Update version

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* fix: upgrade the method of installing LightGBM on MacOS

* add: comments

* test: build package && check package

* test: build package && check package

* test: build package && check package

* optimize yml

.dockerignore

@@ -0,0 +1,8 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+.env
+.git
+

.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/python-publish.yml

@@ -12,53 +12,54 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, macos-11]
-        # FIXME:  macos-latest will raise error now.
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
+        os: [windows-latest, macos-13, macos-latest]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        exclude:
+          - os: macos-13
+            python-version: "3.11"
+          - os: macos-13
+            python-version: "3.12"
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python
-      uses: actions/setup-python@v2
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install setuptools wheel twine
-    - name: Build wheel on Windows
+        make dev
+    - name: Build wheel on ${{ matrix.os }}
       run: |
-        pip install numpy
-        pip install cython
-        python setup.py bdist_wheel
-    - name: Build and publish
+        make build
+    - name: Upload to PyPi
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
-        twine upload dist/*
-        
+        twine check dist/*.whl
+        twine upload dist/*.whl --verbose
+
   deploy_with_manylinux:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
     - name: Build wheel on Linux
-      uses: RalfG/python-wheels-manylinux-build@v0.3.1-manylinux2010_x86_64
+      uses: RalfG/python-wheels-manylinux-build@v0.7.1-manylinux2014_x86_64
       with:
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-versions: 'cp37-cp37m cp38-cp38'
+        python-versions: 'cp38-cp38 cp39-cp39 cp310-cp310 cp311-cp311 cp312-cp312'
         build-requirements: 'numpy cython'
-    - name: Set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.7
     - name: Install dependencies
       run: |
-        pip install twine  
-    - name: Build and publish
+        python -m pip install twine
+    - name: Upload to PyPi
       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
+        twine check dist/pyqlib-*-manylinux*.whl
+        twine upload dist/pyqlib-*-manylinux*.whl --verbose

.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

@@ -13,44 +13,53 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
+        os: [windows-latest, ubuntu-24.04, ubuntu-22.04, macos-14, macos-15]
+        # In github action, using python 3.7, pip install will not match the latest version of the package.
+        # Also, python 3.7 is no longer supported from macos-14, and will be phased out from macos-13 in the near future.
+        # All things considered, we have removed python 3.7.
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - name: Test qlib from pip
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
     - name: Update pip to the latest version
       run: |
         python -m pip install --upgrade pip
+      
+    # Will cancel this step when the next qlib version is released. The current qlib version is: 0.9.6
+    - name: Installing pywinpt for windows
+      if: ${{ matrix.os == 'windows-latest' }}
+      run: |
+        python -m pip install pywinpty --only-binary=:all:
 
+    # # joblib was released on 2025-05-04 with version 1.5.0, in which _backend_args was removed and replaced by _backend_kwargs.
+    # This change caused the application to fail, so the version of joblib is restricted here. 
+    # This restriction will be removed in the next release. The current qlib version is: 0.9.6
     - 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"
+        python -m pip install "joblib<=1.4.2"
 
     - name: Install Lightgbm for MacOS
-      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
       run: |
-        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
-        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
-        # FIX MacOS error: Segmentation fault
-        # reference: https://github.com/microsoft/LightGBM/issues/4229
-        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/fb8323f2b170bd4ae97e1bac9bf3e2983af3fdb0/Formula/libomp.rb
-        brew unlink libomp
-        brew install libomp.rb
+        brew update
+        brew install libomp || brew reinstall libomp
+        python -m pip install --no-binary=:all: lightgbm
 
+    # When the new version is released it should be changed to:
+    # python -m qlib.cli.data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
     - 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

@@ -14,32 +14,32 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
+        os: [windows-latest, ubuntu-24.04, ubuntu-22.04, macos-14, macos-15]
+        # In github action, using python 3.7, pip install will not match the latest version of the package.
+        # Also, python 3.7 is no longer supported from macos-14, and will be phased out from macos-13 in the near future.
+        # All things considered, we have removed python 3.7.
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - name: Test qlib from source
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
     - name: Update pip to the latest version
-      # pip release version 23.1 on Apr.15 2023, CI failed to run, Please refer to #1495 ofr detailed logs.
-      # The pip version has been temporarily fixed to 23.0.1
       run: |
-        python -m pip install pip==23.0.1
+        python -m pip install --upgrade pip
 
     - name: Installing pytorch for macos
-      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
       run: |
         python -m pip install torch torchvision torchaudio
 
     - name: Installing pytorch for ubuntu
-      if: ${{ matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-22.04' }}
+      if: ${{ matrix.os == 'ubuntu-24.04' || matrix.os == 'ubuntu-22.04' }}
       run: |
         python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
 
@@ -50,111 +50,73 @@ jobs:
 
     - name: Set up Python tools
       run: |
-        python -m pip install --upgrade cython
-        python -m pip install -e .[dev]
+        make dev
 
     - name: Lint with Black
       run: |
-        black . -l 120 --check --diff
+        make black
 
     - name: Make html with sphinx
+      # Since read the docs builds on ubuntu 22.04, we only need to test that the build passes on ubuntu 22.04.
+      if: ${{ matrix.os == 'ubuntu-22.04' }}
       run: |
-        cd docs 
-        sphinx-build -W --keep-going -b html . _build
-        cd ..
+        make docs-gen
 
-    # Check Qlib with pylint
-    # TODO: These problems we will solve in the future. Important among them are: W0221, W0223, W0237, E1102
-      # C0103: invalid-name
-      # C0209: consider-using-f-string
-      # R0402: consider-using-from-import
-      # R1705: no-else-return
-      # R1710: inconsistent-return-statements
-      # R1725: super-with-arguments
-      # R1735: use-dict-literal
-      # W0102: dangerous-default-value
-      # W0212: protected-access
-      # W0221: arguments-differ
-      # W0223: abstract-method
-      # W0231: super-init-not-called
-      # W0237: arguments-renamed
-      # W0612: unused-variable
-      # W0621: redefined-outer-name
-      # W0622: redefined-builtin
-      # FIXME: specify exception type
-      # W0703: broad-except
-      # W1309: f-string-without-interpolation
-      # E1102: not-callable
-      # E1136: unsubscriptable-object
-    # References for parameters: https://github.com/PyCQA/pylint/issues/4577#issuecomment-1000245962
-    # We use sys.setrecursionlimit(2000) to make the recursion depth larger to ensure that pylint works properly (the default recursion depth is 1000).
     - 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)"
+        make pylint
 
