": [
-    "df = pd.read_pickle('output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb0.0_head4_hs64_bs512_do0.1_lr0.0005_seed1000/pred.pkl')\n",
-    "code = 'SH600157'\n",
-    "date = '2018-09-28'\n",
+    "df = pd.read_pickle(\n",
+    "    \"output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb0.0_head4_hs64_bs512_do0.1_lr0.0005_seed1000/pred.pkl\"\n",
+    ")\n",
+    "code = \"SH600157\"\n",
+    "date = \"2018-09-28\"\n",
     "lookbackperiod = 50\n",
     "\n",
     "prob = df.iloc[:, -3:].loc(axis=0)[:, code].reset_index(level=1, drop=True).loc[date:].iloc[:lookbackperiod]\n",
-    "pred = df.loc[:,[\"score_0\",\"score_1\",\"score_2\",\"label\"]].loc(axis=0)[:, code].reset_index(level=1, drop=True).loc[date:].iloc[:lookbackperiod]\n",
-    "e_all = pred.iloc[:,:-1].sub(pred.iloc[:,-1], axis=0).pow(2)\n",
+    "pred = (\n",
+    "    df.loc[:, [\"score_0\", \"score_1\", \"score_2\", \"label\"]]\n",
+    "    .loc(axis=0)[:, code]\n",
+    "    .reset_index(level=1, drop=True)\n",
+    "    .loc[date:]\n",
+    "    .iloc[:lookbackperiod]\n",
+    ")\n",
+    "e_all = pred.iloc[:, :-1].sub(pred.iloc[:, -1], axis=0).pow(2)\n",
     "e_all = e_all.sub(e_all.min(axis=1), axis=0)\n",
-    "e_all.columns = [r'$\\theta_%d$'%d for d in range(1, 4)]\n",
+    "e_all.columns = [r\"$\\theta_%d$\" % d for d in range(1, 4)]\n",
     "prob = pd.Series(np.argmax(prob.values, axis=1), index=prob.index).rolling(7).mean().round()\n",
     "\n",
     "fig, axes = plt.subplots(1, 2, figsize=(7, 3))\n",
-    "e_all.plot(ax=axes[0], xlabel='', rot=30)\n",
-    "prob.plot(ax=axes[1], xlabel='', rot=30, color='red', linestyle='None', marker='^', markersize=5)\n",
+    "e_all.plot(ax=axes[0], xlabel=\"\", rot=30)\n",
+    "prob.plot(\n",
+    "    ax=axes[1],\n",
+    "    xlabel=\"\",\n",
+    "    rot=30,\n",
+    "    color=\"red\",\n",
+    "    linestyle=\"None\",\n",
+    "    marker=\"^\",\n",
+    "    markersize=5,\n",
+    ")\n",
     "plt.yticks(np.array([0, 1, 2]), e_all.columns.values)\n",
-    "axes[0].set_ylabel('Predictor Loss')\n",
-    "axes[1].set_ylabel('Router Selection')\n",
+    "axes[0].set_ylabel(\"Predictor Loss\")\n",
+    "axes[1].set_ylabel(\"Router Selection\")\n",
     "plt.tight_layout()\n",
     "# plt.savefig('select.pdf', bbox_inches='tight')\n",
     "plt.show()"
@@ -428,10 +448,18 @@
    "outputs": [],
    "source": [
     "exps = {\n",
-    "    'Random': glob.glob('output/search/LSTM_Attn_tra/K10_traHs16_traSrcNONE_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl'),\n",
-    "    'LR': glob.glob('output/search/LSTM_Attn_tra/K10_traHs16_traSrcLR_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl'),\n",
-    "    'TPE': glob.glob('output/search/LSTM_Attn_tra/K10_traHs16_traSrcTPE_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl'),\n",
-    "    'LR+TPE': glob.glob('output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl')\n",
+    "    \"Random\": glob.glob(\n",
+    "        \"output/search/LSTM_Attn_tra/K10_traHs16_traSrcNONE_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl\"\n",
+    "    ),\n",
+    "    \"LR\": glob.glob(\n",
+    "        \"output/search/LSTM_Attn_tra/K10_traHs16_traSrcLR_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl\"\n",
+    "    ),\n",
+    "    \"TPE\": glob.glob(\n",
+    "        \"output/search/LSTM_Attn_tra/K10_traHs16_traSrcTPE_traLamb1.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl\"\n",
+    "    ),\n",
+    "    \"LR+TPE\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/pred.pkl\"\n",
+    "    ),\n",
     "}"
    ]
   },
@@ -456,14 +484,8 @@
     }
    ],
    "source": [
-    "res = {\n",
-    "    name: backtest_multi(exps[name])\n",
-    "    for name in tqdm(exps)\n",
-    "}\n",
-    "report = pd.DataFrame({\n",
-    "    k: v[0]\n",
-    "    for k, v in res.items()\n",
-    "}).T"
+    "res = {name: backtest_multi(exps[name]) for name in tqdm(exps)}\n",
+    "report = pd.DataFrame({k: v[0] for k, v in res.items()}).T"
    ]
   },
   {
@@ -597,18 +619,22 @@
     }
    ],
    "source": [
-    "a = pd.read_pickle('output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb0.0_head4_hs64_bs512_do0.1_lr0.0005_seed3000/pred.pkl')\n",
-    "b = pd.read_pickle('output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb2.0_head4_hs64_bs512_do0.1_lr0.0005_seed3000/pred.pkl')\n",
+    "a = pd.read_pickle(\n",
+    "    \"output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb0.0_head4_hs64_bs512_do0.1_lr0.0005_seed3000/pred.pkl\"\n",
+    ")\n",
+    "b = pd.read_pickle(\n",
+    "    \"output/search/finetune/Transformer_tra/K3_traHs16_traSrcLR_TPE_traLamb2.0_head4_hs64_bs512_do0.1_lr0.0005_seed3000/pred.pkl\"\n",
+    ")\n",
     "a = a.iloc[:, -3:]\n",
     "b = b.iloc[:, -3:]\n",
     "b = np.eye(3)[b.values.argmax(axis=1)]\n",
     "a = np.eye(3)[a.values.argmax(axis=1)]\n",
     "\n",
-    "res = pd.DataFrame({\n",
-    "    'with OT': b.sum(axis=0) / b.sum(),\n",
-    "    'without OT': a.sum(axis=0)/ a.sum()  \n",
-    "},index=[r'$\\theta_1$',r'$\\theta_2$',r'$\\theta_3$'])\n",
-    "res.plot.bar(rot=30, figsize=(5, 4), color=['b', 'g'])\n",
+    "res = pd.DataFrame(\n",
+    "    {\"with OT\": b.sum(axis=0) / b.sum(), \"without OT\": a.sum(axis=0) / a.sum()},\n",
+    "    index=[r\"$\\theta_1$\", r\"$\\theta_2$\", r\"$\\theta_3$\"],\n",
+    ")\n",
+    "res.plot.bar(rot=30, figsize=(5, 4), color=[\"b\", \"g\"])\n",
     "del a, b"
    ]
   },
@@ -633,11 +659,19 @@
    "outputs": [],
    "source": [
     "exps = {\n",
-    "    'K=1': glob.glob('output/search/LSTM_Attn/hs256_bs1024_do0.1_lr0.0002_seed*/info.json'),\n",
-    "    'K=3': glob.glob('output/search/finetune/LSTM_Attn_tra/K3_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json'),\n",
-    "    'K=5': glob.glob('output/search/finetune/LSTM_Attn_tra/K5_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json'),\n",
-    "    'K=10': glob.glob('output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json'),\n",
-    "    'K=20': glob.glob('output/search/finetune/LSTM_Attn_tra/K20_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json')\n",
+    "    \"K=1\": glob.glob(\"output/search/LSTM_Attn/hs256_bs1024_do0.1_lr0.0002_seed*/info.json\"),\n",
+    "    \"K=3\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K3_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json\"\n",
+    "    ),\n",
+    "    \"K=5\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K5_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json\"\n",
+    "    ),\n",
+    "    \"K=10\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K10_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json\"\n",
+    "    ),\n",
+    "    \"K=20\": glob.glob(\n",
+    "        \"output/search/finetune/LSTM_Attn_tra/K20_traHs16_traSrcLR_TPE_traLamb2.0_hs256_bs1024_do0.1_lr0.0001_seed*/info.json\"\n",
+    "    ),\n",
     "}"
    ]
   },
@@ -649,16 +683,11 @@
    "source": [
     "report = dict()\n",
     "for k, v in exps.items():\n",
-    "    \n",
     "    tmp = dict()\n",
     "    for fname in v:\n",
     "        with open(fname) as f:\n",
     "            info = json.load(f)\n",
-    "        tmp[fname] = (\n",
-    "        {\n",
-    "            \"IC\":info[\"metric\"][\"IC\"],\n",
-    "            \"MSE\":info[\"metric\"][\"MSE\"]\n",
-    "        })\n",
+    "        tmp[fname] = {\"IC\": info[\"metric\"][\"IC\"], \"MSE\": info[\"metric\"][\"MSE\"]}\n",
     "    tmp = pd.DataFrame(tmp).T\n",
     "    report[k] = tmp.mean()\n",
     "report = pd.DataFrame(report).T"
@@ -681,13 +710,14 @@
     }
    ],
    "source": [
-    "fig, axes = plt.subplots(1, 2, figsize=(6,3)); axes = axes.flatten()\n",
-    "report['IC'].plot.bar(rot=30, ax=axes[0])\n",
+    "fig, axes = plt.subplots(1, 2, figsize=(6, 3))\n",
+    "axes = axes.flatten()\n",
+    "report[\"IC\"].plot.bar(rot=30, ax=axes[0])\n",
     "axes[0].set_ylim(0.045, 0.062)\n",
-    "axes[0].set_title('IC performance')\n",
-    "report['MSE'].astype(float).plot.bar(rot=30, ax=axes[1], color='green')\n",
+    "axes[0].set_title(\"IC performance\")\n",
+    "report[\"MSE\"].astype(float).plot.bar(rot=30, ax=axes[1], color=\"green\")\n",
     "axes[1].set_ylim(0.155, 0.1585)\n",
-    "axes[1].set_title('MSE performance')\n",
+    "axes[1].set_title(\"MSE performance\")\n",
     "plt.tight_layout()\n",
     "# plt.savefig('sensitivity.pdf')"
    ]

examples/benchmarks/TRA/example.py

@@ -6,7 +6,6 @@ from qlib.utils import init_instance_by_config
 
 
 def main(seed, config_file="configs/config_alstm.yaml"):
-
     # set random seed
     with open(config_file) as f:
         config = yaml.safe_load(f)
@@ -30,7 +29,6 @@ def main(seed, config_file="configs/config_alstm.yaml"):
 
 
 if __name__ == "__main__":
-
     # set params from cmd
     parser = argparse.ArgumentParser(allow_abbrev=False)
     parser.add_argument("--seed", type=int, default=1000, help="random seed")

examples/benchmarks/TRA/src/dataset.py

@@ -96,7 +96,6 @@ class MTSDatasetH(DatasetH):
         drop_last=False,
         **kwargs,
     ):
-
         assert horizon > 0, "please specify `horizon` to avoid data leakage"
 
         self.seq_len = seq_len
@@ -111,7 +110,6 @@ class MTSDatasetH(DatasetH):
         super().__init__(handler, segments, **kwargs)
 
     def setup_data(self, handler_kwargs: dict = None, **kwargs):
-
         super().setup_data()
 
         # change index to <code, date>

examples/benchmarks/TRA/src/model.py

@@ -45,7 +45,6 @@ class TRAModel(Model):
         avg_params=True,
         **kwargs,
     ):
-
         np.random.seed(seed)
         torch.manual_seed(seed)
 
@@ -93,7 +92,6 @@ class TRAModel(Model):
         self.global_step = -1
 
     def train_epoch(self, data_set):
-
         self.model.train()
         self.tra.train()
 
@@ -146,7 +144,6 @@ class TRAModel(Model):
         return total_loss
 
     def test_epoch(self, data_set, return_pred=False):
-
         self.model.eval()
         self.tra.eval()
         data_set.eval()
@@ -204,7 +201,6 @@ class TRAModel(Model):
         return metrics, preds
 
     def fit(self, dataset, evals_result=dict()):
-
         train_set, valid_set, test_set = dataset.prepare(["train", "valid", "test"])
 
         best_score = -1
@@ -328,7 +324,6 @@ class TRAModel(Model):
 
 
 class LSTM(nn.Module):
-
     """LSTM Model
 
     Args:
@@ -380,7 +375,6 @@ class LSTM(nn.Module):
             self.output_size = hidden_size
 
     def forward(self, x):
-
         x = self.input_drop(x)
 
         if self.training and self.noise_level > 0:
@@ -419,7 +413,6 @@ class PositionalEncoding(nn.Module):
 
 
 class Transformer(nn.Module):
-
     """Transformer Model
 
     Args:
@@ -464,7 +457,6 @@ class Transformer(nn.Module):
         self.output_size = hidden_size
 
     def forward(self, x):
-
         x = self.input_drop(x)
 
         if self.training and self.noise_level > 0:
@@ -481,7 +473,6 @@ class Transformer(nn.Module):
 
 
 class TRA(nn.Module):
-
     """Temporal Routing Adaptor (TRA)
 
     TRA takes historical prediction errors & latent representation as inputs,
@@ -514,7 +505,6 @@ class TRA(nn.Module):
         self.predictors = nn.Linear(input_size, num_states)
 
     def forward(self, hidden, hist_loss):
-
         preds = self.predictors(hidden)
 
         if self.num_states == 1:

examples/benchmarks/TRA/workflow_config_tra_Alpha158.yaml

@@ -57,9 +57,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TRA/workflow_config_tra_Alpha158_full.yaml

@@ -51,9 +51,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TRA/workflow_config_tra_Alpha360.yaml

@@ -51,9 +51,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TabNet/workflow_config_TabNet_Alpha158.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TabNet/workflow_config_TabNet_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Transformer/workflow_config_transformer_Alpha158.yaml

@@ -36,9 +36,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Transformer/workflow_config_transformer_Alpha360.yaml

@@ -28,9 +28,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/XGBoost/workflow_config_xgboost_Alpha158.yaml

@@ -14,9 +14,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/XGBoost/workflow_config_xgboost_Alpha360.yaml

@@ -21,9 +21,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks_dynamic/DDG-DA/Makefile

@@ -0,0 +1,4 @@
+.PHONY: clean
+
+clean:
+	-rm -r *.pkl mlruns || true

examples/benchmarks_dynamic/DDG-DA/README.md

@@ -16,12 +16,12 @@ Though the dataset is different, the conclusion remains the same. By applying `D
 # Run the Code
 Users can try `DDG-DA` by running the following command:
 ```bash
-    python workflow.py run_all
+    python workflow.py run
 ```
 
 The default forecasting models are `Linear`. Users can choose other forecasting models by changing the `forecast_model` parameter when `DDG-DA` initializes. For example, users can try `LightGBM` forecasting models by running the following command:
 ```bash
-    python workflow.py --forecast_model="gbdt" run_all
+    python workflow.py --conf_path=../workflow_config_lightgbm_Alpha158.yaml run
 ```
 
 # Results

examples/benchmarks_dynamic/DDG-DA/vis_data.py

@@ -0,0 +1,107 @@
+import pickle
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+sns.set(color_codes=True)
+plt.rcParams["font.sans-serif"] = "SimHei"
+plt.rcParams["axes.unicode_minus"] = False
+from tqdm.auto import tqdm
+
+# tqdm.pandas()  # for progress_apply
+# %matplotlib inline
+# %load_ext autoreload
+
+
+# # Meta Input
+
+# +
+with open("./internal_data_s20.pkl", "rb") as f:
+    data = pickle.load(f)
+
+data.data_ic_df.columns.names = ["start_date", "end_date"]
+
+data_sim = data.data_ic_df.droplevel(axis=1, level="end_date")
+
+data_sim.index.name = "test datetime"
+# -
+
+plt.figure(figsize=(40, 20))
+sns.heatmap(data_sim)
+
+plt.figure(figsize=(40, 20))
+sns.heatmap(data_sim.rolling(20).mean())
+
+# # Meta Model
+
+from qlib import auto_init
+
+auto_init()
+from qlib.workflow import R
+
+exp = R.get_exp(experiment_name="DDG-DA")
+meta_rec = exp.list_recorders(rtype="list", max_results=1)[0]
+meta_m = meta_rec.load_object("model")
+
+pd.DataFrame(meta_m.tn.twm.linear.weight.detach().numpy()).T[0].plot()
+
+pd.DataFrame(meta_m.tn.twm.linear.weight.detach().numpy()).T[0].rolling(5).mean().plot()
+
+# # Meta Output
+
+# +
+with open("./tasks_s20.pkl", "rb") as f:
+    tasks = pickle.load(f)
+
+task_df = {}
+for t in tasks:
+    test_seg = t["dataset"]["kwargs"]["segments"]["test"]
+    if None not in test_seg:
+        # The last rolling is skipped.
+        task_df[test_seg] = t["reweighter"].time_weight
+task_df = pd.concat(task_df)
+
+task_df.index.names = ["OS_start", "OS_end", "IS_start", "IS_end"]
+task_df = task_df.droplevel(["OS_end", "IS_end"])
+task_df = task_df.unstack("OS_start")
+# -
+
+plt.figure(figsize=(40, 20))
+sns.heatmap(task_df.T)
+
+plt.figure(figsize=(40, 20))
+sns.heatmap(task_df.rolling(10).mean().T)
+
+# # Sub Models
+#
+# NOTE:
+# - this section assumes that the model is Linear model!!
+# - Other models does not support this analysis
+
+exp = R.get_exp(experiment_name="rolling_ds")
+
+
+def show_linear_weight(exp):
+    coef_df = {}
+    for r in exp.list_recorders("list"):
+        t = r.load_object("task")
+        if None in t["dataset"]["kwargs"]["segments"]["test"]:
+            continue
+        m = r.load_object("params.pkl")
+        coef_df[t["dataset"]["kwargs"]["segments"]["test"]] = pd.Series(m.coef_)
+
+    coef_df = pd.concat(coef_df)
+
+    coef_df.index.names = ["test_start", "test_end", "coef_idx"]
+
+    coef_df = coef_df.droplevel("test_end").unstack("coef_idx").T
+
+    plt.figure(figsize=(40, 20))
+    sns.heatmap(coef_df)
+    plt.show()
+
+
+show_linear_weight(R.get_exp(experiment_name="rolling_ds"))
+
+show_linear_weight(R.get_exp(experiment_name="rolling_models"))

examples/benchmarks_dynamic/DDG-DA/workflow.py

@@ -1,259 +1,40 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 from pathlib import Path
-from qlib.model.meta.task import MetaTask
-from qlib.contrib.meta.data_selection.model import MetaModelDS
-from qlib.contrib.meta.data_selection.dataset import InternalData, MetaDatasetDS
-from qlib.data.dataset.handler import DataHandlerLP
+from typing import Union
 
-import pandas as pd
 import fire
-import sys
-import pickle
+
 from qlib import auto_init
-from qlib.model.trainer import TrainerR
-from qlib.utils import init_instance_by_config
-from qlib.workflow import R
+from qlib.contrib.rolling.ddgda import DDGDA
 from qlib.tests.data import GetData
 
 DIRNAME = Path(__file__).absolute().resolve().parent
-sys.path.append(str(DIRNAME.parent / "baseline"))
-from rolling_benchmark import RollingBenchmark  # NOTE: sys.path is changed for import RollingBenchmark
+BENCH_DIR = DIRNAME.parent / "baseline"
 
 
-class DDGDA:
-    """
-    please run `python workflow.py run_all` to run the full workflow of the experiment
+class DDGDABench(DDGDA):
+    # The config in the README.md
+    CONF_LIST = [
+        BENCH_DIR / "workflow_config_linear_Alpha158.yaml",
+        BENCH_DIR / "workflow_config_lightgbm_Alpha158.yaml",
+    ]
 
-    **NOTE**
-    before running the example, please clean your previous results with following command
-    - `rm -r mlruns`
-    """
+    DEFAULT_CONF = CONF_LIST[0]  # Linear by default due to efficiency
 
-    def __init__(self, sim_task_model="linear", forecast_model="linear"):
-        self.step = 20
-        # NOTE:
-        # the horizon must match the meaning in the base task template
-        self.horizon = 20
-        self.meta_exp_name = "DDG-DA"
-        self.sim_task_model = sim_task_model  # The model to capture the distribution of data.
-        self.forecast_model = forecast_model  # downstream forecasting models' type
+    def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwargs) -> None:
+        # This code is for being compatible with the previous old code
+        conf_path = Path(conf_path)
+        super().__init__(conf_path=conf_path, horizon=horizon, working_dir=DIRNAME, **kwargs)
 
-    def get_feature_importance(self):
-        # this must be lightGBM, because it needs to get the feature importance
-        rb = RollingBenchmark(model_type="gbdt")
-        task = rb.basic_task()
-
-        with R.start(experiment_name="feature_importance"):
-            model = init_instance_by_config(task["model"])
-            dataset = init_instance_by_config(task["dataset"])
-            model.fit(dataset)
-
-        fi = model.get_feature_importance()
-
-        # Because the model use numpy instead of dataframe for training lightgbm
-        # So the we must use following extra steps to get the right feature importance
-        df = dataset.prepare(segments=slice(None), col_set="feature", data_key=DataHandlerLP.DK_R)
-        cols = df.columns
-        fi_named = {cols[int(k.split("_")[1])]: imp for k, imp in fi.to_dict().items()}
-
-        return pd.Series(fi_named)
-
-    def dump_data_for_proxy_model(self):
-        """
-        Dump data for training meta model.
-        The meta model will be trained upon the proxy forecasting model.
-        This dataset is for the proxy forecasting model.
-        """
-        topk = 30
-        fi = self.get_feature_importance()
-        col_selected = fi.nlargest(topk)
-
-        rb = RollingBenchmark(model_type=self.sim_task_model)
-        task = rb.basic_task()
-        dataset = init_instance_by_config(task["dataset"])
-        prep_ds = dataset.prepare(slice(None), col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
-
-        feature_df = prep_ds["feature"]
-        label_df = prep_ds["label"]
-
-        feature_selected = feature_df.loc[:, col_selected.index]
-
-        feature_selected = feature_selected.groupby("datetime").apply(lambda df: (df - df.mean()).div(df.std()))
-        feature_selected = feature_selected.fillna(0.0)
-
-        df_all = {
-            "label": label_df.reindex(feature_selected.index),
-            "feature": feature_selected,
-        }
-        df_all = pd.concat(df_all, axis=1)
-        df_all.to_pickle(DIRNAME / "fea_label_df.pkl")
-
-        # dump data in handler format for aligning the interface
-        handler = DataHandlerLP(
-            data_loader={
-                "class": "qlib.data.dataset.loader.StaticDataLoader",
-                "kwargs": {"config": DIRNAME / "fea_label_df.pkl"},
-            }
-        )
-        handler.to_pickle(DIRNAME / "handler_proxy.pkl", dump_all=True)
-
-    @property
-    def _internal_data_path(self):
-        return DIRNAME / f"internal_data_s{self.step}.pkl"
-
-    def dump_meta_ipt(self):
-        """
-        Dump data for training meta model.
-        This function will dump the input data for meta model
-        """
-        # According to the experiments, the choice of the model type is very important for achieving good results
-        rb = RollingBenchmark(model_type=self.sim_task_model)
-        sim_task = rb.basic_task()
-
-        if self.sim_task_model == "gbdt":
-            sim_task["model"].setdefault("kwargs", {}).update({"early_stopping_rounds": None, "num_boost_round": 150})
-
-        exp_name_sim = f"data_sim_s{self.step}"
-
-        internal_data = InternalData(sim_task, self.step, exp_name=exp_name_sim)
-        internal_data.setup(trainer=TrainerR)
-
-        with self._internal_data_path.open("wb") as f:
-            pickle.dump(internal_data, f)
-
-    def train_meta_model(self):
-        """
-        training a meta model based on a simplified linear proxy model;
-        """
-
-        # 1) leverage the simplified proxy forecasting model to train meta model.
-        # - Only the dataset part is important, in current version of meta model will integrate the
-        rb = RollingBenchmark(model_type=self.sim_task_model)
-        sim_task = rb.basic_task()
-        proxy_forecast_model_task = {
-            # "model": "qlib.contrib.model.linear.LinearModel",
-            "dataset": {
-                "class": "qlib.data.dataset.DatasetH",
-                "kwargs": {
-                    "handler": f"file://{(DIRNAME / 'handler_proxy.pkl').absolute()}",
-                    "segments": {
-                        "train": ("2008-01-01", "2010-12-31"),
-                        "test": ("2011-01-01", sim_task["dataset"]["kwargs"]["segments"]["test"][1]),
-                    },
-                },
-            },
-            # "record": ["qlib.workflow.record_temp.SignalRecord"]
-        }
-        # the proxy_forecast_model_task will be used to create meta tasks.
-        # The test date of first task will be 2011-01-01. Each test segment will be about 20days
-        # The tasks include all training tasks and test tasks.
-
-        # 2) preparing meta dataset
-        kwargs = dict(
-            task_tpl=proxy_forecast_model_task,
-            step=self.step,
-            segments=0.62,  # keep test period consistent with the dataset yaml
-            trunc_days=1 + self.horizon,
-            hist_step_n=30,
-            fill_method="max",
-            rolling_ext_days=0,
-        )
-        # NOTE:
-        # the input of meta model (internal data) are shared between proxy model and final forecasting model
-        # but their task test segment are not aligned! It worked in my previous experiment.
-        # So the misalignment will not affect the effectiveness of the method.
-        with self._internal_data_path.open("rb") as f:
-            internal_data = pickle.load(f)
-        md = MetaDatasetDS(exp_name=internal_data, **kwargs)
-
-        # 3) train and logging meta model
-        with R.start(experiment_name=self.meta_exp_name):
-            R.log_params(**kwargs)
-            mm = MetaModelDS(step=self.step, hist_step_n=kwargs["hist_step_n"], lr=0.001, max_epoch=200, seed=43)
-            mm.fit(md)
-            R.save_objects(model=mm)
-
-    @property
-    def _task_path(self):
-        return DIRNAME / f"tasks_s{self.step}.pkl"
-
-    def meta_inference(self):
-        """
-        Leverage meta-model for inference:
-        - Given
-            - baseline tasks
-            - input for meta model(internal data)
-            - meta model (its learnt knowledge on proxy forecasting model is expected to transfer to normal forecasting model)
-        """
-        # 1) get meta model
-        exp = R.get_exp(experiment_name=self.meta_exp_name)
-        rec = exp.list_recorders(rtype=exp.RT_L)[0]
-        meta_model: MetaModelDS = rec.load_object("model")
-
-        # 2)
-        # we are transfer to knowledge of meta model to final forecasting tasks.
-        # Create MetaTaskDataset for the final forecasting tasks
-        # Aligning the setting of it to the MetaTaskDataset when training Meta model is necessary
-
-        # 2.1) get previous config
-        param = rec.list_params()
-        trunc_days = int(param["trunc_days"])
-        step = int(param["step"])
-        hist_step_n = int(param["hist_step_n"])
-        fill_method = param.get("fill_method", "max")
-
-        rb = RollingBenchmark(model_type=self.forecast_model)
-        task_l = rb.create_rolling_tasks()
-
-        # 2.2) create meta dataset for final dataset
-        kwargs = dict(
-            task_tpl=task_l,
-            step=step,
-            segments=0.0,  # all the tasks are for testing
-            trunc_days=trunc_days,
-            hist_step_n=hist_step_n,
-            fill_method=fill_method,
-            task_mode=MetaTask.PROC_MODE_TRANSFER,
-        )
-
-        with self._internal_data_path.open("rb") as f:
-            internal_data = pickle.load(f)
-        mds = MetaDatasetDS(exp_name=internal_data, **kwargs)
-
-        # 3) meta model make inference and get new qlib task
-        new_tasks = meta_model.inference(mds)
-        with self._task_path.open("wb") as f:
-            pickle.dump(new_tasks, f)
-
-    def train_and_eval_tasks(self):
-        """
-        Training the tasks generated by meta model
-        Then evaluate it
-        """
-        with self._task_path.open("rb") as f:
-            tasks = pickle.load(f)
-        rb = RollingBenchmark(rolling_exp="rolling_ds", model_type=self.forecast_model)
-        rb.train_rolling_tasks(tasks)
-        rb.ens_rolling()
-        rb.update_rolling_rec()
-
-    def run_all(self):
-        # 1) file: handler_proxy.pkl
-        self.dump_data_for_proxy_model()
-        # 2)
-        # file: internal_data_s20.pkl
-        # mlflow: data_sim_s20, models for calculating meta_ipt
-        self.dump_meta_ipt()
-        # 3) meta model will be stored in `DDG-DA`
-        self.train_meta_model()
-        # 4) new_tasks are saved in "tasks_s20.pkl" (reweighter is added)
-        self.meta_inference()
-        # 5) load the saved tasks and train model
-        self.train_and_eval_tasks()
+        for f in self.CONF_LIST:
+            if conf_path.samefile(f):
+                break
+        else:
+            self.logger.warning("Model type is not in the benchmark!")
 
 
 if __name__ == "__main__":
     GetData().qlib_data(exists_skip=True)
     auto_init()
-    fire.Fire(DDGDA)
+    fire.Fire(DDGDABench)

examples/benchmarks_dynamic/README.md

@@ -4,15 +4,23 @@ So adapting the forecasting models/strategies to market dynamics is very importa
 
 The table below shows the performances of different solutions on different forecasting models.
 
-## Alpha158 dataset
+## Alpha158 Dataset
+Here is the [crowd sourced version of qlib data](data_collector/crowd_source/README.md): https://github.com/chenditc/investment_data/releases
+```bash
+wget https://github.com/chenditc/investment_data/releases/download/20220720/qlib_bin.tar.gz
+mkdir -p ~/.qlib/qlib_data/cn_data
+tar -zxvf qlib_bin.tar.gz -C ~/.qlib/qlib_data/cn_data --strip-components=2
+rm -f qlib_bin.tar.gz
+```
 
 | Model Name       | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown |
-|------------------|---------|----|------|---------|-----------|-------------------|-------------------|--------------|
-| RR[Linear]       |Alpha158 |0.088|0.570|0.102    |0.622      |0.077              |1.175              |-0.086        |
-| DDG-DA[Linear]   |Alpha158 |0.093|0.622|0.106    |0.670      |0.085              |1.213              |-0.093        |
-| RR[LightGBM]     |Alpha158 |0.079|0.566|0.088    |0.592      |0.075              |1.226              |-0.096        |
-| DDG-DA[LightGBM] |Alpha158 |0.084|0.639|0.093    |0.664      |0.099              |1.442              |-0.071        |
+|------------------|---------|------|------|---------|-----------|-------------------|-------------------|--------------|
+| RR[Linear]       |Alpha158 |0.0945|0.5989|0.1069   |0.6495     |0.0857             |1.3682             |-0.0986       |
+| DDG-DA[Linear]   |Alpha158 |0.0983|0.6157|0.1108   |0.6646     |0.0764             |1.1904             |-0.0769       |
+| RR[LightGBM]     |Alpha158 |0.0816|0.5887|0.0912   |0.6263     |0.0771             |1.3196             |-0.0909       |
+| DDG-DA[LightGBM] |Alpha158 |0.0878|0.6185|0.0975   |0.6524     |0.1261             |2.0096             |-0.0744       |
 
 - The label horizon of the `Alpha158` dataset is set to 20.
 - The rolling time intervals are set to 20 trading days.
 - The test rolling periods are from January 2017 to August 2020.
+- The results are based on the crowd-sourced version. The Yahoo version of qlib data does not contain `VWAP`, so all related factors are missing and filled with 0, which leads to a rank-deficient matrix (a matrix does not have full rank) and makes lower-level optimization of DDG-DA can not be solved.

examples/benchmarks_dynamic/baseline/README.md

@@ -5,11 +5,12 @@ This is the framework of periodically Rolling Retrain (RR) forecasting models. R
 ## Run the Code
 Users can try RR by running the following command:
 ```bash
-    python rolling_benchmark.py run_all
+    python rolling_benchmark.py run
 ```
 
 The default forecasting models are `Linear`. Users can choose other forecasting models by changing the `model_type` parameter.
 For example, users can try `LightGBM` forecasting models by running the following command:
 ```bash
-    python rolling_benchmark.py --model_type="gbdt" run_all
-```
+    python rolling_benchmark.py --conf_path=workflow_config_lightgbm_Alpha158.yaml run
+
+```

examples/benchmarks_dynamic/baseline/rolling_benchmark.py

@@ -1,111 +1,33 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
-from qlib.model.ens.ensemble import RollingEnsemble
-from qlib.utils import init_instance_by_config
-import fire
-import yaml
-from qlib import auto_init
 from pathlib import Path
-from tqdm.auto import tqdm
-from qlib.model.trainer import TrainerR
-from qlib.workflow import R
+from typing import Union
+
+import fire
+
+from qlib import auto_init
+from qlib.contrib.rolling.base import Rolling
 from qlib.tests.data import GetData
 
 DIRNAME = Path(__file__).absolute().resolve().parent
-from qlib.workflow.task.gen import task_generator, RollingGen
-from qlib.workflow.task.collect import RecorderCollector
-from qlib.workflow.record_temp import PortAnaRecord, SigAnaRecord
 
 
-class RollingBenchmark:
-    """
-    **NOTE**
-    before running the example, please clean your previous results with following command
-    - `rm -r mlruns`
+class RollingBenchmark(Rolling):
+    # The config in the README.md
+    CONF_LIST = [DIRNAME / "workflow_config_linear_Alpha158.yaml", DIRNAME / "workflow_config_lightgbm_Alpha158.yaml"]
 
-    """
+    DEFAULT_CONF = CONF_LIST[0]
 
-    def __init__(self, rolling_exp="rolling_models", model_type="linear") -> None:
-        self.step = 20
-        self.horizon = 20
-        self.rolling_exp = rolling_exp
-        self.model_type = model_type
+    def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwargs) -> None:
+        # This code is for being compatible with the previous old code
+        conf_path = Path(conf_path)
+        super().__init__(conf_path=conf_path, horizon=horizon, **kwargs)
 
-    def basic_task(self):
-        """For fast training rolling"""
-        if self.model_type == "gbdt":
-            conf_path = DIRNAME.parent.parent / "benchmarks" / "LightGBM" / "workflow_config_lightgbm_Alpha158.yaml"
-            # dump the processed data on to disk for later loading to speed up the processing
-            h_path = DIRNAME / "lightgbm_alpha158_handler_horizon{}.pkl".format(self.horizon)
-        elif self.model_type == "linear":
-            conf_path = DIRNAME.parent.parent / "benchmarks" / "Linear" / "workflow_config_linear_Alpha158.yaml"
-            h_path = DIRNAME / "linear_alpha158_handler_horizon{}.pkl".format(self.horizon)
+        for f in self.CONF_LIST:
+            if conf_path.samefile(f):
+                break
         else:
-            raise AssertionError("Model type is not supported!")
-        with conf_path.open("r") as f:
-            conf = yaml.safe_load(f)
-
-        # modify dataset horizon
-        conf["task"]["dataset"]["kwargs"]["handler"]["kwargs"]["label"] = [
-            "Ref($close, -{}) / Ref($close, -1) - 1".format(self.horizon + 1)
-        ]
-
-        task = conf["task"]
-
-        if not h_path.exists():
-            h_conf = task["dataset"]["kwargs"]["handler"]
-            h = init_instance_by_config(h_conf)
-            h.to_pickle(h_path, dump_all=True)
-
-        task["dataset"]["kwargs"]["handler"] = f"file://{h_path}"
-        task["record"] = ["qlib.workflow.record_temp.SignalRecord"]
-        return task
-
-    def create_rolling_tasks(self):
-        task = self.basic_task()
-        task_l = task_generator(
-            task, RollingGen(step=self.step, trunc_days=self.horizon + 1)
-        )  # the last two days should be truncated to avoid information leakage
-        return task_l
-
-    def train_rolling_tasks(self, task_l=None):
-        if task_l is None:
-            task_l = self.create_rolling_tasks()
-        trainer = TrainerR(experiment_name=self.rolling_exp)
-        trainer(task_l)
-
-    COMB_EXP = "rolling"
-
-    def ens_rolling(self):
-        rc = RecorderCollector(
-            experiment=self.rolling_exp,
-            artifacts_key=["pred", "label"],
-            process_list=[RollingEnsemble()],
-            # rec_key_func=lambda rec: (self.COMB_EXP, rec.info["id"]),
-            artifacts_path={"pred": "pred.pkl", "label": "label.pkl"},
-        )
-        res = rc()
-        with R.start(experiment_name=self.COMB_EXP):
-            R.log_params(exp_name=self.rolling_exp)
-            R.save_objects(**{"pred.pkl": res["pred"], "label.pkl": res["label"]})
-
-    def update_rolling_rec(self):
-        """
-        Evaluate the combined rolling results
-        """
-        for rid, rec in R.list_recorders(experiment_name=self.COMB_EXP).items():
-            for rt_cls in SigAnaRecord, PortAnaRecord:
-                rt = rt_cls(recorder=rec, skip_existing=True)
-                rt.generate()
-        print(f"Your evaluation results can be found in the experiment named `{self.COMB_EXP}`.")
-
-    def run_all(self):
-        # the results will be  save in mlruns.
-        # 1) each rolling task is saved in rolling_models
-        self.train_rolling_tasks()
-        # 2) combined rolling tasks and evaluation results are saved in rolling
-        self.ens_rolling()
-        self.update_rolling_rec()
+            self.logger.warning("Model type is not in the benchmark!")
 
 
 if __name__ == "__main__":

examples/benchmarks_dynamic/baseline/workflow_config_lightgbm_Alpha158.yaml

@@ -0,0 +1,71 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks_dynamic/baseline/workflow_config_linear_Alpha158.yaml

@@ -0,0 +1,77 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: LinearModel
+        module_path: qlib.contrib.model.linear
+        kwargs:
+            estimator: ridge
+            alpha: 0.05
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: True
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/highfreq/highfreq_handler.py

@@ -14,7 +14,6 @@ class HighFreqHandler(DataHandlerLP):
         fit_end_time=None,
         drop_raw=True,
     ):
-
         infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
         learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
 

examples/highfreq/workflow.py

@@ -18,7 +18,6 @@ from highfreq_ops import get_calendar_day, DayLast, FFillNan, BFillNan, Date, Se
 
 
 class HighfreqWorkflow:
-
     SPEC_CONF = {"custom_ops": [DayLast, FFillNan, BFillNan, Date, Select, IsNull, Cut], "expression_cache": None}
 
     MARKET = "all"