Update qlib/contrib/data/handler.py

* Normal mod

* Black linting

* Linting

.github/PULL_REQUEST_TEMPLATE.md

@@ -8,7 +8,7 @@
 <!--- Why is this change required? What problem does it solve? -->
 
 ## How Has This Been Tested?
-<! ---  Put an `x` in all the boxes that apply: --->
+<!---  Put an `x` in all the boxes that apply: --->
 - [ ] Pass the test by running: `pytest qlib/tests/test_all_pipeline.py` under upper directory of `qlib`.
 - [ ] If you are adding a new feature, test on your own test scripts.
 

.github/labeler.yml

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

.github/release-drafter.yml

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

.github/workflows/labeler.yml

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

.github/workflows/python-publish.yml

@@ -12,13 +12,31 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, macos-latest, macos-11]
+        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]
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python
+    #  This is because on macos systems you can install pyqlib using
+    # `pip install pyqlib` installs, it does not recognize the
+    # `pyqlib-<version>-cp38-cp38-macosx_11_0_x86_64.whl` and `pyqlib-<veresion>-cp38-cp37m-macosx_11_0_x86_64.whl`.
+    # So we limit the version of python, in order to generate a version of qlib that is usable for macos: `pyqlib-<veresion>-cp38-cp37m 
+    # `pyqlib-<version>-cp38-cp38-macosx_10_15_x86_64.whl` and `pyqlib-<veresion>-cp38-cp37m-macosx_10_15_x86_64.whl`.
+    # Python 3.7.16, 3.8.16  can build macosx_10_15.  But  Python 3.7.17, 3.8.17  can build macosx_11_0
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os == 'macos-11' && matrix.python-version == '3.7'
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.7.16"
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os == 'macos-11' && matrix.python-version == '3.8'
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.8.16"
+    - name: Set up Python ${{ matrix.python-version }}
+      if: matrix.os != 'macos-11'
       uses: actions/setup-python@v2
       with:
         python-version: ${{ matrix.python-version }}
@@ -26,18 +44,18 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install setuptools wheel twine
-    - name: Build wheel on Windows
+    - name: Build wheel on ${{ matrix.os }}
       run: |
         pip install numpy
         pip install cython
         python setup.py bdist_wheel
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/*
-        
+
   deploy_with_manylinux:
     runs-on: ubuntu-latest
     steps:
@@ -54,10 +72,10 @@ jobs:
         python-version: 3.7
     - name: Install dependencies
       run: |
-        pip install twine  
+        pip install twine
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/pyqlib-*-manylinux*.whl

.github/workflows/release-drafter.yml

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

.github/workflows/stale.yml

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

.github/workflows/test.yml

@@ -1,66 +0,0 @@
-name: Test
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  build:
-
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04]
-        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
-
-    steps:
-    - uses: actions/checkout@v2
-
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
-      with:
-        python-version: ${{ matrix.python-version }}
-
-    - name: Lint with Black
-      run: |
-        pip install --upgrade pip
-        pip install black wheel
-        black qlib -l 120 --check --diff
-
-    - name: Install Qlib with pip
-      run: |
-        pip install numpy==1.19.5 ruamel.yaml
-        pip install pyqlib --ignore-installed 
-
-    - name: Test data downloads
-      run: |
-        python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-
-    - name: Test workflow by config (install from pip)
-      run: |
-        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
-        python -m pip uninstall -y pyqlib
-
-     # Test Qlib installed from source
-    - name: Install Qlib from source
-      run: |
-        pip install --upgrade cython jupyter jupyter_contrib_nbextensions numpy scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
-        pip install -e .
-
-    - name: Install test dependencies
-      run: |
-        pip install --upgrade pip
-        pip install black pytest
-
-    - name: Unit tests with Pytest
-      run: |
-        cd tests
-        python -m pytest . --durations=10
-
-    - name: Test workflow by config (install from source)
-      run: |
-        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
-      

.github/workflows/test_macos.yml

@@ -1,75 +0,0 @@
-# There are some issues (in the downloading data phase) on MacOS when running with other tests. So we split it into an individual config.
-name: Test MacOS
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  build:
-
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [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]
-
-    steps:
-    - uses: actions/checkout@v2
-
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
-      with:
-        python-version: ${{ matrix.python-version }}
-
-    - name: Lint with Black
-      run: |
-        cd ..
-        python -m pip install pip --upgrade
-        python -m pip install wheel --upgrade
-        python -m pip install black
-        python -m black qlib -l 120 --check --diff
-    # Test Qlib installed with pip
-
-    - name: Install Qlib with pip
-      run: |
-          python -m pip install numpy==1.19.5
-          python -m pip install pyqlib --ignore-installed ruamel.yaml numpy
-    - name: Install Lightgbm for MacOS
-      run: |
-        /bin/bash -c "$(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
-    - name: Test data downloads
-      run: |
-        python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-    - name: Test workflow by config (install from pip)
-      run: |
-        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
-        python -m pip uninstall -y pyqlib
-    # Test Qlib installed from source
-    - name: Install Qlib from source
-      run: |
-        python -m pip install --upgrade cython
-        python -m pip install numpy jupyter jupyter_contrib_nbextensions
-        python -m pip install -U scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
-        pip install -e .
-    - name: Install test dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install -U pyopenssl idna
-        python -m pip install black pytest
-    - name: Unit tests with Pytest
-      run: |
-        cd tests
-        python -m pytest . --durations=0
-    - name: Test workflow by config (install from source)
-      run: |
-          python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

.github/workflows/test_qlib_from_pip.yml

@@ -0,0 +1,75 @@
+name: Test qlib from pip
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    timeout-minutes: 120
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
+
+    steps:
+    - name: Test qlib from pip
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
+
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Update pip to the latest version
+      run: |
+        python -m pip install --upgrade pip
+
+    - name: Qlib installation test
+      run: |
+        # 2024-05-30 scs has released a new version: 3.2.4.post2,
+        # This will cause the CI to fail, so we have limited the version of scs for now.
+        python -m pip install "scs<=3.2.4"
+        python -m pip install pyqlib
+
+    - name: Install Lightgbm for MacOS
+      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      run: |
+        /bin/bash -c "$(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
+
+    - name: Downloads dependencies data
+      run: |
+        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
+      # On macos-11 system, it will lead to "Segmentation fault: 11" error,
+      # which may be caused by the excessive memory overhead of macos-11 system, so we disable macos-11 temporarily here.
+      if: ${{ matrix.os != 'macos-11' }}
+      run: |
+        qrun examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

.github/workflows/test_qlib_from_source.yml

@@ -0,0 +1,185 @@
+name: Test qlib from source
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    timeout-minutes: 180
+    # we may retry for 3 times for `Unit tests with Pytest`
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
+
+    steps:
+    - name: Test qlib from source
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
+
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Update pip to the latest version
+      run: |
+        python -m pip install --upgrade pip
+
+    - name: Installing pytorch for macos
+      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      run: |
+        python -m pip install torch torchvision torchaudio
+
+    - name: Installing pytorch for ubuntu
+      if: ${{ matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-22.04' }}
+      run: |
+        python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+
+    - name: Installing pytorch for windows
+      if: ${{ matrix.os == 'windows-latest' }}
+      run: |
+        python -m pip install torch torchvision torchaudio
+
+    - name: Set up Python tools
+      run: |
+        python -m pip install --upgrade cython
+        python -m pip install -e .[dev]
+
+    - name: Lint with Black
+      # Python 3.7 will use a black with low level. So we use python with higher version for black check
+      if: (matrix.python-version != '3.7')
+      run: |
+        pip install -U black  # follow the latest version of black, previous Qlib dependency will downgrade black
+        black . -l 120 --check --diff
+
+    - name: Make html with sphinx
+      # Since read the docs builds on ubuntu 22.04, we only need to test that the build passes on ubuntu 22.04.
+      if: ${{ matrix.os == 'ubuntu-22.04' }}
+      run: |
+        cd docs
+        sphinx-build -W --keep-going -b html . _build
+        cd ..
+
+    # Check Qlib with pylint
+    # TODO: These problems we will solve in the future. Important among them are: W0221, W0223, W0237, E1102
+      # C0103: invalid-name
+      # C0209: consider-using-f-string
+      # R0402: consider-using-from-import
+      # R1705: no-else-return
+      # R1710: inconsistent-return-statements
+      # R1725: super-with-arguments
+      # R1735: use-dict-literal
+      # W0102: dangerous-default-value
+      # W0212: protected-access
+      # W0221: arguments-differ
+      # W0223: abstract-method
+      # W0231: super-init-not-called
+      # W0237: arguments-renamed
+      # W0612: unused-variable
+      # W0621: redefined-outer-name
+      # W0622: redefined-builtin
+      # FIXME: specify exception type
+      # W0703: broad-except
+      # W1309: f-string-without-interpolation
+      # E1102: not-callable
+      # E1136: unsubscriptable-object
+    # References for parameters: https://github.com/PyCQA/pylint/issues/4577#issuecomment-1000245962
+    # We use sys.setrecursionlimit(2000) to make the recursion depth larger to ensure that pylint works properly (the default recursion depth is 1000).
+    - name: Check Qlib with pylint
+      run: |
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0246,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' scripts --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+
+    # The following flake8 error codes were ignored:
+      # E501 line too long
+        # 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
+
+    # https://github.com/python/mypy/issues/10600
+    - name: Check Qlib with mypy
+      run: |
+        mypy qlib --install-types --non-interactive || true
+        mypy qlib --verbose
+    
+    - name: Check Qlib ipynb with nbqa
+      run: |
+        nbqa black . -l 120 --check --diff
+        nbqa pylint . --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136,W0719,W0104,W0404,C0412,W0611,C0410 --const-rgx='[a-z_][a-z0-9_]{2,30}$'
+
+    - name: Test data downloads
+      run: |
+        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+        python scripts/get_data.py download_data --file_name rl_data.zip --target_dir tests/.data/rl
+
+    - name: Install Lightgbm for MacOS
+      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      run: |
+        /bin/bash -c "$(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
+
+    # Run after data downloads
+    - name: Check Qlib ipynb with nbconvert
+      # Running the nbconvert check on a macos-11 system results in a "Kernel died" error, so we've temporarily disabled macos-11 here.
+      if: ${{ matrix.os != 'macos-11' }}
+      run: |
+        # add more ipynb files in future
+        jupyter nbconvert --to notebook --execute examples/workflow_by_code.ipynb
+
+    - name: Test workflow by config (install from source)
+      # On macos-11 system, it will lead to "Segmentation fault: 11" error,
+      # which may be caused by the excessive memory overhead of macos-11 system, so we disable macos-11 temporarily here.
+      if: ${{ matrix.os != 'macos-11' }}
+      run: |
+        python -m pip install numba
+        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+
+    - name: Unit tests with Pytest
+      uses: nick-fields/retry@v2
+      with:
+        timeout_minutes: 60
+        max_attempts: 3
+        command: |
+          cd tests
+          python -m pytest . -m "not slow" --durations=0

.github/workflows/test_qlib_from_source_slow.yml

@@ -0,0 +1,71 @@
+name: Test qlib from source slow
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    timeout-minutes: 720
+    # we may retry for 3 times for `Unit tests with Pytest`
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
+
+    steps:
+    - name: Test qlib from source slow
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
+
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Set up Python tools
+      run: |
+        python -m pip install --upgrade pip
+        pip install --upgrade cython numpy
+        pip install -e .[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
+
+    - name: Install Lightgbm for MacOS
+      if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
+      run: |
+        /bin/bash -c "$(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
+
+    - name: Unit tests with Pytest
+      uses: nick-fields/retry@v2
+      with:
+        timeout_minutes: 240
+        max_attempts: 3
+        command: |
+          cd tests
+          python -m pytest . -m "slow" --durations=0

.gitignore

@@ -10,7 +10,6 @@ _build
 build/
 dist/
 
-
 *.pkl
 *.hd5
 *.csv
@@ -24,9 +23,18 @@ qlib/VERSION.txt
 qlib/data/_libs/expanding.cpp
 qlib/data/_libs/rolling.cpp
 examples/estimator/estimator_example/
+examples/rl/data/
+examples/rl/checkpoints/
+examples/rl/outputs/
+examples/rl_order_execution/data/
+examples/rl_order_execution/outputs/
 
 *.egg-info/
 
+# test related
+test-output.xml
+.output
+.data
 
 # special software
 mlruns/
@@ -34,8 +42,10 @@ mlruns/
 tags
 
 .pytest_cache/
+.mypy_cache/
 .vscode/
 
 *.swp
 
 ./pretrain
+.idea/

.mypy.ini

@@ -0,0 +1,17 @@
+[mypy]
+exclude = (?x)(
+    ^qlib/backtest/high_performance_ds\.py$
+    | ^qlib/contrib
+    | ^qlib/data
+    | ^qlib/model
+    | ^qlib/strategy
+    | ^qlib/tests
+    | ^qlib/utils
+    | ^qlib/workflow
+    | ^qlib/config\.py$
+    | ^qlib/log\.py$
+    | ^qlib/__init__\.py$
+  )
+ignore_missing_imports = true
+disallow_incomplete_defs = true
+follow_imports = skip

.pre-commit-config.yaml

@@ -0,0 +1,12 @@
+repos:
+-   repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+    -   id: black
+        args: ["qlib", "-l 120"]
+
+-   repo: https://github.com/PyCQA/flake8
+    rev: 4.0.1
+    hooks:
+        - id: flake8
+          args: ["--ignore=E501,F541,E266,E402,W503,E731,E203"]

.pylintrc

@@ -0,0 +1,5 @@
+[TYPECHECK]
+# https://stackoverflow.com/a/53572939 
+# List of members which are set dynamically and missed by Pylint inference
+# system, and so shouldn't trigger E1101 when accessed.
+generated-members=numpy.*, torch.*

.readthedocs.yaml

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

CHANGES.rst

@@ -1,63 +1,63 @@
 Changelog
-====================
+=========
 Here you can see the full list of changes between each QLib release.
 
 Version 0.1.0
---------------------
+-------------
 This is the initial release of QLib library.
 
 Version 0.1.1
---------------------
+-------------
 Performance optimize. Add more features and operators.
 
 Version 0.1.2
---------------------
-- Support operator syntax. Now ``High() - Low()`` is equivalent to ``Sub(High(), Low())``.   
+-------------
+- Support operator syntax. Now ``High() - Low()`` is equivalent to ``Sub(High(), Low())``.
 - Add more technical indicators.
 
 Version 0.1.3
---------------------
+-------------
 Bug fix and add instruments filtering mechanism.
 
 Version 0.2.0
---------------------
+-------------
 - Redesign ``LocalProvider`` database format for performance improvement.
 - Support load features as string fields.
 - Add scripts for database construction.
 - More operators and technical indicators.
 
 Version 0.2.1
---------------------
+-------------
 - Support registering user-defined ``Provider``.
 - Support use operators in string format, e.g. ``['Ref($close, 1)']`` is valid field format.
 - Support dynamic fields in ``$some_field`` format. And existing fields like ``Close()`` may be deprecated in the future.
 
 Version 0.2.2
---------------------
+-------------
 - Add ``disk_cache`` for reusing features (enabled by default).
 - Add ``qlib.contrib`` for experimental model construction and evaluation.
 
 
 Version 0.2.3
---------------------
+-------------
 - Add ``backtest`` module
 - Decoupling the Strategy, Account, Position, Exchange from the backtest module
 
 Version 0.2.4
---------------------
+-------------
 - Add ``profit attribution`` module
 - Add ``rick_control`` and ``cost_control`` strategies
-  
+
 Version 0.3.0
---------------------
+-------------
 - Add ``estimator`` module
 
 Version 0.3.1
---------------------
+-------------
 - Add ``filter`` module
 
 Version 0.3.2
---------------------
+-------------
 - Add real price trading, if the ``factor`` field in the data set is incomplete, use ``adj_price`` trading
 - Refactor ``handler`` ``launcher`` ``trainer`` code
 - Support ``backtest`` configuration parameters in the configuration file
@@ -65,16 +65,16 @@ Version 0.3.2
 - Fix bug of ``filter`` module
 
 Version 0.3.3
--------------------
+-------------
 - Fix bug of ``filter`` module
 
 Version 0.3.4
---------------------
+-------------
 - Support for ``finetune model``
 - Refactor ``fetcher`` code
 
 Version 0.3.5
---------------------
+-------------
 - Support multi-label training, you can provide multiple label in ``handler``. (But LightGBM doesn't support due to the algorithm itself)
 - Refactor ``handler`` code, dataset.py is no longer used, and you can deploy your own labels and features in ``feature_label_config``
 - Handler only offer DataFrame. Also, ``trainer`` and model.py only receive DataFrame
@@ -82,10 +82,10 @@ Version 0.3.5
 - Move some date config from ``handler`` to ``trainer``
 
 Version 0.4.0
---------------------
+-------------
 - Add `data` package that holds all data-related codes
 - Reform the data provider structure
-- Create a server for data centralized management `qlib-server<https://amc-msra.visualstudio.com/trading-algo/_git/qlib-server>`_
+- Create a server for data centralized management `qlib-server <https://amc-msra.visualstudio.com/trading-algo/_git/qlib-server>`_
 - Add a `ClientProvider` to work with server
 - Add a pluggable cache mechanism
 - Add a recursive backtracking algorithm to inspect the furthest reference date for an expression
@@ -100,7 +100,7 @@ Version 0.4.0
 
 
 Version 0.4.1
---------------------
+-------------
 - Add support Windows
 - Fix ``instruments`` type bug
 - Fix ``features`` is empty bug(It will cause failure in updating)
@@ -112,19 +112,19 @@ Version 0.4.1
 
 
 Version 0.4.2
---------------------
+-------------
 - Refactor DataHandler
 - Add ``Alpha360`` DataHandler
 
 
 Version 0.4.3
---------------------
+-------------
 - Implementing Online Inference and Trading Framework
 - Refactoring The interfaces of backtest and strategy module.
 
 
 Version 0.4.4
---------------------
+-------------
 - Optimize cache generation performance
 - Add report module
 - Fix bug when using ``ServerDatasetCache`` offline.
@@ -138,7 +138,7 @@ Version 0.4.4
 
 
 Version 0.4.5
---------------------
+-------------
 - Add multi-kernel implementation for both client and server.
     - Support a new way to load data from client which skips dataset cache.
     - Change the default dataset method from single kernel implementation to multi kernel implementation.
@@ -146,14 +146,14 @@ Version 0.4.5
 - Support a new method to write config file by using dict.
 
 Version 0.4.6
---------------------
+-------------
 - Some bugs are fixed
     - The default config in `Version 0.4.5` is not friendly to daily frequency data.
     - Backtest error in TopkWeightStrategy when `WithInteract=True`.
 
 
 Version 0.5.0
---------------------
+-------------
 - First opensource version
     - Refine the docs, code
     - Add baselines
@@ -161,19 +161,19 @@ Version 0.5.0
 
 
 Version 0.8.0
---------------------
+-------------
 - The backtest is greatly refactored.
     - Nested decision execution framework is supported
     - There are lots of changes for daily trading, it is hard to list all of them. But a few important changes could be noticed
         - The trading limitation is more accurate;
-            - In `previous version <https://github.com/microsoft/qlib/blob/v0.7.2/qlib/contrib/backtest/exchange.py#L160>`_, longing and shorting actions share the same action.
-            - In `current version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/backtest/exchange.py#L304>`_, the trading limitation is different between logging and shorting action.
+            - In `previous version <https://github.com/microsoft/qlib/blob/v0.7.2/qlib/contrib/backtest/exchange.py#L160>`__, longing and shorting actions share the same action.
+            - In `current version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/backtest/exchange.py#L304>`__, the trading limitation is different between logging and shorting action.
         - The constant is different when calculating annualized metrics.
-            - `Current version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/contrib/evaluate.py#L42>`_ uses more accurate constant than `previous version <https://github.com/microsoft/qlib/blob/v0.7.2/qlib/contrib/evaluate.py#L22>`_
-        - `A new version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/tests/data.py#L17>`_ of data is released. Due to the unstability of Yahoo data source, the data may be different after downloading data again.
-        - Users could check out the backtesting results between  `Current version <https://github.com/microsoft/qlib/tree/7c31012b507a3823117bddcc693fc64899460b2a/examples/benchmarks>`_ and `previous version <https://github.com/microsoft/qlib/tree/v0.7.2/examples/benchmarks>`_
+            - `Current version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/contrib/evaluate.py#L42>`_ uses more accurate constant than `previous version <https://github.com/microsoft/qlib/blob/v0.7.2/qlib/contrib/evaluate.py#L22>`__
+        - `A new version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/tests/data.py#L17>`__ of data is released. Due to the unstability of Yahoo data source, the data may be different after downloading data again.
+        - Users could check out the backtesting results between  `Current version <https://github.com/microsoft/qlib/tree/7c31012b507a3823117bddcc693fc64899460b2a/examples/benchmarks>`__ and `previous version <https://github.com/microsoft/qlib/tree/v0.7.2/examples/benchmarks>`__
 
 
 Other Versions
-----------------------------------
+--------------
 Please refer to `Github release Notes <https://github.com/microsoft/qlib/releases>`_

README.md

@@ -11,7 +11,14 @@
 Recent released features
 | Feature | Status |
 | --                      | ------    |
-| Arctic Provider Backend & Orderbook data example | :hammer: [Rleased](https://github.com/microsoft/qlib/pull/744) on Jan 17, 2022 |
+| KRNN and Sandwich models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1414/) on May 26, 2023 |
+| Release Qlib v0.9.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.9.0) on Dec 9, 2022 |
+| RL Learning Framework | :hammer: :chart_with_upwards_trend: Released on Nov 10, 2022. [#1332](https://github.com/microsoft/qlib/pull/1332), [#1322](https://github.com/microsoft/qlib/pull/1322), [#1316](https://github.com/microsoft/qlib/pull/1316),[#1299](https://github.com/microsoft/qlib/pull/1299),[#1263](https://github.com/microsoft/qlib/pull/1263), [#1244](https://github.com/microsoft/qlib/pull/1244), [#1169](https://github.com/microsoft/qlib/pull/1169), [#1125](https://github.com/microsoft/qlib/pull/1125), [#1076](https://github.com/microsoft/qlib/pull/1076)|
+| HIST and IGMTF models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1040) on Apr 10, 2022 |
+| Qlib [notebook tutorial](https://github.com/microsoft/qlib/tree/main/examples/tutorial) | 📖 [Released](https://github.com/microsoft/qlib/pull/1037) on Apr 7, 2022 | 
+| Ibovespa index data | :rice: [Released](https://github.com/microsoft/qlib/pull/990) on Apr 6, 2022 |
+| Point-in-Time database | :hammer: [Released](https://github.com/microsoft/qlib/pull/343) on Mar 10, 2022 |
+| Arctic Provider Backend & Orderbook data example | :hammer: [Released](https://github.com/microsoft/qlib/pull/744) on Jan 17, 2022 |
 | Meta-Learning-based framework & DDG-DA  | :chart_with_upwards_trend:  :hammer: [Released](https://github.com/microsoft/qlib/pull/743) on Jan 10, 2022 | 
 | Planning-based portfolio optimization | :hammer: [Released](https://github.com/microsoft/qlib/pull/754) on Dec 28, 2021 | 
 | Release Qlib v0.8.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.8.0) on Dec 8, 2021 |
@@ -28,69 +35,89 @@ Recent released features
 | High-frequency data processing example | :hammer: [Released](https://github.com/microsoft/qlib/pull/257) on Feb 5, 2021  |
 | High-frequency trading example | :chart_with_upwards_trend: [Part of code released](https://github.com/microsoft/qlib/pull/227) on Jan 28, 2021  | 
 | High-frequency data(1min) | :rice: [Released](https://github.com/microsoft/qlib/pull/221) on Jan 27, 2021 |
-| Tabnet Model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/205) on Jan 22, 2021 | 
+| Tabnet Model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/205) on Jan 22, 2021 |
 
 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.
 
-Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment.
+An increasing number of SOTA Quant research works/papers in diverse paradigms are being released in Qlib to collaboratively solve key challenges in quantitative investment. For example, 1) using supervised learning to mine the market's complex non-linear patterns from rich and heterogeneous financial data, 2) modeling the dynamic nature of the financial market using adaptive concept drift technology, and 3) using reinforcement learning to model continuous investment decisions and assist investors in optimizing their trading strategies.
 
 It contains the full ML pipeline of data processing, model training, back-testing; and covers the entire chain of quantitative investment: alpha seeking, risk modeling, portfolio optimization, and order execution. 
-
-With Qlib, users can easily try ideas to create better Quant investment strategies.
-
 For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative Investment Platform"](https://arxiv.org/abs/2009.11189).
 
-- [**Plans**](#plans)
-- [Framework of Qlib](#framework-of-qlib)
-- [Quick Start](#quick-start)
-  - [Installation](#installation)
-  - [Data Preparation](#data-preparation)
-  - [Auto Quant Research Workflow](#auto-quant-research-workflow)
-  - [Building Customized Quant Research Workflow by Code](#building-customized-quant-research-workflow-by-code)
-- [Main Challenges & Solutions in Quant Research](#main-challenges--solutions-in-quant-research)
-  - [Forecasting: Finding Valuable Signals/Patterns](#forecasting-finding-valuable-signalspatterns)
-    - [**Quant Model (Paper) Zoo**](#quant-model-paper-zoo)
-      - [Run a Single Model](#run-a-single-model)
-      - [Run Multiple Models](#run-multiple-models)
-  - [Adapting to Market Dynamics](#adapting-to-market-dynamics)
-- [**Quant Dataset Zoo**](#quant-dataset-zoo)
-- [More About Qlib](#more-about-qlib)
-- [Offline Mode and Online Mode](#offline-mode-and-online-mode)
-  - [Performance of Qlib Data Server](#performance-of-qlib-data-server)
-- [Related Reports](#related-reports)
-- [Contact Us](#contact-us)
-- [Contributing](#contributing)
 
+<table>
+  <tbody>
+    <tr>
+      <th>Frameworks, Tutorial, Data & DevOps</th>
+      <th>Main Challenges & Solutions in Quant Research</th>
+    </tr>
+    <tr>
+      <td>
+        <li><a href="#plans"><strong>Plans</strong></a></li>
+        <li><a href="#framework-of-qlib">Framework of Qlib</a></li>
+        <li><a href="#quick-start">Quick Start</a></li>
+          <ul dir="auto">
+            <li type="circle"><a href="#installation">Installation</a> </li>
+            <li type="circle"><a href="#data-preparation">Data Preparation</a></li>
+            <li type="circle"><a href="#auto-quant-research-workflow">Auto Quant Research Workflow</a></li>
+            <li type="circle"><a href="#building-customized-quant-research-workflow-by-code">Building Customized Quant Research Workflow by Code</a></li></ul>
+        <li><a href="#quant-dataset-zoo"><strong>Quant Dataset Zoo</strong></a></li>
+        <li><a href="#learning-framework">Learning Framework</a></li>
+        <li><a href="#more-about-qlib">More About Qlib</a></li>
+        <li><a href="#offline-mode-and-online-mode">Offline Mode and Online Mode</a>
+        <ul>
+          <li type="circle"><a href="#performance-of-qlib-data-server">Performance of Qlib Data Server</a></li></ul>
+        <li><a href="#related-reports">Related Reports</a></li>
+        <li><a href="#contact-us">Contact Us</a></li>
+        <li><a href="#contributing">Contributing</a></li>
+      </td>
+      <td valign="baseline">
+        <li><a href="#main-challenges--solutions-in-quant-research">Main Challenges &amp; Solutions in Quant Research</a>
+          <ul>
+            <li type="circle"><a href="#forecasting-finding-valuable-signalspatterns">Forecasting: Finding Valuable Signals/Patterns</a>
+              <ul>
+                <li type="disc"><a href="#quant-model-paper-zoo"><strong>Quant Model (Paper) Zoo</strong></a>
+                  <ul>
+                    <li type="circle"><a href="#run-a-single-model">Run a Single Model</a></li>
+                    <li type="circle"><a href="#run-multiple-models">Run Multiple Models</a></li>
+                  </ul>
+                </li>
+              </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>
+    </tr>
+  </tbody>
+</table>
 
 # Plans
 New features under development(order by estimated release time).
 Your feedbacks about the features are very important.
-| Feature                        | Status      |
-| --                      | ------    |
-| Point-in-Time database | Under review: https://github.com/microsoft/qlib/pull/343 |
+<!-- | Feature                        | Status      | -->
+<!-- | --                      | ------    | -->
 
 # Framework of Qlib
 
 <div style="align: center">
-<img src="docs/_static/img/framework.svg" />
+<img src="docs/_static/img/framework-abstract.jpg" />
 </div>
 
+The high-level framework of Qlib can be found above(users can find the [detailed framework](https://qlib.readthedocs.io/en/latest/introduction/introduction.html#framework) of Qlib's design when getting into nitty gritty).
+The components are designed as loose-coupled modules, and each component could be used stand-alone.
 
-At the module level, Qlib is a platform that consists of the above components. The components are designed as loose-coupled modules, and each component could be used stand-alone.
-
-| Name                   | Description                                                                                                                                                                                                                                                                                                                                                             |
-| ------                 | -----                                                                                                                                                                                                                                                                                                                                                                   |
-| `Infrastructure` layer | `Infrastructure` layer provides underlying support for Quant research. `DataServer` provides a high-performance infrastructure for users to manage and retrieve raw data. `Trainer` provides a flexible interface to control the training process of models, which enable algorithms to control the training process.                                                       |
-| `Workflow` layer       | `Workflow` layer covers the whole workflow of quantitative investment. `Information Extractor` extracts data for models. `Forecast Model` focuses on producing all kinds of forecast signals (e.g. _alpha_, risk) for other modules. With these signals `Decision Generator` will generate the target trading decisions(i.e. portfolio, orders)  to be executed by `Execution Env` (i.e. the trading market).  There may be multiple levels of `Trading Agent` and `Execution Env` (e.g. an _order executor trading agent and intraday order execution environment_ could behave like an interday trading environment and nested in  _daily portfolio management trading agent and interday trading environment_  ) |
-| `Interface` layer      | `Interface` layer tries to present a user-friendly interface for the underlying system. `Analyser` module will provide users detailed analysis reports of forecasting signals, portfolios and execution results                                                                                                                                                                 |
-
-* The modules with hand-drawn style are under development and will be released in the future.
-* The modules with dashed borders are highly user-customizable and extendible.
+Qlib provides a strong infrastructure to support Quant research. [Data](https://qlib.readthedocs.io/en/latest/component/data.html) is always an important part.
+A strong learning framework is designed to support diverse learning paradigms (e.g. [reinforcement learning](https://qlib.readthedocs.io/en/latest/component/rl.html), [supervised learning](https://qlib.readthedocs.io/en/latest/component/workflow.html#model-section)) and patterns at different levels(e.g. [market dynamic modeling](https://qlib.readthedocs.io/en/latest/component/meta.html)).
+By modeling the market, [trading strategies](https://qlib.readthedocs.io/en/latest/component/strategy.html) will generate trade decisions that will be executed. Multiple trading strategies and executors in different levels or granularities can be [nested to be optimized and run together](https://qlib.readthedocs.io/en/latest/component/highfreq.html).
+At last, a comprehensive [analysis](https://qlib.readthedocs.io/en/latest/component/report.html) will be provided and the model can be [served online](https://qlib.readthedocs.io/en/latest/component/online.html) in a low cost.
 
 
 # Quick Start
@@ -112,7 +139,7 @@ This table demonstrates the supported Python version of `Qlib`:
 | Python 3.9    | :x:                   | :heavy_check_mark:   | :x: |
 
 **Note**: 
-1. **Conda** is suggested for managing your Python environment.
+1. **Conda** is suggested for managing your Python environment. In some cases, using Python outside of a `conda` environment may result in missing header files, causing the installation failure of certain packages.
 1. Please pay attention that installing cython in Python 3.6 will raise some error when installing ``Qlib`` from source. If users use Python 3.6 on their machines, it is recommended to *upgrade* Python to version 3.7 or use `conda`'s Python to install ``Qlib`` from source.
 1. For Python 3.9, `Qlib` supports running workflows such as training models, doing backtest and plot most of the related figures (those included in [notebook](examples/workflow_by_code.ipynb)). However, plotting for the *model performance* is not supported for now and we will fix this when the dependent packages are upgraded in the future.
 1. `Qlib`Requires `tables` package, `hdf5` in tables does not support python3.9. 
@@ -139,14 +166,43 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 * 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 recommanded 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**.
+  **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.yml) may help you find the problem.
+**Tips**: If you fail to install `Qlib` or run the examples in your environment,  comparing your steps and the [CI workflow](.github/workflows/test_qlib_from_source.yml) may help you find the problem.
+
+**Tips for Mac**: If you are using Mac with M1, you might encounter issues in building the wheel for LightGBM, which is due to missing dependencies from OpenMP. To solve the problem, install openmp first with ``brew install libomp`` and then run ``pip install .`` to build it successfully. 
 
 ## Data Preparation
+❗ Due to more restrict data security policy. The offical dataset is disabled temporarily. You can try [this data source](https://github.com/chenditc/investment_data/releases) contributed by the community.
+Here is an example to download the data updated on 20220720.
+```bash
+wget https://github.com/chenditc/investment_data/releases/download/20220720/qlib_bin.tar.gz
+mkdir -p ~/.qlib/qlib_data/cn_data
+tar -zxvf qlib_bin.tar.gz -C ~/.qlib/qlib_data/cn_data --strip-components=2
+rm -f qlib_bin.tar.gz
+```
+
+The official dataset below will resume in short future.
+
+
+----
+
 Load and prepare data by running the following code:
+
+### Get with module
+  ```bash
+  # get 1d data
+  python -m qlib.run.get_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
+
+  ```
+
+### Get from source
+
   ```bash
   # get 1d data
   python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
@@ -168,6 +224,8 @@ We recommend users to prepare their own data if they have a high-quality dataset
   > 
   > It is recommended that users update the data manually once (--trading_date 2021-05-25) and then set it to update automatically.
   >
+  > **NOTE**: Users can't incrementally  update data based on the offline data provided by Qlib(some fields are removed to reduce the data size). Users should use [yahoo collector](https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#automatic-update-of-daily-frequency-datafrom-yahoo-finance) to download Yahoo data from scratch and then incrementally update it.
+  > 
   > For more information, please refer to: [yahoo collector](https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#automatic-update-of-daily-frequency-datafrom-yahoo-finance)
 
   * Automatic update of data to the "qlib" directory each trading day(Linux)
@@ -279,7 +337,7 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
 The automatic workflow may not suit the research workflow of all Quant researchers. To support a flexible Quant research workflow, Qlib also provides a modularized interface to allow researchers to build their own workflow by code. [Here](examples/workflow_by_code.ipynb) is a demo for customized Quant research workflow by code.
 
 # Main Challenges & Solutions in Quant Research
-Quant investment is an very unique scenario with lots of key challenges to be solved.
+Quant investment is a very unique scenario with lots of key challenges to be solved.
 Currently, Qlib provides some solutions for several of them.
 
 ## Forecasting: Finding Valuable Signals/Patterns
@@ -311,10 +369,14 @@ Here is a list of models built on `Qlib`.
 - [TCN based on pytorch (Shaojie Bai, et al. 2018)](examples/benchmarks/TCN/)
 - [ADARNN based on pytorch (YunTao Du, et al. 2021)](examples/benchmarks/ADARNN/)
 - [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.
@@ -347,6 +409,17 @@ Here is a list of solutions built on `Qlib`.
 - [Rolling Retraining](examples/benchmarks_dynamic/baseline/)
 - [DDG-DA on pytorch (Wendi, et al. AAAI 2022)](examples/benchmarks_dynamic/DDG-DA/)
 
+##  Reinforcement Learning: modeling continuous decisions
+Qlib now supports reinforcement learning, a feature designed to model continuous investment decisions. This functionality assists investors in optimizing their trading strategies by learning from interactions with the environment to maximize some notion of cumulative reward.
+
+Here is a list of solutions built on `Qlib` categorized by scenarios.
+
+### [RL for order execution](examples/rl_order_execution)
+[Here](https://qlib.readthedocs.io/en/latest/component/rl/overall.html#order-execution) is the introduction of this scenario.  All the methods below are compared [here](examples/rl_order_execution).
+- [TWAP](examples/rl_order_execution/exp_configs/backtest_twap.yml)
+- [PPO: "An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization", IJCAL 2020](examples/rl_order_execution/exp_configs/backtest_ppo.yml)
+- [OPDS: "Universal Trading for Order Execution with Oracle Policy Distillation", AAAI 2021](examples/rl_order_execution/exp_configs/backtest_opds.yml)
+
 # Quant Dataset Zoo
 Dataset plays a very important role in Quant. Here is a list of the datasets built on `Qlib`:
 
@@ -358,7 +431,20 @@ Dataset plays a very important role in Quant. Here is a list of the datasets bui
 [Here](https://qlib.readthedocs.io/en/latest/advanced/alpha.html) is a tutorial to build dataset with `Qlib`.
 Your PR to build new Quant dataset is highly welcomed.
 
+
+# Learning Framework
+Qlib is high customizable and a lot of its components are learnable.
+The learnable components are instances of `Forecast Model` and `Trading Agent`. They are learned based on the `Learning Framework` layer and then applied to multiple scenarios in `Workflow` layer.
+The learning framework leverages the `Workflow` layer as well(e.g. sharing `Information Extractor`, creating environments based on `Execution Env`).
+
+Based on learning paradigms, they can be categorized into reinforcement learning and supervised learning.
+- For supervised learning, the detailed docs can be found [here](https://qlib.readthedocs.io/en/latest/component/model.html).
+- For reinforcement learning, the detailed docs can be found [here](https://qlib.readthedocs.io/en/latest/component/rl.html). Qlib's RL learning framework leverages `Execution Env` in `Workflow` layer to create environments.  It's worth noting that `NestedExecutor` is supported as well. This empowers users to optimize different level of strategies/models/agents together (e.g. optimizing an order execution strategy for a specific portfolio management strategy).
+
+
 # More About Qlib
+If you want to have a quick glance at the most frequently used components of qlib, you can try notebooks [here](examples/tutorial/).
+
 The detailed documents are organized in [docs](docs/).
 [Sphinx](http://www.sphinx-doc.org) and the readthedocs theme is required to build the documentation in html formats. 
 ```bash
@@ -425,7 +511,7 @@ Before we released Qlib as an open-source project on Github in Sep 2020, Qlib is
 
 This project welcomes contributions and suggestions.  
 **Here are some 
-[code standards](docs/developer/code_standard.rst) for submiting a pull request.**
+[code standards and development guidance](docs/developer/code_standard_and_dev_guide.rst) for submiting a pull request.**
 
 Making contributions is not a hard thing. Solving an issue(maybe just answering a question raised in [issues list](https://github.com/microsoft/qlib/issues) or [gitter](https://gitter.im/Microsoft/qlib)), fixing/issuing a bug, improving the documents and even fixing a typo are important contributions to Qlib.
 
@@ -441,9 +527,13 @@ If you don't know how to start to contribute, you can refer to the following exa
 | Docs | [Improve docs quality](https://github.com/microsoft/qlib/pull/797/files) ;  [Fix a typo](https://github.com/microsoft/qlib/pull/774) | 
 | Feature |  Implement a [requested feature](https://github.com/microsoft/qlib/projects) like [this](https://github.com/microsoft/qlib/pull/754); [Refactor interfaces](https://github.com/microsoft/qlib/pull/539/files) |
 | Dataset | [Add a dataset](https://github.com/microsoft/qlib/pull/733) | 
-| Models |  [Implement a new model](https://github.com/microsoft/qlib/pull/689) | 
+| Models |  [Implement a new model](https://github.com/microsoft/qlib/pull/689), [some instructions to contribute models](https://github.com/microsoft/qlib/tree/main/examples/benchmarks#contributing) |
 
-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 you to set the right permission.
+[Good first issues](https://github.com/microsoft/qlib/labels/good%20first%20issue) are labelled to indicate that they are easy to start your contributions.
+
+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
 Most contributions require you to agree to a

docs/FAQ/FAQ.rst

@@ -3,7 +3,7 @@ Qlib FAQ
 ############
 
 Qlib Frequently Asked Questions
-================================
+===============================
 .. contents::
     :depth: 1
     :local:
@@ -13,7 +13,7 @@ Qlib Frequently Asked Questions
 
 
 1. RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase...
-------------------------------------------------------------------------------------------------------------------------------------
+-----------------------------------------------------------------------------------------------------------------------------------
 
 .. code-block:: console
 
@@ -52,7 +52,7 @@ This is caused by the limitation of multiprocessing under windows OS. Please ref
 
 
 2. qlib.data.cache.QlibCacheException: It sees the key(...) of the redis lock has existed in your redis db now.
------------------------------------------------------------------------------------------------------------------
+---------------------------------------------------------------------------------------------------------------
 
 It sees the key of the redis lock has existed in your redis db now. You can use the following command to clear your redis keys and rerun your commands
 
@@ -72,7 +72,7 @@ If the issue is not resolved, use ``keys *`` to find if multiple keys exist. If
 Also, feel free to post a new issue in our GitHub repository. We always check each issue carefully and try our best to solve them.
 
 3. ModuleNotFoundError: No module named 'qlib.data._libs.rolling'
-------------------------------------------------------------------------------------------------------------------------------------
+-----------------------------------------------------------------
 
 .. code-block:: python
 
@@ -101,7 +101,7 @@ Also, feel free to post a new issue in our GitHub repository. We always check ea
 
 
 4. BadNamespaceError: / is not a connected namespace
-------------------------------------------------------------------------------------------------------------------------------------
+----------------------------------------------------
 
 .. code-block:: python
 
@@ -125,7 +125,7 @@ Also, feel free to post a new issue in our GitHub repository. We always check ea
 
 
 5. TypeError: send() got an unexpected keyword argument 'binary'
-------------------------------------------------------------------------------------------------------------------------------------
+----------------------------------------------------------------
 
 .. code-block:: python
 

docs/Makefile

@@ -17,4 +17,5 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
+	pip install -r requirements.txt
 	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/advanced/PIT.rst