-    # The following flake8 error codes were ignored:
-      # E501 line too long
-        # Description: We have used black to limit the length of each line to 120.
-      # F541 f-string is missing placeholders
-        # Description: The same thing is done when using pylint for detection.
-      # E266 too many leading '#' for block comment
-        # Description: To make the code more readable, a lot of "#" is used.
-        # This error code appears centrally in:
-          # qlib/backtest/executor.py
-          # qlib/data/ops.py
-          # qlib/utils/__init__.py
-      # E402 module level import not at top of file
-        # Description: There are times when module level import is not available at the top of the file.
-      # W503 line break before binary operator
-        # Description: Since black formats the length of each line of code, it has to perform a line break when a line of arithmetic is too long.
-      # E731 do not assign a lambda expression, use a def
-        # Description: Restricts the use of lambda expressions, but at some point lambda expressions are required.
-      # E203 whitespace before ':'
-        # Description: If there is whitespace before ":", it cannot pass the black check.
     - name: Check Qlib with flake8
       run: |
-        flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 --per-file-ignores="__init__.py:F401,F403" qlib
+        make flake8
 
-    # https://github.com/python/mypy/issues/10600
     - name: Check Qlib with mypy
       run: |
-        mypy qlib --install-types --non-interactive || true
-        mypy qlib --verbose
+        make mypy
     
     - 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}$'
+        make nbqa
 
     - 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' }}
+      if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
       run: |
-        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
-        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
-        # FIX MacOS error: Segmentation fault
-        # reference: https://github.com/microsoft/LightGBM/issues/4229
-        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/fb8323f2b170bd4ae97e1bac9bf3e2983af3fdb0/Formula/libomp.rb
-        brew unlink libomp
-        brew install libomp.rb
+        brew update
+        brew install libomp || brew reinstall libomp
+        python -m pip install --no-binary=:all: lightgbm
 
-    # 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
+        make nbconvert
 
     - name: Test workflow by config (install from source)
       run: |
         python -m pip install numba
-        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+        python qlib/cli/run.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
 
-    - name: Unit tests with Pytest
+    - name: Unit tests with Pytest (MacOS)
+      if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
+      uses: nick-fields/retry@v2
+      with:
+        timeout_minutes: 60
+        max_attempts: 3
+        command: |
+          # Limit the number of threads in various libraries to prevent Segmentation faults caused by OpenMP multithreading conflicts under macOS.
+          export OMP_NUM_THREADS=1  # Limit the number of OpenMP threads
+          export MKL_NUM_THREADS=1  # Limit the number of Intel MKL threads
+          export NUMEXPR_NUM_THREADS=1  # Limit the number of NumExpr threads
+          export OPENBLAS_NUM_THREADS=1  # Limit the number of OpenBLAS threads
+          export VECLIB_MAXIMUM_THREADS=1  # Limit the number of macOS Accelerate/vecLib threads
+          cd tests
+          python -m pytest . -m "not slow" --durations=0
+
+    - name: Unit tests with Pytest (Ubuntu and Windows)
+      if: ${{ matrix.os != 'macos-13' && matrix.os != 'macos-14' && matrix.os != 'macos-15' }}
       uses: nick-fields/retry@v2
       with:
         timeout_minutes: 60

.github/workflows/test_qlib_from_source_slow.yml

@@ -14,41 +14,37 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
+        os: [windows-latest, ubuntu-24.04, ubuntu-22.04, macos-14, macos-15]
+        # In github action, using python 3.7, pip install will not match the latest version of the package.
+        # Also, python 3.7 is no longer supported from macos-14, and will be phased out from macos-13 in the near future.
+        # All things considered, we have removed python 3.7.
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - name: Test qlib from source slow
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
     - name: Set up Python tools
-      # pip release version 23.1 on Apr.15 2023, CI failed to run, Please refer to #1495 ofr detailed logs.
-      # The pip version has been temporarily fixed to 23.0.1
       run: |
-        python -m pip install pip==23.0.1
-        pip install --upgrade cython numpy
-        pip install -e .[dev]
+        make dev
 
     - 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
 
+    # install.sh file contents from: https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh
+    # brew_install.sh file contents from: https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh
     - name: Install Lightgbm for MacOS
-      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
       run: |
-        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
-        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
-        # FIX MacOS error: Segmentation fault
-        # reference: https://github.com/microsoft/LightGBM/issues/4229
-        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/fb8323f2b170bd4ae97e1bac9bf3e2983af3fdb0/Formula/libomp.rb
-        brew unlink libomp
-        brew install libomp.rb
+        brew update
+        brew install libomp || brew reinstall libomp
+        python -m pip install --no-binary=:all: lightgbm
 
     - name: Unit tests with Pytest
       uses: nick-fields/retry@v2

.gitignore

@@ -49,3 +49,4 @@ tags
 
 ./pretrain
 .idea/
+.aider*

.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: "3.8"
+
 # 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

Dockerfile

@@ -0,0 +1,31 @@
+FROM continuumio/miniconda3:latest
+
+WORKDIR /qlib
+
+COPY . .
+
+RUN apt-get update && \
+    apt-get install -y build-essential
+
+RUN conda create --name qlib_env python=3.8 -y
+RUN echo "conda activate qlib_env" >> ~/.bashrc
+ENV PATH /opt/conda/envs/qlib_env/bin:$PATH
+
+RUN python -m pip install --upgrade pip
+
+RUN python -m pip install numpy==1.23.5
+RUN python -m pip install pandas==1.5.3
+RUN python -m pip install importlib-metadata==5.2.0
+RUN python -m pip install "cloudpickle<3"
+RUN python -m pip install scikit-learn==1.3.2
+
+RUN python -m pip install cython packaging tables matplotlib statsmodels
+RUN python -m pip install pybind11 cvxpy
+
+ARG IS_STABLE="yes"
+
+RUN if [ "$IS_STABLE" = "yes" ]; then \
+        python -m pip install pyqlib; \
+    else \
+        python setup.py install; \
+    fi

MANIFEST.in

@@ -1 +1,6 @@
-include qlib/VERSION.txt
+exclude tests/*
+include qlib/*
+include qlib/*/*
+include qlib/*/*/*
+include qlib/*/*/*/*
+include qlib/*/*/*/*/*

