change weight data download url

* Fix FutureWarning: Passing unit-less datetime64 dtype to .astype is deprecated and will raise in a future version. Pass 'datetime64[ns]' instead

* align index format while end date contains current day data

* fix black

* fix black

* optimize code

* optimize code

* optimize code

* fix ci error

* check ci error

* fix ci error

* check ci error

* check ci error

* check ci error

* check ci error

* check ci error

* check ci error

* fix ci error

* fix ci error

* fix ci error

* fix ci error

* fix ci error

---------

Co-authored-by: Cadenza-Li <362237642@qq.com>
Co-authored-by: Linlang <Lv.Linlang@hotmail.com>

.github/labeler.yml

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

.github/release-drafter.yml

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

.github/workflows/labeler.yml

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

.github/workflows/python-publish.yml

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

.github/workflows/release-drafter.yml

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

.github/workflows/stale.yml

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

.github/workflows/test_qlib_from_pip.yml

@@ -13,16 +13,29 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
     steps:
     - name: Test qlib from pip
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -32,10 +45,10 @@ jobs:
 
     - 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
-        # Specify the numpy version because the numpy upgrade caused the CI test to fail, 
-        # and this line of code will be removed when the next version of qlib is released.
-        python -m pip install "numpy<1.23"
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
@@ -50,8 +63,13 @@ jobs:
 
     - name: Downloads dependencies data
       run: |
-        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+        cd ..
+        python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+        cd qlib
 
     - name: Test workflow by config
+      # 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

@@ -14,16 +14,29 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-18.04, ubuntu-20.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
     steps:
     - name: Test qlib from source
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -37,15 +50,13 @@ jobs:
         python -m pip install torch torchvision torchaudio
 
     - name: Installing pytorch for ubuntu
-      if: ${{ matrix.os == 'ubuntu-18.04' || matrix.os == 'ubuntu-20.04' }}
+      if: ${{ matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-22.04' }}
       run: |
-        python -m pip install --upgrade pip
         python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
 
     - name: Installing pytorch for windows
       if: ${{ matrix.os == 'windows-latest' }}
       run: |
-        python -m pip install --upgrade pip
         python -m pip install torch torchvision torchaudio
 
     - name: Set up Python tools
@@ -54,13 +65,18 @@ jobs:
         python -m pip install -e .[dev]
 
     - name: Lint with Black
+      # Python 3.7 will use a black with low level. So we use python with higher version for black check
+      if: (matrix.python-version != '3.7')
       run: |
+        pip install -U black  # follow the latest version of black, previous Qlib dependency will downgrade black
         black . -l 120 --check --diff
 
     - name: Make html with sphinx
+      # 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 -b html . build
+        cd docs
+        sphinx-build -W --keep-going -b html . _build
         cd ..
 
     # Check Qlib with pylint
@@ -87,9 +103,11 @@ jobs:
       # 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}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' 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
@@ -119,12 +137,16 @@ jobs:
       run: |
         mypy qlib --install-types --non-interactive || true
         mypy qlib --verbose
+    
+    - name: Check Qlib ipynb with nbqa
+      run: |
+        nbqa black . -l 120 --check --diff
+        nbqa pylint . --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136,W0719,W0104,W0404,C0412,W0611,C0410 --const-rgx='[a-z_][a-z0-9_]{2,30}$'
 
     - name: Test data downloads
       run: |
         python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        azcopy copy https://qlibpublic.blob.core.windows.net/data/rl /tmp/qlibpublic/data --recursive
-        mv /tmp/qlibpublic/data tests/.data
+        python scripts/get_data.py download_data --file_name rl_data.zip --target_dir tests/.data/rl
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
@@ -137,12 +159,20 @@ jobs:
         brew unlink libomp
         brew install libomp.rb
 
-    - name: Test workflow by config (install from source)
+    # 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: |
-        # Version 0.52.0 of numba must be installed manually in CI, otherwise it will cause incompatibility with the latest version of numpy.
-        python -m pip install numba==0.52.0
-        # You must update numpy manually, because when installing python tools, it will try to uninstall numpy and cause CI to fail.
-        python -m pip install --upgrade numpy
+        # 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