@@ -0,0 +1,136 @@
+.. _pit:
+
+============================
+(P)oint-(I)n-(T)ime Database
+============================
+.. currentmodule:: qlib
+
+
+Introduction
+------------
+Point-in-time data is a very important consideration when performing any sort of historical market analysis.
+
+For example, let’s say we are backtesting a trading strategy and we are using the past five years of historical data as our input.
+Our model is assumed to trade once a day, at the market close, and we’ll say we are calculating the trading signal for 1 January 2020 in our backtest. At that point, we should only have data for 1 January 2020, 31 December 2019, 30 December 2019 etc.
+
+In financial data (especially financial reports), the same piece of data may be amended for multiple times overtime.  If we only use the latest version for historical backtesting, data leakage will happen.
+Point-in-time database is designed for solving this problem to make sure user get the right version of data at any historical timestamp. It will keep the performance of online trading and historical backtesting the same.
+
+
+
+Data Preparation
+----------------
+
+Qlib provides a crawler to help users to download financial data and then a converter to dump the data in Qlib format.
+Please follow `scripts/data_collector/pit/README.md <https://github.com/microsoft/qlib/tree/main/scripts/data_collector/pit/>`_ to download and convert data.
+Besides, you can find some additional usage examples there.
+
+
+File-based design for PIT data
+------------------------------
+
+Qlib provides a file-based storage for PIT data.
+
+For each feature, it contains 4 columns, i.e. date, period, value, _next.
+Each row corresponds to a statement.
+
+The meaning of each feature with filename like `XXX_a.data`:
+
+- `date`: the statement's date of publication.
+- `period`: the period of the statement. (e.g. it will be quarterly frequency in most of the markets)
+    - If it is an annual period, it will be an integer corresponding to the year
+    - If it is an quarterly  periods, it will be an integer like `<year><index of quarter>`.  The last two decimal digits represents the index of quarter. Others represent the year.
+- `value`: the described value
+- `_next`: the byte index of the next occurance of the field.
+
+Besides the feature data, an index `XXX_a.index` is included to speed up the querying performance
+
+The statements are soted by the `date` in ascending order from the beginning of the file.
+
+.. code-block:: python
+
+    # the data format from XXXX.data
+    array([(20070428, 200701, 0.090219  , 4294967295),
+           (20070817, 200702, 0.13933   , 4294967295),
+           (20071023, 200703, 0.24586301, 4294967295),
+           (20080301, 200704, 0.3479    ,         80),
+           (20080313, 200704, 0.395989  , 4294967295),
+           (20080422, 200801, 0.100724  , 4294967295),
+           (20080828, 200802, 0.24996801, 4294967295),
+           (20081027, 200803, 0.33412001, 4294967295),
+           (20090325, 200804, 0.39011699, 4294967295),
+           (20090421, 200901, 0.102675  , 4294967295),
+           (20090807, 200902, 0.230712  , 4294967295),
+           (20091024, 200903, 0.30072999, 4294967295),
+           (20100402, 200904, 0.33546099, 4294967295),
+           (20100426, 201001, 0.083825  , 4294967295),
+           (20100812, 201002, 0.200545  , 4294967295),
+           (20101029, 201003, 0.260986  , 4294967295),
+           (20110321, 201004, 0.30739301, 4294967295),
+           (20110423, 201101, 0.097411  , 4294967295),
+           (20110831, 201102, 0.24825101, 4294967295),
+           (20111018, 201103, 0.318919  , 4294967295),
+           (20120323, 201104, 0.4039    ,        420),
+           (20120411, 201104, 0.403925  , 4294967295),
+           (20120426, 201201, 0.112148  , 4294967295),
+           (20120810, 201202, 0.26484701, 4294967295),
+           (20121026, 201203, 0.370487  , 4294967295),
+           (20130329, 201204, 0.45004699, 4294967295),
+           (20130418, 201301, 0.099958  , 4294967295),
+           (20130831, 201302, 0.21044201, 4294967295),
+           (20131016, 201303, 0.30454299, 4294967295),
+           (20140325, 201304, 0.394328  , 4294967295),
+           (20140425, 201401, 0.083217  , 4294967295),
+           (20140829, 201402, 0.16450299, 4294967295),
+           (20141030, 201403, 0.23408499, 4294967295),
+           (20150421, 201404, 0.319612  , 4294967295),
+           (20150421, 201501, 0.078494  , 4294967295),
+           (20150828, 201502, 0.137504  , 4294967295),
+           (20151023, 201503, 0.201709  , 4294967295),
+           (20160324, 201504, 0.26420501, 4294967295),
+           (20160421, 201601, 0.073664  , 4294967295),
+           (20160827, 201602, 0.136576  , 4294967295),
+           (20161029, 201603, 0.188062  , 4294967295),
+           (20170415, 201604, 0.244385  , 4294967295),
+           (20170425, 201701, 0.080614  , 4294967295),
+           (20170728, 201702, 0.15151   , 4294967295),
+           (20171026, 201703, 0.25416601, 4294967295),
+           (20180328, 201704, 0.32954201, 4294967295),
+           (20180428, 201801, 0.088887  , 4294967295),
+           (20180802, 201802, 0.170563  , 4294967295),
+           (20181029, 201803, 0.25522   , 4294967295),
+           (20190329, 201804, 0.34464401, 4294967295),
+           (20190425, 201901, 0.094737  , 4294967295),
+           (20190713, 201902, 0.        ,       1040),
+           (20190718, 201902, 0.175322  , 4294967295),
+           (20191016, 201903, 0.25581899, 4294967295)],
+          dtype=[('date', '<u4'), ('period', '<u4'), ('value', '<f8'), ('_next', '<u4')])
+    # - each row contains 20 byte
+
+
+    # The data format from XXXX.index.  It consists of two parts
+    # 1) the start index of the data. So the first part of the info will be like
+    2007
+    # 2) the remain index data will be like information below
+    #    - The data indicate the **byte index** of first data update of a period.
+    #    - e.g. Because the info at both byte 80 and 100 corresponds to 200704. The byte index of first occurance (i.e. 100) is recorded in the data.
+    array([         0,         20,         40,         60,        100,
+                  120,        140,        160,        180,        200,
+                  220,        240,        260,        280,        300,
+                  320,        340,        360,        380,        400,
+                  440,        460,        480,        500,        520,
+                  540,        560,        580,        600,        620,
+                  640,        660,        680,        700,        720,
+                  740,        760,        780,        800,        820,
+                  840,        860,        880,        900,        920,
+                  940,        960,        980,       1000,       1020,
+                 1060, 4294967295], dtype=uint32)
+
+
+
+
+Known limitations:
+
+- Currently, the PIT database is designed for quarterly or annually factors, which can handle fundamental data of financial reports in most markets.
+- Qlib leverage the file name to identify the type of the data. File with name like `XXX_q.data` corresponds to quarterly data. File with name like `XXX_a.data` corresponds to annual data.
+- The caclulation of PIT is not performed in the optimal way. There is great potential to boost the performance of PIT data calcuation.

docs/advanced/alpha.rst

@@ -1,12 +1,12 @@
 .. _alpha:
 
-===========================
-Building Formulaic Alphas 
-===========================
+=========================
+Building Formulaic Alphas
+=========================
 .. currentmodule:: qlib
 
 Introduction
-===================
+============
 
 In quantitative trading practice, designing novel factors that can explain and predict future asset returns are of vital importance to the profitability of a strategy. Such factors are usually called alpha factors, or alphas in short.
 
@@ -15,30 +15,30 @@ A formulaic alpha, as the name suggests, is a kind of alpha that can be presente
 
 
 Building Formulaic Alphas in ``Qlib``
-======================================
+=====================================
 
 In ``Qlib``, users can easily build formulaic alphas.
 
 Example
------------------
+-------
 
 `MACD`, short for moving average convergence/divergence, is a formulaic alpha used in technical analysis of stock prices. It is designed to reveal changes in the strength, direction, momentum, and duration of a trend in a stock's price.
 
 `MACD` can be presented as the following formula:
 
-.. math:: 
+.. math::
 
     MACD = 2\times (DIF-DEA)
 
 .. note::
 
     `DIF` means Differential value, which is 12-period EMA minus 26-period EMA.
-    
+
     .. math::
 
-        DIF = \frac{EMA(CLOSE, 12) - EMA(CLOSE, 26)}{CLOSE} 
+        DIF = \frac{EMA(CLOSE, 12) - EMA(CLOSE, 26)}{CLOSE}
 
-    `DEA`means a 9-period EMA of the DIF.
+    `DEA` means a 9-period EMA of the DIF.
 
     .. math::
 
@@ -65,7 +65,7 @@ Users can use ``Data Handler`` to build formulaic alphas `MACD` in qlib:
     >> print(df)
                             feature     label
                                MACD     LABEL
-    datetime   instrument                    
+    datetime   instrument
     2010-01-04 SH600000   -0.011547 -0.019672
                SH600004    0.002745 -0.014721
                SH600006    0.010133  0.002911
@@ -79,7 +79,7 @@ Users can use ``Data Handler`` to build formulaic alphas `MACD` in qlib:
                SZ300315   -0.030557  0.012455
 
 Reference
-===========
+=========
 
 To learn more about ``Data Loader``, please refer to `Data Loader <../component/data.html#data-loader>`_
 

docs/advanced/serial.rst

@@ -1,26 +1,26 @@
 .. _serial:
 
-=================================
+=============
 Serialization
-=================================
+=============
 .. currentmodule:: qlib
 
 Introduction
-===================
-``Qlib`` supports dumping the state of ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc. into a disk and reloading them. 
+============
+``Qlib`` supports dumping the state of ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc. into a disk and reloading them.
 
 Serializable Class
-========================
+==================
 
-``Qlib`` provides a base class ``qlib.utils.serial.Serializable``, whose state can be dumped into or loaded from disk in `pickle` format. 
+``Qlib`` provides a base class ``qlib.utils.serial.Serializable``, whose state can be dumped into or loaded from disk in `pickle` format.
 When users dump the state of a ``Serializable`` instance, the attributes of the instance whose name **does not** start with `_` will be saved on the disk.
 However, users can use ``config`` method or override ``default_dump_all`` attribute to prevent this feature.
 
 Users can also override ``pickle_backend`` attribute to choose a pickle backend. The supported value is "pickle" (default and common) and "dill" (dump more things such as function, more information in `here <https://pypi.org/project/dill/>`_).
 
 Example
-==========================
-``Qlib``'s serializable class includes  ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc., which are subclass of  ``qlib.utils.serial.Serializable``. 
+=======
+``Qlib``'s serializable class includes  ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc., which are subclass of  ``qlib.utils.serial.Serializable``.
 Specifically, ``qlib.data.dataset.DatasetH`` is one of them. Users can serialize ``DatasetH`` as follows.
 
 .. code-block:: Python
@@ -33,7 +33,7 @@ Specifically, ``qlib.data.dataset.DatasetH`` is one of them. Users can serialize
         dataset = pickle.load(file_dataset)
 
 .. note::
-    Only state of ``DatasetH`` should be saved on the disk, such as some `mean` and `variance` used for data normalization, etc. 
+    Only state of ``DatasetH`` should be saved on the disk, such as some `mean` and `variance` used for data normalization, etc.
 
     After reloading the ``DatasetH``, users need to reinitialize it. It means that users can reset some states of ``DatasetH`` or ``QlibDataHandler`` such as `instruments`, `start_time`, `end_time` and `segments`, etc.,  and generate new data according to the states (data is not state and should not be saved on the disk).
 
@@ -41,5 +41,5 @@ A more detailed example is in this `link <https://github.com/microsoft/qlib/tree
 
 
 API
-===================
+===
 Please refer to `Serializable API <../reference/api.html#module-qlib.utils.serial.Serializable>`_.

docs/advanced/server.rst

@@ -1,15 +1,15 @@
 .. _server:
 
-=================================
+=============================
 ``Online`` & ``Offline`` mode
-=================================
+=============================
 .. currentmodule:: qlib
 
 
 Introduction
-=============
+============
 
-``Qlib`` supports ``Online`` mode and ``Offline`` mode. Only the ``Offline`` mode is introduced in this document. 
+``Qlib`` supports ``Online`` mode and ``Offline`` mode. Only the ``Offline`` mode is introduced in this document.
 
 The ``Online`` mode is designed to solve the following problems:
 
@@ -18,12 +18,12 @@ The ``Online`` mode is designed to solve the following problems:
 - Make the data can be accessed in a remote way.
 
 Qlib-Server
-===============
+===========
 
-``Qlib-Server`` is the assorted server system for ``Qlib``, which utilizes ``Qlib`` for basic calculations and provides extensive server system and cache mechanism. With QLibServer, the data provided for ``Qlib`` can be managed in a centralized manner. With ``Qlib-Server``, users can use ``Qlib`` in ``Online`` mode. 
+``Qlib-Server`` is the assorted server system for ``Qlib``, which utilizes ``Qlib`` for basic calculations and provides extensive server system and cache mechanism. With QLibServer, the data provided for ``Qlib`` can be managed in a centralized manner. With ``Qlib-Server``, users can use ``Qlib`` in ``Online`` mode.
 
 
 
 Reference
-=================
-If users are interested in ``Qlib-Server`` and ``Online`` mode, please refer to `Qlib-Server Project <https://github.com/microsoft/qlib-server>`_ and `Qlib-Server Document <https://qlib-server.readthedocs.io/en/latest/>`_.
+=========
+If users are interested in ``Qlib-Server`` and ``Online`` mode, please refer to `Qlib-Server Project <https://github.com/microsoft/qlib-server>`_ and `Qlib-Server Document <https://qlib-server.readthedocs.io/en/latest/>`_.

docs/advanced/task_management.rst

@@ -1,13 +1,13 @@
 .. _task_management:
 
-=================================
+===============
 Task Management
-=================================
+===============
 .. currentmodule:: qlib
 
 
 Introduction
-=============
+============
 
 The `Workflow <../component/introduction.html>`_ part introduces how to run research workflow in a loosely-coupled way. But it can only execute one ``task`` when you use ``qrun``.
 To automatically generate and execute different tasks, ``Task Management`` provides a whole process including `Task Generating`_, `Task Storing`_, `Task Training`_ and `Task Collecting`_. 
@@ -18,7 +18,7 @@ With this module, users can run their ``task`` automatically at different period
 
 This whole process can be used in `Online Serving <../component/online.html>`_.
 
-An example of the entire process is shown `here <https://github.com/microsoft/qlib/tree/main/examples/model_rolling/task_manager_rolling.py>`_.
+An example of the entire process is shown `here <https://github.com/microsoft/qlib/tree/main/examples/model_rolling/task_manager_rolling.py>`__.
 
 Task Generating
 ===============
@@ -31,12 +31,13 @@ Here is the base class of ``TaskGen``:
 
 .. autoclass:: qlib.workflow.task.gen.TaskGen
     :members:
+    :noindex:
 
 ``Qlib`` provides a class `RollingGen <https://github.com/microsoft/qlib/tree/main/qlib/workflow/task/gen.py>`_ to generate a list of ``task`` of the dataset in different date segments.
-This class allows users to verify the effect of data from different periods on the model in one experiment. More information is `here <../reference/api.html#TaskGen>`_.
+This class allows users to verify the effect of data from different periods on the model in one experiment. More information is `here <../reference/api.html#TaskGen>`__.
 
 Task Storing
-===============
+============
 To achieve higher efficiency and the possibility of cluster operation, ``Task Manager`` will store all tasks in `MongoDB <https://www.mongodb.com/>`_.
 ``TaskManager`` can fetch undone tasks automatically and manage the lifecycle of a set of tasks with error handling.
 Users **MUST** finish the configuration of `MongoDB <https://www.mongodb.com/>`_ when using this module.
@@ -53,22 +54,25 @@ Users need to provide the MongoDB URL and database name for using ``TaskManager`
 
 .. autoclass:: qlib.workflow.task.manage.TaskManager
     :members:
+    :noindex:
 
-More information of ``Task Manager`` can be found in `here <../reference/api.html#TaskManager>`_.
+More information of ``Task Manager`` can be found in `here <../reference/api.html#TaskManager>`__.
 
 Task Training
-===============
+=============
 After generating and storing those ``task``, it's time to run the ``task`` which is in the *WAITING* status.
 ``Qlib`` provides a method called ``run_task`` to run those ``task`` in task pool, however, users can also customize how tasks are executed.
 An easy way to get the ``task_func`` is using ``qlib.model.trainer.task_train`` directly.
 It will run the whole workflow defined by ``task``, which includes *Model*, *Dataset*, *Record*.
 
 .. autofunction:: qlib.workflow.task.manage.run_task
+    :noindex:
 
 Meanwhile, ``Qlib`` provides a module called ``Trainer``. 
 
 .. autoclass:: qlib.model.trainer.Trainer
     :members:
+    :noindex:
 
 ``Trainer`` will train a list of tasks and return a list of model recorders.
 ``Qlib`` offer two kinds of Trainer, TrainerR is the simplest way and TrainerRM is based on TaskManager to help manager tasks lifecycle automatically. 

docs/changelog/changelog.rst

@@ -1,2 +1 @@
 .. include:: ../../CHANGES.rst
-	     

docs/component/data.rst

@@ -1,13 +1,13 @@
 .. _data:
 
-================================
+==================================
 Data Layer: Data Framework & Usage
-================================
+==================================
 
 Introduction
-============================
+============
 
-``Data Layer`` provides user-friendly APIs to manage and retrieve data. It provides high-performance data infrastructure. 
+``Data Layer`` provides user-friendly APIs to manage and retrieve data. It provides high-performance data infrastructure.
 
 It is designed for quantitative investment. For example, users could build formulaic alphas with ``Data Layer`` easily. Please refer to `Building Formulaic Alphas <../advanced/alpha.html>`_ for more details.
 
@@ -23,21 +23,21 @@ The introduction of ``Data Layer`` includes the following parts.
 
 Here is a typical example of Qlib data workflow
 
-- Users download data and converting data into Qlib format(with filename suffix `.bin`).  In this step, typically only some basic data are stored on disk(such as OHLCV). 
-- Creating some basic features based on Qlib's expression Engine(e.g. "Ref($close, 60) / $close", the return of last 60 trading days). Supported operators in the expression engine can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/ops.py>`_. This step is typically implemented in Qlib's `Data Loader <https://qlib.readthedocs.io/en/latest/component/data.html#data-loader>`_ which is a component of `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ .
-- If users require more complicated data processing (e.g. data normalization),  `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ support user-customized processors to process data(some predefined processors can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/dataset/processor.py>`_).  The processors are different from operators in expression engine. It is designed for some complicated data processing methods which is hard to supported in operators in expression engine.
+- Users download data and converting data into Qlib format(with filename suffix `.bin`).  In this step, typically only some basic data are stored on disk(such as OHLCV).
+- Creating some basic features based on Qlib's expression Engine(e.g. "Ref($close, 60) / $close", the return of last 60 trading days). Supported operators in the expression engine can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/ops.py>`__. This step is typically implemented in Qlib's `Data Loader <https://qlib.readthedocs.io/en/latest/component/data.html#data-loader>`_ which is a component of `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ .
+- If users require more complicated data processing (e.g. data normalization),  `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ support user-customized processors to process data(some predefined processors can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/dataset/processor.py>`__).  The processors are different from operators in expression engine. It is designed for some complicated data processing methods which is hard to supported in operators in expression engine.
 - At last, `Dataset <https://qlib.readthedocs.io/en/latest/component/data.html#dataset>`_ is responsible to prepare model-specific dataset from the processed data of Data Handler
 
 Data Preparation
-============================
+================
 
 Qlib Format Data
-------------------
+----------------
 
 We've specially designed a data structure to manage financial data, please refer to the `File storage design section in Qlib paper <https://arxiv.org/abs/2009.11189>`_ for detailed information.
 Such data will be stored with filename suffix `.bin` (We'll call them `.bin` file, `.bin` format, or qlib format). `.bin` file is designed for scientific computing on finance data.
 
-``Qlib`` provides two different off-the-shelf datasets, which can be accessed through this `link <https://github.com/microsoft/qlib/blob/main/qlib/contrib/data/handler.py>`_:
+``Qlib`` provides two different off-the-shelf datasets, which can be accessed through this `link <https://github.com/microsoft/qlib/blob/main/qlib/contrib/data/handler.py>`__:
 
 ========================  =================  ================
 Dataset                   US Market          China Market
@@ -47,12 +47,18 @@ Alpha360                  √                  √
 Alpha158                  √                  √
 ========================  =================  ================
 
-Also, ``Qlib`` provides a high-frequency dataset. Users can run a high-frequency dataset example through this `link <https://github.com/microsoft/qlib/tree/main/examples/highfreq>`_.
+Also, ``Qlib`` provides a high-frequency dataset. Users can run a high-frequency dataset example through this `link <https://github.com/microsoft/qlib/tree/main/examples/highfreq>`__.
 
 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.
-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.
+-------------------
+``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 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. 
+
+- https://github.com/microsoft/qlib/issues/991#issuecomment-1075252402
+
 
 .. code-block:: bash
 
@@ -103,7 +109,7 @@ Automatic update of daily frequency data
 
 
 Converting CSV 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.
 
@@ -113,7 +119,7 @@ Here are some example:
 for daily data:
   .. code-block:: bash
 
-    python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
+    python scripts/get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
 
 for 1min data:
   .. code-block:: bash
@@ -125,33 +131,36 @@ Users can also provide their own data in CSV format. However, the CSV data **mus
 - CSV file is named after a specific stock *or* the CSV file includes a column of the stock name
 
     - Name the CSV file after a stock: `SH600000.csv`, `AAPL.csv` (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:
 
         .. code-block:: bash
 
             python scripts/dump_bin.py dump_all ... --symbol_field_name symbol
-        
+
         where the data are in the following format:
 
-        .. code-block:: 
+            +-----------+-------+
+            | symbol    | close |
+            +===========+=======+
+            | SH600000  | 120   |
+            +-----------+-------+
 
-            symbol,close
-            SH600000,120
-
-- CSV file **must** includes a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
+- CSV file **must** include a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
 
     .. code-block:: bash
 
         python scripts/dump_bin.py dump_all ... --date_field_name date
-    
+
     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.
@@ -171,7 +180,7 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
 .. 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.
-    
+
     - `open`
         The adjusted opening price
     - `close`
@@ -185,11 +194,11 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
     - `factor`
         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. 
+    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.
 
 Stock Pool (Market)
---------------------------------
+-------------------
 
 ``Qlib`` defines `stock pool <https://github.com/microsoft/qlib/blob/main/examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml#L4>`_ as stock list and their date ranges. Predefined stock pools (e.g. csi300) may be imported as follows.
 
@@ -199,7 +208,7 @@ Stock Pool (Market)
 
 
 Multiple Stock Modes
---------------------------------
+--------------------
 
 ``Qlib`` now provides two different stock modes for users: China-Stock Mode & US-Stock Mode. Here are some different settings of these two modes:
 
@@ -217,23 +226,23 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
     - Download china-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in china-stock mode
         Supposed that users download their Qlib format data in the directory ``~/.qlib/qlib_data/cn_data``. Users only need to initialize ``Qlib`` as follows.
-        
+
         .. code-block:: python
 
             from qlib.constant import REG_CN
             qlib.init(provider_uri='~/.qlib/qlib_data/cn_data', region=REG_CN)
-        
+
 
 - If users use ``Qlib`` in US-stock mode, US-stock data is required. ``Qlib`` also provides a script to download US-stock data. Users can use ``Qlib`` in US-stock mode according to the following steps:
     - Download us-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in US-stock mode
         Supposed that users prepare their Qlib format data in the directory ``~/.qlib/qlib_data/us_data``. Users only need to initialize ``Qlib`` as follows.
-        
+
         .. code-block:: python
 
             from qlib.config import REG_US
             qlib.init(provider_uri='~/.qlib/qlib_data/us_data', region=REG_US)
-        
+
 
 .. note::
 
@@ -241,14 +250,14 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
 
 
 Data API
-========================
+========
 
 Data Retrieval
----------------
+--------------
 Users can use APIs in ``qlib.data`` to retrieve data, please refer to `Data Retrieval <../start/getdata.html>`_.
 
 Feature
-------------------
+-------
 
 ``Qlib`` provides `Feature` and `ExpressionOps` to fetch the features according to users' needs.
 
@@ -263,7 +272,7 @@ Feature
 To know more about  ``Feature``, please refer to `Feature API <../reference/api.html#module-qlib.data.base>`_.
 
 Filter
--------------------
+------
 ``Qlib`` provides `NameDFilter` and `ExpressionDFilter` to filter the instruments according to users' needs.
 
 - `NameDFilter`
@@ -271,7 +280,7 @@ Filter
 
 - `ExpressionDFilter`
     Expression dynamic instrument filter. Filter the instruments based on a certain expression. An expression rule indicating a certain feature field is required.
-    
+
     - `basic features filter`: rule_expression = '$close/$open>5'
     - `cross-sectional features filter` \: rule_expression = '$rank($close)<10'
     - `time-sequence features filter`: rule_expression = '$Ref($close, 3)>100'
@@ -298,63 +307,65 @@ Here is a simple example showing how to use filter in a basic ``Qlib`` workflow
 To know more about ``Filter``, please refer to `Filter API <../reference/api.html#module-qlib.data.filter>`_.
 