Makefile

@@ -0,0 +1,209 @@
+.PHONY: clean deepclean prerequisite dependencies lightgbm rl develop lint docs package test analysis all install dev black pylint flake8 mypy nbqa nbconvert lint build upload docs-gen
+#You can modify it according to your terminal
+SHELL := /bin/bash
+
+########################################################################################
+# Variables
+########################################################################################
+
+# Documentation target directory, will be adapted to specific folder for readthedocs.
+PUBLIC_DIR := $(shell [ "$$READTHEDOCS" = "True" ] && echo "$$READTHEDOCS_OUTPUT/html" || echo "public")
+
+SO_DIR := qlib/data/_libs
+SO_FILES := $(wildcard $(SO_DIR)/*.so)
+
+ifeq ($(OS),Windows_NT)
+    IS_WINDOWS = true
+else
+    IS_WINDOWS = false
+endif
+
+########################################################################################
+# Development Environment Management
+########################################################################################
+# Remove common intermediate files.
+clean:
+	-rm -rf \
+		$(PUBLIC_DIR) \
+		qlib/data/_libs/*.cpp \
+		qlib/data/_libs/*.so \
+		mlruns \
+		public \
+		build \
+		.coverage \
+		.mypy_cache \
+		.pytest_cache \
+		.ruff_cache \
+		Pipfile* \
+		coverage.xml \
+		dist \
+		release-notes.md
+
+	find . -name '*.egg-info' -print0 | xargs -0 rm -rf
+	find . -name '*.pyc' -print0 | xargs -0 rm -f
+	find . -name '*.swp' -print0 | xargs -0 rm -f
+	find . -name '.DS_Store' -print0 | xargs -0 rm -f
+	find . -name '__pycache__' -print0 | xargs -0 rm -rf
+
+# Remove pre-commit hook, virtual environment alongside itermediate files.
+deepclean: clean
+	if command -v pre-commit > /dev/null 2>&1; then pre-commit uninstall --hook-type pre-push; fi
+	if command -v pipenv >/dev/null 2>&1 && pipenv --venv >/dev/null 2>&1; then pipenv --rm; fi
+
+# Prerequisite section
+# What this code does is compile two Cython modules, rolling and expanding, using setuptools and Cython,
+# and builds them as binary expansion modules that can be imported directly into Python.
+# Since pyproject.toml can't do that, we compile it here.
+
+# pywinpty as a dependency of jupyter on windows, if you use pip install pywinpty installation,
+# will first download the tar.gz file, and then locally compiled and installed,
+# this will lead to some unnecessary trouble, so we choose to install the compiled whl file, to avoid trouble.
+prerequisite:
+	@if [ -n "$(SO_FILES)" ]; then \
+		echo "Shared library files exist, skipping build."; \
+	else \
+		echo "No shared library files found, building..."; \
+		pip install --upgrade setuptools wheel; \
+		python -m pip install cython numpy; \
+		python -c "from setuptools import setup, Extension; from Cython.Build import cythonize; import numpy; extensions = [Extension('qlib.data._libs.rolling', ['qlib/data/_libs/rolling.pyx'], language='c++', include_dirs=[numpy.get_include()]), Extension('qlib.data._libs.expanding', ['qlib/data/_libs/expanding.pyx'], language='c++', include_dirs=[numpy.get_include()])]; setup(ext_modules=cythonize(extensions, language_level='3'), script_args=['build_ext', '--inplace'])"; \
+	fi
+
+	@if [ "$(IS_WINDOWS)" = "true" ]; then \
+		python -m pip install pywinpty --only-binary=:all:; \
+	fi
+
+# Install the package in editable mode.
+dependencies:
+	python -m pip install -e .
+
+lightgbm:
+	python -m pip install lightgbm --prefer-binary
+
+rl:
+	python -m pip install -e .[rl]
+
+develop:
+	python -m pip install -e .[dev]
+
+lint:
+	python -m pip install -e .[lint]
+
+docs:
+	python -m pip install -e .[docs]
+
+package:
+	python -m pip install -e .[package]
+
+test:
+	python -m pip install -e .[test]
+
+analysis:
+	python -m pip install -e .[analysis]
+
+all:
+	python -m pip install -e .[pywinpty,dev,lint,docs,package,test,analysis,rl]
+
+install: prerequisite dependencies
+
+dev: prerequisite all
+
+########################################################################################
+# Lint and pre-commit
+########################################################################################
+
+# Check lint with black.
+black:
+	black . -l 120 --check --diff
+
+# Check code folder with pylint.
+# TODO: These problems we will solve in the future. Important among them are: W0221, W0223, W0237, E1102
+# 	C0103: invalid-name
+# 	C0209: consider-using-f-string
+# 	R0402: consider-using-from-import
+# 	R1705: no-else-return
+# 	R1710: inconsistent-return-statements
+# 	R1725: super-with-arguments
+# 	R1735: use-dict-literal
+# 	W0102: dangerous-default-value
+# 	W0212: protected-access
+# 	W0221: arguments-differ
+# 	W0223: abstract-method
+# 	W0231: super-init-not-called
+# 	W0237: arguments-renamed
+# 	W0612: unused-variable
+# 	W0621: redefined-outer-name
+# 	W0622: redefined-builtin
+# 	FIXME: specify exception type
+# 	W0703: broad-except
+# 	W1309: f-string-without-interpolation
+# 	E1102: not-callable
+# 	E1136: unsubscriptable-object
+# 	W4904: deprecated-class
+# 	R0917: too-many-positional-arguments
+# 	E1123: unexpected-keyword-arg
+# References for disable error: https://pylint.pycqa.org/en/latest/user_guide/messages/messages_overview.html
+# We use sys.setrecursionlimit(2000) to make the recursion depth larger to ensure that pylint works properly (the default recursion depth is 1000).
+# References for parameters: https://github.com/PyCQA/pylint/issues/4577#issuecomment-1000245962
+pylint:
+	pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,W4904,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1730,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,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,E1123,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)"
+
+# Check code with flake8.
+# The following flake8 error codes were ignored:
+# E501 line too long
+# 	Description: We have used black to limit the length of each line to 120.
+# F541 f-string is missing placeholders
+# 	Description: The same thing is done when using pylint for detection.
+# E266 too many leading '#' for block comment
+# 	Description: To make the code more readable, a lot of "#" is used.
+#         This error code appears centrally in:
+# 			qlib/backtest/executor.py
+# 			qlib/data/ops.py
+# 			qlib/utils/__init__.py
+# E402 module level import not at top of file
+# 	Description: There are times when module level import is not available at the top of the file.
+# W503 line break before binary operator
+# 	Description: Since black formats the length of each line of code, it has to perform a line break when a line of arithmetic is too long.
+# E731 do not assign a lambda expression, use a def
+# 	Description: Restricts the use of lambda expressions, but at some point lambda expressions are required.
+# E203 whitespace before ':'
+# 	Description: If there is whitespace before ":", it cannot pass the black check.
+flake8:
+	flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 --per-file-ignores="__init__.py:F401,F403" qlib
+
+# Check code with mypy.
+# https://github.com/python/mypy/issues/10600
+mypy:
+	mypy qlib --install-types --non-interactive
+	mypy qlib --verbose
+
+# Check ipynb with nbqa.
+nbqa:
+	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}'
+
+# Check ipynb with nbconvert.(Run after data downloads)
+# TODO: Add more ipynb files in future
+nbconvert:
+	jupyter nbconvert --to notebook --execute examples/workflow_by_code.ipynb
+
+lint: black pylint flake8 mypy nbqa
+
+########################################################################################
+# Package
+########################################################################################
+
+# Build the package.
+build:
+	python -m build --wheel
+
+# Upload the package.
+upload:
+	python -m twine upload dist/*
+
+########################################################################################
+# Documentation
+########################################################################################
+
+docs-gen:
+	python -m sphinx.cmd.build -W docs $(PUBLIC_DIR)