.github/workflows/test_qlib_from_source_slow.yml

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

.gitignore

@@ -10,7 +10,6 @@ _build
 build/
 dist/
 
-
 *.pkl
 *.hd5
 *.csv
@@ -24,6 +23,11 @@ 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/
 
@@ -44,4 +48,4 @@ tags
 *.swp
 
 ./pretrain
-.idea/
+.idea/

.pre-commit-config.yaml

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

.readthedocs.yaml

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

CHANGES.rst

@@ -85,7 +85,7 @@ 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
@@ -166,12 +166,12 @@ Version 0.8.0
     - 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

README.md

@@ -11,6 +11,9 @@
 Recent released features
 | Feature | Status |
 | --                      | ------    |
+| KRNN and Sandwich models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1414/) on May 26, 2023 |
+| Release Qlib v0.9.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.9.0) on Dec 9, 2022 |
+| RL Learning Framework | :hammer: :chart_with_upwards_trend: Released on Nov 10, 2022. [#1332](https://github.com/microsoft/qlib/pull/1332), [#1322](https://github.com/microsoft/qlib/pull/1322), [#1316](https://github.com/microsoft/qlib/pull/1316),[#1299](https://github.com/microsoft/qlib/pull/1299),[#1263](https://github.com/microsoft/qlib/pull/1263), [#1244](https://github.com/microsoft/qlib/pull/1244), [#1169](https://github.com/microsoft/qlib/pull/1169), [#1125](https://github.com/microsoft/qlib/pull/1125), [#1076](https://github.com/microsoft/qlib/pull/1076)|
 | HIST and IGMTF models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1040) on Apr 10, 2022 |
 | Qlib [notebook tutorial](https://github.com/microsoft/qlib/tree/main/examples/tutorial) | 📖 [Released](https://github.com/microsoft/qlib/pull/1037) on Apr 7, 2022 | 
 | Ibovespa index data | :rice: [Released](https://github.com/microsoft/qlib/pull/990) on Apr 6, 2022 |
@@ -37,16 +40,14 @@ Recent released features
 Features released before 2021 are not listed here.
 
 <p align="center">
-  <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
+  <img src="docs/_static/img/logo/1.png" />
 </p>
 
+Qlib is an open-source, AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms, including supervised learning, market dynamics modeling, and reinforcement learning.
 
-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).
 
 
@@ -67,6 +68,7 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
             <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>
@@ -89,6 +91,7 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
               </ul>
             </li>
           <li type="circle"><a href="#adapting-to-market-dynamics">Adapting to Market Dynamics</a></li>
+          <li type="circle"><a href="#reinforcement-learning-modeling-continuous-decisions">Reinforcement Learning: modeling continuous decisions</a></li>
           </ul>
         </li>
       </td>
@@ -105,21 +108,16 @@ Your feedbacks about the features are very important.
 # Framework of Qlib
 
 <div style="align: center">
-<img src="docs/_static/img/framework.svg" />
+<img src="docs/_static/img/framework-abstract.jpg" />
 </div>
 
-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.
+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.
 
-| 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.
-
-(p.s. framework image is created with https://draw.io/)
+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
@@ -141,7 +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. 
@@ -168,13 +166,29 @@ 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_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
@@ -323,7 +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
@@ -357,10 +371,12 @@ Here is a list of models built on `Qlib`.
 - [ADD based on pytorch (Hongshun Tang, et al.2020)](examples/benchmarks/ADD/)
 - [IGMTF based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/IGMTF/)
 - [HIST based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/HIST/)
+- [KRNN based on pytorch](examples/benchmarks/KRNN/)
+- [Sandwich based on pytorch](examples/benchmarks/Sandwich/)
 
 Your PR of new Quant models is highly welcomed.
 
-The performance of each model on the `Alpha158` and `Alpha360` dataset can be found [here](examples/benchmarks/README.md).
+The performance of each model on the `Alpha158` and `Alpha360` datasets can be found [here](examples/benchmarks/README.md).
 