 Reference
--------------
+---------
 
 To know more about ``Data API``, please refer to `Data API <../reference/api.html#data>`_.
 
 
 Data Loader
-=================
+===========
 
 ``Data Loader`` in ``Qlib`` is designed to load raw data from the original data source. It will be loaded and used in the ``Data Handler`` module.
 
 QlibDataLoader
----------------
+--------------
 
 The ``QlibDataLoader`` class in ``Qlib`` is such an interface that allows users to load raw data from the ``Qlib`` data source.
 
 StaticDataLoader
----------------
+----------------
 
 The ``StaticDataLoader`` class in ``Qlib`` is such an interface that allows users to load raw data from file or as provided.
 
 
 Interface
-------------
+---------
 
 Here are some interfaces of the ``QlibDataLoader`` class:
 
 .. autoclass:: qlib.data.dataset.loader.DataLoader
     :members:
+    :noindex:
 
 API
------------
+---
 
 To know more about ``Data Loader``, please refer to `Data Loader API <../reference/api.html#module-qlib.data.dataset.loader>`_.
 
 
 Data Handler
-=================
+============
 
 The ``Data Handler`` module in ``Qlib`` is designed to handler those common data processing methods which will be used by most of the models.
 
-Users can use ``Data Handler`` in an automatic workflow by ``qrun``, refer to `Workflow: Workflow Management <workflow.html>`_ for more details. 
+Users can use ``Data Handler`` in an automatic workflow by ``qrun``, refer to `Workflow: Workflow Management <workflow.html>`_ for more details.
 
 DataHandlerLP
---------------
+-------------
 
-In addition to use ``Data Handler`` in an automatic workflow with ``qrun``, ``Data Handler`` can be used as an independent module, by which users can easily preprocess data (standardization, remove NaN, etc.) and build datasets. 
+In addition to use ``Data Handler`` in an automatic workflow with ``qrun``, ``Data Handler`` can be used as an independent module, by which users can easily preprocess data (standardization, remove NaN, etc.) and build datasets.
 
 In order to achieve so, ``Qlib`` provides a base class `qlib.data.dataset.DataHandlerLP <../reference/api.html#qlib.data.dataset.handler.DataHandlerLP>`_. The core idea of this class is that: we will have some learnable ``Processors`` which can learn the parameters of data processing(e.g., parameters for zscore normalization). When new data comes in, these `trained` ``Processors`` can then process the new data and thus processing real-time data in an efficient way becomes possible. More information about ``Processors`` will be listed in the next subsection.
 
 
 Interface
-----------------------
+---------
 
 Here are some important interfaces that ``DataHandlerLP`` provides:
 
 .. autoclass:: qlib.data.dataset.handler.DataHandlerLP
     :members: __init__, fetch, get_cols
+    :noindex:
 
 
 If users want to load features and labels by config, users can define a new handler and call the static method `parse_config_to_fields` of ``qlib.contrib.data.handler.Alpha158``.
@@ -363,7 +374,7 @@ Also, users can pass ``qlib.contrib.data.processor.ConfigSectionProcessor`` that
 
 
 Processor
-----------
+---------
 
 The ``Processor`` module in ``Qlib`` is designed to be learnable and it is responsible for handling data processing such as `normalization` and `drop none/nan features/labels`.
 
@@ -381,14 +392,14 @@ The ``Processor`` module in ``Qlib`` is designed to be learnable and it is respo
 - ``CSRankNorm``: `processor` that applies cross sectional rank normalization.
 - ``CSZFillna``: `processor` that fills N/A values in a cross sectional way by the mean of the column.
 
-Users can also create their own `processor` by inheriting the base class of ``Processor``. Please refer to the implementation of all the processors for more information (`Processor Link <https://github.com/microsoft/qlib/blob/main/qlib/data/dataset/processor.py>`_). 
+Users can also create their own `processor` by inheriting the base class of ``Processor``. Please refer to the implementation of all the processors for more information (`Processor Link <https://github.com/microsoft/qlib/blob/main/qlib/data/dataset/processor.py>`_).
 
 To know more about ``Processor``, please refer to `Processor API <../reference/api.html#module-qlib.data.dataset.processor>`_.
 
 Example
---------------
+-------
 
-``Data Handler`` can be run with ``qrun`` by modifying the configuration file, and can also be used as a single module. 
+``Data Handler`` can be run with ``qrun`` by modifying the configuration file, and can also be used as a single module.
 
 Know more about how to run ``Data Handler`` with ``qrun``, please refer to `Workflow: Workflow Management <workflow.html>`_
 
@@ -426,17 +437,17 @@ Qlib provides implemented data handler `Alpha158`. The following example shows h
 .. note:: In the ``Alpha158``, ``Qlib`` uses the label `Ref($close, -2)/Ref($close, -1) - 1` that means the change from T+1 to T+2, rather than `Ref($close, -1)/$close - 1`, of which the reason is that when getting the T day close price of a china stock, the stock can be bought on T+1 day and sold on T+2 day.
 
 API
----------
+---
 
 To know more about ``Data Handler``, please refer to `Data Handler API <../reference/api.html#module-qlib.data.dataset.handler>`_.
 
 
 Dataset
-=================
+=======
 
 The ``Dataset`` module in ``Qlib`` aims to prepare data for model training and inferencing.
 
-The motivation of this module is that we want to maximize the flexibility of of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data. 
+The motivation of this module is that we want to maximize the flexibility of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data.
 
 If user's model need process its data in a different way, user could implement his own ``Dataset`` class. If the model's
 data processing is not special, ``DatasetH`` can be used directly.
@@ -445,32 +456,35 @@ The ``DatasetH`` class is the `dataset` with `Data Handler`. Here is the most im
 
 .. autoclass:: qlib.data.dataset.__init__.DatasetH
     :members:
+    :noindex:
 
 API
----------
+---
 
 To know more about ``Dataset``, please refer to `Dataset API <../reference/api.html#dataset>`_.
 
 
 Cache
-==========
+=====
 
 ``Cache`` is an optional module that helps accelerate providing data by saving some frequently-used data as cache file. ``Qlib`` provides a `Memcache` class to cache the most-frequently-used data in memory, an inheritable `ExpressionCache` class, and an inheritable `DatasetCache` class.
 
 Global Memory Cache
----------------------
+-------------------
 
 `Memcache` is a global memory cache mechanism that composes of three `MemCacheUnit` instances to cache **Calendar**, **Instruments**, and **Features**. The `MemCache` is defined globally in `cache.py` as `H`. Users can use `H['c'], H['i'], H['f']` to get/set `memcache`.
 
 .. autoclass:: qlib.data.cache.MemCacheUnit
     :members:
+    :noindex:
 
 .. autoclass:: qlib.data.cache.MemCache
     :members:
+    :noindex:
 
 
 ExpressionCache
------------------
+---------------
 
 `ExpressionCache` is a cache mechanism that saves expressions such as **Mean($close, 5)**. Users can inherit this base class to define their own cache mechanism that saves expressions according to the following steps.
 
@@ -481,11 +495,12 @@ The following shows the details about the interfaces:
 
 .. autoclass:: qlib.data.cache.ExpressionCache
     :members:
+    :noindex:
 
 ``Qlib`` has currently provided implemented disk cache `DiskExpressionCache` which inherits from `ExpressionCache` . The expressions data will be stored in the disk.
 
 DatasetCache
------------------
+------------
 
 `DatasetCache` is a cache mechanism that saves datasets. A certain dataset is regulated by a stock pool configuration (or a series of instruments, though not recommended), a list of expressions or static feature fields, the start time, and end time for the collected features and the frequency. Users can inherit this base class to define their own cache mechanism that saves datasets according to the following steps.
 
@@ -496,17 +511,18 @@ The following shows the details about the interfaces:
 
 .. autoclass:: qlib.data.cache.DatasetCache
     :members:
+    :noindex:
 
 ``Qlib`` has currently provided implemented disk cache `DiskDatasetCache` which inherits from `DatasetCache` . The datasets' data will be stored in the disk.
 
 
 
 Data and Cache File Structure
-==================================
+=============================
 
 We've specially designed a file structure to manage data and cache, please refer to the `File storage design section in Qlib paper <https://arxiv.org/abs/2009.11189>`_ for detailed information. The file structure of data and cache is listed as follows.
 
-.. code-block:: json
+.. code-block::
 
     - data/
         [raw data] updated by data providers
@@ -535,4 +551,3 @@ We've specially designed a file structure to manage data and cache, please refer
                 - .meta : an assorted meta file recording the stockpool config, field names and visit times
                 - .index : an assorted index file recording the line index of all calendars
             - ...
-

docs/component/highfreq.rst

@@ -1,31 +1,40 @@
 .. _highfreq:
 
-============================================
+========================================================================
 Design of Nested Decision Execution Framework for High-Frequency Trading
-============================================
+========================================================================
 .. currentmodule:: qlib
 
 Introduction
-===================
+============
 
-Daily trading (e.g. portfolio management) and intraday trading (e.g. orders execution) are two hot topics in Quant investment and usually studied separately.
+Daily trading (e.g. portfolio management) and intraday trading (e.g. orders execution) are two hot topics in Quant investment and are usually studied separately.
 
 To get the join trading performance of daily and intraday trading, they must interact with each other and run backtest jointly.
-In order to support the joint backtest strategies in multiple levels, a corresponding framework is required. None of the publicly available high-frequency trading frameworks considers multi-level joint trading, which make the backtesting aforementioned inaccurate.
+In order to support the joint backtest strategies at multiple levels, a corresponding framework is required. None of the publicly available high-frequency trading frameworks considers multi-level joint trading, which makes the backtesting aforementioned inaccurate.
 
 Besides backtesting, the optimization of strategies from different levels is not standalone and can be affected by each other.
-For example, the best portfolio management strategy may change with the performance of order executions(e.g. a portfolio with higher turnover may becomes a better choice when we improve the order execution strategies).
-To achieve the overall good performance , it is necessary to consider the interaction of strategies in different level. 
+For example, the best portfolio management strategy may change with the performance of order executions(e.g. a portfolio with higher turnover may become a better choice when we improve the order execution strategies).
+To achieve overall good performance, it is necessary to consider the interaction of strategies at a different levels.
 
-Therefore, building a new framework for trading in multiple levels becomes necessary to solve the various problems mentioned above, for which we designed a nested decision execution framework that consider the interaction of strategies.
+Therefore, building a new framework for trading on multiple levels becomes necessary to solve the various problems mentioned above, for which we designed a nested decision execution framework that considers the interaction of strategies.
 
 .. image:: ../_static/img/framework.svg
 
-The design of the framework is shown in the yellow part in the middle of the figure above. Each level consists of ``Trading Agent`` and ``Execution Env``. ``Trading Agent`` has its own data processing module (``Information Extractor``), forecasting module (``Forecast Model``) and decision generator (``Decision Generator``). The trading algorithm generates the decisions by the ``Decision Generator`` based on the forecast signals output by the ``Forecast Module``, and the decisions generated by the trading algorithm are passed to the ``Execution Env``, which returns the execution results. 
+The design of the framework is shown in the yellow part in the middle of the figure above. Each level consists of ``Trading Agent`` and ``Execution Env``. ``Trading Agent`` has its own data processing module (``Information Extractor``), forecasting module (``Forecast Model``) and decision generator (``Decision Generator``). The trading algorithm generates the decisions by the ``Decision Generator`` based on the forecast signals output by the ``Forecast Module``, and the decisions generated by the trading algorithm are passed to the ``Execution Env``, which returns the execution results.
 
-The frequency of 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 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 trading algorithm.
+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>`_. 
 
 Example
-===========================
+=======
 
-An example of nested decision execution framework for high-frequency can be found `here <https://github.com/microsoft/qlib/blob/main/examples/nested_decision_execution/workflow.py>`_.
+An example of a nested decision execution framework for high-frequency can be found `here <https://github.com/microsoft/qlib/blob/main/examples/nested_decision_execution/workflow.py>`_.
+
+
+Besides, the above examples, here are some other related works about high-frequency trading in Qlib.
+
+- `Prediction with high-frequency data <https://github.com/microsoft/qlib/tree/main/examples/highfreq#benchmarks-performance-predicting-the-price-trend-in-high-frequency-data>`_
+- `Examples <https://github.com/microsoft/qlib/blob/main/examples/orderbook_data/>`_ to extract features from high-frequency data without fixed frequency.
+- `A paper <https://github.com/microsoft/qlib/tree/high-freq-execution#high-frequency-execution>`_ for high-frequency trading.

docs/component/meta.rst

@@ -1,17 +1,17 @@
 .. _meta:
 
-=================================
+======================================================
 Meta Controller: Meta-Task & Meta-Dataset & Meta-Model
-=================================
+======================================================
 .. currentmodule:: qlib
 
 
 Introduction
-=============
+============
 ``Meta Controller`` provides guidance to ``Forecast Model``, which aims to learn regular patterns among a series of forecasting tasks and use learned patterns to guide forthcoming forecasting tasks. Users can implement their own meta-model instance based on ``Meta Controller`` module.
 
 Meta Task
-=============
+=========
 
 A `Meta Task` instance is the basic element in the meta-learning framework. It saves the data that can be used for the `Meta Model`. Multiple `Meta Task` instances may share the same `Data Handler`, controlled by `Meta Dataset`. Users should use `prepare_task_data()` to obtain the data that can be directly fed into the `Meta Model`.
 
@@ -19,7 +19,7 @@ A `Meta Task` instance is the basic element in the meta-learning framework. It s
     :members:
 
 Meta Dataset
-=============
+============
 
 `Meta Dataset` controls the meta-information generating process. It is on the duty of providing data for training the `Meta Model`. Users should use `prepare_tasks` to retrieve a list of `Meta Task` instances.
 
@@ -27,26 +27,26 @@ Meta Dataset
     :members:
 
 Meta Model
-=============
+==========
 
 General Meta Model
 ------------------
 `Meta Model` instance is the part that controls the workflow. The usage of the `Meta Model` includes:
-1. Users train their `Meta Model` with the `fit` function. 
+1. Users train their `Meta Model` with the `fit` function.
 2. The `Meta Model` instance guides the workflow by giving useful information via the `inference` function.
 
 .. autoclass:: qlib.model.meta.model.MetaModel
     :members:
 
 Meta Task Model
-------------------
+---------------
 This type of meta-model may interact with task definitions directly. Then, the `Meta Task Model` is the class for them to inherit from. They guide the base tasks by modifying the base task definitions. The function `prepare_tasks` can be used to obtain the modified base task definitions.
 
 .. autoclass:: qlib.model.meta.model.MetaTaskModel
     :members:
 
 Meta Guide Model
-------------------
+----------------
 This type of meta-model participates in the training process of the base forecasting model. The meta-model may guide the base forecasting models during their training to improve their performances.
 
 .. autoclass:: qlib.model.meta.model.MetaGuideModel
@@ -54,9 +54,9 @@ This type of meta-model participates in the training process of the base forecas
 
 
 Example
-=============
-``Qlib`` provides an implementation of ``Meta Model`` module, ``DDG-DA``, 
-which adapts to the market dynamics. 
+=======
+``Qlib`` provides an implementation of ``Meta Model`` module, ``DDG-DA``,
+which adapts to the market dynamics.
 
 ``DDG-DA`` includes four steps:
 

docs/component/model.rst

@@ -1,13 +1,13 @@
 .. _model:
 
-============================================
+===========================================
 Forecast Model: Model Training & Prediction
-============================================
+===========================================
 
 Introduction
-===================
+============
 
-``Forecast Model`` is designed to make the `prediction score` about stocks. Users can use the ``Forecast Model`` in an automatic workflow by ``qrun``, please refer to `Workflow: Workflow Management <workflow.html>`_.  
+``Forecast Model`` is designed to make the `prediction score` about stocks. Users can use the ``Forecast Model`` in an automatic workflow by ``qrun``, please refer to `Workflow: Workflow Management <workflow.html>`_.
 
 Because the components in ``Qlib`` are designed in a loosely-coupled way, ``Forecast Model`` can be used as an independent module also.
 
@@ -20,13 +20,14 @@ The base class provides the following interfaces:
 
 .. autoclass:: qlib.model.base.Model
     :members:
+    :noindex:
 
 ``Qlib`` also provides a base class `qlib.model.base.ModelFT <../reference/api.html#qlib.model.base.ModelFT>`_, which includes the method for finetuning the model.
-    
+
 For other interfaces such as `finetune`, please refer to `Model API <../reference/api.html#module-qlib.model.base>`_.
 
 Example
-==================
+=======
 
 ``Qlib``'s `Model Zoo` includes models such as ``LightGBM``, ``MLP``, ``LSTM``, etc.. These models are treated as the baselines of ``Forecast Model``. The following steps show how to run`` LightGBM`` as an independent module.
 
@@ -84,8 +85,8 @@ Example
                 },
             },
         }
-        
-        # model initiaiton
+
+        # model initialization
         model = init_instance_by_config(task["model"])
         dataset = init_instance_by_config(task["dataset"])
 
@@ -100,22 +101,22 @@ Example
             sr = SignalRecord(model, dataset, recorder)
             sr.generate()
 
-    .. note:: 
-        
+    .. note::
+
         `Alpha158` is the data handler provided by ``Qlib``, please refer to `Data Handler <data.html#data-handler>`_.
         `SignalRecord` is the `Record Template` in ``Qlib``, please refer to `Workflow <recorder.html#record-template>`_.
 
 Also, the above example has been given in ``examples/train_backtest_analyze.ipynb``.
 Technically, the meaning of the model prediction depends on the label setting designed by user.
-By default, the meaning of the score is normally the rating of the instruments by the forecasting model. The higher the score, the more profit the instruments. 
+By default, the meaning of the score is normally the rating of the instruments by the forecasting model. The higher the score, the more profit the instruments.
 
 
 Custom Model
-===================
+============
 
 Qlib supports custom models. If users are interested in customizing their own models and integrating the models into ``Qlib``, please refer to `Custom Model Integration <../start/integration.html>`_.
 
 
 API
-===================
+===
 Please refer to `Model API <../reference/api.html#module-qlib.model.base>`_.

docs/component/online.rst

@@ -1,13 +1,13 @@
-.. _online:
+.. _online_serving:
 
-=================================
+==============
 Online Serving
-=================================
+==============
 .. currentmodule:: qlib
 
 
 Introduction
-=============
+============
 
 .. image:: ../_static/img/online_serving.png
     :align: center
@@ -15,7 +15,7 @@ Introduction
 
 In addition to backtesting, one way to test a model is effective is to make predictions in real market conditions or even do real trading based on those predictions.
 ``Online Serving`` is a set of modules for online models using the latest data,
-which including `Online Manager <#Online Manager>`_, `Online Strategy <#Online Strategy>`_, `Online Tool <#Online Tool>`_, `Updater <#Updater>`_. 
+which including `Online Manager <#Online Manager>`_, `Online Strategy <#Online Strategy>`_, `Online Tool <#Online Tool>`_, `Updater <#Updater>`_.
 
 `Here <https://github.com/microsoft/qlib/tree/main/examples/online_srv>`_ are several examples for reference, which demonstrate different features of ``Online Serving``.
 If you have many models or `task` needs to be managed, please consider `Task Management <../advanced/task_management.html>`_.
@@ -28,25 +28,29 @@ Known limitations currently
 
 
 Online Manager
-=============
+==============
 
 .. automodule:: qlib.workflow.online.manager
     :members:
+    :noindex:
 
 Online Strategy
-=============
+===============
 
 .. automodule:: qlib.workflow.online.strategy
     :members:
+    :noindex:
 
 Online Tool
-=============
+===========
 
 .. automodule:: qlib.workflow.online.utils
     :members:
+    :noindex:
 
 Updater
-=============
+=======
 
 .. automodule:: qlib.workflow.online.update
     :members:
+    :noindex:

docs/component/recorder.rst

@@ -6,8 +6,8 @@ Qlib Recorder: Experiment Management
 .. currentmodule:: qlib
 
 Introduction
-===================
-``Qlib`` contains an experiment management system named ``QlibRecorder``, which is designed to help users handle experiment and analyse results in an efficient way. 
+============
+``Qlib`` contains an experiment management system named ``QlibRecorder``, which is designed to help users handle experiment and analyse results in an efficient way.
 
 There are three components of the system:
 
@@ -34,13 +34,13 @@ Here is a general view of the structure of the system:
             - Recorder 2
             - ...
         - ...
-        
-This experiment management system defines a set of interface and provided a concrete implementation ``MLflowExpManager``, which is based on the machine learning platform: ``MLFlow`` (`link <https://mlflow.org/>`_). 
+
+This experiment management system defines a set of interface and provided a concrete implementation ``MLflowExpManager``, which is based on the machine learning platform: ``MLFlow`` (`link <https://mlflow.org/>`_).
 
 If users set the implementation of ``ExpManager`` to be ``MLflowExpManager``, they can use the command `mlflow ui` to visualize and check the experiment results. For more information, please refer to the related documents `here <https://www.mlflow.org/docs/latest/cli.html#mlflow-ui>`_.
 
 Qlib Recorder
-===================
+=============
 ``QlibRecorder`` provides a high level API for users to use the experiment management system. The interfaces are wrapped in the variable ``R`` in ``Qlib``, and users can directly use ``R`` to interact with the system. The following command shows how to import ``R`` in Python:
 
 .. code-block:: Python
@@ -55,29 +55,31 @@ Here are the available interfaces of ``QlibRecorder``:
     :members:
 
 Experiment Manager
-===================
+==================
 
 The ``ExpManager`` module in ``Qlib`` is responsible for managing different experiments. Most of the APIs of ``ExpManager`` are similar to ``QlibRecorder``, and the most important API will be the ``get_exp`` method. User can directly refer to the documents above for some detailed information about how to use the ``get_exp`` method.
 
 .. autoclass:: qlib.workflow.expm.ExpManager
     :members: get_exp, list_experiments
+    :noindex:
 
 For other interfaces such as `create_exp`, `delete_exp`, please refer to `Experiment Manager API <../reference/api.html#experiment-manager>`_.
 
 Experiment
-===================
+==========
 
 The ``Experiment`` class is solely responsible for a single experiment, and it will handle any operations that are related to an experiment. Basic methods such as `start`, `end` an experiment are included. Besides, methods related to `recorders` are also available: such methods include `get_recorder` and `list_recorders`.
 
 .. autoclass:: qlib.workflow.exp.Experiment
     :members: get_recorder, list_recorders
+    :noindex:
 
 For other interfaces such as `search_records`, `delete_recorder`, please refer to `Experiment API <../reference/api.html#experiment>`_.
 