README.md

@@ -8,9 +8,46 @@
 [![Join the chat at https://gitter.im/Microsoft/qlib](https://badges.gitter.im/Microsoft/qlib.svg)](https://gitter.im/Microsoft/qlib?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
 
 ## :newspaper: **What's NEW!**     :sparkling_heart: 
+
 Recent released features
+
+### Introducing <a href="https://github.com/microsoft/RD-Agent"><img src="docs/_static/img/rdagent_logo.png" alt="RD_Agent" style="height: 2em"></a>: LLM-Based Autonomous Evolving Agents for Industrial Data-Driven R&D
+
+We are excited to announce the release of **RD-Agent**📢, a powerful tool that supports automated factor mining and model optimization in quant investment R&D.
+
+RD-Agent is now available on [GitHub](https://github.com/microsoft/RD-Agent), and we welcome your star🌟!
+
+To learn more, please visit our [♾️Demo page](https://rdagent.azurewebsites.net/). Here, you will find demo videos in both English and Chinese to help you better understand the scenario and usage of RD-Agent.
+
+We have prepared several demo videos for you:
+| Scenario | Demo video (English) | Demo video (中文) |
+| --                      | ------    | ------    |
+| Quant Factor Mining | [Link](https://rdagent.azurewebsites.net/factor_loop?lang=en) | [Link](https://rdagent.azurewebsites.net/factor_loop?lang=zh) |
+| Quant Factor Mining from reports | [Link](https://rdagent.azurewebsites.net/report_factor?lang=en) | [Link](https://rdagent.azurewebsites.net/report_factor?lang=zh) |
+| Quant Model Optimization | [Link](https://rdagent.azurewebsites.net/model_loop?lang=en) | [Link](https://rdagent.azurewebsites.net/model_loop?lang=zh) |
+
+- 📃**Paper**: [R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization](https://arxiv.org/abs/2505.15155)
+- 👾**Code**: https://github.com/microsoft/RD-Agent/
+```BibTeX
+@misc{li2025rdagentquant,
+    title={R\&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization},
+    author={Yuante Li and Xu Yang and Xiao Yang and Minrui Xu and Xisen Wang and Weiqing Liu and Jiang Bian},
+    year={2025},
+    eprint={2505.15155},
+    archivePrefix={arXiv},
+    primaryClass={cs.AI}
+}
+```
+![image](https://github.com/user-attachments/assets/3198bc10-47ba-4ee0-8a8e-46d5ce44f45d)
+
+***
+
 | Feature | Status |
 | --                      | ------    |
+| [R&D-Agent-Quant](https://arxiv.org/abs/2505.15155) Published | Apply R&D-Agent to Qlib for quant trading | 
+| BPQP for End-to-end learning | 📈Coming soon!([Under review](https://github.com/microsoft/qlib/pull/1863)) |
+| 🔥LLM-driven Auto Quant Factory🔥 | 🚀 Released in [♾️RD-Agent](https://github.com/microsoft/RD-Agent) on Aug 8, 2024 |
+| 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 |
@@ -39,7 +76,7 @@ Recent released features
 Features released before 2021 are not listed here.
 
 <p align="center">
-  <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
+  <img src="docs/_static/img/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.
@@ -90,6 +127,7 @@ 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>
@@ -130,17 +168,17 @@ Here is a quick **[demo](https://terminalizer.com/view/3f24561a4470)** shows how
 ## Installation
 
 This table demonstrates the supported Python version of `Qlib`:
-|               | install with pip           | install from source  | plot |
-| ------------- |:---------------------:|:--------------------:|:----:|
-| Python 3.7    | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
+|               | install with pip      | install from source  |        plot        |
+| ------------- |:---------------------:|:--------------------:|:------------------:|
 | Python 3.8    | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
-| Python 3.9    | :x:                   | :heavy_check_mark:   | :x: |
+| Python 3.9    | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
+| Python 3.10   | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
+| Python 3.11   | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
+| Python 3.12   | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
 
 **Note**: 
-1. **Conda** is suggested for managing your Python environment.
-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. 
+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.
+2. 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 3.8 or higher, or use `conda`'s Python to install ``Qlib`` from source.
 
 ### Install with pip
 Users can easily install ``Qlib`` by pip according to the following command.
@@ -158,28 +196,43 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 
   ```bash
   pip install numpy
-  pip install --upgrade  cython
+  pip install --upgrade cython
   ```
 
 * Clone the repository and install ``Qlib`` as follows.
     ```bash
     git clone https://github.com/microsoft/qlib.git && cd qlib
-    pip install .
+    pip install .  # `pip install -e .[dev]` is recommended for development. check details in docs/developer/code_standard_and_dev_guide.rst
     ```
-  **Note**:  You can install Qlib with `python setup.py install` as well. But it is not the recommended approach. It will skip `pip` and cause obscure problems. For example, **only** the command ``pip install .`` **can** overwrite the stable version installed by ``pip install pyqlib``, while the command ``python setup.py install`` **can't**.
 
 **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 official 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 latest data.
+```bash
+wget https://github.com/chenditc/investment_data/releases/latest/download/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=1
+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
   ```bash
   # get 1d data
-  python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+  python -m qlib.cli.data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
 
   # get 1min data
-  python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --region cn --interval 1min
+  python -m qlib.cli.data qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --region cn --interval 1min
 
   ```
 
@@ -226,6 +279,16 @@ We recommend users to prepare their own data if they have a high-quality dataset
       * *trading_date*: start of trading day
       * *end_date*: end of trading day(not included)
 
+### Checking the health of the data
+  * We provide a script to check the health of the data, you can run the following commands to check whether the data is healthy or not.
+    ```
+    python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data
+    ```
+  * Of course, you can also add some parameters to adjust the test results, such as this.
+    ```
+    python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data --missing_data_num 30055 --large_step_threshold_volume 94485 --large_step_threshold_price 20
+    ```
+  * If you want more information about `check_data_health`, please refer to the [documentation](https://qlib.readthedocs.io/en/latest/component/data.html#checking-the-health-of-the-data).
 