 ### Run a single model
 All the models listed above are runnable with ``Qlib``. Users can find the config files we provide and some details about the model through the [benchmarks](examples/benchmarks) folder. More information can be retrieved at the model files listed above.
@@ -393,6 +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`:
 
@@ -404,6 +431,17 @@ 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/).
 

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/alpha.rst

@@ -38,7 +38,7 @@ Example
 
         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::
 

docs/advanced/task_management.rst

@@ -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
 ===============
@@ -31,9 +31,10 @@ 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
 ============
@@ -53,8 +54,9 @@ 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
 =============
@@ -64,11 +66,13 @@ An easy way to get the ``task_func`` is using ``qlib.model.trainer.task_train``
 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/component/data.rst

@@ -24,8 +24,8 @@ 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) / $close", the return of last 60 trading days). Supported operators in the expression engine can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/ops.py>`_. This step is typically implemented in Qlib's `Data Loader <https://qlib.readthedocs.io/en/latest/component/data.html#data-loader>`_ which is a component of `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ .
-- If users require more complicated data processing (e.g. data normalization),  `Data Handler <https://qlib.readthedocs.io/en/latest/component/data.html#data-handler>`_ support user-customized processors to process data(some predefined processors can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/data/dataset/processor.py>`_).  The processors are different from operators in expression engine. It is designed for some complicated data processing methods which is hard to supported in operators in expression engine.
+- Creating some basic features based on Qlib's expression Engine(e.g. "Ref($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
@@ -37,7 +37,7 @@ 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 +47,12 @@ 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. User can also use numpy to load `.bin` file to validate data.
-The price volume data look different from the actual dealling price because of they are **adjusted** (`adjusted price <https://www.investopedia.com/terms/a/adjusted_closing_price.asp>`_).  And then you may find that the adjusted price may be different from different data sources. This is because different data sources may vary in the way of adjusting prices. Qlib normalize the price on first trading day of each stock to 1 when adjusting them.
+The price volume data look different from the actual dealing price because of they are **adjusted** (`adjusted price <https://www.investopedia.com/terms/a/adjusted_closing_price.asp>`_).  And then you may find that the adjusted price may be different from different data sources. This is because different data sources may vary in the way of adjusting prices. Qlib normalize the price on first trading day of each stock to 1 when adjusting them.
 Users can leverage `$factor` to get the original trading price (e.g. `$close / $factor` to get the original close price).
 
 Here are some discussions about the price adjusting of Qlib. 
@@ -119,7 +119,7 @@ Here are some example:
 for daily data:
   .. code-block:: bash
 
-    python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
+    python scripts/get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
 
 for 1min data:
   .. code-block:: bash
@@ -140,12 +140,13 @@ Users can also provide their own data in CSV format. However, the CSV data **mus
 
         where the data are in the following format:
 
-        .. code-block::
+            +-----------+-------+
+            | symbol    | close |
+            +===========+=======+
+            | SH600000  | 120   |
+            +-----------+-------+
 
-            symbol,close
-            SH600000,120
-
-- CSV file **must** includes a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
+- CSV file **must** include a column for the date, and when dumping the data, user must specify the date column name. Here is an example:
 
     .. code-block:: bash
 
@@ -153,11 +154,13 @@ Users can also provide their own data in CSV format. However, the CSV data **mus
 
     where the data are in the following format:
 
-    .. code-block::
-
-        symbol,date,close,open,volume
-        SH600000,2020-11-01,120,121,12300000
-        SH600000,2020-11-02,123,120,12300000
+        +---------+------------+-------+------+----------+
+        | symbol  | date       | close | open | volume   |
+        +=========+============+=======+======+==========+
+        | SH600000| 2020-11-01 | 120   | 121  | 12300000 |
+        +---------+------------+-------+------+----------+
+        | SH600000| 2020-11-02 | 123   | 120  | 12300000 |
+        +---------+------------+-------+------+----------+
 
 
 Supposed that users prepare their CSV format data in the directory ``~/.qlib/csv_data/my_data``, they can run the following command to start the conversion.
@@ -332,6 +335,7 @@ Here are some interfaces of the ``QlibDataLoader`` class:
 
 .. autoclass:: qlib.data.dataset.loader.DataLoader
     :members:
+    :noindex:
 
 API
 ---
@@ -361,6 +365,7 @@ 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``.
@@ -451,6 +456,7 @@ The ``DatasetH`` class is the `dataset` with `Data Handler`. Here is the most im
 
 .. autoclass:: qlib.data.dataset.__init__.DatasetH
     :members:
+    :noindex:
 
 API
 ---
@@ -470,9 +476,11 @@ Global Memory Cache
 
 .. autoclass:: qlib.data.cache.MemCacheUnit
     :members:
+    :noindex:
 
 .. autoclass:: qlib.data.cache.MemCache
     :members:
+    :noindex:
 
 
 ExpressionCache
@@ -487,6 +495,7 @@ 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.
 
@@ -502,6 +511,7 @@ 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.
 
@@ -512,7 +522,7 @@ 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

docs/component/highfreq.rst

@@ -8,31 +8,33 @@ Design of Nested Decision Execution Framework for High-Frequency Trading
 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 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 work about high-frequency trading in Qlib.
+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 form high-frequency data without fixed frequency.
+- `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/model.rst

@@ -20,6 +20,7 @@ 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.
 
@@ -85,7 +86,7 @@ Example
             },
         }
 
-        # model initiaiton
+        # model initialization
         model = init_instance_by_config(task["model"])
         dataset = init_instance_by_config(task["dataset"])
 

docs/component/online.rst

@@ -1,4 +1,4 @@
-.. _online:
+.. _online_serving:
 
 ==============
 Online Serving
@@ -32,21 +32,25 @@ 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

@@ -61,6 +61,7 @@ The ``ExpManager`` module in ``Qlib`` is responsible for managing different expe
 
 .. 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>`_.
 
@@ -71,6 +72,7 @@ The ``Experiment`` class is solely responsible for a single experiment, and it w
 
 .. 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>`_.
 
@@ -85,6 +87,7 @@ 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>`_.
 
@@ -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
 

docs/component/report.rst

@@ -51,6 +51,7 @@ API
 
 .. automodule:: qlib.contrib.report.analysis_position.report
     :members:
+    :noindex:
 
 Graphical Result
 ~~~~~~~~~~~~~~~~
@@ -93,6 +94,7 @@ API
 
 .. automodule:: qlib.contrib.report.analysis_position.score_ic
     :members:
+    :noindex:
 
 
 Graphical Result
@@ -151,6 +153,7 @@ API
 
 .. automodule:: qlib.contrib.report.analysis_position.risk_analysis
     :members:
+    :noindex:
 
 
 Graphical Result
@@ -174,6 +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`
@@ -269,6 +273,7 @@ API
 
 .. automodule:: qlib.contrib.report.analysis_model.analysis_model_performance
     :members:
+    :noindex:
 
 
 Graphical Results

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

@@ -80,6 +80,7 @@ TopkDropoutStrategy
         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
 

docs/component/workflow.rst

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

docs/conf.py

@@ -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"

docs/developer/code_standard_and_dev_guide.rst

@@ -15,7 +15,8 @@ Continuous Integration (CI) tools help you stick to the quality standards by run
 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 inputing the following code in the command line.
+
+   You can fix the bug by inputting the following code in the command line.
 
 .. code-block:: bash
 
@@ -32,7 +33,8 @@ When you submit a PR request, you can check whether your code passes the CI test
 
 
 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.
+
+   You can fix the bug by inputing the following code in the command line.
 
 .. code-block:: bash
 
@@ -40,7 +42,8 @@ When you submit a PR request, you can check whether your code passes the CI test
 
 
 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.
+
+   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
 

docs/hidden/client.rst

@@ -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,
@@ -161,7 +162,7 @@ Limitations
 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
 -----

docs/index.rst

@@ -33,7 +33,7 @@ Document Structure
 
 .. toctree::
    :maxdepth: 3
-   :caption: COMPONENTS:
+   :caption: MAIN COMPONENTS:
 
    Workflow: Workflow Management <component/workflow.rst>
    Data Layer: Data Framework & Usage <component/data.rst>
@@ -44,10 +44,11 @@ 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>
@@ -55,6 +56,12 @@ Document Structure
    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
    :caption: REFERENCE:

docs/introduction/introduction.rst

@@ -15,38 +15,56 @@ With ``Qlib``, users can easily try their ideas to create better Quant investmen
 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

@@ -16,11 +16,12 @@ 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
 

docs/reference/api.rst

@@ -1,4 +1,5 @@
 .. _api:
+
 =============
 API Reference
 =============
@@ -116,7 +117,7 @@ Model
 Strategy
 --------
 
-.. automodule:: qlib.contrib.strategy.strategy
+.. automodule:: qlib.contrib.strategy
     :members:
 
 Evaluate
@@ -254,5 +255,38 @@ 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

@@ -83,15 +83,14 @@ Load features of certain instruments in a given time range:
    >> 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:
 
@@ -105,15 +104,14 @@ 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>`_.

docs/start/integration.rst

@@ -21,84 +21,88 @@ The Custom models need to inherit `qlib.model.base.Model <../reference/api.html#
     - ``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):
+        .. code-block:: Python
 
-            # 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"]
+            def fit(self, dataset: DatasetH, num_boost_round = 1000, **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")
+                # 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"]
 
-            dtrain = lgb.Dataset(x_train.values, label=y_train)
-            dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+                # 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")
 
-            # 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
-            )
+                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
 ==================
@@ -107,21 +111,21 @@ The configuration file is described in detail in the `Workflow <../component/wor
 
 - 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
+    .. 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
+        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.
 

examples/benchmarks/ADARNN/workflow_config_adarnn_Alpha360.yaml

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

examples/benchmarks/ADD/workflow_config_add_Alpha360.yaml

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

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml

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

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158_csi500.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_early_stop_Alpha158.yaml

@@ -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/workflow_config_hist_Alpha360.yaml

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

examples/benchmarks/IGMTF/workflow_config_igmtf_Alpha360.yaml

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

examples/benchmarks/KRNN/README.md

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

examples/benchmarks/KRNN/requirements.txt

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

examples/benchmarks/KRNN/workflow_config_krnn_Alpha360.yaml

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

examples/benchmarks/LSTM/workflow_config_lstm_Alpha158.yaml

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

examples/benchmarks/LSTM/workflow_config_lstm_Alpha360.yaml

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

examples/benchmarks/LightGBM/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/workflow_config_lightgbm_Alpha158.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_csi500.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_multi_freq.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360_csi500.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_configurable_dataset.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_multi_freq.yaml

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

examples/benchmarks/Linear/workflow_config_linear_Alpha158.yaml

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

examples/benchmarks/Linear/workflow_config_linear_Alpha158_csi500.yaml

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

examples/benchmarks/Linear/workflow_config_linear_Alpha158_multi_pass_bt.yaml

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

examples/benchmarks/Localformer/workflow_config_localformer_Alpha158.yaml

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

examples/benchmarks/Localformer/workflow_config_localformer_Alpha360.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha158.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha158_csi500.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha360.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha360_csi500.yaml

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

examples/benchmarks/README.md

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

examples/benchmarks/SFM/workflow_config_sfm_Alpha360.yaml

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

examples/benchmarks/Sandwich/README.md

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

examples/benchmarks/Sandwich/requirements.txt

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

examples/benchmarks/Sandwich/workflow_config_sandwich_Alpha360.yaml

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

examples/benchmarks/TCN/workflow_config_tcn_Alpha158.yaml

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

examples/benchmarks/TCN/workflow_config_tcn_Alpha360.yaml

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

examples/benchmarks/TCTS/workflow_config_tcts_Alpha360.yaml

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

examples/benchmarks/TFT/data_formatters/base.py

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

examples/benchmarks/TFT/expt_settings/configs.py

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

examples/benchmarks/TFT/libs/hyperparam_opt.py

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

examples/benchmarks/TFT/libs/tft_model.py

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

examples/benchmarks/TFT/workflow_config_tft_Alpha158.yaml

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

examples/benchmarks/TRA/Reports.ipynb

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