 ``Qlib`` also provides a default ``Experiment``, which will be created and used under certain situations when users use the APIs such as `log_metrics` or `get_exp`. If the default ``Experiment`` is used, there will be related logged information when running ``Qlib``. Users are able to change the name of the default ``Experiment`` in the config file of ``Qlib`` or during ``Qlib``'s `initialization <../start/initialization.html#parameters>`_, which is set to be '`Experiment`'.
 
 Recorder
-===================
+========
 
 The ``Recorder`` class is responsible for a single recorder. It will handle some detailed operations such as ``log_metrics``, ``log_params`` of a single run. It is designed to help user to easily track results and things being generated during a run.
 
@@ -85,11 +87,12 @@ Here are some important APIs that are not included in the ``QlibRecorder``:
 
 .. autoclass:: qlib.workflow.recorder.Recorder
     :members: list_artifacts, list_metrics, list_params, list_tags
+    :noindex:
 
 For other interfaces such as `save_objects`, `load_object`, please refer to `Recorder API <../reference/api.html#recorder>`_.
 
 Record Template
-===================
+===============
 
 The ``RecordTemp`` class is a class that enables generate experiment results such as IC and backtest in a certain format. We have provided three different `Record Template` class:
 
@@ -107,7 +110,7 @@ Here is a simple example of what is done in ``SigAnaRecord``, which users can re
 
 - ``PortAnaRecord``: This class generates the results of `backtest`. The detailed information about `backtest` as well as the available `strategy`, users can refer to `Strategy <../component/strategy.html>`_ and `Backtest <../component/backtest.html>`_.
 
-Here is a simple exampke of what is done in ``PortAnaRecord``, which users can refer to if they want to do backtest based on their own prediction and label.
+Here is a simple example of what is done in ``PortAnaRecord``, which users can refer to if they want to do backtest based on their own prediction and label.
 
 .. code-block:: Python
 
@@ -131,7 +134,7 @@ Here is a simple exampke of what is done in ``PortAnaRecord``, which users can r
         "close_cost": 0.0015,
         "min_cost": 5,
     }
-    
+
     strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
     report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
 
@@ -143,3 +146,9 @@ Here is a simple exampke of what is done in ``PortAnaRecord``, which users can r
     print(analysis_df)
 
 For more information about the APIs, please refer to `Record Template API <../reference/api.html#module-qlib.workflow.record_temp>`_.
+
+
+
+Known Limitations
+=================
+- The Python objects are saved based on pickle, which may results in issues when the environment dumping objects and loading objects are different.

docs/component/report.rst

@@ -1,11 +1,11 @@
 .. _report:
 
-==========================================
+=======================================
 Analysis: Evaluation & Results Analysis
-==========================================
+=======================================
 
 Introduction
-===================
+============
 
 ``Analysis`` is designed to show the graphical reports of ``Intraday Trading`` , which helps users to evaluate and analyse investment portfolios visually. The following are some graphics to view:
 
@@ -20,8 +20,11 @@ Introduction
     - model_performance_graph
 
 
+All of the accumulated profit metrics(e.g. return, max drawdown) in Qlib are calculated by summation.
+This avoids the metrics or the plots being skewed exponentially over time.
+
 Graphical Reports
-===================
+=================
 
 Users can run the following code to get all supported reports.
 
@@ -38,16 +41,17 @@ Users can run the following code to get all supported reports.
 
 
 Usage & Example
-===================
+===============
 
 Usage of `analysis_position.report`
 -----------------------------------
 
 API
-~~~~~~~~~~~~~~~~
+~~~
 
 .. automodule:: qlib.contrib.report.analysis_position.report
     :members:
+    :noindex:
 
 Graphical Result
 ~~~~~~~~~~~~~~~~
@@ -55,7 +59,7 @@ Graphical Result
 .. note::
 
     - Axis X: Trading day
-    - Axis Y: 
+    - Axis Y:
         - `cum bench`
             Cumulative returns series of benchmark
         - `cum return wo cost`
@@ -79,34 +83,35 @@ Graphical Result
     - The shaded part above: Maximum drawdown corresponding to `cum return wo cost`
     - The shaded part below: Maximum drawdown corresponding to `cum ex return wo cost`
 
-.. image:: ../_static/img/analysis/report.png 
+.. image:: ../_static/img/analysis/report.png
 
 
 Usage of `analysis_position.score_ic`
 -------------------------------------
 
 API
-~~~~~~~~~~~~~~~~
+~~~
 
 .. automodule:: qlib.contrib.report.analysis_position.score_ic
     :members:
+    :noindex:
 
 
 Graphical Result
-~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~
 
-.. note:: 
+.. note::
 
     - Axis X: Trading day
-    - Axis Y: 
+    - Axis Y:
         - `ic`
             The `Pearson correlation coefficient` series between `label` and `prediction score`.
-            In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. Please refer to `Data Feature <data.html#feature>`_ for more details.
-                
+            In the above example, the `label` is formulated as `Ref($close, -2)/Ref($close, -1)-1`. Please refer to `Data Feature <data.html#feature>`_ for more details.
+
         - `rank_ic`
             The `Spearman's rank correlation coefficient` series between `label` and `prediction score`.
 
-.. image:: ../_static/img/analysis/score_ic.png 
+.. image:: ../_static/img/analysis/score_ic.png
 
 
 .. Usage of `analysis_position.cumulative_return`
@@ -121,7 +126,7 @@ Graphical Result
 .. Graphical Result
 .. ~~~~~~~~~~~~~~~~~
 ..
-.. .. note:: 
+.. .. note::
 ..
 ..     - Axis X: Trading day
 ..     - Axis Y:
@@ -131,27 +136,28 @@ Graphical Result
 ..     - In the **buy_minus_sell** graph, the **y** value of the **weight** graph at the bottom is `buy_weight + sell_weight`.
 ..     - In each graph, the **red line** in the histogram on the right represents the average.
 ..
-.. .. image:: ../_static/img/analysis/cumulative_return_buy.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_buy.png
 ..
-.. .. image:: ../_static/img/analysis/cumulative_return_sell.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_sell.png
 ..
-.. .. image:: ../_static/img/analysis/cumulative_return_buy_minus_sell.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_buy_minus_sell.png
 ..
-.. .. image:: ../_static/img/analysis/cumulative_return_hold.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_hold.png
 
 
 Usage of `analysis_position.risk_analysis`
-----------------------------------------------
+------------------------------------------
 
 API
-~~~~~~~~~~~~~~~~
+~~~
 
 .. automodule:: qlib.contrib.report.analysis_position.risk_analysis
     :members:
+    :noindex:
 
 
 Graphical Result
-~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~
 
 .. note::
 
@@ -171,6 +177,7 @@ Graphical Result
                 The `Information Ratio` without cost.
             - `excess_return_with_cost`
                 The `Information Ratio` with cost.
+
             To know more about `Information Ratio`, please refer to `Information Ratio – IR <https://www.investopedia.com/terms/i/informationratio.asp>`_.
         -  `max_drawdown`
             - `excess_return_without_cost`
@@ -207,7 +214,7 @@ Graphical Result
                     The `Standard Deviation` series of monthly `CAR` (cumulative abnormal return) without cost.
                 - `excess_return_with_cost_max_drawdown`
                     The `Standard Deviation` series of monthly `CAR` (cumulative abnormal return) with cost.
-                
+
 
 .. image:: ../_static/img/analysis/risk_analysis_annualized_return.png
     :align: center
@@ -218,58 +225,59 @@ Graphical Result
 .. image:: ../_static/img/analysis/risk_analysis_information_ratio.png
     :align: center
 
-.. image:: ../_static/img/analysis/risk_analysis_std.png 
+.. image:: ../_static/img/analysis/risk_analysis_std.png
     :align: center
 
 ..
 .. Usage of `analysis_position.rank_label`
-.. ----------------------------------------------
+.. ---------------------------------------
 ..
 .. API
-.. ~~~~~
+.. ~~~
 ..
 .. .. automodule:: qlib.contrib.report.analysis_position.rank_label
 ..     :members:
 ..
 ..
 .. Graphical Result
-.. ~~~~~~~~~~~~~~~~~
+.. ~~~~~~~~~~~~~~~~
 ..
-.. .. note:: 
+.. .. note::
 ..
 ..     - hold/sell/buy graphics:
 ..         - Axis X: Trading day
-..         - Axis Y: 
+..         - Axis Y:
 ..             Average `ranking ratio`of `label` for stocks that is held/sold/bought on the trading day.
 ..
 ..             In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. The `ranking ratio` can be formulated as follows.
 ..             .. math::
-..                 
+..
 ..                 ranking\ ratio = \frac{Ascending\ Ranking\ of\ label}{Number\ of\ Stocks\ in\ the\ Portfolio}
 ..
-.. .. image:: ../_static/img/analysis/rank_label_hold.png 
+.. .. image:: ../_static/img/analysis/rank_label_hold.png
 ..     :align: center
 ..
-.. .. image:: ../_static/img/analysis/rank_label_buy.png 
+.. .. image:: ../_static/img/analysis/rank_label_buy.png
 ..     :align: center
 ..
-.. .. image:: ../_static/img/analysis/rank_label_sell.png 
+.. .. image:: ../_static/img/analysis/rank_label_sell.png
 ..     :align: center
 ..
 ..
 
 Usage of `analysis_model.analysis_model_performance`
------------------------------------------------------
+----------------------------------------------------
 
 API
-~~~~~
+~~~
 
 .. automodule:: qlib.contrib.report.analysis_model.analysis_model_performance
     :members:
+    :noindex:
 
 
 Graphical Results
-~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~
 
 .. note::
 
@@ -288,13 +296,13 @@ Graphical Results
             The Difference series between `Cumulative Return` of `Group1` and of `Group5`
         - `long-average`
             The Difference series between `Cumulative Return` of `Group1` and average `Cumulative Return` for all stocks.
-        
+
         The `ranking ratio` can be formulated as follows.
             .. math::
-                
+
                 ranking\ ratio = \frac{Ascending\ Ranking\ of\ label}{Number\ of\ Stocks\ in\ the\ Portfolio}
 
-.. image:: ../_static/img/analysis/analysis_model_cumulative_return.png 
+.. image:: ../_static/img/analysis/analysis_model_cumulative_return.png
     :align: center
 
 .. note::
@@ -302,7 +310,7 @@ Graphical Results
         The distribution of long-short/long-average returns on each trading day
 
 
-.. image:: ../_static/img/analysis/analysis_model_long_short.png 
+.. image:: ../_static/img/analysis/analysis_model_long_short.png
     :align: center
 
 .. TODO: ask xiao yang for detial
@@ -312,14 +320,14 @@ Graphical Results
         - The `Pearson correlation coefficient` series between `labels` and `prediction scores` of stocks in portfolio.
         - The graphics reports can be used to evaluate the `prediction scores`.
 
-.. image:: ../_static/img/analysis/analysis_model_IC.png 
+.. image:: ../_static/img/analysis/analysis_model_IC.png
     :align: center
 
 .. note::
     - Monthly IC
         Monthly average of the `Information Coefficient`
 
-.. image:: ../_static/img/analysis/analysis_model_monthly_IC.png 
+.. image:: ../_static/img/analysis/analysis_model_monthly_IC.png
     :align: center
 
 .. note::
@@ -328,14 +336,14 @@ Graphical Results
     - IC Normal Dist. Q-Q
         The `Quantile-Quantile Plot` is used for the normal distribution of `Information Coefficient` on each trading day.
 
-.. image:: ../_static/img/analysis/analysis_model_NDQ.png 
+.. image:: ../_static/img/analysis/analysis_model_NDQ.png
     :align: center
 
 .. note::
     - Auto Correlation
-        - The `Pearson correlation coefficient` series between the latest `prediction scores` and the `prediction scores` `lag` days ago of stocks in portfolio on each trading day. 
+        - The `Pearson correlation coefficient` series between the latest `prediction scores` and the `prediction scores` `lag` days ago of stocks in portfolio on each trading day.
         - The graphics reports can be used to estimate the turnover rate.
-         
 
-.. image:: ../_static/img/analysis/analysis_model_auto_correlation.png 
+
+.. image:: ../_static/img/analysis/analysis_model_auto_correlation.png
     :align: center

docs/component/rl/framework.rst

@@ -0,0 +1,49 @@
+The Framework of QlibRL
+=======================
+
+QlibRL contains a full set of components that cover the entire lifecycle of an RL pipeline, including building the simulator of the market, shaping states & actions, training policies (strategies), and backtesting strategies in the simulated environment.
+
+QlibRL is basically implemented with the support of Tianshou and Gym frameworks. The high-level structure of QlibRL is demonstrated below:
+
+.. image:: ../../_static/img/QlibRL_framework.png
+   :width: 600
+   :align: center
+
+Here, we briefly introduce each component in the figure.
+
+EnvWrapper
+------------
+EnvWrapper is the complete capsulation of the simulated environment. It receives actions from outside (policy/strategy/agent), simulates the changes in the market, and then replies rewards and updated states, thus forming an interaction loop.
+
+In QlibRL, EnvWrapper is a subclass of gym.Env, so it implements all necessary interfaces of gym.Env. Any classes or pipelines that accept gym.Env should also accept EnvWrapper. Developers do not need to implement their own EnvWrapper to build their own environment. Instead, they only need to implement 4 components of the EnvWrapper:
+
+- `Simulator`
+    The simulator is the core component responsible for the environment simulation. Developers could implement all the logic that is directly related to the environment simulation in the Simulator in any way they like. In QlibRL, there are already two implementations of Simulator for single asset trading: 1) ``SingleAssetOrderExecution``, which is built based on Qlib's backtest toolkits and hence considers a lot of practical trading details but is slow. 2) ``SimpleSingleAssetOrderExecution``, which is built based on a simplified trading simulator, which ignores a lot of details (e.g. trading limitations, rounding) but is quite fast.
+- `State interpreter` 
+    The state interpreter is responsible for "interpret" states in the original format (format provided by the simulator) into states in a format that the policy could understand. For example, transform unstructured raw features into numerical tensors.
+- `Action interpreter` 
+    The action interpreter is similar to the state interpreter. But instead of states, it interprets actions generated by the policy, from the format provided by the policy to the format that is acceptable to the simulator.
+- `Reward function` 
+    The reward function returns a numerical reward to the policy after each time the policy takes an action. 
+
+EnvWrapper will organically organize these components. Such decomposition allows for better flexibility in development. For example, if the developers want to train multiple types of policies in the same environment, they only need to design one simulator and design different state interpreters/action interpreters/reward functions for different types of policies.
+
+QlibRL has well-defined base classes for all these 4 components. All the developers need to do is define their own components by inheriting the base classes and then implementing all interfaces required by the base classes. The API for the above base components can be found `here <../../reference/api.html#module-qlib.rl>`__.
+
+Policy
+------------
+QlibRL directly uses Tianshou's policy. Developers could use policies provided by Tianshou off the shelf, or implement their own policies by inheriting Tianshou's policies.
+
+Training Vessel & Trainer
+-------------------------
+As stated by their names, training vessels and trainers are helper classes used in training. A training vessel is a ship that contains a simulator/interpreters/reward function/policy, and it controls algorithm-related parts of training. Correspondingly, the trainer is responsible for controlling the runtime parts of training.
+
+As you may have noticed, a training vessel itself holds all the required components to build an EnvWrapper rather than holding an instance of EnvWrapper directly. This allows the training vessel to create duplicates of EnvWrapper dynamically when necessary (for example, under parallel training).
+
+With a training vessel, the trainer could finally launch the training pipeline by simple, Scikit-learn-like interfaces (i.e., ``trainer.fit()``).
+
+The API for Trainer and TrainingVessel and can be found `here <../../reference/api.html#module-qlib.rl.trainer>`__.
+
+The RL module is designed in a loosely-coupled way. Currently, RL examples are integrated with concrete business logic.
+But the core part of RL is much simpler than what you see.
+To demonstrate the simple core of RL, `a dedicated notebook <https://github.com/microsoft/qlib/tree/main/examples/rl/simple_example.ipynb>`__ for RL without business loss is created.

docs/component/rl/guidance.rst

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

docs/component/rl/overall.rst

@@ -0,0 +1,70 @@
+=====================================================
+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(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. 
+In general, the agent can perceive and interpret its environment, take actions and learn through reward, to seek long-term and maximum overall reward to achieve an optimal solution.
+
+.. image:: ../../_static/img/RL_framework.png
+   :width: 300
+   :align: center 
+
+RL attempts to learn to produce actions by trial and error. 
+By sampling actions and then observing which one leads to our desired outcome, a policy is obtained to generate optimal actions. 
+In contrast to supervised learning, RL learns this not from a label but from a time-delayed label called a reward. 
+This scalar value lets us know whether the current outcome is good or bad. 
+In a word, the target of RL is to take actions to maximize reward.
+
+The Qlib Reinforcement Learning toolkit (QlibRL) is an RL platform for quantitative investment, which provides support to implement the RL algorithms in Qlib.
+
+
+Potential Application Scenarios in Quantitative Trading
+=======================================================
+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
+---------------
+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.
+
+ - 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.
+
+    - 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.
+
+    - 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.
+
+    - 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/quickstart.rst

@@ -0,0 +1,175 @@
+
+Quick Start
+============
+.. currentmodule:: qlib
+
+QlibRL provides an example of an implementation of a single asset order execution task and the following is an example of the config file to train with QlibRL.
+
+.. code-block:: yaml
+
+    simulator:
+        # Each step contains 30mins
+        time_per_step: 30
+        # Upper bound of volume, should be null or a float between 0 and 1, if it is a float, represent upper bound is calculated by the percentage of the market volume
+        vol_limit: null
+    env:
+        # Concurrent environment workers.
+        concurrency: 1
+        # dummy or subproc or shmem. Corresponding to `parallelism in tianshou <https://tianshou.readthedocs.io/en/master/api/tianshou.env.html#vectorenv>`_.
+        parallel_mode: dummy
+    action_interpreter:
+        class: CategoricalActionInterpreter
+        kwargs:
+            # Candidate actions, it can be a list with length L: [a_1, a_2,..., a_L] or an integer n, in which case the list of length n+1 is auto-generated, i.e., [0, 1/n, 2/n,..., n/n].
+            values: 14
+            # Total number of steps (an upper-bound estimation)
+            max_step: 8
+        module_path: qlib.rl.order_execution.interpreter
+    state_interpreter:
+        class: FullHistoryStateInterpreter
+        kwargs:
+            # Number of dimensions in data.
+            data_dim: 6
+            # Equal to the total number of records. For example, in SAOE per minute, data_ticks is the length of the day in minutes.
+            data_ticks: 240
+            # The total number of steps (an upper-bound estimation). For example, 390min / 30min-per-step = 13 steps.
+            max_step: 8
+            # Provider of the processed data.
+            processed_data_provider:
+                class: PickleProcessedDataProvider
+                module_path: qlib.rl.data.pickle_styled
+                kwargs:
+                    data_dir: ./data/pickle_dataframe/feature
+        module_path: qlib.rl.order_execution.interpreter
+    reward:
+        class: PAPenaltyReward
+        kwargs:
+            # The penalty for a large volume in a short time.
+            penalty: 100.0
+        module_path: qlib.rl.order_execution.reward
+    data:
+        source:
+            order_dir: ./data/training_order_split
+            data_dir: ./data/pickle_dataframe/backtest
+            # number of time indexes
+            total_time: 240
+            # start time index
+            default_start_time: 0
+            # end time index
+            default_end_time: 240
+            proc_data_dim: 6
+        num_workers: 0
+        queue_size: 20
+    network:
+        class: Recurrent
+        module_path: qlib.rl.order_execution.network
+    policy:
+        class: PPO
+        kwargs:
+            lr: 0.0001
+        module_path: qlib.rl.order_execution.policy
+    runtime:
+        seed: 42
+        use_cuda: false
+    trainer:
+        max_epoch: 2
+        # Number of episodes collected in each training iteration
+        repeat_per_collect: 5
+        earlystop_patience: 2
+        # Episodes per collect at training.
+        episode_per_collect: 20
+        batch_size: 16
+        # Perform validation every n iterations
+        val_every_n_epoch: 1
+        checkpoint_path: ./checkpoints
+        checkpoint_every_n_iters: 1
+
+
+And the config file for backtesting:
+
+.. code-block:: yaml
+
+    order_file: ./data/backtest_orders.csv
+    start_time: "9:45"
+    end_time: "14:44"
+    qlib:
+        provider_uri_1min: ./data/bin
+        feature_root_dir: ./data/pickle
+        # feature generated by today's information
+        feature_columns_today: [
+            "$open", "$high", "$low", "$close", "$vwap", "$volume",
+        ]
+        # feature generated by yesterday's information
+        feature_columns_yesterday: [
+            "$open_v1", "$high_v1", "$low_v1", "$close_v1", "$vwap_v1", "$volume_v1",
+        ]
+    exchange:
+        # the expression for buying and selling stock limitation
+        limit_threshold: ['$close == 0', '$close == 0']
+        # deal price for buying and selling
+        deal_price: ["If($close == 0, $vwap, $close)", "If($close == 0, $vwap, $close)"]
+    volume_threshold:
+        # volume limits are both buying and selling, "cum" means that this is a cumulative value over time
+        all: ["cum", "0.2 * DayCumsum($volume, '9:45', '14:44')"]
+        # the volume limits of buying
+        buy: ["current", "$close"]
+        # the volume limits of selling, "current" means that this is a real-time value and will not accumulate over time
+        sell: ["current", "$close"]
+    strategies: 
+        30min: 
+            class: TWAPStrategy
+            module_path: qlib.contrib.strategy.rule_strategy
+            kwargs: {}
+        1day: 
+            class: SAOEIntStrategy
+            module_path: qlib.rl.order_execution.strategy
+            kwargs:
+            state_interpreter:
+                class: FullHistoryStateInterpreter
+                module_path: qlib.rl.order_execution.interpreter
+                kwargs:
+                max_step: 8
+                data_ticks: 240
+                data_dim: 6
+                processed_data_provider:
+                    class: PickleProcessedDataProvider
+                    module_path: qlib.rl.data.pickle_styled
+                    kwargs:
+                    data_dir: ./data/pickle_dataframe/feature
+            action_interpreter: 
+                class: CategoricalActionInterpreter
+                module_path: qlib.rl.order_execution.interpreter
+                kwargs: 
+                values: 14
+                max_step: 8
+            network: 
+                class: Recurrent
+                module_path: qlib.rl.order_execution.network
+                kwargs: {}
+            policy: 
+                class: PPO
+                module_path: qlib.rl.order_execution.policy
+                kwargs: 
+                    lr: 1.0e-4
+                    # Local path to the latest model. The model is generated during training, so please run training first if you want to run backtest with a trained policy. You could also remove this parameter file to run backtest with a randomly initialized policy.
+                    weight_file: ./checkpoints/latest.pth
+    # Concurrent environment workers.
+    concurrency: 5
+
+With the above config files, you can start training the agent by the following command:
+
+.. code-block:: console
+
+    $ python -m qlib.rl.contrib.train_onpolicy.py --config_path train_config.yml
+
+After the training, you can backtest with the following command:
+
+.. code-block:: console
+
+    $ python -m qlib.rl.contrib.backtest.py --config_path backtest_config.yml
+
+In that case, :class:`~qlib.rl.order_execution.simulator_qlib.SingleAssetOrderExecution` and :class:`~qlib.rl.order_execution.simulator_simple.SingleAssetOrderExecutionSimple` as examples for simulator, :class:`qlib.rl.order_execution.interpreter.FullHistoryStateInterpreter` and :class:`qlib.rl.order_execution.interpreter.CategoricalActionInterpreter` as examples for interpreter, :class:`qlib.rl.order_execution.policy.PPO` as an example for policy, and :class:`qlib.rl.order_execution.reward.PAPenaltyReward` as an example for reward.
+For the single asset order execution task, if developers have already defined their simulator/interpreters/reward function/policy, they could launch the training and backtest pipeline by simply modifying the corresponding settings in the config files.
+The details about the example can be found `here <https://github.com/microsoft/qlib/blob/main/examples/rl/README.md>`_. 
+
+In the future, we will provide more examples for different scenarios such as RL-based portfolio construction.

docs/component/rl/toctree.rst

@@ -0,0 +1,11 @@
+.. _rl:
+
+========================================================================
+Reinforcement Learning in Quantitative Trading
+========================================================================
+
+.. toctree::
+    Guidance <guidance>
+    Overall <overall>
+    Quick Start <quickstart>
+    Framework <framework>

docs/component/strategy.rst

@@ -6,7 +6,7 @@ Portfolio Strategy: Portfolio Management
 .. currentmodule:: qlib
 
 Introduction
-===================
+============
 
 ``Portfolio Strategy`` is designed to adopt different portfolio strategies, which means that users can adopt different algorithms to generate investment portfolios based on the prediction scores of the ``Forecast Model``. Users can use the ``Portfolio Strategy`` in an automatic workflow by ``Workflow`` module, please refer to `Workflow: Workflow Management <workflow.html>`_.
 
@@ -20,22 +20,19 @@ Base Class & Interface
 ======================
 
 BaseStrategy
-------------------
+------------
 
 Qlib provides a base class ``qlib.strategy.base.BaseStrategy``. All strategy classes need to inherit the base class and implement its interface.
 
-- `get_risk_degree`
-    Return the proportion of your total value you will use in investment. Dynamically risk_degree will result in Market timing.
-
-- `generate_order_list`
-    Return the order list.
+- `generate_trade_decision`
+    generate_trade_decision is a key interface that generates trade decisions in each trading bar.
     The frequency to call this method depends on the executor frequency("time_per_step"="day" by default). But the trading frequency can be decided by users' implementation.
     For example, if the user wants to trading in weekly while the `time_per_step` is "day" in executor, user can return non-empty TradeDecision weekly(otherwise return empty like `this <https://github.com/microsoft/qlib/blob/main/qlib/contrib/strategy/signal_strategy.py#L132>`_ ).
 
 Users can inherit `BaseStrategy` to customize their strategy class.
 
 WeightStrategyBase
---------------------
+------------------
 
 Qlib also provides a class ``qlib.contrib.strategy.WeightStrategyBase`` that is a subclass of `BaseStrategy`.
 
@@ -63,24 +60,31 @@ Implemented Strategy
 Qlib provides a implemented strategy classes named `TopkDropoutStrategy`.
 
 TopkDropoutStrategy
-------------------
+-------------------
 `TopkDropoutStrategy` is a subclass of `BaseStrategy` and implement the interface `generate_order_list` whose process is as follows.
 
 - Adopt the ``Topk-Drop`` algorithm to calculate the target amount of each stock
 
     .. note::
-        ``Topk-Drop`` algorithm：
+        There are two parameters for the ``Topk-Drop`` algorithm:
 
         - `Topk`: The number of stocks held
         - `Drop`: The number of stocks sold on each trading day
 
-        Currently, the number of held stocks is `Topk`.
-        On each trading day, the `Drop` number of held stocks with the worst `prediction score` will be sold, and the same number of unheld stocks with the best `prediction score` will be bought.
+        In general, the number of stocks currently held is `Topk`, with the exception of being zero at the beginning period of trading.
+        For each trading day, let $d$ be the number of the instruments currently held and with a rank $\gt K$ when ranked by the prediction scores from high to low.
+        Then `d` number of stocks currently held with the worst `prediction score` will be sold, and the same number of unheld stocks with the best `prediction score` will be bought.
+
+        In general, $d=$`Drop`, especially when the pool of the candidate instruments is large, $K$ is large, and `Drop` is small.
+
+        In most cases, ``TopkDrop`` algorithm sells and buys `Drop` stocks every trading day, which yields a turnover rate of 2$\times$`Drop`/$K$.
+
+        The following images illustrate a typical scenario.
 
         .. image:: ../_static/img/topk_drop.png
             :alt: Topk-Drop
 
-        ``TopkDrop`` algorithm sells `Drop` stocks every trading day, which guarantees a fixed turnover rate.
+
 
 - Generate the order list from the target amount
 
@@ -95,12 +99,12 @@ and `qlib.contrib.strategy.optimizer.enhanced_indexing.EnhancedIndexingOptimizer
 
 
 Usage & Example
-====================
+===============
 
 First, user can create a model to get trading signals(the variable name is ``pred_score`` in following cases).
 
 Prediction Score
------------------
+----------------
 
 The `prediction score` is a pandas DataFrame. Its index is <datetime(pd.Timestamp), instrument(str)> and it must
 contains a `score` column.
@@ -126,10 +130,12 @@ A prediction sample is shown as follows.
 
 Normally, the prediction score is the output of the models. But some models are learned from a label with a different scale. So the scale of the prediction score may be different from your expectation(e.g. the return of instruments).
 
-Qlib didn't add a step to scale the prediction score to a unified scale. Because not every trading strategy cares about the scale(e.g. TopkDropoutStrategy only cares about the order).  So the strategy is responsible for rescaling the prediction score(e.g. some portfolio-optimization-based strategies may require a meaningful scale).
+Qlib didn't add a step to scale the prediction score to a unified scale due to the following reasons.
+- Because not every trading strategy cares about the scale(e.g. TopkDropoutStrategy only cares about the order).  So the strategy is responsible for rescaling the prediction score(e.g. some portfolio-optimization-based strategies may require a meaningful scale).
+- The model has the flexibility to define the target, loss, and data processing. So we don't think there is a silver bullet to rescale it back directly barely based on the model's outputs. If you want to scale it back to some meaningful values(e.g. stock returns.), an intuitive solution is to create a regression model for the model's recent outputs and your recent target values.
 
 Running backtest
------------------
+----------------
 
 - In most cases, users could backtest their portfolio management strategy  with ``backtest_daily``.
 
@@ -162,12 +168,9 @@ Running backtest
             start_time="2017-01-01", end_time="2020-08-01", strategy=strategy_obj
         )
         analysis = dict()
-        analysis["excess_return_without_cost"] = risk_analysis(
-            report_normal["return"] - report_normal["bench"], freq=analysis_freq
-        )
-        analysis["excess_return_with_cost"] = risk_analysis(
-            report_normal["return"] - report_normal["bench"] - report_normal["cost"], freq=analysis_freq
-        )
+        # default frequency will be daily (i.e. "day")
+        analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+        analysis["excess_return_with_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"] - report_normal["cost"])
 
         analysis_df = pd.concat(analysis)  # type: pd.DataFrame
         pprint(analysis_df)
@@ -192,6 +195,14 @@ Running backtest
         qlib.init(provider_uri=<qlib data dir>)
 
         CSI300_BENCH = "SH000300"
+        # Benchmark is for calculating the excess return of your strategy.
+        # Its data format will be like **ONE normal instrument**.
+        # For example, you can query its data with the code below
+        # `D.features(["SH000300"], ["$close"], start_time='2010-01-01', end_time='2017-12-31', freq='day')`
+        # It is different from the argument `market`, which indicates a universe of stocks (e.g. **A SET** of stocks like csi300)
+        # For example, you can query all data from a stock market with the code below.
+        # ` D.features(D.instruments(market='csi300'), ["$close"], start_time='2010-01-01', end_time='2017-12-31', freq='day')`
+
         FREQ = "day"
         STRATEGY_CONFIG = {
             "topk": 50,
@@ -252,7 +263,7 @@ Running backtest
 
 
 Result
-------------------
+------
 
 The backtest results are in the following form:
 
@@ -297,5 +308,5 @@ The backtest results are in the following form:
 
 
 Reference
-===================
+=========
 To know more about the `prediction score` `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.

docs/component/workflow.rst

@@ -1,12 +1,12 @@
 .. _workflow:
 
-=================================
+=============================
 Workflow: Workflow Management
-=================================
+=============================
 .. currentmodule:: qlib
 
 Introduction
-===================
+============
 
 The components in `Qlib Framework <../introduction/introduction.html#framework>`_ are designed in a loosely-coupled way. Users could build their own Quant research workflow with these components like `Example <https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.py>`_.
 
@@ -28,7 +28,7 @@ With ``qrun``, user can easily start an `execution`, which includes the followin
 For each `execution`, ``Qlib`` has a complete system to tracking all the information as well as artifacts generated during training, inference and evaluation phase. For more information about how ``Qlib`` handles this, please refer to the related document: `Recorder: Experiment Management <../component/recorder.html>`_.
 
 Complete Example
-===================
+================
 
 Before getting into details, here is a complete example of ``qrun``, which defines the workflow in typical Quant research.
 Below is a typical config file of ``qrun``.
@@ -53,9 +53,7 @@ Below is a typical config file of ``qrun``.
             kwargs:
                 topk: 50
                 n_drop: 5
-                signal:
-                    - <MODEL> 
-                    - <DATASET>
+                signal: <PRED>
         backtest:
             limit_threshold: 0.095
             account: 100000000
@@ -90,13 +88,13 @@ Below is a typical config file of ``qrun``.
                     train: [2008-01-01, 2014-12-31]
                     valid: [2015-01-01, 2016-12-31]
                     test: [2017-01-01, 2020-08-01]
-        record: 
+        record:
             - class: SignalRecord
               module_path: qlib.workflow.record_temp
               kwargs: {}
             - class: PortAnaRecord
               module_path: qlib.workflow.record_temp
-              kwargs: 
+              kwargs:
                   config: *port_analysis_config
 