 <!-- 
 - Run the initialization code and get stock data:
@@ -254,6 +317,38 @@ We recommend users to prepare their own data if they have a high-quality dataset
   ```
  -->
 
+## Docker images
+1. Pulling a docker image from a docker hub repository
+    ```bash
+    docker pull pyqlib/qlib_image_stable:stable
+    ```
+2. Start a new Docker container
+    ```bash
+    docker run -it --name <container name> -v <Mounted local directory>:/app qlib_image_stable
+    ```
+3. At this point you are in the docker environment and can run the qlib scripts. An example:
+    ```bash
+    >>> python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+    >>> python qlib/cli/run.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+    ```
+4. Exit the container
+    ```bash
+    >>> exit
+    ```
+5. Restart the container
+    ```bash
+    docker start -i -a <container name>
+    ```
+6. Stop the container
+    ```bash
+    docker stop <container name>
+    ```
+7. Delete the container
+    ```bash
+    docker rm <container name>
+    ```
+8. If you want to know more information, please refer to the [documentation](https://qlib.readthedocs.io/en/latest/developer/how_to_build_image.html).
+
 ## Auto Quant Research Workflow
 Qlib provides a tool named `qrun` to run the whole workflow automatically (including building dataset, training models, backtest and evaluation). You can start an auto quant research workflow and have a graphical reports analysis according to the following steps: 
 
@@ -264,9 +359,9 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
     ```
     If users want to use `qrun` under debug mode, please use the following command:
     ```bash
-    python -m pdb qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+    python -m pdb qlib/cli/run.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
     ```
-    The result of `qrun` is as follows, please refer to [Intraday Trading](https://qlib.readthedocs.io/en/latest/component/backtest.html) for more details about the result. 
+    The result of `qrun` is as follows, please refer to [docs](https://qlib.readthedocs.io/en/latest/component/strategy.html#result) for more explanations about the result. 
 
     ```bash
 
@@ -287,22 +382,22 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
     ```
     Here are detailed documents for `qrun` and [workflow](https://qlib.readthedocs.io/en/latest/component/workflow.html).
 
-2. Graphical Reports Analysis: Run `examples/workflow_by_code.ipynb` with `jupyter notebook` to get graphical reports
+2. Graphical Reports Analysis: First, run `python -m pip install .[analysis]` to install the required dependencies. Then run `examples/workflow_by_code.ipynb` with `jupyter notebook` to get graphical reports. 
     - Forecasting signal (model prediction) analysis
       - Cumulative Return of groups
-      ![Cumulative Return](http://fintech.msra.cn/images_v070/analysis/analysis_model_cumulative_return.png?v=0.1)
+      ![Cumulative Return](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_cumulative_return.png)
       - Return distribution
-      ![long_short](http://fintech.msra.cn/images_v070/analysis/analysis_model_long_short.png?v=0.1)
+      ![long_short](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_long_short.png)
       - Information Coefficient (IC)
-      ![Information Coefficient](http://fintech.msra.cn/images_v070/analysis/analysis_model_IC.png?v=0.1)
-      ![Monthly IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_monthly_IC.png?v=0.1)
-      ![IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_NDQ.png?v=0.1)
+      ![Information Coefficient](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_IC.png)
+      ![Monthly IC](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_monthly_IC.png)
+      ![IC](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_NDQ.png)
       - Auto Correlation of forecasting signal (model prediction)
-      ![Auto Correlation](http://fintech.msra.cn/images_v070/analysis/analysis_model_auto_correlation.png?v=0.1)
+      ![Auto Correlation](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/analysis_model_auto_correlation.png)
 
     - Portfolio analysis
       - Backtest return
-      ![Report](http://fintech.msra.cn/images_v070/analysis/report.png?v=0.1)
+      ![Report](https://github.com/microsoft/qlib/blob/main/docs/_static/img/analysis/report.png)
       <!-- 
       - Score IC
       ![Score IC](docs/_static/img/score_ic.png)
@@ -319,7 +414,7 @@ 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
@@ -353,10 +448,12 @@ 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.
@@ -380,6 +477,14 @@ python run_all_model.py run 10
 
 It also provides the API to run specific models at once. For more use cases, please refer to the file's [docstrings](examples/run_all_model.py). 
 
+### Break change
+In `pandas`, `group_key` is one of the parameters of the `groupby` method. From version 1.5 to 2.0 of `pandas`, the default value of `group_key` has been changed from `no default` to `True`, which will cause qlib to report an error during operation. So we set `group_key=False`, but it doesn't guarantee that some programmes will run correctly, including:
+* qlib\examples\rl_order_execution\scripts\gen_training_orders.py
+* qlib\examples\benchmarks\TRA\src\dataset.MTSDatasetH.py
+* qlib\examples\benchmarks\TFT\tft.py
+
+
+
 ## [Adapting to Market Dynamics](examples/benchmarks_dynamic)
 
 Due to the non-stationary nature of the environment of the financial market, the data distribution may change in different periods, which makes the performance of models build on training data decays in the future test data.
@@ -389,6 +494,17 @@ 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`:
 
@@ -468,7 +584,7 @@ Qlib data are stored in a compact format, which is efficient to be combined into
 Join IM discussion groups:
 |[Gitter](https://gitter.im/Microsoft/qlib)|
 |----|
-|![image](http://fintech.msra.cn/images_v070/qrcode/gitter_qr.png)|
+|![image](https://github.com/microsoft/qlib/blob/main/docs/_static/img/qrcode/gitter_qr.png)|
 
 # Contributing
 We appreciate all contributions and thank all the contributors!
@@ -504,7 +620,7 @@ You can find some impefect implementation in Qlib by  `rg 'TODO|FIXME' qlib`
  
 If you would like to become one of Qlib's maintainers to contribute more (e.g. help merge PR, triage issues), please contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).  We are glad to help to upgrade your permission.
 