 After saving the config into `configuration.yaml`, users could start the workflow and test their ideas with a single command below.
@@ -111,22 +109,22 @@ If users want to use ``qrun`` under debug mode, please use the following command
 
     python -m pdb qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
 
-.. note:: 
+.. note::
 
     `qrun` will be placed in your $PATH directory when installing ``Qlib``.
 
-.. note:: 
-        
+.. note::
+
     The symbol `&` in `yaml` file stands for an anchor of a field, which is useful when another fields include this parameter as part of the value. Taking the configuration file above as an example, users can directly change the value of `market` and `benchmark` without traversing the entire configuration file.
 
 
 Configuration File
-===================
+==================
 
 Let's get into details of ``qrun`` in this section.
 Before using ``qrun``, users need to prepare a configuration file. The following content shows how to prepare each part of the configuration file.
 
-The design logic of the configuration file is very simple. It predefines fixed workflows and provide this yaml interface to users to define how to initialize each component. 
+The design logic of the configuration file is very simple. It predefines fixed workflows and provide this yaml interface to users to define how to initialize each component.
 It follow the design of `init_instance_by_config <https://github.com/microsoft/qlib/blob/2aee9e0145decc3e71def70909639b5e5a6f4b58/qlib/utils/__init__.py#L264>`_ .  It defines the initialization of each component of Qlib, which typically include the class and the initialization arguments.
 
 For example, the following yaml and code are equivalent.
@@ -166,7 +164,7 @@ For example, the following yaml and code are equivalent.
 
 
 Qlib Init Section
---------------------
+-----------------
 
 At first, the configuration file needs to contain several basic parameters which will be used for qlib initialization.
 
@@ -181,21 +179,21 @@ The meaning of each field is as follows:
     Type: str. The URI of the Qlib data. For example, it could be the location where the data loaded by ``get_data.py`` are stored.
 
 - `region`
-    - If `region` == "us", ``Qlib`` will be initialized in US-stock mode. 
+    - If `region` == "us", ``Qlib`` will be initialized in US-stock mode.
     - If `region` == "cn", ``Qlib`` will be initialized in China-stock mode.
 
-    .. note:: 
-        
+    .. note::
+
         The value of `region` should be aligned with the data stored in `provider_uri`.
 
 
 Task Section
---------------------
+------------
 
 The `task` field in the configuration corresponds to a `task`, which contains the parameters of three different subsections: `Model`, `Dataset` and `Record`.
 
 Model Section
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~
 
 In the `task` field, the `model` section describes the parameters of the model to be used for training and inference. For more information about the base ``Model`` class, please refer to `Qlib Model <../component/model.html>`_.
 
@@ -224,16 +222,16 @@ The meaning of each field is as follows:
     Type: str. The path for the model in qlib.
 
 - `kwargs`
-    The keywords arguments for the model. Please refer to the specific model implementation for more information: `models <https://github.com/microsoft/qlib/blob/main/qlib/contrib/model>`_. 
+    The keywords arguments for the model. Please refer to the specific model implementation for more information: `models <https://github.com/microsoft/qlib/blob/main/qlib/contrib/model>`_.
+
+.. note::
 
-.. note:: 
-        
     ``Qlib`` provides a util named: ``init_instance_by_config`` to initialize any class inside ``Qlib`` with the configuration includes the fields: `class`, `module_path` and `kwargs`.
 
 Dataset Section
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~
 
-The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Model <../component/data.html#dataset>`_.
+The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Data <../component/data.html#dataset>`_.
 
 The keywords arguments configuration of the ``DataHandler`` is as follows:
 
@@ -248,7 +246,7 @@ The keywords arguments configuration of the ``DataHandler`` is as follows:
 
 Users can refer to the document of `DataHandler <../component/data.html#datahandler>`_ for more information about the meaning of each field in the configuration.
 
-Here is the configuration for the ``Dataset`` module which will take care of data preprossing and slicing during the training and testing phase.
+Here is the configuration for the ``Dataset`` module which will take care of data preprocessing and slicing during the training and testing phase.
 
 .. code-block:: YAML
 
@@ -266,7 +264,7 @@ Here is the configuration for the ``Dataset`` module which will take care of dat
                 test: [2017-01-01, 2020-08-01]
 
 Record Section
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~
 
 The `record` field is about the parameters the ``Record`` module in ``Qlib``. ``Record`` is responsible for tracking training process and results such as `information Coefficient (IC)` and `backtest` in a standard format.
 
@@ -281,9 +279,7 @@ The following script is the configuration of `backtest` and the `strategy` used
             kwargs:
                 topk: 50
                 n_drop: 5
-                signal:
-                    - <MODEL> 
-                    - <DATASET>
+                signal: <PRED>
         backtest:
             limit_threshold: 0.095
             account: 100000000
@@ -299,13 +295,13 @@ Here is the configuration details of different `Record Template` such as ``Signa
 
 .. code-block:: YAML
 
-    record: 
+    record:
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
           kwargs: {}
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs: 
+          kwargs:
             config: *port_analysis_config
 
 For more information about the ``Record`` module in ``Qlib``, user can refer to the related document: `Record <../component/recorder.html#record-template>`_.

docs/conf.py

@@ -54,9 +54,9 @@ master_doc = "index"
 
 
 # General information about the project.
-project = u"QLib"
-copyright = u"Microsoft"
-author = u"Microsoft"
+project = "QLib"
+copyright = "Microsoft"
+author = "Microsoft"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -77,7 +77,7 @@ language = "en_US"
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "hidden"]
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = "sphinx"
@@ -174,7 +174,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, "qlib.tex", u"QLib Documentation", u"Microsoft", "manual"),
+    (master_doc, "qlib.tex", "QLib Documentation", "Microsoft", "manual"),
 ]
 
 
@@ -182,7 +182,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [(master_doc, "qlib", u"QLib Documentation", [author], 1)]
+man_pages = [(master_doc, "qlib", "QLib Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output -------------------------------------------
@@ -194,7 +194,7 @@ texinfo_documents = [
     (
         master_doc,
         "QLib",
-        u"QLib Documentation",
+        "QLib Documentation",
         author,
         "QLib",
         "One line description of project.",

docs/developer/code_standard.rst

@@ -1,22 +0,0 @@
-.. _code_standard:
-
-=================================
-Code Standard
-=================================
-
-Docstring
-=================================
-Please use the `Numpydoc Style <https://stackoverflow.com/a/24385103>`_.
-
-Continuous Integration
-=================================
-Continuous Integration (CI) tools help you stick to the quality standards by running tests every time you push a new commit and reporting the results to a pull request. 
-
-When you submit a PR request, you can check whether your code passes the CI tests in the "check" section at the bottom of the web page.
-
-A common error is the mixed use of space and tab. You can fix the bug by inputing the following code in the command line.
-
-.. code-block:: python
-
-    pip install black
-    python -m black . -l 120

docs/developer/code_standard_and_dev_guide.rst

@@ -0,0 +1,63 @@
+.. _code_standard:
+
+=============
+Code Standard
+=============
+
+Docstring
+=========
+Please use the `Numpydoc Style <https://stackoverflow.com/a/24385103>`_.
+
+Continuous Integration
+======================
+Continuous Integration (CI) tools help you stick to the quality standards by running tests every time you push a new commit and reporting the results to a pull request.
+
+When you submit a PR request, you can check whether your code passes the CI tests in the "check" section at the bottom of the web page.
+
+1. Qlib will check the code format with black. The PR will raise error if your code does not align to the standard of Qlib(e.g. a common error is the mixed use of space and tab).
+
+   You can fix the bug by inputting the following code in the command line.
+
+.. code-block:: bash
+
+    pip install black
+    python -m black . -l 120
+
+
+2. Qlib will check your code style pylint. The checking command is implemented in [github action workflow](https://github.com/microsoft/qlib/blob/0e8b94a552f1c457cfa6cd2c1bb3b87ebb3fb279/.github/workflows/test.yml#L66).
+   Sometime pylint's restrictions are not that reasonable. You can ignore specific errors like this
+
+.. code-block:: python
+
+    return -ICLoss()(pred, target, index)  # pylint: disable=E1130
+
+
+3. Qlib will check your code style flake8. The checking command is implemented in [github action workflow](https://github.com/microsoft/qlib/blob/0e8b94a552f1c457cfa6cd2c1bb3b87ebb3fb279/.github/workflows/test.yml#L73).
+
+   You can fix the bug by inputing the following code in the command line.
+
+.. code-block:: bash
+
+    flake8 --ignore E501,F541,E402,F401,W503,E741,E266,E203,E302,E731,E262,F523,F821,F811,F841,E713,E265,W291,E712,E722,W293 qlib
+
+
+4. Qlib has integrated pre-commit, which will make it easier for developers to format their code.
+
+   Just run the following two commands, and the code will be automatically formatted using black and flake8 when the git commit command is executed.
+
+.. code-block:: bash
+
+    pip install -e .[dev]
+    pre-commit install
+
+
+=================================
+Development Guidance
+=================================
+
+As a developer, you often want make changes to `Qlib` and hope it would reflect directly in your environment without reinstalling it. You can install `Qlib` in editable mode with following command.
+The `[dev]` option will help you to install some related packages when developing `Qlib` (e.g. pytest, sphinx)
+
+.. code-block:: bash
+
+    pip install -e ".[dev]"

docs/hidden/client.rst

@@ -1,12 +1,12 @@
 .. _client:
 
 Qlib Client-Server Framework
-===================
+============================
 
 .. currentmodule:: qlib
 
 Introduction
------------
+------------
 Client-Server is designed to solve following  problems
 
 - Manage the data in a centralized way. Users don't have to manage data of different versions.
@@ -81,6 +81,7 @@ If running on Windows, open **NFS** features and write correct **mount_path**, i
     * Open ``Programs and Features``.
     * Click ``Turn Windows features on or off``.
     * Scroll down and check the option ``Services for NFS``, then click OK
+
     Reference address: https://graspingtech.com/mount-nfs-share-windows-10/
 2.config correct mount_path
     * In windows, mount path must be not exist path and root path,
@@ -159,13 +160,11 @@ Limitations
 2. The rolling operation expression with parameter `0` can not be updated rightly under mechanism of the client-server framework.
 
 API
-********************
+***
 
-The client is based on `python-socketio<https://python-socketio.readthedocs.io>`_ which is a framework that supports WebSocket client for Python language. The client can only propose requests and receive results, which do not include any calculating procedure.
+The client is based on `python-socketio <https://python-socketio.readthedocs.io>`_ which is a framework that supports WebSocket client for Python language. The client can only propose requests and receive results, which do not include any calculating procedure.
 
 Class
---------------------
+-----
 
 .. automodule:: qlib.data.client
-
-

docs/hidden/online.rst

@@ -1,11 +1,11 @@
 .. _online:
 
 Online
-===================
+======
 .. currentmodule:: qlib
 
 Introduction
--------------------
+------------
 
 Welcome to use Online, this module simulates what will be like if we do the real trading use our model and strategy.
 
@@ -31,11 +31,11 @@ The file structure can be viewed at fileStruct_.
 
 
 Example
--------------------
+-------
 
 Let's take an example,
 
-.. note:: Make sure you have the latest version of `qlib` installed. 
+.. note:: Make sure you have the latest version of `qlib` installed.
 
 If you want to use the models and data provided by `qlib`, you only need to do as follows.
 
@@ -93,7 +93,7 @@ If Your account was saved in "./user_data/", you can see the performance of your
 Here 'SH000905' represents csi500 and 'SH000300' represents csi300
 
 Manage your account
---------------------
+-------------------
 
 Any account processed by `online` should be saved in a folder. you can use commands
 defined to manage your accounts.
@@ -161,7 +161,7 @@ be called at each trading date.
         >> online update -date 2019-10-16 -path ./user_data/
 
 API
-------------------
+---
 
 All those operations are based on defined in `qlib.contrib.online.operator`
 
@@ -170,7 +170,7 @@ All those operations are based on defined in `qlib.contrib.online.operator`
 .. _fileStruct:
 
 File structure
-------------------
+--------------
 
 'user_data' indicates the root of folder.
 Name that bold indicates it’s a folder, otherwise it’s a document.
@@ -214,7 +214,7 @@ Configuration file
 The configure file used in `online` should contain the model and strategy information.
 
 About the model
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~
 
 First, your configuration file needs to have a field about the model,
 this field and its contents determine the model we used when generating score at predict date.
@@ -243,7 +243,7 @@ contains 2 methods used in `online` module.
 
 
 About the strategy
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~
 
 Your need define the strategy used to generate the order list at predict date.
 
@@ -259,7 +259,7 @@ Followings are two examples for a TopkAmountStrategy
             n_drop: 10
 
 Generated files
-------------------
+---------------
 
 The 'online_generate' command will create the order list at {folder_path}/{user_id}/temp/,
 the name of that is orderlist_{YYYY-MM-DD}.json, YYYY-MM-DD is the date that those orders to be executed.

docs/hidden/tuner.rst

@@ -1,11 +1,11 @@
 .. _tuner:
 
 Tuner
-===================
+=====
 .. currentmodule:: qlib
 
 Introduction
--------------------
+------------
 
 Welcome to use Tuner, this document is based on that you can use Estimator proficiently and correctly.
 
@@ -41,19 +41,19 @@ We write a simple configuration example as following,
         tuner_class: QLibTuner
     qlib_client:
         auto_mount: False
-        logging_level: INFO 
+        logging_level: INFO
     optimization_criteria:
         report_type: model
         report_factor: model_score
         optim_type: max
     tuner_pipeline:
-      - 
-        model: 
+      -
+        model:
             class: SomeModel
             space: SomeModelSpace
-        trainer: 
+        trainer:
             class: RollingTrainer
-        strategy: 
+        strategy:
             class: TopkAmountStrategy
             space: TopkAmountStrategySpace
         max_evals: 2
@@ -166,13 +166,13 @@ Also, there are some optional fields. The meaning of each field is as follows:
     The class of tuner, str type, must be an already implemented model, such as `QLibTuner` in `qlib`, or a custom tuner, but it must be a subclass of `qlib.contrib.tuner.Tuner`, the default value is `QLibTuner`.
 
 - `tuner_module_path`
-    The module path, str type, absolute url is also supported, indicates the path of the implementation of tuner. The default value is `qlib.contrib.tuner.tuner` 
+    The module path, str type, absolute url is also supported, indicates the path of the implementation of tuner. The default value is `qlib.contrib.tuner.tuner`
 
 About the optimization criteria
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 You need to designate a factor to optimize, for tuner need a factor to decide which case is better than other cases.
-Usually, we use the result of `estimator`, such as backtest results and the score of model. 
+Usually, we use the result of `estimator`, such as backtest results and the score of model.
 
 This part needs contain these fields:
 
@@ -203,13 +203,13 @@ The tuner pipeline contains different tuners, and the `tuner` program will proce
 .. code-block:: YAML
 
     tuner_pipeline:
-      - 
-        model: 
+      -
+        model:
             class: SomeModel
             space: SomeModelSpace
-        trainer: 
+        trainer:
             class: RollingTrainer
-        strategy: 
+        strategy:
             class: TopkAmountStrategy
             space: TopkAmountStrategySpace
         max_evals: 2
@@ -249,25 +249,25 @@ You need to use the same dataset to evaluate your different `estimator` experime
         test_start_date: 2016-07-01
         test_end_date: 2018-04-30
 
-- `rolling_period`    
+- `rolling_period`
     The rolling period, integer type, indicates how many time steps need rolling when rolling the data. The default value is `60`. If you use `RollingTrainer`, this config will be used, or it will be ignored.
 
 - `train_start_date`
     Training start time, str type.
 
-- `train_end_date`      
+- `train_end_date`
     Training end time, str type.
 
-- `validate_start_date`    
+- `validate_start_date`
     Validation start time, str type.
 
-- `validate_end_date`    
+- `validate_end_date`
     Validation end time, str type.
 
-- `test_start_date`    
+- `test_start_date`
     Test start time, str type.
 
-- `test_end_date`     
+- `test_end_date`
     Test end time, str type. If `test_end_date` is `-1` or greater than the last date of the data, the last date of the data will be used as `test_end_date`.
 
 About the data and backtest
@@ -315,11 +315,10 @@ About the data and backtest
 Experiment Result
 -----------------
 
-All the results are stored in experiment file directly, you can check them directly in the corresponding files. 
+All the results are stored in experiment file directly, you can check them directly in the corresponding files.
 What we save are as following:
 
 - Global optimal parameters
 - Local optimal parameters of each tuner
 - Config file of this `tuner` experiment
 - Every `estimator` experiments result in the process
-

docs/index.rst

@@ -1,6 +1,6 @@
-============================================================
+======================
 ``Qlib`` Documentation
-============================================================
+======================
 
 ``Qlib`` is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment.
 
@@ -24,16 +24,16 @@ Document Structure
 .. toctree::
    :maxdepth: 3
    :caption: FIRST STEPS:
-   
+
    Installation <start/installation.rst>
    Initialization <start/initialization.rst>
    Data Retrieval <start/getdata.rst>
    Custom Model Integration <start/integration.rst>
-   
+
 
 .. toctree::
    :maxdepth: 3
-   :caption: COMPONENTS:
+   :caption: MAIN COMPONENTS:
 
    Workflow: Workflow Management <component/workflow.rst>
    Data Layer: Data Framework & Usage <component/data.rst>
@@ -44,15 +44,23 @@ Document Structure
    Qlib Recorder: Experiment Management <component/recorder.rst>
    Analysis: Evaluation & Results Analysis <component/report.rst>
    Online Serving: Online Management & Strategy & Tool <component/online.rst>
+   Reinforcement Learning <component/rl/toctree>
 
 .. toctree::
    :maxdepth: 3
-   :caption: ADVANCED TOPICS:
-   
+   :caption: OTHER COMPONENTS/FEATURES/TOPICS:
+
    Building Formulaic Alphas <advanced/alpha.rst>
    Online & Offline mode <advanced/server.rst>
    Serialization <advanced/serial.rst>
    Task Management <advanced/task_management.rst>
+   Point-In-Time database <advanced/PIT.rst>
+
+.. toctree::
+   :maxdepth: 3
+   :caption: FOR DEVELOPERS:
+
+   Code Standard & Development Guidance <developer/code_standard_and_dev_guide.rst>
 
 .. toctree::
    :maxdepth: 3

docs/introduction/introduction.rst

@@ -3,7 +3,7 @@
 ===============================
 
 Introduction
-===================
+============
 
 .. image:: ../_static/img/logo/white_bg_rec+word.png
     :align: center
@@ -13,40 +13,58 @@ Introduction
 With ``Qlib``, users can easily try their ideas to create better Quant investment strategies.
 
 Framework
-===================
-   
+=========
+
+
 .. image:: ../_static/img/framework.svg
     :align: center
 
 
 At the module level, Qlib is a platform that consists of above components. The components are designed as loose-coupled modules and each component could be used stand-alone.
 
+This framework may be intimidating for new users to Qlib. It tries to accurately include a lot of details of Qlib's design.
+For users new to Qlib, you can skip it first and read it later.
 
 
-========================  ==============================================================================
-Name                      Description
-========================  ==============================================================================
-`Infrastructure` layer    `Infrastructure` layer provides underlying support for Quant research.
-                          `DataServer` provides high-performance infrastructure for users to manage 
-                          and retrieve raw data. `Trainer` provides flexible interface to control
-                          the training process of models which enable algorithms controlling the
-                          training process.
 
-`Workflow` layer          `Workflow` layer covers the whole workflow of quantitative investment.
-                          `Information Extractor` extracts data for models. `Forecast Model` focuses
-                          on producing all kinds of forecast signals (e.g. *alpha*, risk) for other
-                          modules.  With these signals `Decision Generator` will generate the target 
-                          trading decisions(i.e. portfolio, orders)  to be executed by `Execution Env`
-                          (i.e. the trading market).  There may be multiple levels of `Trading Agent`
-                          and `Execution Env` (e.g. an *order executor trading agent and intraday
-                          order execution environment* could behave like an interday trading
-                          environment and nested in  *daily portfolio management trading agent and
-                          interday trading environment*  ) 
+===========================  ==============================================================================
+Name                         Description
+===========================  ==============================================================================
+`Infrastructure` layer       `Infrastructure` layer provides underlying support for Quant research.
+                             `DataServer` provides high-performance infrastructure for users to manage
+                             and retrieve raw data. `Trainer` provides flexible interface to control
+                             the training process of models which enable algorithms controlling the
+                             training process.
 
-`Interface` layer         `Interface` layer tries to present a user-friendly interface for the underlying
-                          system. `Analyser` module will provide users detailed analysis reports of
-                          forecasting signals, portfolios and execution results
-========================  ==============================================================================
+`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
+                             leverages the `Workflow` layer as well(e.g. sharing `Information Extractor`,
+                             creating environments based on `Execution Env`).
+
+`Workflow` layer             `Workflow` layer covers the whole workflow of quantitative investment.
+                             Both supervised-learning-based strategies and RL-based Strategies
+                             are supported.
+                             `Information Extractor` extracts data for models. `Forecast Model` focuses
+                             on producing all kinds of forecast signals (e.g. *alpha*, risk) for other
+                             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 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*
+                             could behave like an interday trading loop and be nested in
+                             *daily portfolio management trading strategy and interday trading executor*
+                             trading loop)
+
+`Interface` layer            `Interface` layer tries to present a user-friendly interface for the underlying
+                             system. `Analyser` module will provide users detailed analysis reports of
+                             forecasting signals, portfolios and execution results
+===========================  ==============================================================================
 
 - The modules with hand-drawn style are under development and will be released in the future.
 - The modules with dashed borders are highly user-customizable and extendible.
+
+(p.s. framework image is created with https://draw.io/)

docs/introduction/quick.rst

@@ -1,10 +1,10 @@
 
-===============================
+===========
 Quick Start
-===============================
+===========
 
 Introduction
-==============
+============
 
 This ``Quick Start`` guide tries to demonstrate
 
@@ -14,13 +14,14 @@ 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:
 
     .. code-block::
+
         pip install numpy
         pip install --upgrade  cython
 
@@ -34,7 +35,7 @@ Users can easily intsall ``Qlib`` according to the following steps:
 To known more about `installation`, please refer to `Qlib Installation <../start/installation.html>`_.
 
 Prepare Data
-==============
+============
 
 Load and prepare data by running the following code:
 
@@ -47,14 +48,14 @@ This dataset is created by public data collected by crawler scripts in ``scripts
 To known more about `prepare data`, please refer to `Data Preparation <../component/data.html#data-preparation>`_.
 
 Auto Quant Research Workflow
-====================================
+============================
 
-``Qlib`` provides a tool named ``qrun`` to run the whole workflow automatically (including building dataset, training models, backtest and evaluation). Users can start an auto quant research workflow and have a graphical reports analysis according to the following steps: 
+``Qlib`` provides a tool named ``qrun`` to run the whole workflow automatically (including building dataset, training models, backtest and evaluation). Users can start an auto quant research workflow and have a graphical reports analysis according to the following steps:
 
-- Quant Research Workflow: 
+- Quant Research Workflow:
     - Run  ``qrun`` with a config file of the LightGBM model `workflow_config_lightgbm.yaml` as following.
 
-        .. code-block:: 
+        .. code-block::
 
             cd examples  # Avoid running program under the directory contains `qlib`
             qrun benchmarks/LightGBM/workflow_config_lightgbm.yaml
@@ -64,7 +65,7 @@ Auto Quant Research Workflow
         The result of ``qrun`` is as follows, which is also the typical result of ``Forecast model(alpha)``. Please refer to  `Intraday Trading <../component/backtest.html>`_. for more details about the result.
 
         .. code-block:: python
-        
+
                                                               risk
             excess_return_without_cost mean               0.000605
                                        std                0.005481
@@ -77,7 +78,7 @@ Auto Quant Research Workflow
                                        information_ratio  1.187411
                                        max_drawdown      -0.075024
 
-        
+
     To know more about `workflow` and `qrun`, please refer to `Workflow: Workflow Management <../component/workflow.html>`_.
 
 - Graphical Reports Analysis:
@@ -89,6 +90,6 @@ Auto Quant Research Workflow
 
 
 Custom Model Integration
-===============================================
+========================
 
 ``Qlib`` provides a batch of models (such as ``lightGBM`` and ``MLP`` models) as examples of ``Forecast Model``. In addition to the default model, users can integrate their own custom models into ``Qlib``. If users are interested in the custom model, please refer to `Custom Model Integration <../start/integration.html>`_.

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/reference/api.rst

@@ -1,7 +1,8 @@
 .. _api:
-================================
+
+=============
 API Reference
-================================
+=============
 
 
 
@@ -9,32 +10,32 @@ Here you can find all ``Qlib`` interfaces.
 
 
 Data
-====================
+====
 
 Provider
---------------------
+--------
 
 .. automodule:: qlib.data.data
     :members:
-		
+
 Filter
---------------------
+------
 
 .. automodule:: qlib.data.filter
     :members:
 
 Class
---------------------
+-----
 .. automodule:: qlib.data.base
     :members:
 
 Operator
---------------------
+--------
 .. automodule:: qlib.data.ops
     :members:
-	       
+
 Cache
-----------------
+-----
 .. autoclass:: qlib.data.cache.MemCacheUnit
     :members:
 
@@ -55,7 +56,7 @@ Cache
 
 
 Storage
--------------
+-------
 .. autoclass:: qlib.data.storage.storage.BaseStorage
     :members:
 
@@ -82,52 +83,52 @@ Storage
 
 
 Dataset
----------------
+-------
 
 Dataset Class
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~
 .. automodule:: qlib.data.dataset.__init__
     :members:
 
 Data Loader
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~
 .. automodule:: qlib.data.dataset.loader
     :members:
 
 Data Handler
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~
 .. automodule:: qlib.data.dataset.handler
     :members:
 
 Processor
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~
 .. automodule:: qlib.data.dataset.processor
     :members:
 
 
 Contrib
-====================
+=======
 
 Model
---------------------
+-----
 .. automodule:: qlib.model.base
     :members:
 
 Strategy
--------------------
+--------
 
-.. automodule:: qlib.contrib.strategy.strategy
+.. automodule:: qlib.contrib.strategy
     :members:
 
 Evaluate
------------------
+--------
 
 .. automodule:: qlib.contrib.evaluate
     :members:
-    
+
 
 Report
------------------
+------
 
 .. automodule:: qlib.contrib.report.analysis_position.report
     :members:
@@ -159,103 +160,133 @@ Report
 
 
 Workflow
-====================
+========
 
 
 Experiment Manager
---------------------
+------------------
 .. autoclass:: qlib.workflow.expm.ExpManager
     :members:
 
 Experiment
---------------------
+----------
 .. autoclass:: qlib.workflow.exp.Experiment
     :members:
 
 Recorder
---------------------
+--------
 .. autoclass:: qlib.workflow.recorder.Recorder
     :members:
 
 Record Template
---------------------
+---------------
 .. automodule:: qlib.workflow.record_temp
     :members:
 
 Task Management
-====================
+===============
 
 
 TaskGen
---------------------
+-------
 .. automodule:: qlib.workflow.task.gen
     :members:
 
 TaskManager
---------------------
+-----------
 .. automodule:: qlib.workflow.task.manage
     :members:
 
 Trainer
---------------------
+-------
 .. automodule:: qlib.model.trainer
     :members:
 
 Collector
---------------------
+---------
 .. automodule:: qlib.workflow.task.collect
     :members:
 
 Group
---------------------
+-----
 .. automodule:: qlib.model.ens.group
     :members:
 
 Ensemble
---------------------
+--------
 .. automodule:: qlib.model.ens.ensemble
     :members:
 
 Utils
---------------------
+-----
 .. automodule:: qlib.workflow.task.utils
     :members:
 
 
 Online Serving
-====================
+==============
 
 
 Online Manager
---------------------
+--------------
 .. automodule:: qlib.workflow.online.manager
     :members:
 
 Online Strategy
---------------------
+---------------
 .. automodule:: qlib.workflow.online.strategy
     :members:
 
 Online Tool
---------------------
+-----------
 .. automodule:: qlib.workflow.online.utils
     :members:
 
 
 RecordUpdater
---------------------
+-------------
 .. automodule:: qlib.workflow.online.update
     :members:
 
 
 Utils
-====================
+=====
 
 Serializable
---------------------
+------------
 
-.. automodule:: qlib.utils.serial.Serializable
+.. automodule:: qlib.utils.serial
     :members:
 
+RL
+==============
 
-    
+Base Component
+--------------
+.. automodule:: qlib.rl
+    :members:
+    :imported-members:
+
+Strategy
+--------
+.. automodule:: qlib.rl.strategy
+    :members:
+    :imported-members:
+
+Trainer
+-------
+.. automodule:: qlib.rl.trainer
+    :members:
+    :imported-members:
+
+Order Execution
+---------------
+.. automodule:: qlib.rl.order_execution
+    :members:
+    :imported-members:
+
+Utils
+---------------
+.. automodule:: qlib.rl.utils
+    :members:
+    :imported-members:

docs/requirements.txt

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

docs/start/getdata.rst

@@ -1,18 +1,18 @@
 .. _getdata:
 
-=============================
+==============
 Data Retrieval
-=============================
+==============
 
 .. currentmodule:: qlib
 
 Introduction
-====================
+============
 
 Users can get stock data with ``Qlib``. The following examples demonstrate the basic user interface.
 
 Examples
-====================
+========
 
 
 ``QLib`` Initialization:
@@ -30,7 +30,7 @@ If users followed steps in `initialization <initialization.html>`_ and downloade
 Load trading calendar with given time range and frequency:
 
 .. code-block:: python
-		
+
    >> from qlib.data import D
    >> D.calendar(start_time='2010-01-01', end_time='2017-12-31', freq='day')[:2]
    [Timestamp('2010-01-04 00:00:00'), Timestamp('2010-01-05 00:00:00')]
@@ -46,7 +46,7 @@ Parse a given market name into a stock pool config:
 Load instruments of certain stock pool in the given time range:
 
 .. code-block:: python
-		
+
    >> from qlib.data import D
    >> instruments = D.instruments(market='csi300')
    >> D.list_instruments(instruments=instruments, start_time='2010-01-01', end_time='2017-12-31', as_list=True)[:6]
@@ -79,19 +79,18 @@ For more details about filter, please refer `Filter API <../component/data.html>
 Load features of certain instruments in a given time range:
 
 .. code-block:: python
-		
+
    >> from qlib.data import D
    >> instruments = ['SH600000']
    >> fields = ['$close', '$volume', 'Ref($close, 1)', 'Mean($close, 3)', '$high-$low']
-   >> D.features(instruments, fields, start_time='2010-01-01', end_time='2017-12-31', freq='day').head()
-                              
-                              $close     $volume  Ref($close, 1)  Mean($close, 3)  $high-$low
-      instrument  datetime                                                                      
-      SH600000    2010-01-04  86.778313  16162960.0       88.825928        88.061483    2.907631
-                  2010-01-05  87.433578  28117442.0       86.778313        87.679273    3.235252
-                  2010-01-06  85.713585  23632884.0       87.433578        86.641825    1.720009
-                  2010-01-07  83.788803  20813402.0       85.713585        85.645322    3.030487
-                  2010-01-08  84.730675  16044853.0       83.788803        84.744354    2.047623
+   >> D.features(instruments, fields, start_time='2010-01-01', end_time='2017-12-31', freq='day').head().to_string()
+   '                           $close     $volume  Ref($close, 1)  Mean($close, 3)  $high-$low
+   ... instrument  datetime
+   ... SH600000    2010-01-04  86.778313  16162960.0       88.825928        88.061483    2.907631
+   ...             2010-01-05  87.433578  28117442.0       86.778313        87.679273    3.235252
+   ...             2010-01-06  85.713585  23632884.0       87.433578        86.641825    1.720009
+   ...             2010-01-07  83.788803  20813402.0       85.713585        85.645322    3.030487
+   ...             2010-01-08  84.730675  16044853.0       83.788803        84.744354    2.047623'
 
 Load features of certain stock pool in a given time range:
 
@@ -105,21 +104,46 @@ Load features of certain stock pool in a given time range:
    >> expressionDFilter = ExpressionDFilter(rule_expression='$close>Ref($close,1)')
    >> instruments = D.instruments(market='csi300', filter_pipe=[nameDFilter, expressionDFilter])
    >> fields = ['$close', '$volume', 'Ref($close, 1)', 'Mean($close, 3)', '$high-$low']
-   >> D.features(instruments, fields, start_time='2010-01-01', end_time='2017-12-31', freq='day').head()
-
-                                 $close        $volume  Ref($close, 1)  Mean($close, 3)  $high-$low
-      instrument  datetime                                                                           
-      SH600655    2010-01-04  2699.567383  158193.328125     2619.070312      2626.097738  124.580566
-                  2010-01-08  2612.359619   77501.406250     2584.567627      2623.220133   83.373047
-                  2010-01-11  2712.982422  160852.390625     2612.359619      2636.636556  146.621582
-                  2010-01-12  2788.688232  164587.937500     2712.982422      2704.676758  128.413818
-                  2010-01-13  2790.604004  145460.453125     2788.688232      2764.091553  128.413818
+   >> D.features(instruments, fields, start_time='2010-01-01', end_time='2017-12-31', freq='day').head().to_string()
+   '                              $close        $volume  Ref($close, 1)  Mean($close, 3)  $high-$low
+   ... instrument  datetime
+   ... SH600655    2010-01-04  2699.567383  158193.328125     2619.070312      2626.097738  124.580566
+   ...             2010-01-08  2612.359619   77501.406250     2584.567627      2623.220133   83.373047
+   ...             2010-01-11  2712.982422  160852.390625     2612.359619      2636.636556  146.621582
+   ...             2010-01-12  2788.688232  164587.937500     2712.982422      2704.676758  128.413818
+   ...             2010-01-13  2790.604004  145460.453125     2788.688232      2764.091553  128.413818'
 
 
 For more details about features, please refer `Feature API <../component/data.html>`_.
 
 .. note:: When calling `D.features()` at the client, use parameter `disk_cache=0` to skip dataset cache, use `disk_cache=1` to generate and use dataset cache. In addition, when calling at the server, users can use `disk_cache=2` to update the dataset cache.
 
+
+When you are building complicated expressions, implementing all the expressions in a single string may not be easy.
+For example, it looks quite long and complicated:
+
+.. code-block:: python
+
+   >> from qlib.data import D
+   >> data = D.features(["sh600519"], ["(($high / $close) + ($open / $close)) * (($high / $close) + ($open / $close)) / (($high / $close) + ($open / $close))"], start_time="20200101")
+
+
+But using string is not the only way to implement the expression. You can also implement expression by code.
+Here is an exmaple which does the same thing as above examples.
+
+
+.. code-block:: python
+
+   >> from qlib.data.ops import *
+   >> f1 = Feature("high") / Feature("close")
+   >> f2 = Feature("open") / Feature("close")
+   >> f3 = f1 + f2
+   >> f4 = f3 * f3 / f3
+
+   >> data = D.features(["sh600519"], [f4], start_time="20200101")
+   >> data.head()
+
+
 API
-====================
+===
 To know more about how to use the Data, go to API Reference: `Data API <../reference/api.html#data>`_

docs/start/initialization.rst

@@ -1,23 +1,23 @@
 .. _initialization:
 
-====================
+===================
 Qlib Initialization
-====================
+===================
 
 .. currentmodule:: qlib
 
 
 Initialization
-=========================
+==============
 
 Please follow the steps below to initialize ``Qlib``.
 
 Download and prepare the Data: execute the following command to download stock data. Please pay `attention` that the data is collected from `Yahoo Finance <https://finance.yahoo.com/lookup>`_ and the data might not be perfect. We recommend users to prepare their own data if they have high-quality datasets. Please refer to `Data <../component/data.html#converting-csv-format-into-qlib-format>`_ for more information about customized dataset.
-    
+
     .. code-block:: bash
-    
+
         python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
-        
+
 Please refer to `Data Preparation <../component/data.html#data-preparation>`_ for more information about `get_data.py`,
 
 
@@ -30,14 +30,15 @@ Initialize Qlib before calling other APIs: run following code in python.
         from qlib.constant import REG_CN
         provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
         qlib.init(provider_uri=provider_uri, region=REG_CN)
-    
+
 .. note::
    Do not import qlib package in the repository directory  of ``Qlib``, otherwise, errors may occur.
 
 Parameters
 -------------------
 
-Besides `provider_uri` and `region`, `qlib.init` has other parameters. The following are several important parameters of `qlib.init`:
+Besides `provider_uri` and `region`, `qlib.init` has other parameters.
+The following are several important parameters of `qlib.init` (`Qlib` has a lot of config. Only part of parameters are limited here. More detailed setting can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/config.py>`_):
 
 - `provider_uri`
     Type: str. The URI of the Qlib data. For example, it could be the location where the data loaded by ``get_data.py`` are stored.
@@ -48,23 +49,23 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
         - ``qlib.constant.REG_CN``: China stock market.
 
         Different modes will result in different trading limitations and costs.
-        The region is just `shortcuts for defining a batch of configurations <https://github.com/microsoft/qlib/blob/main/qlib/config.py#L239>`_. Users can set the key configurations manually if the existing region setting can't meet their requirements.
+        The region is just `shortcuts for defining a batch of configurations <https://github.com/microsoft/qlib/blob/528f74af099bf6156e9480bcd2bb28e453231212/qlib/config.py#L249>`_, which include minimal trading order unit (``trade_unit``),  trading limitation (``limit_threshold``) , etc.  It is not a necessary part and users can set the key configurations manually if the existing region setting can't meet their requirements.
 - `redis_host`
     Type: str, optional parameter(default: "127.0.0.1"), host of `redis`
         The lock and cache mechanism relies on redis.
 - `redis_port`
     Type: int, optional parameter(default: 6379), port of `redis`
 
-    .. note:: 
-        
+    .. note::
+
         The value of `region` should be aligned with the data stored in `provider_uri`. Currently, ``scripts/get_data.py`` only provides China stock market data. If users want to use the US stock market data, they should prepare their own US-stock data in `provider_uri` and switch to US-stock mode.
 
     .. note::
-        
+
         If Qlib fails to connect redis via `redis_host` and `redis_port`, cache mechanism will not be used! Please refer to `Cache <../component/data.html#cache>`_ for details.
 - `exp_manager`
     Type: dict, optional parameter, the setting of `experiment manager` to be used in qlib. Users can specify an experiment manager class, as well as the tracking URI for all the experiments. However, please be aware that we only support input of a dictionary in the following style for `exp_manager`. For more information about `exp_manager`, users can refer to `Recorder: Experiment Management <../component/recorder.html>`_.
-    
+
     .. code-block:: Python
 
         # For example, if you want to set your tracking_uri to a <specific folder>, you can initialize qlib below
@@ -77,7 +78,7 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
             }
         })
 - `mongo`
-    Type: dict, optional parameter, the setting of `MongoDB <https://www.mongodb.com/>`_ which will be used in some features such as `Task Management <../advanced/task_management.html>`_, with high performance and clustered processing. 
+    Type: dict, optional parameter, the setting of `MongoDB <https://www.mongodb.com/>`_ which will be used in some features such as `Task Management <../advanced/task_management.html>`_, with high performance and clustered processing.
     Users need to follow the steps in  `installation <https://www.mongodb.com/try/download/community>`_  to install MongoDB firstly and then access it via a URI.
     Users can access mongodb with credential by setting "task_url"  to a string like `"mongodb://%s:%s@%s" % (user, pwd, host + ":" + port)`.
 
@@ -88,3 +89,9 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
             "task_url": "mongodb://localhost:27017/",  # your mongo url
             "task_db_name": "rolling_db", # the database name of Task Management
         })
+
+- `logging_level`
+    The logging level for the system.
+
+- `kernels`
+    The number of processes used when calculating features in Qlib's expression engine. It is very helpful to set it to 1 when you are debuggin an expression calculating exception

docs/start/installation.rst

@@ -1,8 +1,8 @@
 .. _installation:
 
-====================
+============
 Installation
-====================
+============
 
 .. currentmodule:: qlib
 
@@ -24,7 +24,7 @@ Also, Users can install ``Qlib`` by the source code according to the following s
 
 - Enter the root directory of ``Qlib``, in which the file ``setup.py`` exists.
 - Then, please execute the following command to install the environment dependencies and install ``Qlib``:
-   
+
    .. code-block:: bash
 
       $ pip install numpy
@@ -34,7 +34,7 @@ Also, Users can install ``Qlib`` by the source code according to the following s
 
 .. note::
    It's recommended to use anaconda/miniconda to setup the environment. ``Qlib`` needs lightgbm and pytorch packages, use pip to install them.
-   
+
 
 
 Use the following code to make sure the installation successful:
@@ -44,6 +44,3 @@ Use the following code to make sure the installation successful:
    >>> import qlib
    >>> qlib.__version__
    <LATEST VERSION>
-
-
-=====================

docs/start/integration.rst

@@ -1,9 +1,9 @@
-=========================================
+========================
 Custom Model Integration
-=========================================
+========================
 
 Introduction
-===================
+============
 
 ``Qlib``'s `Model Zoo` includes models such as ``LightGBM``, ``MLP``, ``LSTM``, etc.. These models are examples of ``Forecast Model``. In addition to the default models ``Qlib`` provide, users can integrate their own custom models into ``Qlib``.
 
@@ -14,119 +14,123 @@ Users can integrate their own custom models according to the following steps.
 - Test the custom model.
 
 Custom Model Class
-===========================
+==================
 The Custom models need to inherit `qlib.model.base.Model <../reference/api.html#module-qlib.model.base>`_ and override the methods in it.
 
 - Override the `__init__` method
     - ``Qlib`` passes the initialized parameters to the \_\_init\_\_ method.
     - The hyperparameters of model in the configuration must be consistent with those defined in the `__init__` method.
     - Code Example: In the following example, the hyperparameters of model in the configuration file should contain parameters such as `loss:mse`.
-    .. code-block:: Python
 
-        def __init__(self, loss='mse', **kwargs):
-            if loss not in {'mse', 'binary'}:
-                raise NotImplementedError
-            self._scorer = mean_squared_error if loss == 'mse' else roc_auc_score
-            self._params.update(objective=loss, **kwargs)
-            self._model = None
+        .. code-block:: Python
+
+            def __init__(self, loss='mse', **kwargs):
+                if loss not in {'mse', 'binary'}:
+                    raise NotImplementedError
+                self._scorer = mean_squared_error if loss == 'mse' else roc_auc_score
+                self._params.update(objective=loss, **kwargs)
+                self._model = None
 
 - Override the `fit` method
     - ``Qlib`` calls the fit method to train the model.
     - The parameters must include training feature `dataset`, which is designed in the interface.
     - The parameters could include some `optional` parameters with default values, such as `num_boost_round = 1000` for `GBDT`.
     - Code Example: In the following example, `num_boost_round = 1000` is an optional parameter.
-    .. code-block:: Python
-    
-        def fit(self, dataset: DatasetH, num_boost_round = 1000, **kwargs):
 
-            # prepare dataset for lgb training and evaluation
-            df_train, df_valid = dataset.prepare(
-                ["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
-            )
-            x_train, y_train = df_train["feature"], df_train["label"]
-            x_valid, y_valid = df_valid["feature"], df_valid["label"]
+        .. code-block:: Python
 
-            # Lightgbm need 1D array as its label
-            if y_train.values.ndim == 2 and y_train.values.shape[1] == 1:
-                y_train, y_valid = np.squeeze(y_train.values), np.squeeze(y_valid.values)
-            else:
-                raise ValueError("LightGBM doesn't support multi-label training")
+            def fit(self, dataset: DatasetH, num_boost_round = 1000, **kwargs):
 
-            dtrain = lgb.Dataset(x_train.values, label=y_train)
-            dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+                # prepare dataset for lgb training and evaluation
+                df_train, df_valid = dataset.prepare(
+                    ["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
+                )
+                x_train, y_train = df_train["feature"], df_train["label"]
+                x_valid, y_valid = df_valid["feature"], df_valid["label"]
 
-            # fit the model
-            self.model = lgb.train(
-                self.params,
-                dtrain,
-                num_boost_round=num_boost_round,
-                valid_sets=[dtrain, dvalid],
-                valid_names=["train", "valid"],
-                early_stopping_rounds=early_stopping_rounds,
-                verbose_eval=verbose_eval,
-                evals_result=evals_result,
-                **kwargs
-            )
+                # Lightgbm need 1D array as its label
+                if y_train.values.ndim == 2 and y_train.values.shape[1] == 1:
+                    y_train, y_valid = np.squeeze(y_train.values), np.squeeze(y_valid.values)
+                else:
+                    raise ValueError("LightGBM doesn't support multi-label training")
+
+                dtrain = lgb.Dataset(x_train.values, label=y_train)
+                dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+
+                # fit the model
+                self.model = lgb.train(
+                    self.params,
+                    dtrain,
+                    num_boost_round=num_boost_round,
+                    valid_sets=[dtrain, dvalid],
+                    valid_names=["train", "valid"],
+                    early_stopping_rounds=early_stopping_rounds,
+                    verbose_eval=verbose_eval,
+                    evals_result=evals_result,
+                    **kwargs
+                )
 
 - Override the `predict` method
     - The parameters must include the parameter `dataset`, which will be userd to get the test dataset.
     - Return the `prediction score`.
     - Please refer to `Model API <../reference/api.html#module-qlib.model.base>`_ for the parameter types of the fit method.
     - Code Example: In the following example, users need to use `LightGBM` to predict the label(such as `preds`) of test data `x_test` and return it.
-    .. code-block:: Python
 
-        def predict(self, dataset: DatasetH, **kwargs)-> pandas.Series:
-            if self.model is None:
-                raise ValueError("model is not fitted yet!")
-            x_test = dataset.prepare("test", col_set="feature", data_key=DataHandlerLP.DK_I)
-            return pd.Series(self.model.predict(x_test.values), index=x_test.index)
+        .. code-block:: Python
+
+            def predict(self, dataset: DatasetH, **kwargs)-> pandas.Series:
+                if self.model is None:
+                    raise ValueError("model is not fitted yet!")
+                x_test = dataset.prepare("test", col_set="feature", data_key=DataHandlerLP.DK_I)
+                return pd.Series(self.model.predict(x_test.values), index=x_test.index)
 
 - Override the `finetune` method (Optional)
     - This method is optional to the users. When users want to use this method on their own models, they should inherit the ``ModelFT`` base class, which includes the interface of `finetune`.
     - The parameters must include the parameter `dataset`.
     - Code Example: In the following example, users will use `LightGBM` as the model and finetune it.
-    .. code-block:: Python
 
-        def finetune(self, dataset: DatasetH, num_boost_round=10, verbose_eval=20):
-            # Based on existing model and finetune by train more rounds
-            dtrain, _ = self._prepare_data(dataset)
-            self.model = lgb.train(
-                self.params,
-                dtrain,
-                num_boost_round=num_boost_round,
-                init_model=self.model,
-                valid_sets=[dtrain],
-                valid_names=["train"],
-                verbose_eval=verbose_eval,
-            )
+        .. code-block:: Python
+
+            def finetune(self, dataset: DatasetH, num_boost_round=10, verbose_eval=20):
+                # Based on existing model and finetune by train more rounds
+                dtrain, _ = self._prepare_data(dataset)
+                self.model = lgb.train(
+                    self.params,
+                    dtrain,
+                    num_boost_round=num_boost_round,
+                    init_model=self.model,
+                    valid_sets=[dtrain],
+                    valid_names=["train"],
+                    verbose_eval=verbose_eval,
+                )
 
 Configuration File
-=======================
+==================
 
 The configuration file is described in detail in the `Workflow <../component/workflow.html#complete-example>`_ document. In order to integrate the custom model into ``Qlib``, users need to modify the "model" field in the configuration file. The configuration describes which models to use and how we can initialize it.
 
-- Example: The following example describes the `model` field of configuration file about the custom lightgbm model mentioned above, where `module_path` is the module path, `class` is the class name, and `args` is the hyperparameter passed into the __init__ method. All parameters in the field is passed to `self._params` by `\*\*kwargs` in `__init__` except `loss = mse`. 
+- Example: The following example describes the `model` field of configuration file about the custom lightgbm model mentioned above, where `module_path` is the module path, `class` is the class name, and `args` is the hyperparameter passed into the __init__ method. All parameters in the field is passed to `self._params` by `\*\*kwargs` in `__init__` except `loss = mse`.
 
-.. code-block:: YAML
-    
-    model:
-        class: LGBModel
-        module_path: qlib.contrib.model.gbdt
-        args:
-            loss: mse
-            colsample_bytree: 0.8879
-            learning_rate: 0.0421
-            subsample: 0.8789
-            lambda_l1: 205.6999
-            lambda_l2: 580.9768
-            max_depth: 8
-            num_leaves: 210
-            num_threads: 20
+    .. code-block:: YAML
+
+        model:
+            class: LGBModel
+            module_path: qlib.contrib.model.gbdt
+            args:
+                loss: mse
+                colsample_bytree: 0.8879
+                learning_rate: 0.0421
+                subsample: 0.8789
+                lambda_l1: 205.6999
+                lambda_l2: 580.9768
+                max_depth: 8
+                num_leaves: 210
+                num_threads: 20
 
 Users could find configuration file of the baselines of the ``Model`` in ``examples/benchmarks``. All the configurations of different models are listed under the corresponding model folder.
 
 Model Testing
-=====================
+=============
 Assuming that the configuration file is ``examples/benchmarks/LightGBM/workflow_config_lightgbm.yaml``, users can run the following command to test the custom model:
 
 .. code-block:: bash
@@ -136,10 +140,10 @@ Assuming that the configuration file is ``examples/benchmarks/LightGBM/workflow_
 
 .. note:: ``qrun`` is a built-in command of ``Qlib``.
 
-Also, ``Model`` can also be tested as a single module. An example has been given in ``examples/workflow_by_code.ipynb``. 
+Also, ``Model`` can also be tested as a single module. An example has been given in ``examples/workflow_by_code.ipynb``.
 
 
 Reference
-=====================
+=========
 
 To know more about ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <../component/model.html>`_ and `Model API <../reference/api.html#module-qlib.model.base>`_.

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/README.md

@@ -6,3 +6,4 @@
 
   [https://www.ijcai.org/Proceedings/2017/0366.pdf](https://www.ijcai.org/Proceedings/2017/0366.pdf)
 
+- NOTE: Current version of implementation is just a simplified version of ALSTM. It is an LSTM with attention.

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

@@ -0,0 +1,70 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: CatBoostModel
+        module_path: qlib.contrib.model.catboost_model
+        kwargs:
+            loss: RMSE
+            learning_rate: 0.0421
+            subsample: 0.8789
+            max_depth: 6
+            num_leaves: 100
+            thread_count: 20
+            grow_policy: Lossguide
+            bootstrap_type: Poisson
+    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/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

@@ -0,0 +1,77 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+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: []
+    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: CatBoostModel
+        module_path: qlib.contrib.model.catboost_model
+        kwargs:
+            loss: RMSE
+            learning_rate: 0.0421
+            subsample: 0.8789
+            max_depth: 6
+            num_leaves: 100
+            thread_count: 20
+            grow_policy: Lossguide
+            bootstrap_type: Poisson
+    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/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:
@@ -37,7 +35,7 @@ task:
         kwargs:
             base_model: "gbm"
             loss: mse
-            num_models: 6
+            num_models: 3
             enable_sr: True
             enable_fs: True
             alpha1: 1
@@ -53,11 +51,8 @@ task:
                 - 0.4
             sub_weights:
                 - 1
-                - 0.2
-                - 0.2
-                - 0.2
-                - 0.2
-                - 0.2
+                - 1
+                - 1
             epochs: 28
             colsample_bytree: 0.8879
             learning_rate: 0.2

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158_csi500.yaml

@@ -0,0 +1,95 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 28
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    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/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:
@@ -44,7 +42,7 @@ task:
         kwargs:
             base_model: "gbm"
             loss: mse
-            num_models: 6
+            num_models: 3
             enable_sr: True
             enable_fs: True
             alpha1: 1
@@ -60,11 +58,8 @@ task:
                 - 0.4
             sub_weights:
                 - 1
-                - 0.2
-                - 0.2
-                - 0.2
-                - 0.2
-                - 0.2
+                - 1
+                - 1
             epochs: 136
             colsample_bytree: 0.8879
             learning_rate: 0.0421

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360_csi500.yaml

@@ -0,0 +1,102 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+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: []
+    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: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 136
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    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/DoubleEnsemble/workflow_config_doubleensemble_early_stop_Alpha158.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
+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: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 3
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 1
+                - 1
+            epochs: 1000
+            early_stopping_rounds: 50
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    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/GATs/workflow_config_gats_Alpha158.yaml

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

examples/benchmarks/GATs/workflow_config_gats_Alpha360.yaml

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

examples/benchmarks/GRU/workflow_config_gru_Alpha158.yaml

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

examples/benchmarks/GRU/workflow_config_gru_Alpha360.yaml

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

examples/benchmarks/HIST/README.md

@@ -0,0 +1,3 @@
+# HIST
+* Code: [https://github.com/Wentao-Xu/HIST](https://github.com/Wentao-Xu/HIST)
+* Paper: [HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared InformationAdaRNN: Adaptive Learning and Forecasting for Time Series](https://arxiv.org/abs/2110.13716).

examples/benchmarks/HIST/requirements.txt

@@ -0,0 +1,4 @@
+pandas==1.1.2
+numpy==1.21.0
+scikit_learn==0.23.2
+torch==1.7.0

examples/benchmarks/HIST/workflow_config_hist_Alpha360.yaml

@@ -0,0 +1,90 @@
+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: HIST
+        module_path: qlib.contrib.model.pytorch_hist
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0
+            n_epochs: 200
+            lr: 1e-4
+            early_stop: 20
+            metric: ic
+            loss: mse
+            base_model: LSTM
+            model_path: "benchmarks/LSTM/model_lstm_csi300.pkl"
+            stock2concept: "benchmarks/HIST/qlib_csi300_stock2concept.npy"
+            stock_index: "benchmarks/HIST/qlib_csi300_stock_index.npy"
+            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/IGMTF/README.md

@@ -0,0 +1,4 @@
+# IGMTF
+* Code: [https://github.com/Wentao-Xu/IGMTF](https://github.com/Wentao-Xu/IGMTF)
+* Paper: [IGMTF: An Instance-wise Graph-based Framework for
+Multivariate Time Series Forecasting](https://arxiv.org/abs/2109.06489).

examples/benchmarks/IGMTF/requirements.txt

@@ -0,0 +1,4 @@
+pandas==1.1.2
+numpy==1.21.0
+scikit_learn==0.23.2
+torch==1.7.0

examples/benchmarks/IGMTF/workflow_config_igmtf_Alpha360.yaml

@@ -0,0 +1,88 @@
+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: IGMTF
+        module_path: qlib.contrib.model.pytorch_igmtf
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0
+            n_epochs: 200
+            lr: 1e-4
+            early_stop: 20
+            metric: ic
+            loss: mse
+            base_model: LSTM
+            model_path: "benchmarks/LSTM/model_lstm_csi300.pkl"
+            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/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/README.md

@@ -1,4 +1,10 @@
 # LightGBM
 * Code: [https://github.com/microsoft/LightGBM](https://github.com/microsoft/LightGBM)
 * Paper: LightGBM: A Highly Efficient Gradient Boosting
-Decision Tree. [https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf).
+Decision Tree. [https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf).
+
+
+# Introductions about the settings/configs.
+
+`workflow_config_lightgbm_multi_freq.yaml`
+- It uses data sources of different frequencies (i.e. multiple frequencies) for daily prediction.

examples/benchmarks/LightGBM/features_sample.py

@@ -5,6 +5,8 @@ from qlib.data.inst_processor import InstProcessor
 
 
 class Resample1minProcessor(InstProcessor):
+    """This processor tries to resample the data. It will reasmple the data from 1min freq to day freq by selecting a specific miniute"""
+
     def __init__(self, hour: int, minute: int, **kwargs):
         self.hour = hour
         self.minute = minute

examples/benchmarks/LightGBM/multi_freq_handler.py

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

examples/benchmarks/LightGBM/requirements.txt

@@ -1,3 +1,3 @@
 pandas==1.1.2
 numpy==1.21.0
-lightgbm==3.1.0
+lightgbm

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

@@ -0,0 +1,71 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal: <PRED>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.9
+            learning_rate: 0.1
+            subsample: 0.9
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 250
+            num_threads: 20
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_multi_freq.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360_csi500.yaml

@@ -0,0 +1,78 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi500
+benchmark: &benchmark SH000905
+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: []
+    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: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: 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