-## Licence
+## License
 Most contributions require you to agree to a
 Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
 the right to use your contribution. For details, visit https://cla.opensource.microsoft.com.

build_docker_image.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+docker_user="your_dockerhub_username"
+
+read -p "Do you want to build the nightly version of the qlib image? (default is stable) (yes/no): " answer;
+answer=$(echo "$answer" | tr '[:upper:]' '[:lower:]')
+
+if [ "$answer" = "yes" ]; then
+    # Build the nightly version of the qlib image
+    docker build --build-arg IS_STABLE=no -t qlib_image -f ./Dockerfile .
+    image_tag="nightly"
+else
+    # Build the stable version of the qlib image
+    docker build -t qlib_image -f ./Dockerfile .
+    image_tag="stable"
+fi
+
+read -p "Is it uploaded to docker hub? (default is no) (yes/no): " answer;
+answer=$(echo "$answer" | tr '[:upper:]' '[:lower:]')
+
+if [ "$answer" = "yes" ]; then
+    # Log in to Docker Hub
+    # If you are a new docker hub user, please verify your email address before proceeding with this step.
+    docker login
+    # Tag the Docker image
+    docker tag qlib_image "$docker_user/qlib_image:$image_tag"
+    # Push the Docker image to Docker Hub
+    docker push "$docker_user/qlib_image:$image_tag"
+else
+    echo "Not uploaded to docker hub."
+fi

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. 
@@ -108,10 +108,10 @@ Automatic update of daily frequency data
 
 
 
-Converting CSV Format into Qlib Format
---------------------------------------
+Converting CSV and Parquet Format into Qlib Format
+--------------------------------------------------
 
-``Qlib`` has provided the script ``scripts/dump_bin.py`` to convert **any** data in CSV format into `.bin` files (``Qlib`` format) as long as they are in the correct format.
+``Qlib`` has provided the script ``scripts/dump_bin.py`` to convert **any** data in CSV or Parquet format into `.bin` files (``Qlib`` format) as long as they are in the correct format.
 
 Besides downloading the prepared demo data, users could download demo data directly from the Collector as follows for reference to the CSV format.
 Here are some example:
@@ -119,64 +119,67 @@ 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
 
     python scripts/data_collector/yahoo/collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1min --region CN --start 2021-05-20 --end 2021-05-23 --delay 0.1 --interval 1min --limit_nums 10
 
-Users can also provide their own data in CSV format. However, the CSV data **must satisfies** following criterions:
+Users can also provide their own data in CSV or Parquet format. However, the data **must satisfies** following criterions:
 
-- CSV file is named after a specific stock *or* the CSV file includes a column of the stock name
+- CSV or Parquet file is named after a specific stock *or* the CSV or Parquet file includes a column of the stock name
 
-    - Name the CSV file after a stock: `SH600000.csv`, `AAPL.csv` (not case sensitive).
+    - Name the CSV or Parquet file after a stock: `SH600000.csv`, `AAPL.csv` or `SH600000.parquet`, `AAPL.parquet` (not case sensitive).
 
-    - CSV file includes a column of the stock name. User **must** specify the column name when dumping the data. Here is an example:
+    - CSV or Parquet file includes a column of the stock name. User **must** specify the column name when dumping the data. Here is an example:
 
         .. code-block:: bash
 
-            python scripts/dump_bin.py dump_all ... --symbol_field_name symbol
+            python scripts/dump_bin.py dump_all ... --symbol_field_name symbol --file_suffix <.csv or .parquet>
 
         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 or Parquet 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
 
-        python scripts/dump_bin.py dump_all ... --date_field_name date
+        python scripts/dump_bin.py dump_all ... --date_field_name date --file_suffix <.csv or .parquet>
 
     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.
+Supposed that users prepare their CSV or Parquet format data in the directory ``~/.qlib/my_data``, they can run the following command to start the conversion.
 
 .. code-block:: bash
 
-    python scripts/dump_bin.py dump_all --csv_path  ~/.qlib/csv_data/my_data --qlib_dir ~/.qlib/qlib_data/my_data --include_fields open,close,high,low,volume,factor
+    python scripts/dump_bin.py dump_all --data_path  ~/.qlib/my_data --qlib_dir ~/.qlib/qlib_data/ --include_fields open,close,high,low,volume,factor --file_suffix <.csv or .parquet>
 
 For other supported parameters when dumping the data into `.bin` file, users can refer to the information by running the following commands:
 
 .. code-block:: bash
 
-    python dump_bin.py dump_all --help
+    python scripts/dump_bin.py dump_all --help
 
-After conversion, users can find their Qlib format data in the directory `~/.qlib/qlib_data/my_data`.
+After conversion, users can find their Qlib format data in the directory `~/.qlib/qlib_data/`.
 
 .. note::
 
-    The arguments of `--include_fields` should correspond with the column names of CSV files. The columns names of dataset provided by ``Qlib`` should include open, close, high, low, volume and factor at least.
+    The arguments of `--include_fields` should correspond with the column names of CSV or Parquet files. The columns names of dataset provided by ``Qlib`` should include open, close, high, low, volume and factor at least.
 
     - `open`
         The adjusted opening price
@@ -192,7 +195,58 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
         The Restoration factor. Normally, ``factor = adjusted_price / original_price``, `adjusted price` reference: `split adjusted <https://www.investopedia.com/terms/s/splitadjusted.asp>`_
 
     In the convention of `Qlib` data processing, `open, close, high, low, volume, money and factor` will be set to NaN if the stock is suspended.
-    If you want to use your own alpha-factor which can't be calculate by OCHLV, like PE, EPS and so on, you could add it to the CSV files with OHCLV together and then dump it to the Qlib format data.
+    If you want to use your own alpha-factor which can't be calculate by OCHLV, like PE, EPS and so on, you could add it to the CSV or Parquet files with OHCLV together and then dump it to the Qlib format data.
+
+Checking the health of the data
+-------------------------------
+
+``Qlib`` provides a script to check the health of the data.
+
+- The main points to check are as follows
+
+    - Check if any data is missing in the DataFrame.
+
+    - Check if there are any large step changes above the threshold in the OHLCV columns.
+
+    - Check if any of the required columns (OLHCV) are missing in the DataFrame.
+
+    - Check if the 'factor' column is missing in the DataFrame.
+
+- You can run the following commands to check whether the data is healthy or not.
+
+    for daily data:
+        .. code-block:: bash
+
+            python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data
+
+    for 1min data:
+        .. code-block:: bash
+
+            python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data_1min --freq 1min
+
+- Of course, you can also add some parameters to adjust the test results.
+
+    - The available parameters are these.
+
+        - freq: Frequency of data.
+
+        - large_step_threshold_price: Maximum permitted price change
+
+        - large_step_threshold_volume: Maximum permitted volume change.
+
+        - missing_data_num: Maximum value for which data is allowed to be null.
+
+- You can run the following commands to check whether the data is healthy or not.
+
+    for daily data:
+        .. code-block:: bash
+
+            python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data --missing_data_num 30055 --large_step_threshold_volume 94485 --large_step_threshold_price 20
+
+    for 1min data:
+        .. code-block:: bash
+
+            python scripts/check_data_health.py check_data --qlib_dir ~/.qlib/qlib_data/cn_data --freq 1min --missing_data_num 35806 --large_step_threshold_volume 3205452000000 --large_step_threshold_price 0.91
 
 Stock Pool (Market)
 -------------------

docs/component/highfreq.rst

@@ -25,7 +25,7 @@ The design of the framework is shown in the yellow part in the middle of the fig
 
 The frequency of the trading algorithm, decision content and execution environment can be customized by users (e.g. intraday trading, daily-frequency trading, weekly-frequency trading), and the execution environment can be nested with finer-grained trading algorithm and execution environment inside (i.e. sub-workflow in the figure, e.g. daily-frequency orders can be turned into finer-grained decisions by splitting orders within the day). The flexibility of the nested decision execution framework makes it easy for users to explore the effects of combining different levels of trading strategies and break down the optimization barriers between different levels of the trading algorithm.
 
-The optimization for the nested decision execution framework can be implemented with the support of `QlibRL <https://qlib.readthedocs.io/en/latest/component/rl.html>`_. To know more about how to use the QlibRL, go to API Reference: `RL API <../reference/api.html#rl>`_. 
+The optimization for the nested decision execution framework can be implemented with the support of `QlibRL <./rl/overall.html>`_. To know more about how to use the QlibRL, go to API Reference: `RL API <../reference/api.html#rl>`_. 
 
 Example
 =======

docs/component/model.rst

@@ -86,7 +86,7 @@ Example
             },
         }
 
-        # model initiaiton
+        # model initialization
         model = init_instance_by_config(task["model"])
         dataset = init_instance_by_config(task["dataset"])
 

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

@@ -53,17 +53,18 @@ Below is a typical config file of ``qrun``.
             kwargs:
                 topk: 50
                 n_drop: 5
-                signal:
-                    - <MODEL>
-                    - <DATASET>
+                signal: <PRED>
         backtest:
-            limit_threshold: 0.095
+            start_time: 2017-01-01
+            end_time: 2020-08-01
             account: 100000000
             benchmark: *benchmark
-            deal_price: close
-            open_cost: 0.0005
-            close_cost: 0.0015
-            min_cost: 5
+            exchange_kwargs:
+                limit_threshold: 0.095
+                deal_price: close
+                open_cost: 0.0005
+                close_cost: 0.0015
+                min_cost: 5
     task:
         model:
             class: LGBModel
@@ -109,7 +110,7 @@ If users want to use ``qrun`` under debug mode, please use the following command
 
 .. code-block:: bash
 
-    python -m pdb qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+    python -m pdb qlib/cli/run.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
 
 .. note::
 
@@ -281,9 +282,7 @@ 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/conf.py

@@ -123,7 +123,6 @@ html_logo = "_static/img/logo/1.png"
 html_theme_options = {
     "logo_only": True,
     "collapse_navigation": False,
-    "display_version": False,
     "navigation_depth": 4,
 }
 

docs/developer/code_standard_and_dev_guide.rst

@@ -60,4 +60,4 @@ The `[dev]` option will help you to install some related packages when developin
 
 .. code-block:: bash
 
-    pip install -e .[dev]
+    pip install -e ".[dev]"

docs/developer/how_to_build_image.rst

@@ -0,0 +1,81 @@
+.. _docker_image:
+
+==================
+Build Docker Image
+==================
+
+Dockerfile
+==========
+
+There is a **Dockerfile** file in the root directory of the project from which you can build the docker image. There are two build methods in Dockerfile to choose from.
+When executing the build command, use the ``--build-arg`` parameter to control the image version. The ``--build-arg`` parameter defaults to ``yes``, which builds the ``stable`` version of the qlib image.
+
+1.For the ``stable`` version, use ``pip install pyqlib`` to build the qlib image.
+
+.. code-block:: bash
+
+    docker build --build-arg IS_STABLE=yes -t <image name> -f ./Dockerfile .
+
+.. code-block:: bash
+
+    docker build -t <image name> -f ./Dockerfile .
+
+2. For the ``nightly`` version, use current source code to build the qlib image.
+
+.. code-block:: bash
+
+    docker build --build-arg IS_STABLE=no -t <image name> -f ./Dockerfile .
+
+Auto build of qlib images
+=========================
+
+1. There is a **build_docker_image.sh** file in the root directory of your project, which can be used to automatically build docker images and upload them to your docker hub repository(Optional, configuration required).
+
+.. code-block:: bash
+
+    sh build_docker_image.sh
+    >>> Do you want to build the nightly version of the qlib image? (default is stable) (yes/no):
+    >>> Is it uploaded to docker hub? (default is no) (yes/no):
+
+2. If you want to upload the built image to your docker hub repository, you need to edit your **build_docker_image.sh** file first, fill in ``docker_user`` in the file, and then execute this file.
+
+How to use qlib images
+======================
+1. Start a new Docker container
+
+.. code-block:: bash
+
+    docker run -it --name <container name> -v <Mounted local directory>:/app <image name>
+
+2. At this point you are in the docker environment and can run the qlib scripts. An example:
+
+.. code-block:: bash
+
+    >>> python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+    >>> python qlib/cli/run.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+
+3. Exit the container
+
+.. code-block:: bash
+
+    >>> exit
+
+4. Restart the container
+
+.. code-block:: bash
+
+    docker start -i -a <container name>
+
+5. Stop the container
+
+.. code-block:: bash
+
+    docker stop -i -a <container name>
+
+6. Delete the container
+
+.. code-block:: bash
+
+    docker rm <container name>
+
+7. For more information on using docker see the `docker documentation <https://docs.docker.com/reference/cli/docker/>`_.

docs/index.rst

@@ -61,6 +61,7 @@ Document Structure
    :caption: FOR DEVELOPERS:
 
    Code Standard & Development Guidance <developer/code_standard_and_dev_guide.rst>
+   How to build image <developer/how_to_build_image.rst>
 
 .. toctree::
    :maxdepth: 3

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/GeneralPtNN/README.md

@@ -0,0 +1,19 @@
+
+
+# Introduction
+
+What is GeneralPtNN
+- Fix previous design that fail to support both Time-series and tabular data
+- Now you can just replace the Pytorch model structure to run a NN model.
+
+We provide an example to demonstrate the effectiveness of the current design.
+- `workflow_config_gru.yaml` align with previous results [GRU(Kyunghyun Cho, et al.)](../README.md#Alpha158-dataset)
+  - `workflow_config_gru2mlp.yaml` to demonstrate we can convert config from time-series to tabular data with minimal changes
+    - You only have to change the net & dataset class to make the conversion.
+- `workflow_config_mlp.yaml` achieved similar functionality with [MLP](../README.md#Alpha158-dataset)
+
+# TODO
+
+- We will align existing models to current design.
+
+- The result of `workflow_config_mlp.yaml` is different with the result of [MLP](../README.md#Alpha158-dataset) since GeneralPtNN has a different stopping method compared to previous implementations. Specificly, GeneralPtNN controls training according to epoches, whereas previous methods controlled by max_steps. 

examples/benchmarks/GeneralPtNN/workflow_config_gru.yaml

@@ -0,0 +1,100 @@
+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: FilterCol
+          kwargs:
+              fields_group: feature
+              col_list: ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", 
+                            "ROC60", "RESI10", "VSTD5", "RSQR60", "CORR60", "WVMA60", "STD5", 
+                            "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"
+                        ]
+        - 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: GeneralPTNN
+        module_path: qlib.contrib.model.pytorch_general_nn
+        kwargs:
+            n_epochs: 200
+            lr: 2e-4
+            early_stop: 10
+            batch_size: 800
+            metric: loss
+            loss: mse
+            n_jobs: 20
+            GPU: 0
+            pt_model_uri: "qlib.contrib.model.pytorch_gru_ts.GRUModel"
+            pt_model_kwargs: {
+                "d_feat": 20,
+                "hidden_size": 64,
+                "num_layers": 2,
+                "dropout": 0.,
+            }
+    dataset:
+        class: TSDatasetH
+        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]
+            step_len: 20
+    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/GeneralPtNN/workflow_config_gru2mlp.yaml

@@ -0,0 +1,93 @@
+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: FilterCol
+          kwargs:
+              fields_group: feature
+              col_list: ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", 
+                            "ROC60", "RESI10", "VSTD5", "RSQR60", "CORR60", "WVMA60", "STD5", 
+                            "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"
+                        ]
+        - 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: GeneralPTNN
+        module_path: qlib.contrib.model.pytorch_general_nn
+        kwargs:
+            lr: 1e-3
+            n_epochs: 1
+            batch_size: 800
+            loss: mse
+            optimizer: adam
+            pt_model_uri: "qlib.contrib.model.pytorch_nn.Net"
+            pt_model_kwargs: 
+                input_dim: 20
+                layers: [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/GeneralPtNN/workflow_config_mlp.yaml

@@ -0,0 +1,98 @@
+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" : "DropCol", 
+            "kwargs":{"col_list": ["VWAP0"]}
+        },
+        {
+             "class" : "CSZFillna", 
+             "kwargs":{"fields_group": "feature"}
+        }
+    ]
+    learn_processors: [
+        {
+            "class" : "DropCol", 
+            "kwargs":{"col_list": ["VWAP0"]}
+        },
+        {
+            "class" : "DropnaProcessor", 
+            "kwargs":{"fields_group": "feature"}
+        },
+        "DropnaLabel",
+        {
+            "class": "CSZScoreNorm", 
+            "kwargs": {"fields_group": "label"}
+        }
+    ]
+    process_type: "independent"
+
+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: GeneralPTNN
+        module_path: qlib.contrib.model.pytorch_general_nn
+        kwargs:
+            # FIXME: wrong parameters.
+            lr: 2e-3
+            batch_size: 8192
+            loss: mse
+            weight_decay: 0.0002
+            optimizer: adam
+            pt_model_uri: "qlib.contrib.model.pytorch_nn.Net"
+            pt_model_kwargs: 
+                input_dim: 157
+    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/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

@@ -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

@@ -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

@@ -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:

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:

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:

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:

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]),
@@ -600,7 +599,7 @@ class TemporalFusionTransformer:
         print("Getting valid sampling locations.")
         valid_sampling_locations = []
         split_data_map = {}
-        for identifier, df in data.groupby(id_col):
+        for identifier, df in data.groupby(id_col, group_key=False):
             print("Getting locations for {}".format(identifier))
             num_entries = len(df)
             if num_entries >= self.time_steps:
@@ -679,8 +678,7 @@ class TemporalFusionTransformer:
         input_cols = [tup[0] for tup in self.column_definition if tup[2] not in {InputTypes.ID, InputTypes.TIME}]
 
         data_map = {}
-        for _, sliced in data.groupby(id_col):
-
+        for _, sliced in data.groupby(id_col, group_keys=False):
             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/tft.py

@@ -78,13 +78,15 @@ DATASET_SETTING = {
 
 
 def get_shifted_label(data_df, shifts=5, col_shift="LABEL0"):
-    return data_df[[col_shift]].groupby("instrument").apply(lambda df: df.shift(shifts))
+    return data_df[[col_shift]].groupby("instrument", group_keys=False).apply(lambda df: df.shift(shifts))
 
 
 def fill_test_na(test_df):
     test_df_res = test_df.copy()
     feature_cols = ~test_df_res.columns.str.contains("label", case=False)
-    test_feature_fna = test_df_res.loc[:, feature_cols].groupby("datetime").apply(lambda df: df.fillna(df.mean()))
+    test_feature_fna = (
+        test_df_res.loc[:, feature_cols].groupby("datetime", group_keys=False).apply(lambda df: df.fillna(df.mean()))
+    )
     test_df_res.loc[:, feature_cols] = test_feature_fna
     return test_df_res
 

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/example.py

@@ -1,15 +1,15 @@
 import argparse
 
 import qlib
-import ruamel.yaml as yaml
+from ruamel.yaml import YAML
 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)
+        yaml = YAML(typ="safe", pure=True)
+        config = yaml.load(f)
 
     # seed_suffix = "/seed1000" if "init" in config_file else f"/seed{seed}"
     seed_suffix = ""
@@ -30,7 +30,6 @@ 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

@@ -29,7 +29,7 @@ def _create_ts_slices(index, seq_len):
     assert index.is_lexsorted(), "index should be sorted"
 
     # number of dates for each code
-    sample_count_by_codes = pd.Series(0, index=index).groupby(level=0).size().values
+    sample_count_by_codes = pd.Series(0, index=index).groupby(level=0, group_keys=False).size().values
 
     # start_index for each code
     start_index_of_codes = np.roll(np.cumsum(sample_count_by_codes), 1)
@@ -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:
@@ -112,7 +110,6 @@ task:
         valid: [2015-01-01, 2016-12-31]
         test: [2017-01-01, 2020-08-01]
       seq_len: 60
-      horizon: 2
       input_size:
       num_states: *num_states
       batch_size: 1024

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:
@@ -106,7 +104,6 @@ task:
         valid: [2015-01-01, 2016-12-31]
         test: [2017-01-01, 2020-08-01]
       seq_len: 60
-      horizon: 2
       input_size:
       num_states: *num_states
       batch_size: 1024

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:
@@ -106,7 +104,6 @@ task:
         valid: [2015-01-01, 2016-12-31]
         test: [2017-01-01, 2020-08-01]
       seq_len: 60
-      horizon: 2
       input_size: 6
       num_states: *num_states
       batch_size: 1024

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: