add gym (#1104)

* fix SepDataFrame when we del it to empty

* init_instance_by_config enhancement

* Update test_sepdf.py

.deepsource.toml

@@ -0,0 +1,12 @@
+version = 1
+
+test_patterns = ["tests/test_*.py"]
+
+exclude_patterns = ["examples/**"]
+
+[[analyzers]]
+name = "python"
+enabled = true
+
+  [analyzers.meta]
+  runtime_version = "3.x.x"

.github/PULL_REQUEST_TEMPLATE.md

@@ -8,6 +8,7 @@
 <!--- Why is this change required? What problem does it solve? -->
 
 ## How Has This Been Tested?
+<!---  Put an `x` in all the boxes that apply: --->
 - [ ] Pass the test by running: `pytest qlib/tests/test_all_pipeline.py` under upper directory of `qlib`.
 - [ ] If you are adding a new feature, test on your own test scripts.
 

.github/stale.yml

@@ -1,62 +0,0 @@
-# Configuration for probot-stale - https://github.com/probot/stale
-
-# Number of days of inactivity before an Issue or Pull Request becomes stale
-daysUntilStale: 60
-
-# Number of days of inactivity before an Issue or Pull Request with the stale label is closed.
-# Set to false to disable. If disabled, issues still need to be closed manually, but will remain marked as stale.
-daysUntilClose: 7
-
-# Only issues or pull requests with all of these labels are check if stale. Defaults to `[]` (disabled)
-onlyLabels: []
-
-# Issues or Pull Requests with these labels will never be considered stale. Set to `[]` to disable
-exemptLabels:
-  - bug
-  - pinned
-  - security
-  - "[Status] Maybe Later"
-
-# Set to true to ignore issues in a project (defaults to false)
-exemptProjects: false
-
-# Set to true to ignore issues in a milestone (defaults to false)
-exemptMilestones: false
-
-# Set to true to ignore issues with an assignee (defaults to false)
-exemptAssignees: false
-
-# Label to use when marking as stale
-staleLabel: wontfix
-
-# Comment to post when marking as stale. Set to `false` to disable
-markComment: >
-  This issue has been automatically marked as stale because it has not had
-  recent activity. It will be closed if no further activity occurs. Thank you
-  for your contributions.
-
-# Comment to post when removing the stale label.
-# unmarkComment: >
-#   Your comment here.
-
-# Comment to post when closing a stale Issue or Pull Request.
-# closeComment: >
-#   Your comment here.
-
-# Limit the number of actions per hour, from 1-30. Default is 30
-limitPerRun: 30
-
-# Limit to only `issues` or `pulls`
-# only: issues
-
-# Optionally, specify configuration settings that are specific to just 'issues' or 'pulls':
-# pulls:
-#   daysUntilStale: 30
-#   markComment: >
-#     This pull request has been automatically marked as stale because it has not had
-#     recent activity. It will be closed if no further activity occurs. Thank you
-#     for your contributions.
-
-# issues:
-#   exemptLabels:
-#     - confirmed

.github/workflows/python-publish.yml

@@ -12,8 +12,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, macos-latest]
-        python-version: [3.6, 3.7, 3.8]
+        os: [windows-latest, macos-11]
+        # FIXME:  macos-latest will raise error now.
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
 
     steps:
     - uses: actions/checkout@v2
@@ -44,7 +46,8 @@ jobs:
     - name: Build wheel on Linux
       uses: RalfG/python-wheels-manylinux-build@v0.3.1-manylinux2010_x86_64
       with:
-        python-versions: 'cp36-cp36m cp37-cp37m cp38-cp38'
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-versions: 'cp37-cp37m cp38-cp38'
         build-requirements: 'numpy cython'
     - name: Set up Python
       uses: actions/setup-python@v2

.github/workflows/stale.yml

@@ -0,0 +1,24 @@
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: "0 0/3 * * *"
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/stale@v3
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'This issue is stale because it has been open for three months with no activity. Remove the stale label or comment on the issue otherwise this will be closed in 5 days'
+        stale-pr-message: 'This PR is stale because it has been open for a year with no activity. Remove the stale label or comment on the PR otherwise this will be closed in 5 days'
+        stale-issue-label: 'stale'
+        stale-pr-label: 'stale'
+        days-before-stale: 90
+        days-before-close: 5
+        operations-per-run: 100
+        exempt-issue-labels: 'bug,enhancement'
+        remove-stale-when-updated: true

.github/workflows/test.yml

@@ -1,4 +1,4 @@
-name: Test 
+name: Test
 
 on:
   push:
@@ -12,8 +12,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-16.04, ubuntu-18.04, ubuntu-20.04, macos-latest]
-        python-version: [3.6, 3.7, 3.8, 3.9]
+        os: [windows-latest, ubuntu-18.04, ubuntu-20.04]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
 
     steps:
     - uses: actions/checkout@v2
@@ -25,94 +26,116 @@ jobs:
 
     - name: Lint with Black
       run: |
-        cd ..
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe -m pip install black
-          $CONDA\\python.exe -m black qlib -l 120 --check --diff
-        else
-          sudo $CONDA/bin/python -m pip install black
-          $CONDA/bin/python -m black qlib -l 120 --check --diff
-        fi
-      shell: bash
+        pip install --upgrade pip
+        pip install black wheel
+        black qlib -l 120 --check --diff
 
-    # Test Qlib installed with pip
     - name: Install Qlib with pip
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe -m pip install pyqlib --ignore-installed ruamel.yaml --user
-        else
-          sudo $CONDA/bin/python -m pip install pyqlib --ignore-installed ruamel.yaml
-        fi
-      shell: bash
-    
-    - name: Install Lightgbm for MacOS
-      if: runner.os == 'macOS'
+        pip install numpy==1.19.5 ruamel.yaml
+        pip install pyqlib --ignore-installed
+
+    - name: Make html with sphinx
       run: |
-        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
-        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
+        pip install -U sphinx
+        pip install sphinx_rtd_theme readthedocs_sphinx_ext
+        pip install --exists-action=w --no-cache-dir -r docs/requirements.txt 
+        cd docs 
+        sphinx-build -b html . build
+        cd ..
+        
+    # Check Qlib with pylint
+    # TODO: These problems we will solve in the future. Important among them are: W0221, W0223, W0237, E1102
+      # C0103: invalid-name
+      # C0209: consider-using-f-string
+      # R0402: consider-using-from-import
+      # R1705: no-else-return
+      # R1710: inconsistent-return-statements
+      # R1725: super-with-arguments
+      # R1735: use-dict-literal
+      # W0102: dangerous-default-value
+      # W0212: protected-access
+      # W0221: arguments-differ
+      # W0223: abstract-method
+      # W0231: super-init-not-called
+      # W0237: arguments-renamed
+      # W0612: unused-variable
+      # W0621: redefined-outer-name
+      # W0622: redefined-builtin
+      # FIXME: specify exception type
+      # W0703: broad-except
+      # W1309: f-string-without-interpolation
+      # E1102: not-callable
+      # E1136: unsubscriptable-object
+    # References for parameters: https://github.com/PyCQA/pylint/issues/4577#issuecomment-1000245962 
+    - name: Check Qlib with pylint
+      run: |
+        pip install --upgrade pip
+        pip install pylint
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0201,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"
+
+    # The following flake8 error codes were ignored:
+      # E501 line too long
+        # Description: We have used black to limit the length of each line to 120.
+      # F541 f-string is missing placeholders
+        # Description: The same thing is done when using pylint for detection.
+      # E266 too many leading '#' for block comment
+        # Description: To make the code more readable, a lot of "#" is used.
+        # This error code appears centrally in:
+          # qlib/backtest/executor.py
+          # qlib/data/ops.py
+          # qlib/utils/__init__.py
+      # E402 module level import not at top of file
+        # Description: There are times when module level import is not available at the top of the file.
+      # W503 line break before binary operator
+        # Description: Since black formats the length of each line of code, it has to perform a line break when a line of arithmetic is too long.
+      # E731 do not assign a lambda expression, use a def
+        # Description: Restricts the use of lambda expressions, but at some point lambda expressions are required.
+      # E203 whitespace before ':'
+        # Description: If there is whitespace before ":", it cannot pass the black check.
+    - name: Check Qlib with flake8
+      run: |
+        pip install --upgrade pip
+        pip install flake8
+        flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 --per-file-ignores="__init__.py:F401,F403" qlib
+
+    # https://github.com/python/mypy/issues/10600
+    - name: Check Qlib with mypy
+      run: |
+        pip install mypy
+        mypy qlib --install-types --non-interactive || true
+        mypy qlib
 
     - name: Test data downloads
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        else
-          $CONDA/bin/python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        fi
-      shell: bash
+        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data_simple --interval 1d --region cn
+        python -c "import os; userpath=os.path.expanduser('~'); os.rename(userpath + '/.qlib/qlib_data/cn_data_simple', userpath + '/.qlib/qlib_data/cn_data')"
+        azcopy copy https://qlibpublic.blob.core.windows.net/data /tmp/qlibpublic --recursive
+        mv /tmp/qlibpublic/data tests/.data
 
     - name: Test workflow by config (install from pip)
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe qlib\\workflow\\cli.py examples\\benchmarks\\LightGBM\\workflow_config_lightgbm_Alpha158.yaml 
-          $CONDA\\python.exe -m pip uninstall -y pyqlib
-        else
-          $CONDA/bin/python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml 
-          sudo $CONDA/bin/python -m pip uninstall -y pyqlib
-        fi
-      shell: bash
-      
-    # Test Qlib installed from source
+        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+        python -m pip uninstall -y pyqlib
+
+     # Test Qlib installed from source
     - name: Install Qlib from source
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe -m pip install --upgrade cython
-          $CONDA\\python.exe -m pip install numpy jupyter jupyter_contrib_nbextensions
-          $CONDA\\python.exe -m pip install -U scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
-          $CONDA\\python.exe setup.py install
-        else
-          sudo $CONDA/bin/python -m pip install --upgrade cython
-          sudo $CONDA/bin/python -m pip install numpy jupyter jupyter_contrib_nbextensions
-          sudo $CONDA/bin/python -m pip install -U scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
-          sudo $CONDA/bin/python setup.py install
-        fi
-      shell: bash
+        pip install --upgrade cython jupyter jupyter_contrib_nbextensions numpy scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
+        pip install gym tianshou torch
+        pip install -e .
 
     - name: Install test dependencies
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe -m pip install --upgrade pip
-          $CONDA\\python.exe -m pip install black pytest
-        else
-          sudo $CONDA/bin/python -m pip install --upgrade pip
-          sudo $CONDA/bin/python -m pip install black pytest
-        fi
-      shell: bash 
+        pip install --upgrade pip
+        pip install black pytest
 
     - name: Unit tests with Pytest
       run: |
+        pip install -r scripts/data_collector/pit/requirements.txt
         cd tests
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe -m pytest . --durations=0
-        else
-          $CONDA/bin/python -m pytest . --durations=0
-        fi
-      shell: bash
+        python -m pytest . --durations=10
 
     - name: Test workflow by config (install from source)
       run: |
-        if [ "$RUNNER_OS" == "Windows" ]; then
-          $CONDA\\python.exe qlib\\workflow\\cli.py examples\\benchmarks\\LightGBM\\workflow_config_lightgbm_Alpha158.yaml 
-        else
-          $CONDA/bin/python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml 
-        fi
-      shell: bash
+        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

.github/workflows/test_macos.yml

@@ -0,0 +1,94 @@
+# There are some issues (in the downloading data phase) on MacOS when running with other tests. So we split it into an individual config.
+name: Test MacOS
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-11, macos-latest]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Lint with Black
+      run: |
+        cd ..
+        python -m pip install pip --upgrade
+        python -m pip install wheel --upgrade
+        python -m pip install black
+        python -m black qlib -l 120 --check --diff
+    # Test Qlib installed with pip
+
+    - name: Check Qlib with flake8
+      run: |
+        pip install --upgrade pip
+        pip install flake8
+        flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 --per-file-ignores="__init__.py:F401,F403" qlib
+
+    - name: Install Qlib with pip
+      run: |
+          python -m pip install numpy==1.19.5
+          python -m pip install pyqlib --ignore-installed ruamel.yaml numpy
+    - name: Make html with sphnix
+      run: |
+        pip install -U sphinx
+        pip install sphinx_rtd_theme readthedocs_sphinx_ext
+        pip install --exists-action=w --no-cache-dir -r docs/requirements.txt 
+        cd docs 
+        sphinx-build -b html . build
+        cd ..
+    - name: Install Lightgbm for MacOS
+      run: |
+        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
+        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
+        # FIX MacOS error: Segmentation fault
+        # reference: https://github.com/microsoft/LightGBM/issues/4229
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/fb8323f2b170bd4ae97e1bac9bf3e2983af3fdb0/Formula/libomp.rb
+        brew unlink libomp
+        brew install libomp.rb
+    - name: Test data downloads
+      run: |
+        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data_simple --interval 1d --region cn
+        python -c "import os; userpath=os.path.expanduser('~'); os.rename(userpath + '/.qlib/qlib_data/cn_data_simple', userpath + '/.qlib/qlib_data/cn_data')"
+        azcopy copy https://qlibpublic.blob.core.windows.net/data /tmp/qlibpublic --recursive
+        mv /tmp/qlibpublic/data tests/.data
+    - name: Test workflow by config (install from pip)
+      run: |
+        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+        python -m pip uninstall -y pyqlib
+    # Test Qlib installed from source
+    - name: Install Qlib from source
+      run: |
+        python -m pip install --upgrade cython
+        python -m pip install numpy jupyter jupyter_contrib_nbextensions
+        python -m pip install -U scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
+        python -m pip install gym tianshou torch
+        pip install -e .
+    - name: Install test dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install -U pyopenssl idna
+        python -m pip install black pytest
+    - name: Unit tests with Pytest
+      run: |
+        pip install -r scripts/data_collector/pit/requirements.txt
+        cd tests
+        python -m pytest . --durations=0
+    - name: Test workflow by config (install from source)
+      run: |
+          python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

.gitignore

@@ -20,12 +20,17 @@ dist/
 .nvimrc
 .vscode
 
+qlib/VERSION.txt
 qlib/data/_libs/expanding.cpp
 qlib/data/_libs/rolling.cpp
 examples/estimator/estimator_example/
 
 *.egg-info/
 
+# test related
+test-output.xml
+.output
+.data
 
 # special software
 mlruns/
@@ -33,4 +38,9 @@ mlruns/
 tags
 
 .pytest_cache/
+.mypy_cache/
 .vscode/
+
+*.swp
+
+./pretrain

.mypy.ini

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

.pre-commit-config.yaml

@@ -0,0 +1,12 @@
+repos:
+-   repo: https://github.com/psf/black
+    rev: 22.1.0
+    hooks:
+    -   id: black
+        args: ["qlib", "-l 120"]
+
+-   repo: https://github.com/PyCQA/flake8
+    rev: 4.0.1
+    hooks:
+        - id: flake8
+          args: ["--ignore=E501,F541,E266,E402,W503,E731,E203"]

.pylintrc

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

.readthedocs.yml

@@ -17,5 +17,5 @@ python:
   version: 3.7
   install:
     - requirements: docs/requirements.txt
-    - method: setuptools
-      path: .
+    - method: pip
+      path: .

CHANGES.rst

@@ -30,7 +30,7 @@ Version 0.2.1
 --------------------
 - Support registering user-defined ``Provider``.
 - Support use operators in string format, e.g. ``['Ref($close, 1)']`` is valid field format.
-- Support dynamic fields in ``$some_field`` format. And exising fields like ``Close()`` may be deprecated in the future.
+- Support dynamic fields in ``$some_field`` format. And existing fields like ``Close()`` may be deprecated in the future.
 
 Version 0.2.2
 --------------------
@@ -78,7 +78,7 @@ Version 0.3.5
 - Support multi-label training, you can provide multiple label in ``handler``. (But LightGBM doesn't support due to the algorithm itself)
 - Refactor ``handler`` code, dataset.py is no longer used, and you can deploy your own labels and features in ``feature_label_config``
 - Handler only offer DataFrame. Also, ``trainer`` and model.py only receive DataFrame
-- Change ``split_rolling_data``, we roll the data on market calender now, not on normal date
+- Change ``split_rolling_data``, we roll the data on market calendar now, not on normal date
 - Move some date config from ``handler`` to ``trainer``
 
 Version 0.4.0
@@ -159,6 +159,21 @@ Version 0.5.0
     - Add baselines
     - public data crawler
 
-Version greater than Version 0.5.0
+
+Version 0.8.0
+--------------------
+- The backtest is greatly refactored.
+    - Nested decision execution framework is supported
+    - There are lots of changes for daily trading, it is hard to list all of them. But a few important changes could be noticed
+        - The trading limitation is more accurate;
+            - In `previous version <https://github.com/microsoft/qlib/blob/v0.7.2/qlib/contrib/backtest/exchange.py#L160>`_, longing and shorting actions share the same action.
+            - In `current version <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/backtest/exchange.py#L304>`_, the trading limitation is different between logging and shorting action.
+        - 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>`_
+
+
+Other Versions
 ----------------------------------
 Please refer to `Github release Notes <https://github.com/microsoft/qlib/releases>`_

MANIFEST.in

@@ -0,0 +1 @@
+include qlib/VERSION.txt

README.md

@@ -7,9 +7,37 @@
 [![License](https://img.shields.io/pypi/l/pyqlib)](LICENSE)
 [![Join the chat at https://gitter.im/Microsoft/qlib](https://badges.gitter.im/Microsoft/qlib.svg)](https://gitter.im/Microsoft/qlib?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
 
+## :newspaper: **What's NEW!**     :sparkling_heart: 
+Recent released features
+| Feature | Status |
+| --                      | ------    |
+| HIST and IGMTF models | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/1040) on Apr 10, 2022 |
+| Qlib [notebook tutorial](https://github.com/microsoft/qlib/tree/main/examples/tutorial) | 📖 [Released](https://github.com/microsoft/qlib/pull/1037) on Apr 7, 2022 | 
+| Ibovespa index data | :rice: [Released](https://github.com/microsoft/qlib/pull/990) on Apr 6, 2022 |
+| Point-in-Time database | :hammer: [Released](https://github.com/microsoft/qlib/pull/343) on Mar 10, 2022 |
+| Arctic Provider Backend & Orderbook data example | :hammer: [Released](https://github.com/microsoft/qlib/pull/744) on Jan 17, 2022 |
+| Meta-Learning-based framework & DDG-DA  | :chart_with_upwards_trend:  :hammer: [Released](https://github.com/microsoft/qlib/pull/743) on Jan 10, 2022 | 
+| Planning-based portfolio optimization | :hammer: [Released](https://github.com/microsoft/qlib/pull/754) on Dec 28, 2021 | 
+| Release Qlib v0.8.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.8.0) on Dec 8, 2021 |
+| ADD model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/704) on Nov 22, 2021 |
+| ADARNN  model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/689) on Nov 14, 2021 |
+| TCN  model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/668) on Nov 4, 2021 |
+| Nested Decision Framework | :hammer: [Released](https://github.com/microsoft/qlib/pull/438) on Oct 1, 2021. [Example](https://github.com/microsoft/qlib/blob/main/examples/nested_decision_execution/workflow.py) and [Doc](https://qlib.readthedocs.io/en/latest/component/highfreq.html) |
+| Temporal Routing Adaptor (TRA) | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/531) on July 30, 2021 |
+| Transformer & Localformer | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/508) on July 22, 2021 |
+| Release Qlib v0.7.0 | :octocat: [Released](https://github.com/microsoft/qlib/releases/tag/v0.7.0) on July 12, 2021 |
+| TCTS Model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/491) on July 1, 2021 |
+| Online serving and automatic model rolling | :hammer:  [Released](https://github.com/microsoft/qlib/pull/290) on May 17, 2021 | 
+| DoubleEnsemble Model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/286) on Mar 2, 2021 | 
+| High-frequency data processing example | :hammer: [Released](https://github.com/microsoft/qlib/pull/257) on Feb 5, 2021  |
+| High-frequency trading example | :chart_with_upwards_trend: [Part of code released](https://github.com/microsoft/qlib/pull/227) on Jan 28, 2021  | 
+| High-frequency data(1min) | :rice: [Released](https://github.com/microsoft/qlib/pull/221) on Jan 27, 2021 |
+| Tabnet Model | :chart_with_upwards_trend: [Released](https://github.com/microsoft/qlib/pull/205) on Jan 22, 2021 |
+
+Features released before 2021 are not listed here.
 
 <p align="center">
-  <img src="http://fintech.msra.cn/images_v060/logo/1.png" />
+  <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
 </p>
 
 
@@ -17,46 +45,82 @@ Qlib is an AI-oriented quantitative investment platform, which aims to realize t
 
 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, user can easily try ideas to create better Quant investment strategies.
+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).
 
-- [Framework of Qlib](#framework-of-qlib)
-- [Quick Start](#quick-start)
-  - [Installation](#installation)
-  - [Data Preparation](#data-preparation)
-  - [Auto Quant Research Workflow](#auto-quant-research-workflow)
-  - [Building Customized Quant Research Workflow by Code](#building-customized-quant-research-workflow-by-code)
-- [**Quant Model Zoo**](#quant-model-zoo)
-  - [Run a single model](#run-a-single-model)
-  - [Run multiple models](#run-multiple-models)
-- [**Quant Dataset Zoo**](#quant-dataset-zoo)
-- [More About Qlib](#more-about-qlib)
-- [Offline Mode and Online Mode](#offline-mode-and-online-mode)
-  - [Performance of Qlib Data Server](#performance-of-qlib-data-server)
-- [Related Reports](#related-reports)
-- [Contributing](#contributing)
 
+<table>
+  <tbody>
+    <tr>
+      <th>Frameworks, Tutorial, Data & DevOps</th>
+      <th>Main Challenges & Solutions in Quant Research</th>
+    </tr>
+    <tr>
+      <td>
+        <li><a href="#plans"><strong>Plans</strong></a></li>
+        <li><a href="#framework-of-qlib">Framework of Qlib</a></li>
+        <li><a href="#quick-start">Quick Start</a></li>
+          <ul dir="auto">
+            <li type="circle"><a href="#installation">Installation</a> </li>
+            <li type="circle"><a href="#data-preparation">Data Preparation</a></li>
+            <li type="circle"><a href="#auto-quant-research-workflow">Auto Quant Research Workflow</a></li>
+            <li type="circle"><a href="#building-customized-quant-research-workflow-by-code">Building Customized Quant Research Workflow by Code</a></li></ul>
+        <li><a href="#quant-dataset-zoo"><strong>Quant Dataset Zoo</strong></a></li>
+        <li><a href="#more-about-qlib">More About Qlib</a></li>
+        <li><a href="#offline-mode-and-online-mode">Offline Mode and Online Mode</a>
+        <ul>
+          <li type="circle"><a href="#performance-of-qlib-data-server">Performance of Qlib Data Server</a></li></ul>
+        <li><a href="#related-reports">Related Reports</a></li>
+        <li><a href="#contact-us">Contact Us</a></li>
+        <li><a href="#contributing">Contributing</a></li>
+      </td>
+      <td valign="baseline">
+        <li><a href="#main-challenges--solutions-in-quant-research">Main Challenges &amp; Solutions in Quant Research</a>
+          <ul>
+            <li type="circle"><a href="#forecasting-finding-valuable-signalspatterns">Forecasting: Finding Valuable Signals/Patterns</a>
+              <ul>
+                <li type="disc"><a href="#quant-model-paper-zoo"><strong>Quant Model (Paper) Zoo</strong></a>
+                  <ul>
+                    <li type="circle"><a href="#run-a-single-model">Run a Single Model</a></li>
+                    <li type="circle"><a href="#run-multiple-models">Run Multiple Models</a></li>
+                  </ul>
+                </li>
+              </ul>
+            </li>
+          <li type="circle"><a href="#adapting-to-market-dynamics">Adapting to Market Dynamics</a></li>
+          </ul>
+        </li>
+      </td>
+    </tr>
+  </tbody>
+</table>
 
+# Plans
+New features under development(order by estimated release time).
+Your feedbacks about the features are very important.
+<!-- | Feature                        | Status      | -->
+<!-- | --                      | ------    | -->
 
 # Framework of Qlib
 
 <div style="align: center">
-<img src="http://fintech.msra.cn/images_v060/framework.png?v=0.1" />
+<img src="docs/_static/img/framework.svg" />
 </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.
+At the module level, Qlib is a platform that consists of the above components. The components are designed as loose-coupled modules, and each component could be used stand-alone.
 
 | Name                   | Description                                                                                                                                                                                                                                                                                                                                                             |
 | ------                 | -----                                                                                                                                                                                                                                                                                                                                                                   |
-| `Infrastructure` layer | `Infrastructure` layer provides underlying support for Quant research. `DataServer` provides 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 `Portfolio Generator` will generate the target portfolio and produce orders to be executed by `Order Executor`. |
+| `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/)
+
 
 # Quick Start
 
@@ -72,14 +136,15 @@ Here is a quick **[demo](https://terminalizer.com/view/3f24561a4470)** shows how
 This table demonstrates the supported Python version of `Qlib`:
 |               | install with pip           | install from source  | plot |
 | ------------- |:---------------------:|:--------------------:|:----:|
-| Python 3.6    | :heavy_check_mark:    | :heavy_check_mark: (only with `Anaconda`)                  | :heavy_check_mark: |
 | Python 3.7    | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
 | Python 3.8    | :heavy_check_mark:    | :heavy_check_mark:   | :heavy_check_mark: |
 | Python 3.9    | :x:                   | :heavy_check_mark:   | :x: |
 
 **Note**: 
+1. **Conda** is suggested for managing your Python environment.
 1. Please pay attention that installing cython in Python 3.6 will raise some error when installing ``Qlib`` from source. If users use Python 3.6 on their machines, it is recommended to *upgrade* Python to version 3.7 or use `conda`'s Python to install ``Qlib`` from source.
-2. 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. 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. 
 
 ### Install with pip
 Users can easily install ``Qlib`` by pip according to the following command.
@@ -101,31 +166,55 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
   ```
 
 * Clone the repository and install ``Qlib`` as follows.
-  * If you haven't installed qlib by the command ``pip install pyqlib`` before:
-    ```bash
-    git clone https://github.com/microsoft/qlib.git && cd qlib
-    python setup.py install
-    ```
-  * If you have already installed the stable version by the command ``pip install pyqlib``:
     ```bash
     git clone https://github.com/microsoft/qlib.git && cd qlib
     pip install .
     ```
-  **Note**: **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 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**.
 
 **Tips**: If you fail to install `Qlib` or run the examples in your environment,  comparing your steps and the [CI workflow](.github/workflows/test.yml) may help you find the problem.
 
 ## Data Preparation
 Load and prepare data by running the following code:
   ```bash
+  # get 1d data
   python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+
+  # get 1min data
+  python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --region cn --interval 1min
+
   ```
 
 This dataset is created by public data collected by [crawler scripts](scripts/data_collector/), which have been released in
 the same repository.
-Users could create the same dataset with it. 
+Users could create the same dataset with it. [Description of dataset](https://github.com/microsoft/qlib/tree/main/scripts/data_collector#description-of-dataset)
+
+*Please pay **ATTENTION** that the data is collected from [Yahoo Finance](https://finance.yahoo.com/lookup), and the data might not be perfect.
+We recommend users to prepare their own data if they have a high-quality dataset. For more information, users can refer to the [related document](https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format)*.
+
+### Automatic update of daily frequency data (from yahoo finance)
+  > This step is *Optional* if users only want to try their models and strategies on history data.
+  > 
+  > It is recommended that users update the data manually once (--trading_date 2021-05-25) and then set it to update automatically.
+  >
+  > For more information, please refer to: [yahoo collector](https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#automatic-update-of-daily-frequency-datafrom-yahoo-finance)
+
+  * Automatic update of data to the "qlib" directory each trading day(Linux)
+      * use *crontab*: `crontab -e`
+      * set up timed tasks:
+
+        ```
+        * * * * 1-5 python <script path> update_data_to_bin --qlib_data_1d_dir <user data dir>
+        ```
+        * **script path**: *scripts/data_collector/yahoo/collector.py*
+
+  * Manual update of data
+      ```
+      python scripts/data_collector/yahoo/collector.py update_data_to_bin --qlib_data_1d_dir <user data dir> --trading_date <start date> --end_date <end date>
+      ```
+      * *trading_date*: start of trading day
+      * *end_date*: end of trading day(not included)
 
-*Please pay **ATTENTION** that the data is collected from [Yahoo Finance](https://finance.yahoo.com/lookup) and the data might not be perfect. We recommend users to prepare their own data if they have high-quality dataset. For more information, users can refer to the [related document](https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format)*.
 
 <!-- 
 - Run the initialization code and get stock data:
@@ -133,7 +222,7 @@ Users could create the same dataset with it.
   ```python
   import qlib
   from qlib.data import D
-  from qlib.config import REG_CN
+  from qlib.constant import REG_CN
 
   # Initialization
   mount_path = "~/.qlib/qlib_data/cn_data"  # target_dir
@@ -190,19 +279,19 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
 2. Graphical Reports Analysis: Run `examples/workflow_by_code.ipynb` with `jupyter notebook` to get graphical reports
     - Forecasting signal (model prediction) analysis
       - Cumulative Return of groups
-      ![Cumulative Return](http://fintech.msra.cn/images_v060/analysis/analysis_model_cumulative_return.png?v=0.1)
+      ![Cumulative Return](http://fintech.msra.cn/images_v070/analysis/analysis_model_cumulative_return.png?v=0.1)
       - Return distribution
-      ![long_short](http://fintech.msra.cn/images_v060/analysis/analysis_model_long_short.png?v=0.1)
+      ![long_short](http://fintech.msra.cn/images_v070/analysis/analysis_model_long_short.png?v=0.1)
       - Information Coefficient (IC)
-      ![Information Coefficient](http://fintech.msra.cn/images_v060/analysis/analysis_model_IC.png?v=0.1)        
-      ![Monthly IC](http://fintech.msra.cn/images_v060/analysis/analysis_model_monthly_IC.png?v=0.1)
-      ![IC](http://fintech.msra.cn/images_v060/analysis/analysis_model_NDQ.png?v=0.1)
+      ![Information Coefficient](http://fintech.msra.cn/images_v070/analysis/analysis_model_IC.png?v=0.1)
+      ![Monthly IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_monthly_IC.png?v=0.1)
+      ![IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_NDQ.png?v=0.1)
       - Auto Correlation of forecasting signal (model prediction)
-      ![Auto Correlation](http://fintech.msra.cn/images_v060/analysis/analysis_model_auto_correlation.png?v=0.1)
+      ![Auto Correlation](http://fintech.msra.cn/images_v070/analysis/analysis_model_auto_correlation.png?v=0.1)
 
     - Portfolio analysis
       - Backtest return
-      ![Report](http://fintech.msra.cn/images_v060/analysis/report.png?v=0.1)
+      ![Report](http://fintech.msra.cn/images_v070/analysis/report.png?v=0.1)
       <!-- 
       - Score IC
       ![Score IC](docs/_static/img/score_ic.png)
@@ -213,51 +302,81 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
       - Rank Label
       ![Rank Label](docs/_static/img/rank_label.png)
       -->
+   - [Explanation](https://qlib.readthedocs.io/en/latest/component/report.html) of above results
 
 ## Building Customized Quant Research Workflow by Code
-The automatic workflow may not suite 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.
+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.
+Currently, Qlib provides some solutions for several of them.
+
+## Forecasting: Finding Valuable Signals/Patterns
+Accurate forecasting of the stock price trend is a very important part to construct profitable portfolios.
+However, huge amount of data with various formats in the financial market which make it challenging to build forecasting models.
+
+An increasing number of SOTA Quant research works/papers, which focus on building forecasting models to mine valuable signals/patterns in complex financial data, are released in `Qlib`
 
 
-# [Quant Model Zoo](examples/benchmarks)
+### [Quant Model (Paper) Zoo](examples/benchmarks)
 
 Here is a list of models built on `Qlib`.
-- [GBDT based on XGBoost (Tianqi Chen, et al. 2016)](qlib/contrib/model/xgboost.py)
-- [GBDT based on LightGBM (Guolin Ke, et al. 2017)](qlib/contrib/model/gbdt.py)
-- [GBDT based on Catboost (Liudmila Prokhorenkova, et al. 2017)](qlib/contrib/model/catboost_model.py)
-- [MLP based on pytorch](qlib/contrib/model/pytorch_nn.py)
-- [LSTM based on pytorch (Sepp Hochreiter, et al. 1997)](qlib/contrib/model/pytorch_lstm.py)
-- [GRU based on pytorch (Kyunghyun Cho, et al. 2014)](qlib/contrib/model/pytorch_gru.py)
-- [ALSTM based on pytorch (Yao Qin, et al. 2017)](qlib/contrib/model/pytorch_alstm.py)
-- [GATs based on pytorch (Petar Velickovic, et al. 2017)](qlib/contrib/model/pytorch_gats.py)
-- [SFM based on pytorch (Liheng Zhang, et al. 2017)](qlib/contrib/model/pytorch_sfm.py)
-- [TFT based on tensorflow (Bryan Lim, et al. 2019)](examples/benchmarks/TFT/tft.py)
-- [TabNet based on pytorch (Sercan O. Arik, et al. 2019)](qlib/contrib/model/pytorch_tabnet.py)
+- [GBDT based on XGBoost (Tianqi Chen, et al. KDD 2016)](examples/benchmarks/XGBoost/)
+- [GBDT based on LightGBM (Guolin Ke, et al. NIPS 2017)](examples/benchmarks/LightGBM/)
+- [GBDT based on Catboost (Liudmila Prokhorenkova, et al. NIPS 2018)](examples/benchmarks/CatBoost/)
+- [MLP based on pytorch](examples/benchmarks/MLP/)
+- [LSTM based on pytorch (Sepp Hochreiter, et al. Neural computation 1997)](examples/benchmarks/LSTM/)
+- [GRU based on pytorch (Kyunghyun Cho, et al. 2014)](examples/benchmarks/GRU/)
+- [ALSTM based on pytorch (Yao Qin, et al. IJCAI 2017)](examples/benchmarks/ALSTM)
+- [GATs based on pytorch (Petar Velickovic, et al. 2017)](examples/benchmarks/GATs/)
+- [SFM based on pytorch (Liheng Zhang, et al. KDD 2017)](examples/benchmarks/SFM/)
+- [TFT based on tensorflow (Bryan Lim, et al. International Journal of Forecasting 2019)](examples/benchmarks/TFT/)
+- [TabNet based on pytorch (Sercan O. Arik, et al. AAAI 2019)](examples/benchmarks/TabNet/)
+- [DoubleEnsemble based on LightGBM (Chuheng Zhang, et al. ICDM 2020)](examples/benchmarks/DoubleEnsemble/)
+- [TCTS based on pytorch (Xueqing Wu, et al. ICML 2021)](examples/benchmarks/TCTS/)
+- [Transformer based on pytorch (Ashish Vaswani, et al. NeurIPS 2017)](examples/benchmarks/Transformer/)
+- [Localformer based on pytorch (Juyong Jiang, et al.)](examples/benchmarks/Localformer/)
+- [TRA based on pytorch (Hengxu, Dong, et al. KDD 2021)](examples/benchmarks/TRA/)
+- [TCN based on pytorch (Shaojie Bai, et al. 2018)](examples/benchmarks/TCN/)
+- [ADARNN based on pytorch (YunTao Du, et al. 2021)](examples/benchmarks/ADARNN/)
+- [ADD based on pytorch (Hongshun Tang, et al.2020)](examples/benchmarks/ADD/)
+- [IGMTF based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/IGMTF/)
+- [HIST based on pytorch (Wentao Xu, et al.2021)](examples/benchmarks/HIST/)
 
 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).
 
-## Run a single model
+### 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.
 
 `Qlib` provides three different ways to run a single model, users can pick the one that fits their cases best:
-- User can use the tool `qrun` mentioned above to run a model's workflow based from a config file.
-- User can create a `workflow_by_code` python script based on the [one](examples/workflow_by_code.py) listed in the `examples` folder.
+- Users can use the tool `qrun` mentioned above to run a model's workflow based from a config file.
+- Users can create a `workflow_by_code` python script based on the [one](examples/workflow_by_code.py) listed in the `examples` folder.
 
-- User can use the script [`run_all_model.py`](examples/run_all_model.py) listed in the `examples` folder to run a model. Here is an example of the specific shell command to be used: `python run_all_model.py --models=lightgbm`, where the `--models` arguments can take any number of models listed above(the available models can be found  in [benchmarks](examples/benchmarks/)). For more use cases, please refer to the file's [docstrings](examples/run_all_model.py).
+- Users can use the script [`run_all_model.py`](examples/run_all_model.py) listed in the `examples` folder to run a model. Here is an example of the specific shell command to be used: `python run_all_model.py run --models=lightgbm`, where the `--models` arguments can take any number of models listed above(the available models can be found  in [benchmarks](examples/benchmarks/)). For more use cases, please refer to the file's [docstrings](examples/run_all_model.py).
+    - **NOTE**: Each baseline has different environment dependencies, please make sure that your python version aligns with the requirements(e.g. TFT only supports Python 3.6~3.7 due to the limitation of `tensorflow==1.15.0`)
 
-## Run multiple models
-`Qlib` also provides a script [`run_all_model.py`](examples/run_all_model.py) which can run multiple models for several iterations. (**Note**: the script only support *Linux* for now. Other OS will be supported in the future. Besides, it doesn't support parrallel running the same model for multiple times as well, and this will be fixed in the future development too.)
+### Run multiple models
+`Qlib` also provides a script [`run_all_model.py`](examples/run_all_model.py) which can run multiple models for several iterations. (**Note**: the script only support *Linux* for now. Other OS will be supported in the future. Besides, it doesn't support parallel running the same model for multiple times as well, and this will be fixed in the future development too.)
 
 The script will create a unique virtual environment for each model, and delete the environments after training. Thus, only experiment results such as `IC` and `backtest` results will be generated and stored.
 
 Here is an example of running all the models for 10 iterations:
 ```python
-python run_all_model.py 10
+python run_all_model.py run 10
 ```
 
 It also provides the API to run specific models at once. For more use cases, please refer to the file's [docstrings](examples/run_all_model.py). 
 
+## [Adapting to Market Dynamics](examples/benchmarks_dynamic)
+
+Due to the non-stationary nature of the environment of the financial market, the data distribution may change in different periods, which makes the performance of models build on training data decays in the future test data.
+So adapting the forecasting models/strategies to market dynamics is very important to the model/strategies' performance.
+
+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/)
 
 # Quant Dataset Zoo
 Dataset plays a very important role in Quant. Here is a list of the datasets built on `Qlib`:
@@ -271,6 +390,8 @@ Dataset plays a very important role in Quant. Here is a list of the datasets bui
 Your PR to build new Quant dataset is highly welcomed.
 
 # More About Qlib
+If you want to have a quick glance at the most frequently used components of qlib, you can try notebooks [here](examples/tutorial/).
+
 The detailed documents are organized in [docs](docs/).
 [Sphinx](http://www.sphinx-doc.org) and the readthedocs theme is required to build the documentation in html formats. 
 ```bash
@@ -307,21 +428,62 @@ which creates a dataset (14 features/factors) from the basic OHLCV daily data of
 * `+(-)E` indicates with (out) `ExpressionCache`
 * `+(-)D` indicates with (out) `DatasetCache`
 
-Most general-purpose databases take too much time on loading data. After looking into the underlying implementation, we find that data go through too many layers of interfaces and unnecessary format transformations in general-purpose database solutions.
+Most general-purpose databases take too much time to load data. After looking into the underlying implementation, we find that data go through too many layers of interfaces and unnecessary format transformations in general-purpose database solutions.
 Such overheads greatly slow down the data loading process.
 Qlib data are stored in a compact format, which is efficient to be combined into arrays for scientific computation.
 
-
 # Related Reports
 - [Guide To Qlib: Microsoft’s AI Investment Platform](https://analyticsindiamag.com/qlib/)
-- [【华泰金工林晓明团队】微软AI量化投资平台Qlib体验——华泰人工智能系列之四十](https://mp.weixin.qq.com/s/Brcd7im4NibJOJzZfMn6tQ)
 - [微软也搞AI量化平台？还是开源的！](https://mp.weixin.qq.com/s/47bP5YwxfTp2uTHjUBzJQQ)
 - [微矿Qlib：业内首个AI量化投资开源平台](https://mp.weixin.qq.com/s/vsJv7lsgjEi-ALYUz4CvtQ)
 
+# Contact Us
+- If you have any issues, please create issue [here](https://github.com/microsoft/qlib/issues/new/choose) or send messages in [gitter](https://gitter.im/Microsoft/qlib).
+- If you want to make contributions to `Qlib`, please [create pull requests](https://github.com/microsoft/qlib/compare). 
+- For other reasons, you are welcome to contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).
+  - We are recruiting new members(both FTEs and interns), your resumes are welcome!
+
+Join IM discussion groups:
+|[Gitter](https://gitter.im/Microsoft/qlib)|
+|----|
+|![image](http://fintech.msra.cn/images_v070/qrcode/gitter_qr.png)|
 
 # Contributing
+We appreciate all contributions and thank all the contributors!
+<a href="https://github.com/microsoft/qlib/graphs/contributors"><img src="https://contrib.rocks/image?repo=microsoft/qlib" /></a>
 
-This project welcomes contributions and suggestions.  Most contributions require you to agree to a
+Before we released Qlib as an open-source project on Github in Sep 2020, Qlib is an internal project in our group. Unfortunately, the internal commit history is not kept. A lot of members in our group have also contributed a lot to Qlib, which includes Ruihua Wang, Yinda Zhang, Haisu Yu, Shuyu Wang, Bochen Pang, and [Dong Zhou](https://github.com/evanzd/evanzd). Especially thanks to [Dong Zhou](https://github.com/evanzd/evanzd) due to his initial version of Qlib.
+
+## Guidance
+
+This project welcomes contributions and suggestions.  
+**Here are some 
+[code standards](docs/developer/code_standard.rst) for submiting a pull request.**
+
+Making contributions is not a hard thing. Solving an issue(maybe just answering a question raised in [issues list](https://github.com/microsoft/qlib/issues) or [gitter](https://gitter.im/Microsoft/qlib)), fixing/issuing a bug, improving the documents and even fixing a typo are important contributions to Qlib.
+
+For example, if you want to contribute to Qlib's document/code, you can follow the steps in the figure below.
+<p align="center">
+  <img src="https://github.com/demon143/qlib/blob/main/docs/_static/img/change%20doc.gif" />
+</p>
+
+If you don't know how to start to contribute, you can refer to the following examples.
+| Type | Examples |
+| -- | -- |
+| Solving issues | [Answer a question](https://github.com/microsoft/qlib/issues/749);  [issuing](https://github.com/microsoft/qlib/issues/765) or [fixing](https://github.com/microsoft/qlib/pull/792) a bug |
+| Docs | [Improve docs quality](https://github.com/microsoft/qlib/pull/797/files) ;  [Fix a typo](https://github.com/microsoft/qlib/pull/774) | 
+| Feature |  Implement a [requested feature](https://github.com/microsoft/qlib/projects) like [this](https://github.com/microsoft/qlib/pull/754); [Refactor interfaces](https://github.com/microsoft/qlib/pull/539/files) |
+| Dataset | [Add a dataset](https://github.com/microsoft/qlib/pull/733) | 
+| Models |  [Implement a new model](https://github.com/microsoft/qlib/pull/689), [some instructions to contribute models](https://github.com/microsoft/qlib/tree/main/examples/benchmarks#contributing) |
+
+[Good first issues](https://github.com/microsoft/qlib/labels/good%20first%20issue) are labelled to indicate that they are easy to start your contributions.
+
+You can find some impefect implementation in Qlib by  `rg 'TODO|FIXME' qlib`
+ 
+If you would like to become one of Qlib's maintainers to contribute more (e.g. help merge PR, triage issues), please contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).  We are glad to help to upgrade your permission.
+
+## Licence
+Most contributions require you to agree to a
 Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
 the right to use your contribution. For details, visit https://cla.opensource.microsoft.com.
 

docs/FAQ/FAQ.rst

@@ -70,3 +70,84 @@ If the issue is not resolved, use ``keys *`` to find if multiple keys exist. If
 
 
 Also, feel free to post a new issue in our GitHub repository. We always check each issue carefully and try our best to solve them.
+
+3. ModuleNotFoundError: No module named 'qlib.data._libs.rolling'
+------------------------------------------------------------------------------------------------------------------------------------
+
+.. code-block:: python
+
+    #### Do not import qlib package in the repository directory in case of importing qlib from . without compiling #####
+    Traceback (most recent call last):
+    File "<stdin>", line 1, in <module>
+    File "qlib/qlib/__init__.py", line 19, in init
+        from .data.cache import H
+    File "qlib/qlib/data/__init__.py", line 8, in <module>
+        from .data import (
+    File "qlib/qlib/data/data.py", line 20, in <module>
+        from .cache import H
+    File "qlib/qlib/data/cache.py", line 36, in <module>
+        from .ops import Operators
+    File "qlib/qlib/data/ops.py", line 19, in <module>
+        from ._libs.rolling import rolling_slope, rolling_rsquare, rolling_resi
+    ModuleNotFoundError: No module named 'qlib.data._libs.rolling'
+
+- If the error occurs when importing ``qlib`` package with ``PyCharm`` IDE, users can execute the following command in the project root folder to compile Cython files and generate executable files:
+
+    .. code-block:: bash
+
+        python setup.py build_ext --inplace
+
+- If the error occurs when importing ``qlib`` package with command ``python`` , users need to change the running directory to ensure that the script does not run in the project directory.
+
+
+4. BadNamespaceError: / is not a connected namespace
+------------------------------------------------------------------------------------------------------------------------------------
+
+.. code-block:: python
+
+      File "qlib_online.py", line 35, in <module>
+        cal = D.calendar()
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\data.py", line 973, in calendar
+        return Cal.calendar(start_time, end_time, freq, future=future)
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\data.py", line 798, in calendar
+        self.conn.send_request(
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\client.py", line 101, in send_request
+        self.sio.emit(request_type + "_request", request_content)
+      File "G:\apps\miniconda\envs\qlib\lib\site-packages\python_socketio-5.3.0-py3.8.egg\socketio\client.py", line 369, in emit
+        raise exceptions.BadNamespaceError(
+      BadNamespaceError: / is not a connected namespace.
+
+- The version of ``python-socketio`` in qlib needs to be the same as the version of ``python-socketio`` in qlib-server:
+
+    .. code-block:: bash
+
+        pip install -U python-socketio==<qlib-server python-socketio version>
+
+
+5. TypeError: send() got an unexpected keyword argument 'binary'
+------------------------------------------------------------------------------------------------------------------------------------
+
+.. code-block:: python
+
+      File "qlib_online.py", line 35, in <module>
+        cal = D.calendar()
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\data.py", line 973, in calendar
+        return Cal.calendar(start_time, end_time, freq, future=future)
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\data.py", line 798, in calendar
+        self.conn.send_request(
+      File "e:\code\python\microsoft\qlib_latest\qlib\qlib\data\client.py", line 101, in send_request
+        self.sio.emit(request_type + "_request", request_content)
+      File "G:\apps\miniconda\envs\qlib\lib\site-packages\socketio\client.py", line 263, in emit
+        self._send_packet(packet.Packet(packet.EVENT, namespace=namespace,
+      File "G:\apps\miniconda\envs\qlib\lib\site-packages\socketio\client.py", line 339, in _send_packet
+        self.eio.send(ep, binary=binary)
+      TypeError: send() got an unexpected keyword argument 'binary'
+
+
+- The ``python-engineio`` version needs to be compatible with the ``python-socketio`` version, reference: https://github.com/miguelgrinberg/python-socketio#version-compatibility
+
+    .. code-block:: bash
+
+        pip install -U python-engineio==<compatible python-socketio version>
+        # or
+        pip install -U python-socketio==3.1.2 python-engineio==3.13.2

docs/advanced/PIT.rst

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

docs/advanced/serial.rst

@@ -0,0 +1,45 @@
+.. _serial:
+
+=================================
+Serialization
+=================================
+.. currentmodule:: qlib
+
+Introduction
+===================
+``Qlib`` supports dumping the state of ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc. into a disk and reloading them. 
+
+Serializable Class
+========================
+
+``Qlib`` provides a base class ``qlib.utils.serial.Serializable``, whose state can be dumped into or loaded from disk in `pickle` format. 
+When users dump the state of a ``Serializable`` instance, the attributes of the instance whose name **does not** start with `_` will be saved on the disk.
+However, users can use ``config`` method or override ``default_dump_all`` attribute to prevent this feature.
+
+Users can also override ``pickle_backend`` attribute to choose a pickle backend. The supported value is "pickle" (default and common) and "dill" (dump more things such as function, more information in `here <https://pypi.org/project/dill/>`_).
+
+Example
+==========================
+``Qlib``'s serializable class includes  ``DataHandler``, ``DataSet``, ``Processor`` and ``Model``, etc., which are subclass of  ``qlib.utils.serial.Serializable``. 
+Specifically, ``qlib.data.dataset.DatasetH`` is one of them. Users can serialize ``DatasetH`` as follows.
+
+.. code-block:: Python
+
+    ##=============dump dataset=============
+    dataset.to_pickle(path="dataset.pkl") # dataset is an instance of qlib.data.dataset.DatasetH
+
+    ##=============reload dataset=============
+    with open("dataset.pkl", "rb") as file_dataset:
+        dataset = pickle.load(file_dataset)
+
+.. note::
+    Only state of ``DatasetH`` should be saved on the disk, such as some `mean` and `variance` used for data normalization, etc. 
+
+    After reloading the ``DatasetH``, users need to reinitialize it. It means that users can reset some states of ``DatasetH`` or ``QlibDataHandler`` such as `instruments`, `start_time`, `end_time` and `segments`, etc.,  and generate new data according to the states (data is not state and should not be saved on the disk).
+
+A more detailed example is in this `link <https://github.com/microsoft/qlib/tree/main/examples/highfreq>`_.
+
+
+API
+===================
+Please refer to `Serializable API <../reference/api.html#module-qlib.utils.serial.Serializable>`_.

docs/advanced/task_management.rst

@@ -0,0 +1,96 @@
+.. _task_management:
+
+=================================
+Task Management
+=================================
+.. currentmodule:: qlib
+
+
+Introduction
+=============
+
+The `Workflow <../component/introduction.html>`_ part introduces how to run research workflow in a loosely-coupled way. But it can only execute one ``task`` when you use ``qrun``.
+To automatically generate and execute different tasks, ``Task Management`` provides a whole process including `Task Generating`_, `Task Storing`_, `Task Training`_ and `Task Collecting`_. 
+With this module, users can run their ``task`` automatically at different periods, in different losses, or even by different models.The processes of task generation, model training and combine and collect data are shown in the following figure.
+
+.. image:: ../_static/img/Task-Gen-Recorder-Collector.svg
+    :align: center
+
+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>`_.
+
+Task Generating
+===============
+A ``task`` consists of `Model`, `Dataset`, `Record`, or anything added by users. 
+The specific task template can be viewed in 
+`Task Section <../component/workflow.html#task-section>`_.
+Even though the task template is fixed, users can customize their ``TaskGen`` to generate different ``task`` by task template.
+
+Here is the base class of ``TaskGen``:
+
+.. autoclass:: qlib.workflow.task.gen.TaskGen
+    :members:
+
+``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>`_.
+
+Task Storing
+===============
+To achieve higher efficiency and the possibility of cluster operation, ``Task Manager`` will store all tasks in `MongoDB <https://www.mongodb.com/>`_.
+``TaskManager`` can fetch undone tasks automatically and manage the lifecycle of a set of tasks with error handling.
+Users **MUST** finish the configuration of `MongoDB <https://www.mongodb.com/>`_ when using this module.
+
+Users need to provide the MongoDB URL and database name for using ``TaskManager`` in `initialization <../start/initialization.html#Parameters>`_ or make a statement like this.
+
+    .. code-block:: python
+
+        from qlib.config import C
+        C["mongo"] = {
+            "task_url" : "mongodb://localhost:27017/", # your MongoDB url
+            "task_db_name" : "rolling_db" # database name
+        }
+
+.. autoclass:: qlib.workflow.task.manage.TaskManager
+    :members:
+
+More information of ``Task Manager`` can be found in `here <../reference/api.html#TaskManager>`_.
+
+Task Training
+===============
+After generating and storing those ``task``, it's time to run the ``task`` which is in the *WAITING* status.
+``Qlib`` provides a method called ``run_task`` to run those ``task`` in task pool, however, users can also customize how tasks are executed.
+An easy way to get the ``task_func`` is using ``qlib.model.trainer.task_train`` directly.
+It will run the whole workflow defined by ``task``, which includes *Model*, *Dataset*, *Record*.
+
+.. autofunction:: qlib.workflow.task.manage.run_task
+
+Meanwhile, ``Qlib`` provides a module called ``Trainer``. 
+
+.. autoclass:: qlib.model.trainer.Trainer
+    :members:
+
+``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. 
+If you do not want to use ``Task Manager`` to manage tasks, then use TrainerR to train a list of tasks generated by ``TaskGen`` is enough.
+`Here <../reference/api.html#Trainer>`_ are the details about different ``Trainer``.
+
+Task Collecting
+===============
+Before collecting model training results, you need to use the ``qlib.init`` to specify the path of mlruns.
+
+To collect the results of ``task`` after training, ``Qlib`` provides `Collector <../reference/api.html#Collector>`_, `Group <../reference/api.html#Group>`_ and `Ensemble <../reference/api.html#Ensemble>`_ to collect the results in a readable, expandable and loosely-coupled way.
+
+`Collector <../reference/api.html#Collector>`_ can collect objects from everywhere and process them such as merging, grouping, averaging and so on. It has 2 step action including ``collect`` (collect anything in a dict) and ``process_collect`` (process collected dict).
+
+`Group <../reference/api.html#Group>`_ also has 2 steps including ``group`` (can group a set of object based on `group_func` and change them to a dict) and ``reduce`` (can make a dict become an ensemble based on some rule).
+For example: {(A,B,C1): object, (A,B,C2): object} ---``group``---> {(A,B): {C1: object, C2: object}} ---``reduce``---> {(A,B): object}
+
+`Ensemble <../reference/api.html#Ensemble>`_ can merge the objects in an ensemble. 
+For example: {C1: object, C2: object} ---``Ensemble``---> object.
+You can set the ensembles you want in the ``Collector``'s process_list.
+Common ensembles include ``AverageEnsemble`` and ``RollingEnsemble``. Average ensemble is used to ensemble the results of different models in the same time period. Rollingensemble is used to ensemble the results of different models in the same time period
+
+So the hierarchy is ``Collector``'s second step corresponds to ``Group``. And ``Group``'s second step correspond to ``Ensemble``.
+
+For more information, please see `Collector <../reference/api.html#Collector>`_, `Group <../reference/api.html#Group>`_ and `Ensemble <../reference/api.html#Ensemble>`_, or the `example <https://github.com/microsoft/qlib/tree/main/examples/model_rolling/task_manager_rolling.py>`_.

docs/component/backtest.rst

@@ -1,114 +0,0 @@
-.. _backtest:
-
-============================================
-Intraday Trading: Model&Strategy Testing
-============================================
-.. currentmodule:: qlib
-
-Introduction
-===================
-
-``Intraday Trading`` is designed to test models and strategies, which help users to check the performance of a custom model/strategy.
-
-
-.. note::
-
-    ``Intraday Trading`` uses ``Order Executor`` to trade and execute orders output by ``Portfolio Strategy``. ``Order Executor`` is a component in `Qlib Framework <../introduction/introduction.html#framework>`_, which can execute orders. ``VWAP Executor`` and ``Close Executor`` is supported by ``Qlib`` now. In the future, ``Qlib`` will support ``HighFreq Executor`` also. 
-
-
-
-Example
-===========================
-
-Users need to generate a `prediction score`(a pandas DataFrame) with MultiIndex<instrument, datetime> and a `score` column. And users need to assign a strategy used in backtest, if strategy is not assigned,
-a `TopkDropoutStrategy` strategy with `(topk=50, n_drop=5, risk_degree=0.95, limit_threshold=0.0095)` will be used.
-If ``Strategy`` module is not users' interested part, `TopkDropoutStrategy` is enough. 
-
-The simple example of the default strategy is as follows.
-
-.. code-block:: python
-
-    from qlib.contrib.evaluate import backtest
-    # pred_score is the prediction score
-    report, positions = backtest(pred_score, topk=50, n_drop=0.5, verbose=False, limit_threshold=0.0095)
-
-To know more about backtesting with a specific ``Strategy``, please refer to `Portfolio Strategy <strategy.html>`_.
-
-To know more about the prediction score `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
-
-Prediction Score
------------------
-
-The `prediction score` is a pandas DataFrame. Its index is <datetime(pd.Timestamp), instrument(str)> and it must
-contains a `score` column.
-
-A prediction sample is shown as follows.
-
-.. code-block:: python
-
-      datetime instrument     score
-    2019-01-04   SH600000 -0.505488
-    2019-01-04   SZ002531 -0.320391
-    2019-01-04   SZ000999  0.583808
-    2019-01-04   SZ300569  0.819628
-    2019-01-04   SZ001696 -0.137140
-                 ...            ...
-    2019-04-30   SZ000996 -1.027618
-    2019-04-30   SH603127  0.225677
-    2019-04-30   SH603126  0.462443
-    2019-04-30   SH603133 -0.302460
-    2019-04-30   SZ300760 -0.126383
-
-``Forecast Model`` module can make predictions, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
-
-Backtest Result
-------------------
-
-The backtest results are in the following form:
-
-.. code-block:: python
-
-                                                      risk
-    excess_return_without_cost mean               0.000605
-                               std                0.005481
-                               annualized_return  0.152373
-                               information_ratio  1.751319
-                               max_drawdown      -0.059055
-    excess_return_with_cost    mean               0.000410
-                               std                0.005478
-                               annualized_return  0.103265
-                               information_ratio  1.187411
-                               max_drawdown      -0.075024
-
-
-
-- `excess_return_without_cost`
-    - `mean`
-        Mean value of the `CAR` (cumulative abnormal return) without cost
-    - `std`
-        The `Standard Deviation` of `CAR` (cumulative abnormal return) without cost.
-    - `annualized_return`
-        The `Annualized Rate` of `CAR` (cumulative abnormal return) without cost.
-    - `information_ratio`
-        The `Information Ratio` without cost. please refer to `Information Ratio – IR <https://www.investopedia.com/terms/i/informationratio.asp>`_.
-    - `max_drawdown`
-        The `Maximum Drawdown` of `CAR` (cumulative abnormal return) without cost, please refer to `Maximum Drawdown (MDD) <https://www.investopedia.com/terms/m/maximum-drawdown-mdd.asp>`_.
-
-- `excess_return_with_cost`
-    - `mean`
-        Mean value of the `CAR` (cumulative abnormal return) series with cost
-    - `std`
-        The `Standard Deviation` of `CAR` (cumulative abnormal return) series with cost.
-    - `annualized_return`
-        The `Annualized Rate` of `CAR` (cumulative abnormal return) with cost.
-    - `information_ratio`
-        The `Information Ratio` with cost. please refer to `Information Ratio – IR <https://www.investopedia.com/terms/i/informationratio.asp>`_.
-    - `max_drawdown`
-        The `Maximum Drawdown` of `CAR` (cumulative abnormal return) with cost, please refer to `Maximum Drawdown (MDD) <https://www.investopedia.com/terms/m/maximum-drawdown-mdd.asp>`_.
-
-
-
-Reference
-==============
-
-To know more about ``Intraday Trading``, please refer to `Intraday Trading <../reference/api.html#module-qlib.contrib.evaluate>`_.

docs/component/data.rst

@@ -21,6 +21,12 @@ The introduction of ``Data Layer`` includes the following parts.
 - Cache
 - Data and Cache File Structure
 
+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.
+- 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
 ============================
@@ -31,7 +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 dataset, 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
@@ -41,38 +47,80 @@ 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>`_.
 
 Qlib Format Dataset
 --------------------
 ``Qlib`` has provided an off-the-shelf dataset in `.bin` format, users could use the script ``scripts/get_data.py`` to download the China-Stock dataset as follows.
+The price volume data look different from the actual dealling price because of they are **adjusted** (`adjusted price <https://www.investopedia.com/terms/a/adjusted_closing_price.asp>`_).  And then you may find that the adjusted price may be different from different data sources. This is because different data sources may vary in the way of adjusting prices. Qlib normalize the price on first trading day of each stock to 1 when adjusting them. 
+Users can leverage `$factor` to get the original trading price (e.g. `$close / $factor` to get the original close price).
 
 .. code-block:: bash
 
+    # download 1d
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
 
+    # download 1min
+    python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/qlib_cn_1min --region cn --interval 1min
+
 In addition to China-Stock data, ``Qlib`` also includes a US-Stock dataset, which can be downloaded with the following command:
 
 .. code-block:: bash
 
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/us_data --region us
 
-After running the above command, users can find china-stock and us-stock data in ``Qlib`` format in the ``~/.qlib/csv_data/cn_data`` directory and ``~/.qlib/csv_data/us_data`` directory respectively.
+After running the above command, users can find china-stock and us-stock data in ``Qlib`` format in the ``~/.qlib/qlib_data/cn_data`` directory and ``~/.qlib/qlib_data/us_data`` directory respectively.
 
 ``Qlib`` also provides the scripts in ``scripts/data_collector`` to help users crawl the latest data on the Internet and convert it to qlib format.
 
 When ``Qlib`` is initialized with this dataset, users could build and evaluate their own models with it.  Please refer to `Initialization <../start/initialization.html>`_ for more details.
 
+Automatic update of daily frequency data
+----------------------------------------
+
+  **It is recommended that users update the data manually once (\-\-trading_date 2021-05-25) and then set it to update automatically.**
+
+  For more information refer to: `yahoo collector <https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#Automatic-update-of-daily-frequency-data>`_
+
+  - Automatic update of data to the "qlib" directory each trading day(Linux)
+      - use *crontab*: `crontab -e`
+      - set up timed tasks:
+
+        .. code-block:: bash
+
+            * * * * 1-5 python <script path> update_data_to_bin --qlib_data_1d_dir <user data dir>
+
+        - **script path**: *scripts/data_collector/yahoo/collector.py*
+
+  - Manual update of data
+
+      .. code-block:: bash
+
+        python scripts/data_collector/yahoo/collector.py update_data_to_bin --qlib_data_1d_dir <user data dir> --trading_date <start date> --end_date <end date>
+
+      - *trading_date*: start of trading day
+      - *end_date*: end of trading day(not included)
+
+
+
 Converting CSV Format into Qlib Format
 -------------------------------------------
 
 ``Qlib`` has provided the script ``scripts/dump_bin.py`` to convert **any** data in CSV format into `.bin` files (``Qlib`` format) as long as they are in the correct format.
 
-Users can download the demo china-stock data in CSV format as follows for reference to the CSV format.
+Besides downloading the prepared demo data, users could download demo data directly from the Collector as follows for reference to the CSV format.
+Here are some example:
 
-.. code-block:: bash
+for daily data:
+  .. code-block:: bash
 
     python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
 
+for 1min data:
+  .. code-block:: bash
+
+    python scripts/data_collector/yahoo/collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1min --region CN --start 2021-05-20 --end 2021-05-23 --delay 0.1 --interval 1min --limit_nums 10
+
 Users can also provide their own data in CSV format. However, the CSV data **must satisfies** following criterions:
 
 - CSV file is named after a specific stock *or* the CSV file includes a column of the stock name
@@ -139,6 +187,17 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
         The Restoration factor. Normally, ``factor = adjusted_price / original_price``, `adjusted price` reference: `split adjusted <https://www.investopedia.com/terms/s/splitadjusted.asp>`_
 
     In the convention of `Qlib` data processing, `open, close, high, low, volume, money and factor` will be set to NaN if the stock is suspended. 
+    If you want to use your own alpha-factor which can't be calculate by OCHLV, like PE, EPS and so on, you could add it to the CSV files with OHCLV together and then dump it to the Qlib format data.
+
+Stock Pool (Market)
+--------------------------------
+
+``Qlib`` defines `stock pool <https://github.com/microsoft/qlib/blob/main/examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml#L4>`_ as stock list and their date ranges. Predefined stock pools (e.g. csi300) may be imported as follows.
+
+.. code-block:: bash
+
+    python collector.py --index_name CSI300 --qlib_dir <user qlib data dir> --method parse_instruments
+
 
 Multiple Stock Modes
 --------------------------------
@@ -158,18 +217,18 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
 - If users use ``Qlib`` in china-stock mode, china-stock data is required. Users can use ``Qlib`` in china-stock mode according to the following steps:
     - Download china-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in china-stock mode
-        Supposed that users download their Qlib format data in the directory ``~/.qlib/csv_data/cn_data``. Users only need to initialize ``Qlib`` as follows.
+        Supposed that users download their Qlib format data in the directory ``~/.qlib/qlib_data/cn_data``. Users only need to initialize ``Qlib`` as follows.
         
         .. code-block:: python
 
-            from qlib.config import REG_CN
+            from qlib.constant import REG_CN
             qlib.init(provider_uri='~/.qlib/qlib_data/cn_data', region=REG_CN)
         
 
 - If users use ``Qlib`` in US-stock mode, US-stock data is required. ``Qlib`` also provides a script to download US-stock data. Users can use ``Qlib`` in US-stock mode according to the following steps:
-    - Download china-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
+    - Download us-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in US-stock mode
-        Supposed that users prepare their Qlib format data in the directory ``~/.qlib/csv_data/us_data``. Users only need to initialize ``Qlib`` as follows.
+        Supposed that users prepare their Qlib format data in the directory ``~/.qlib/qlib_data/us_data``. Users only need to initialize ``Qlib`` as follows.
         
         .. code-block:: python
 
@@ -177,6 +236,11 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
             qlib.init(provider_uri='~/.qlib/qlib_data/us_data', region=REG_US)
         
 
+.. note::
+
+    PRs for new data source are highly welcome! Users could commit the code to crawl data as a PR like `the examples here  <https://github.com/microsoft/qlib/tree/main/scripts>`_. And then we will use the code to create data cache on our server which other users could use directly.
+
+
 Data API
 ========================
 
@@ -213,6 +277,25 @@ Filter
     - `cross-sectional features filter` \: rule_expression = '$rank($close)<10'
     - `time-sequence features filter`: rule_expression = '$Ref($close, 3)>100'
 
+Here is a simple example showing how to use filter in a basic ``Qlib`` workflow configuration file:
+
+.. code-block:: yaml
+
+    filter: &filter
+        filter_type: ExpressionDFilter
+        rule_expression: "Ref($close, -2) / Ref($close, -1) > 1"
+        filter_start_time: 2010-01-01
+        filter_end_time: 2010-01-07
+        keep: False
+
+    data_handler_config: &data_handler_config
+        start_time: 2010-01-01
+        end_time: 2021-01-22
+        fit_start_time: 2010-01-01
+        fit_end_time: 2015-12-31
+        instruments: *market
+        filter_pipe: [*filter]
+
 To know more about ``Filter``, please refer to `Filter API <../reference/api.html#module-qlib.data.filter>`_.
 
 Reference
@@ -263,7 +346,7 @@ DataHandlerLP
 
 In addition to use ``Data Handler`` in an automatic workflow with ``qrun``, ``Data Handler`` can be used as an independent module, by which users can easily preprocess data (standardization, remove NaN, etc.) and build datasets. 
 
-In order to achieve so, ``Qlib`` provides a base class `qlib.data.dataset.DataHandlerLP <../reference/api.html#qlib.data.dataset.handler.DataHandlerLP>`_. The core idea of this class is that: we will have some leanable ``Processors`` which can learn the parameters of data processing(e.g., parameters for zscore normalization). When new data comes in, these `trained` ``Processors`` can then process the new data and thus processing real-time data in an efficient way becomes possible. More information about ``Processors`` will be listed in the next subsection.
+In order to achieve so, ``Qlib`` provides a base class `qlib.data.dataset.DataHandlerLP <../reference/api.html#qlib.data.dataset.handler.DataHandlerLP>`_. The core idea of this class is that: we will have some learnable ``Processors`` which can learn the parameters of data processing(e.g., parameters for zscore normalization). When new data comes in, these `trained` ``Processors`` can then process the new data and thus processing real-time data in an efficient way becomes possible. More information about ``Processors`` will be listed in the next subsection.
 
 
 Interface
@@ -274,9 +357,10 @@ Here are some important interfaces that ``DataHandlerLP`` provides:
 .. autoclass:: qlib.data.dataset.handler.DataHandlerLP
     :members: __init__, fetch, get_cols
 
-If users want to load features and labels by config, users can inherit ``qlib.data.dataset.handler.ConfigDataHandler``, ``Qlib`` also provides some preprocess method in this subclass.
 
-If users want to use qlib data, `QLibDataHandler` is recommended. Users can inherit their custom class from `QLibDataHandler`, which is also a subclass of `ConfigDataHandler`.
+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``.
+
+Also, users can pass ``qlib.contrib.data.processor.ConfigSectionProcessor`` that provides some preprocess methods for features defined by config into the new handler.
 
 
 Processor
@@ -313,7 +397,6 @@ Qlib provides implemented data handler `Alpha158`. The following example shows h
 
 .. note:: Users need to initialize ``Qlib`` with `qlib.init` first, please refer to `initialization <../start/initialization.html>`_.
 
-
 .. code-block:: Python
 
     import qlib
@@ -340,6 +423,9 @@ Qlib provides implemented data handler `Alpha158`. The following example shows h
         # fetch all the features
         print(h.fetch(col_set="feature"))
 
+
+.. note:: In the ``Alpha158``, ``Qlib`` uses the label `Ref($close, -2)/Ref($close, -1) - 1` that means the change from T+1 to T+2, rather than `Ref($close, -1)/$close - 1`, of which the reason is that when getting the T day close price of a china stock, the stock can be bought on T+1 day and sold on T+2 day.
+
 API
 ---------
 
@@ -351,7 +437,7 @@ Dataset
 
 The ``Dataset`` module in ``Qlib`` aims to prepare data for model training and inferencing.
 
-The motivation of this module is that we want to maximize the flexibility of of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data. 
+The motivation of this module is that we want to maximize the flexibility of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data. 
 
 If user's model need process its data in a different way, user could implement his own ``Dataset`` class. If the model's
 data processing is not special, ``DatasetH`` can be used directly.
@@ -364,8 +450,7 @@ The ``DatasetH`` class is the `dataset` with `Data Handler`. Here is the most im
 API
 ---------
 
-To know more about ``Dataset``, please refer to `Dataset API <../reference/api.html#module-qlib.data.dataset.__init__>`_.
-
+To know more about ``Dataset``, please refer to `Dataset API <../reference/api.html#dataset>`_.
 
 
 Cache

docs/component/highfreq.rst

@@ -0,0 +1,38 @@
+.. _highfreq:
+
+============================================
+Design of Nested Decision Execution Framework for High-Frequency Trading
+============================================
+.. currentmodule:: qlib
+
+Introduction
+===================
+
+Daily trading (e.g. portfolio management) and intraday trading (e.g. orders execution) are two hot topics in Quant investment and usually studied separately.
+
+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.
+
+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. 
+
+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.
+
+.. 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.
+
+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>`_.
+
+
+Besides, the above examples, here are some other related work 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.
+- `A paper <https://github.com/microsoft/qlib/tree/high-freq-execution#high-frequency-execution>`_ for high-frequency trading.

docs/component/meta.rst

@@ -0,0 +1,68 @@
+.. _meta:
+
+=================================
+Meta Controller: Meta-Task & Meta-Dataset & Meta-Model
+=================================
+.. currentmodule:: qlib
+
+
+Introduction
+=============
+``Meta Controller`` provides guidance to ``Forecast Model``, which aims to learn regular patterns among a series of forecasting tasks and use learned patterns to guide forthcoming forecasting tasks. Users can implement their own meta-model instance based on ``Meta Controller`` module.
+
+Meta Task
+=============
+
+A `Meta Task` instance is the basic element in the meta-learning framework. It saves the data that can be used for the `Meta Model`. Multiple `Meta Task` instances may share the same `Data Handler`, controlled by `Meta Dataset`. Users should use `prepare_task_data()` to obtain the data that can be directly fed into the `Meta Model`.
+
+.. autoclass:: qlib.model.meta.task.MetaTask
+    :members:
+
+Meta Dataset
+=============
+
+`Meta Dataset` controls the meta-information generating process. It is on the duty of providing data for training the `Meta Model`. Users should use `prepare_tasks` to retrieve a list of `Meta Task` instances.
+
+.. autoclass:: qlib.model.meta.dataset.MetaTaskDataset
+    :members:
+
+Meta Model
+=============
+
+General Meta Model
+------------------
+`Meta Model` instance is the part that controls the workflow. The usage of the `Meta Model` includes:
+1. Users train their `Meta Model` with the `fit` function. 
+2. The `Meta Model` instance guides the workflow by giving useful information via the `inference` function.
+
+.. autoclass:: qlib.model.meta.model.MetaModel
+    :members:
+
+Meta Task Model
+------------------
+This type of meta-model may interact with task definitions directly. Then, the `Meta Task Model` is the class for them to inherit from. They guide the base tasks by modifying the base task definitions. The function `prepare_tasks` can be used to obtain the modified base task definitions.
+
+.. autoclass:: qlib.model.meta.model.MetaTaskModel
+    :members:
+
+Meta Guide Model
+------------------
+This type of meta-model participates in the training process of the base forecasting model. The meta-model may guide the base forecasting models during their training to improve their performances.
+
+.. autoclass:: qlib.model.meta.model.MetaGuideModel
+    :members:
+
+
+Example
+=============
+``Qlib`` provides an implementation of ``Meta Model`` module, ``DDG-DA``, 
+which adapts to the market dynamics. 
+
+``DDG-DA`` includes four steps:
+
+1. Calculate meta-information and encapsulate it into ``Meta Task`` instances. All the meta-tasks form a ``Meta Dataset`` instance.
+2. Train ``DDG-DA`` based on the training data of the meta-dataset.
+3. Do the inference of the ``DDG-DA`` to get guide information.
+4. Apply guide information to the forecasting models to improve their performances.
+
+The `above example <https://github.com/microsoft/qlib/tree/main/examples/benchmarks_dynamic/DDG-DA>`_ can be found in ``examples/benchmarks_dynamic/DDG-DA/workflow.py``.

docs/component/model.rst

@@ -106,6 +106,9 @@ Example
         `SignalRecord` is the `Record Template` in ``Qlib``, please refer to `Workflow <recorder.html#record-template>`_.
 
 Also, the above example has been given in ``examples/train_backtest_analyze.ipynb``.
+Technically, the meaning of the model prediction depends on the label setting designed by user.
+By default, the meaning of the score is normally the rating of the instruments by the forecasting model. The higher the score, the more profit the instruments. 
+
 
 Custom Model
 ===================

docs/component/online.rst

@@ -0,0 +1,52 @@
+.. _online:
+
+=================================
+Online Serving
+=================================
+.. currentmodule:: qlib
+
+
+Introduction
+=============
+
+.. image:: ../_static/img/online_serving.png
+    :align: center
+
+
+In addition to backtesting, one way to test a model is effective is to make predictions in real market conditions or even do real trading based on those predictions.
+``Online Serving`` is a set of modules for online models using the latest data,
+which including `Online Manager <#Online Manager>`_, `Online Strategy <#Online Strategy>`_, `Online Tool <#Online Tool>`_, `Updater <#Updater>`_. 
+
+`Here <https://github.com/microsoft/qlib/tree/main/examples/online_srv>`_ are several examples for reference, which demonstrate different features of ``Online Serving``.
+If you have many models or `task` needs to be managed, please consider `Task Management <../advanced/task_management.html>`_.
+The `examples <https://github.com/microsoft/qlib/tree/main/examples/online_srv>`_ are based on some components in `Task Management <../advanced/task_management.html>`_ such as ``TrainerRM`` or ``Collector``.
+
+**NOTE**: User should keep his data source updated to support online serving. For example, Qlib provides `a batch of scripts <https://github.com/microsoft/qlib/blob/main/scripts/data_collector/yahoo/README.md#automatic-update-of-daily-frequency-datafrom-yahoo-finance>`_ to help users update Yahoo daily data.
+
+Known limitations currently
+- Currently, the daily updating prediction for the next trading day is supported. But generating orders for the next trading day is not supported due to the `limitations of public data <https://github.com/microsoft/qlib/issues/215#issuecomment-766293563>_`
+
+
+Online Manager
+=============
+
+.. automodule:: qlib.workflow.online.manager
+    :members:
+
+Online Strategy
+=============
+
+.. automodule:: qlib.workflow.online.strategy
+    :members:
+
+Online Tool
+=============
+
+.. automodule:: qlib.workflow.online.utils
+    :members:
+
+Updater
+=============
+
+.. automodule:: qlib.workflow.online.update
+    :members:

docs/component/recorder.rst

@@ -34,9 +34,10 @@ Here is a general view of the structure of the system:
             - Recorder 2
             - ...
         - ...
+        
 This experiment management system defines a set of interface and provided a concrete implementation ``MLflowExpManager``, which is based on the machine learning platform: ``MLFlow`` (`link <https://mlflow.org/>`_). 
 
-If users set the implementation of ``ExpManager`` to be ``MLflowExpManager``, they can use the command `mlflow ui` to visualize and check the experiment results. For more information, pleaes refer to the related documents `here <https://www.mlflow.org/docs/latest/cli.html#mlflow-ui>`_.
+If users set the implementation of ``ExpManager`` to be ``MLflowExpManager``, they can use the command `mlflow ui` to visualize and check the experiment results. For more information, please refer to the related documents `here <https://www.mlflow.org/docs/latest/cli.html#mlflow-ui>`_.
 
 Qlib Recorder
 ===================
@@ -94,6 +95,57 @@ The ``RecordTemp`` class is a class that enables generate experiment results suc
 
 - ``SignalRecord``: This class generates the `prediction` results of the model.
 - ``SigAnaRecord``: This class generates the `IC`, `ICIR`, `Rank IC` and `Rank ICIR` of the model.
+
+Here is a simple example of what is done in ``SigAnaRecord``, which users can refer to if they want to calculate IC, Rank IC, Long-Short Return with their own prediction and label.
+
+.. code-block:: Python
+
+    from qlib.contrib.eva.alpha import calc_ic, calc_long_short_return
+
+    ic, ric = calc_ic(pred.iloc[:, 0], label.iloc[:, 0])
+    long_short_r, long_avg_r = calc_long_short_return(pred.iloc[:, 0], label.iloc[:, 0])
+
 - ``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.
+
+.. code-block:: Python
+
+    from qlib.contrib.strategy.strategy import TopkDropoutStrategy
+    from qlib.contrib.evaluate import (
+        backtest as normal_backtest,
+        risk_analysis,
+    )
+
+    # backtest
+    STRATEGY_CONFIG = {
+        "topk": 50,
+        "n_drop": 5,
+    }
+    BACKTEST_CONFIG = {
+        "limit_threshold": 0.095,
+        "account": 100000000,
+        "benchmark": BENCHMARK,
+        "deal_price": "close",
+        "open_cost": 0.0005,
+        "close_cost": 0.0015,
+        "min_cost": 5,
+    }
+    
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
+    report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
+
+    # analysis
+    analysis = dict()
+    analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+    analysis["excess_return_with_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"] - report_normal["cost"])
+    analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+    print(analysis_df)
+
 For more information about the APIs, please refer to `Record Template API <../reference/api.html#module-qlib.workflow.record_temp>`_.
+
+
+
+Known Limitations
+=================
+- The Python objects are saved based on pickle, which may results in issues when the environment dumping objects and loading objects are different.

docs/component/report.rst

@@ -20,6 +20,9 @@ Introduction
     - model_performance_graph
 
 
+All of the accumulated profit metrics(e.g. return, max drawdown) in Qlib are calculated by summation.
+This avoids the metrics or the plots being skewed exponentially over time.
+
 Graphical Reports
 ===================
 
@@ -101,7 +104,7 @@ Graphical Result
     - Axis Y: 
         - `ic`
             The `Pearson correlation coefficient` series between `label` and `prediction score`.
-            In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. Please refer to `Data Featrue <data.html#feature>`_ for more details.
+            In the above example, the `label` is formulated as `Ref($close, -2)/Ref($close, -1)-1`. Please refer to `Data Feature <data.html#feature>`_ for more details.
                 
         - `rank_ic`
             The `Spearman's rank correlation coefficient` series between `label` and `prediction score`.

docs/component/strategy.rst

@@ -8,11 +8,13 @@ Portfolio Strategy: Portfolio Management
 Introduction
 ===================
 
-``Portfolio Strategy`` is designed to adopt different portfolio strategies, which means that users can adopt different algorithms to generate investment portfolios based on the prediction scores of the ``Forecast Model``. Users can use the ``Portfolio Strategy`` in an automatic workflow by ``Workflow`` module, please refer to `Workflow: Workflow Management <workflow.html>`_.  
+``Portfolio Strategy`` is designed to adopt different portfolio strategies, which means that users can adopt different algorithms to generate investment portfolios based on the prediction scores of the ``Forecast Model``. Users can use the ``Portfolio Strategy`` in an automatic workflow by ``Workflow`` module, please refer to `Workflow: Workflow Management <workflow.html>`_.
 
 Because the components in ``Qlib`` are designed in a loosely-coupled way, ``Portfolio Strategy`` can be used as an independent module also.
 
-``Qlib`` provides several implemented portfolio strategies. Also, ``Qlib`` supports custom strategy, users can customize strategies according to their own needs.
+``Qlib`` provides several implemented portfolio strategies. Also, ``Qlib`` supports custom strategy, users can customize strategies according to their own requirements.
+
+After users specifying the models(forecasting signals) and strategies, running backtest will help users to check the performance of a custom model(forecasting signals)/strategy.
 
 Base Class & Interface
 ======================
@@ -20,20 +22,19 @@ Base Class & Interface
 BaseStrategy
 ------------------
 
-Qlib provides a base class ``qlib.contrib.strategy.BaseStrategy``. All strategy classes need to inherit the base class and implement its interface.
+Qlib provides a base class ``qlib.strategy.base.BaseStrategy``. All strategy classes need to inherit the base class and implement its interface.
 
-- `get_risk_degree`
-    Return the proportion of your total value you will use in investment. Dynamically risk_degree will result in Market timing.
-
-- `generate_order_list`
-    Return the order list. 
+- `generate_trade_decision`
+    generate_trade_decision is a key interface that generates trade decisions in each trading bar.
+    The frequency to call this method depends on the executor frequency("time_per_step"="day" by default). But the trading frequency can be decided by users' implementation.
+    For example, if the user wants to trading in weekly while the `time_per_step` is "day" in executor, user can return non-empty TradeDecision weekly(otherwise return empty like `this <https://github.com/microsoft/qlib/blob/main/qlib/contrib/strategy/signal_strategy.py#L132>`_ ).
 
 Users can inherit `BaseStrategy` to customize their strategy class.
 
 WeightStrategyBase
 --------------------
 
-Qlib also provides a class ``qlib.contrib.strategy.WeightStrategyBase`` that is a subclass of `BaseStrategy`. 
+Qlib also provides a class ``qlib.contrib.strategy.WeightStrategyBase`` that is a subclass of `BaseStrategy`.
 
 `WeightStrategyBase` only focuses on the target positions, and automatically generates an order list based on positions. It provides the `generate_target_weight_position` interface.
 
@@ -65,58 +66,246 @@ TopkDropoutStrategy
 - Adopt the ``Topk-Drop`` algorithm to calculate the target amount of each stock
 
     .. note::
-        ``Topk-Drop`` algorithm：
+        There are two parameters for the ``Topk-Drop`` algorithm：
 
         - `Topk`: The number of stocks held
         - `Drop`: The number of stocks sold on each trading day
+
+        In general, the number of stocks currently held is `Topk`, with the exception of being zero at the beginning period of trading.
+        For each trading day, let $d$ be the number of the instruments currently held and with a rank $\gt K$ when ranked by the prediction scores from high to low.
+        Then `d` number of stocks currently held with the worst `prediction score` will be sold, and the same number of unheld stocks with the best `prediction score` will be bought.
         
-        Currently, the number of held stocks is `Topk`.
-        On each trading day, the `Drop` number of held stocks with the worst `prediction score` will be sold, and the same number of unheld stocks with the best `prediction score` will be bought.
-        
+        In general, $d=$`Drop`, especially when the pool of the candidate instruments is large, $K$ is large, and `Drop` is small.
+         
+        In most cases, ``TopkDrop`` algorithm sells and buys `Drop` stocks every trading day, which yields a turnover rate of 2$\times$`Drop`/$K$.
+         
+        The following images illustrate a typical scenario.
         .. image:: ../_static/img/topk_drop.png
             :alt: Topk-Drop
 
-        ``TopkDrop`` algorithm sells `Drop` stocks every trading day, which guarantees a fixed turnover rate.
-        
+       
+
 - Generate the order list from the target amount
 
+EnhancedIndexingStrategy
+------------------------
+`EnhancedIndexingStrategy` Enhanced indexing combines the arts of active management and passive management,
+with the aim of outperforming a benchmark index (e.g., S&P 500) in terms of portfolio return while controlling
+the risk exposure (a.k.a. tracking error).
+
+For more information, please refer to `qlib.contrib.strategy.signal_strategy.EnhancedIndexingStrategy`
+and `qlib.contrib.strategy.optimizer.enhanced_indexing.EnhancedIndexingOptimizer`.
+
+
 Usage & Example
 ====================
-``Portfolio Strategy`` can be specified in the ``Intraday Trading(Backtest)``, the example is as follows.
+
+First, user can create a model to get trading signals(the variable name is ``pred_score`` in following cases).
+
+Prediction Score
+-----------------
+
+The `prediction score` is a pandas DataFrame. Its index is <datetime(pd.Timestamp), instrument(str)> and it must
+contains a `score` column.
+
+A prediction sample is shown as follows.
 
 .. code-block:: python
 
-    from qlib.contrib.strategy.strategy import TopkDropoutStrategy
-    from qlib.contrib.evaluate import backtest
-    STRATEGY_CONFIG = {
-        "topk": 50,
-        "n_drop": 5,
-    }
-    BACKTEST_CONFIG = {
-        "verbose": False,
-        "limit_threshold": 0.095,
-        "account": 100000000,
-        "benchmark": BENCHMARK,
-        "deal_price": "close",
-        "open_cost": 0.0005,
-        "close_cost": 0.0015,
-        "min_cost": 5,
-        
-    }
-    # use default strategy
-    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
+      datetime instrument     score
+    2019-01-04   SH600000 -0.505488
+    2019-01-04   SZ002531 -0.320391
+    2019-01-04   SZ000999  0.583808
+    2019-01-04   SZ300569  0.819628
+    2019-01-04   SZ001696 -0.137140
+                 ...            ...
+    2019-04-30   SZ000996 -1.027618
+    2019-04-30   SH603127  0.225677
+    2019-04-30   SH603126  0.462443
+    2019-04-30   SH603133 -0.302460
+    2019-04-30   SZ300760 -0.126383
 
-    # pred_score is the `prediction score` output by Model
-    report_normal, positions_normal = backtest(
-        pred_score, strategy=strategy, **BACKTEST_CONFIG
-    )
+``Forecast Model`` module can make predictions, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
 
-Also, the above example has been given in ``examples/train_backtest_analyze.ipynb``.
+Normally, the prediction score is the output of the models. But some models are learned from a label with a different scale. So the scale of the prediction score may be different from your expectation(e.g. the return of instruments).
 
-To know more about the `prediction score` `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
+Qlib didn't add a step to scale the prediction score to a unified scale due to the following reasons.
+- Because not every trading strategy cares about the scale(e.g. TopkDropoutStrategy only cares about the order).  So the strategy is responsible for rescaling the prediction score(e.g. some portfolio-optimization-based strategies may require a meaningful scale).
+- The model has the flexibility to define the target, loss, and data processing. So we don't think there is a silver bullet to rescale it back directly barely based on the model's outputs. If you want to scale it back to some meaningful values(e.g. stock returns.), an intuitive solution is to create a regression model for the model's recent outputs and your recent target values.
+
+Running backtest
+-----------------
+
+- In most cases, users could backtest their portfolio management strategy  with ``backtest_daily``.
+
+    .. code-block:: python
+
+        from pprint import pprint
+
+        import qlib
+        import pandas as pd
+        from qlib.utils.time import Freq
+        from qlib.utils import flatten_dict
+        from qlib.contrib.evaluate import backtest_daily
+        from qlib.contrib.evaluate import risk_analysis
+        from qlib.contrib.strategy import TopkDropoutStrategy
+
+        # init qlib
+        qlib.init(provider_uri=<qlib data dir>)
+
+        CSI300_BENCH = "SH000300"
+        STRATEGY_CONFIG = {
+            "topk": 50,
+            "n_drop": 5,
+            # pred_score, pd.Series
+            "signal": pred_score,
+        }
+
+
+        strategy_obj = TopkDropoutStrategy(**STRATEGY_CONFIG)
+        report_normal, positions_normal = backtest_daily(
+            start_time="2017-01-01", end_time="2020-08-01", strategy=strategy_obj
+        )
+        analysis = dict()
+        # default frequency will be daily (i.e. "day")
+        analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+        analysis["excess_return_with_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"] - report_normal["cost"])
+
+        analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+        pprint(analysis_df)
+
+
+
+- If users would like to control their strategies in a more detailed(e.g. users have a more advanced version of executor), user could follow this example.
+
+    .. code-block:: python
+
+        from pprint import pprint
+
+        import qlib
+        import pandas as pd
+        from qlib.utils.time import Freq
+        from qlib.utils import flatten_dict
+        from qlib.backtest import backtest, executor
+        from qlib.contrib.evaluate import risk_analysis
+        from qlib.contrib.strategy import TopkDropoutStrategy
+
+        # init qlib
+        qlib.init(provider_uri=<qlib data dir>)
+
+        CSI300_BENCH = "SH000300"
+        # Benchmark is for calculating the excess return of your strategy.
+        # Its data format will be like **ONE normal instrument**. 
+        # For example, you can query its data with the code below
+        # `D.features(["SH000300"], ["$close"], start_time='2010-01-01', end_time='2017-12-31', freq='day')`
+        # It is different from the argument `market`, which indicates a universe of stocks (e.g. **A SET** of stocks like csi300)
+        # For example, you can query all data from a stock market with the code below.
+        # ` D.features(D.instruments(market='csi300'), ["$close"], start_time='2010-01-01', end_time='2017-12-31', freq='day')`
+
+        FREQ = "day"
+        STRATEGY_CONFIG = {
+            "topk": 50,
+            "n_drop": 5,
+            # pred_score, pd.Series
+            "signal": pred_score,
+        }
+
+        EXECUTOR_CONFIG = {
+            "time_per_step": "day",
+            "generate_portfolio_metrics": True,
+        }
+
+        backtest_config = {
+            "start_time": "2017-01-01",
+            "end_time": "2020-08-01",
+            "account": 100000000,
+            "benchmark": CSI300_BENCH,
+            "exchange_kwargs": {
+                "freq": FREQ,
+                "limit_threshold": 0.095,
+                "deal_price": "close",
+                "open_cost": 0.0005,
+                "close_cost": 0.0015,
+                "min_cost": 5,
+            },
+        }
+
+        # strategy object
+        strategy_obj = TopkDropoutStrategy(**STRATEGY_CONFIG)
+        # executor object
+        executor_obj = executor.SimulatorExecutor(**EXECUTOR_CONFIG)
+        # backtest
+        portfolio_metric_dict, indicator_dict = backtest(executor=executor_obj, strategy=strategy_obj, **backtest_config)
+        analysis_freq = "{0}{1}".format(*Freq.parse(FREQ))
+        # backtest info
+        report_normal, positions_normal = portfolio_metric_dict.get(analysis_freq)
+
+        # analysis
+        analysis = dict()
+        analysis["excess_return_without_cost"] = risk_analysis(
+            report_normal["return"] - report_normal["bench"], freq=analysis_freq
+        )
+        analysis["excess_return_with_cost"] = risk_analysis(
+            report_normal["return"] - report_normal["bench"] - report_normal["cost"], freq=analysis_freq
+        )
+
+        analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+        # log metrics
+        analysis_dict = flatten_dict(analysis_df["risk"].unstack().T.to_dict())
+        # print out results
+        pprint(f"The following are analysis results of benchmark return({analysis_freq}).")
+        pprint(risk_analysis(report_normal["bench"], freq=analysis_freq))
+        pprint(f"The following are analysis results of the excess return without cost({analysis_freq}).")
+        pprint(analysis["excess_return_without_cost"])
+        pprint(f"The following are analysis results of the excess return with cost({analysis_freq}).")
+        pprint(analysis["excess_return_with_cost"])
+
+
+Result
+------------------
+
+The backtest results are in the following form:
+
+.. code-block:: python
+
+                                                      risk
+    excess_return_without_cost mean               0.000605
+                               std                0.005481
+                               annualized_return  0.152373
+                               information_ratio  1.751319
+                               max_drawdown      -0.059055
+    excess_return_with_cost    mean               0.000410
+                               std                0.005478
+                               annualized_return  0.103265
+                               information_ratio  1.187411
+                               max_drawdown      -0.075024
+
+
+- `excess_return_without_cost`
+    - `mean`
+        Mean value of the `CAR` (cumulative abnormal return) without cost
+    - `std`
+        The `Standard Deviation` of `CAR` (cumulative abnormal return) without cost.
+    - `annualized_return`
+        The `Annualized Rate` of `CAR` (cumulative abnormal return) without cost.
+    - `information_ratio`
+        The `Information Ratio` without cost. please refer to `Information Ratio – IR <https://www.investopedia.com/terms/i/informationratio.asp>`_.
+    - `max_drawdown`
+        The `Maximum Drawdown` of `CAR` (cumulative abnormal return) without cost, please refer to `Maximum Drawdown (MDD) <https://www.investopedia.com/terms/m/maximum-drawdown-mdd.asp>`_.
+
+- `excess_return_with_cost`
+    - `mean`
+        Mean value of the `CAR` (cumulative abnormal return) series with cost
+    - `std`
+        The `Standard Deviation` of `CAR` (cumulative abnormal return) series with cost.
+    - `annualized_return`
+        The `Annualized Rate` of `CAR` (cumulative abnormal return) with cost.
+    - `information_ratio`
+        The `Information Ratio` with cost. please refer to `Information Ratio – IR <https://www.investopedia.com/terms/i/informationratio.asp>`_.
+    - `max_drawdown`
+        The `Maximum Drawdown` of `CAR` (cumulative abnormal return) with cost, please refer to `Maximum Drawdown (MDD) <https://www.investopedia.com/terms/m/maximum-drawdown-mdd.asp>`_.
 
-To know more about ``Intraday Trading``, please refer to `Intraday Trading: Model&Strategy Testing <backtest.html>`_.
 
 Reference
 ===================
-To know more about ``Portfolio Strategy``, please refer to `Strategy API <../reference/api.html#module-qlib.contrib.strategy.strategy>`_.
+To know more about the `prediction score` `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.

docs/component/workflow.rst

@@ -53,8 +53,10 @@ Below is a typical config file of ``qrun``.
             kwargs:
                 topk: 50
                 n_drop: 5
+                signal:
+                    - <MODEL> 
+                    - <DATASET>
         backtest:
-            verbose: False
             limit_threshold: 0.095
             account: 100000000
             benchmark: *benchmark
@@ -90,12 +92,12 @@ Below is a typical config file of ``qrun``.
                     test: [2017-01-01, 2020-08-01]
         record: 
             - class: SignalRecord
-            module_path: qlib.workflow.record_temp
-            kwargs: {}
+              module_path: qlib.workflow.record_temp
+              kwargs: {}
             - class: PortAnaRecord
-            module_path: qlib.workflow.record_temp
-            kwargs: 
-                config: *port_analysis_config
+              module_path: qlib.workflow.record_temp
+              kwargs: 
+                  config: *port_analysis_config
 
 After saving the config into `configuration.yaml`, users could start the workflow and test their ideas with a single command below.
 
@@ -122,9 +124,47 @@ Configuration File
 ===================
 
 Let's get into details of ``qrun`` in this section.
-
 Before using ``qrun``, users need to prepare a configuration file. The following content shows how to prepare each part of the configuration file.
 
+The design logic of the configuration file is very simple. It predefines fixed workflows and provide this yaml interface to users to define how to initialize each component. 
+It follow the design of `init_instance_by_config <https://github.com/microsoft/qlib/blob/2aee9e0145decc3e71def70909639b5e5a6f4b58/qlib/utils/__init__.py#L264>`_ .  It defines the initialization of each component of Qlib, which typically include the class and the initialization arguments.
+
+For example, the following yaml and code are equivalent.
+
+.. code-block:: YAML
+
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+
+
+.. code-block:: python
+
+        from qlib.contrib.model.gbdt import LGBModel
+        kwargs = {
+            "loss": "mse" ,
+            "colsample_bytree": 0.8879,
+            "learning_rate": 0.0421,
+            "subsample": 0.8789,
+            "lambda_l1": 205.6999,
+            "lambda_l2": 580.9768,
+            "max_depth": 8,
+            "num_leaves": 210,
+            "num_threads": 20,
+        }
+        LGBModel(kwargs)
+
+
 Qlib Init Section
 --------------------
 
@@ -142,7 +182,7 @@ The meaning of each field is as follows:
 
 - `region`
     - If `region` == "us", ``Qlib`` will be initialized in US-stock mode. 
-    - If `region` == "cn", ``Qlib`` will be initialized in china-stock mode.
+    - If `region` == "cn", ``Qlib`` will be initialized in China-stock mode.
 
     .. note:: 
         
@@ -193,7 +233,7 @@ The meaning of each field is as follows:
 Dataset Section
 ~~~~~~~~~~~~~~~~~~~~
 
-The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Model <../component/data.html#dataset>`_.
+The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Data <../component/data.html#dataset>`_.
 
 The keywords arguments configuration of the ``DataHandler`` is as follows:
 
@@ -208,7 +248,7 @@ The keywords arguments configuration of the ``DataHandler`` is as follows:
 
 Users can refer to the document of `DataHandler <../component/data.html#datahandler>`_ for more information about the meaning of each field in the configuration.
 
-Here is the configuration for the ``Dataset`` module which will take care of data preprossing and slicing during the training and testing phase.
+Here is the configuration for the ``Dataset`` module which will take care of data preprocessing and slicing during the training and testing phase.
 
 .. code-block:: YAML
 
@@ -241,8 +281,10 @@ The following script is the configuration of `backtest` and the `strategy` used
             kwargs:
                 topk: 50
                 n_drop: 5
+                signal:
+                    - <MODEL> 
+                    - <DATASET>
         backtest:
-            verbose: False
             limit_threshold: 0.095
             account: 100000000
             benchmark: *benchmark

docs/conf.py

@@ -54,9 +54,9 @@ master_doc = "index"
 
 
 # General information about the project.
-project = u"QLib"
-copyright = u"Microsoft"
-author = u"Microsoft"
+project = "QLib"
+copyright = "Microsoft"
+author = "Microsoft"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -174,7 +174,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, "qlib.tex", u"QLib Documentation", u"Microsoft", "manual"),
+    (master_doc, "qlib.tex", "QLib Documentation", "Microsoft", "manual"),
 ]
 
 
@@ -182,7 +182,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [(master_doc, "qlib", u"QLib Documentation", [author], 1)]
+man_pages = [(master_doc, "qlib", "QLib Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output -------------------------------------------
@@ -194,7 +194,7 @@ texinfo_documents = [
     (
         master_doc,
         "QLib",
-        u"QLib Documentation",
+        "QLib Documentation",
         author,
         "QLib",
         "One line description of project.",

docs/developer/code_standard.rst

@@ -0,0 +1,48 @@
+.. _code_standard:
+
+=================================
+Code Standard
+=================================
+
+Docstring
+=================================
+Please use the `Numpydoc Style <https://stackoverflow.com/a/24385103>`_.
+
+Continuous Integration
+=================================
+Continuous Integration (CI) tools help you stick to the quality standards by running tests every time you push a new commit and reporting the results to a pull request. 
+
+When you submit a PR request, you can check whether your code passes the CI tests in the "check" section at the bottom of the web page.
+
+1. Qlib will check the code format with black. The PR will raise error if your code does not align to the standard of Qlib(e.g. a common error is the mixed use of space and tab).
+ You can fix the bug by inputing the following code in the command line.
+
+.. code-block:: bash
+
+    pip install black
+    python -m black . -l 120
+
+
+2. Qlib will check your code style pylint. The checking command is implemented in [github action workflow](https://github.com/microsoft/qlib/blob/0e8b94a552f1c457cfa6cd2c1bb3b87ebb3fb279/.github/workflows/test.yml#L66). 
+   Sometime pylint's restrictions are not that reasonable. You can ignore specific errors like this
+
+.. code-block:: python
+
+    return -ICLoss()(pred, target, index)  # pylint: disable=E1130
+
+
+3. Qlib will check your code style flake8. The checking command is implemented in [github action workflow](https://github.com/microsoft/qlib/blob/0e8b94a552f1c457cfa6cd2c1bb3b87ebb3fb279/.github/workflows/test.yml#L73).
+ You can fix the bug by inputing the following code in the command line.
+
+.. code-block:: bash
+
+    flake8 --ignore E501,F541,E402,F401,W503,E741,E266,E203,E302,E731,E262,F523,F821,F811,F841,E713,E265,W291,E712,E722,W293 qlib
+
+
+4. Qlib has integrated pre-commit, which will make it easier for developers to format their code.
+ Just run the following two commands, and the code will be automatically formatted using black and flake8 when the git commit command is executed.
+
+.. code-block:: bash
+
+    pip install -e .[dev]
+    pre-commit install

docs/hidden/tuner.rst

@@ -31,7 +31,7 @@ Let's see an example,
 
 First make sure you have the latest version of `qlib` installed.
 
-Then, you need to privide a configuration to setup the experiment.
+Then, you need to provide a configuration to setup the experiment.
 We write a simple configuration example as following,
 
 .. code-block:: YAML
@@ -93,7 +93,6 @@ We write a simple configuration example as following,
                   fend_time: 2018-12-11
     backtest:
         normal_backtest_args:
-            verbose: False
             limit_threshold: 0.095
             account: 500000
             benchmark: SH000905
@@ -218,13 +217,13 @@ The tuner pipeline contains different tuners, and the `tuner` program will proce
 Each part represents a tuner, and its modules which are to be tuned. Space in each part is the hyper-parameters' space of a certain module, you need to create your searching space and modify it in `/qlib/contrib/tuner/space.py`. We use `hyperopt` package to help us to construct the space, you can see the detail of how to use it in https://github.com/hyperopt/hyperopt/wiki/FMin .
 
 - model
-    You need to provide the `class` and the `space` of the model. If the model is user's own implementation, you need to privide the `module_path`. 
+    You need to provide the `class` and the `space` of the model. If the model is user's own implementation, you need to provide the `module_path`.
 
 - trainer
-    You need to proveide the `class` of the trainer. If the trainer is user's own implementation, you need to privide the `module_path`. 
+    You need to provide the `class` of the trainer. If the trainer is user's own implementation, you need to provide the `module_path`.
 
 - strategy
-    You need to provide the `class` and the `space` of the strategy. If the strategy is user's own implementation, you need to privide the `module_path`. 
+    You need to provide the `class` and the `space` of the strategy. If the strategy is user's own implementation, you need to provide the `module_path`.
 
 - data_label
     The label of the data, you can search which kinds of labels will lead to a better result. This part is optional, and you only need to provide `space`.
@@ -274,7 +273,7 @@ You need to use the same dataset to evaluate your different `estimator` experime
 About the data and backtest
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-`data` and `backtest` are all same in the whole `tuner` experiment. Different `estimator` experiments must use the same data and backtest method. So, these two parts of config are same with that in `estimator` configuration. You can see the precise defination of these parts in `estimator` introduction. We only provide an example here.
+`data` and `backtest` are all same in the whole `tuner` experiment. Different `estimator` experiments must use the same data and backtest method. So, these two parts of config are same with that in `estimator` configuration. You can see the precise definition of these parts in `estimator` introduction. We only provide an example here.
 
 .. code-block:: YAML
 
@@ -306,7 +305,6 @@ About the data and backtest
                   fend_time: 2018-12-11
     backtest:
         normal_backtest_args:
-            verbose: False
             limit_threshold: 0.095
             account: 500000
             benchmark: SH000905

docs/index.rst

@@ -36,12 +36,14 @@ Document Structure
    :caption: COMPONENTS:
 
    Workflow: Workflow Management <component/workflow.rst>
-   Data Layer: Data Framework&Usage <component/data.rst>
+   Data Layer: Data Framework & Usage <component/data.rst>
    Forecast Model: Model Training & Prediction <component/model.rst>
-   Strategy: Portfolio Management <component/strategy.rst>
-   Intraday Trading: Model&Strategy Testing <component/backtest.rst>
+   Portfolio Management and Backtest <component/strategy.rst>
+   Nested Decision Execution: High-Frequency Trading <component/highfreq.rst>
+   Meta Controller: Meta-Task & Meta-Dataset & Meta-Model <component/meta.rst>
    Qlib Recorder: Experiment Management <component/recorder.rst>
    Analysis: Evaluation & Results Analysis <component/report.rst>
+   Online Serving: Online Management & Strategy & Tool <component/online.rst>
 
 .. toctree::
    :maxdepth: 3
@@ -49,6 +51,9 @@ Document Structure
    
    Building Formulaic Alphas <advanced/alpha.rst>
    Online & Offline mode <advanced/server.rst>
+   Serialization <advanced/serial.rst>
+   Task Management <advanced/task_management.rst>
+   Point-In-Time database <advanced/PIT.rst>
 
 .. toctree::
    :maxdepth: 3

docs/introduction/introduction.rst

@@ -15,7 +15,7 @@ With ``Qlib``, users can easily try their ideas to create better Quant investmen
 Framework
 ===================
    
-.. image:: ../_static/img/framework.png
+.. image:: ../_static/img/framework.svg
     :align: center
 
 
@@ -34,9 +34,14 @@ Name                      Description
 
 `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 `Portfolio Generator` will generate the target
-                          portfolio and produce orders to be executed by `Order Executor`.
+                          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

docs/introduction/quick.rst

@@ -31,7 +31,7 @@ Users can easily intsall ``Qlib`` according to the following steps:
         git clone https://github.com/microsoft/qlib.git && cd qlib
         python setup.py install
 
-To kown more about `installation`, please refer to `Qlib Installation <../start/installation.html>`_.
+To known more about `installation`, please refer to `Qlib Installation <../start/installation.html>`_.
 
 Prepare Data
 ==============
@@ -44,7 +44,7 @@ Load and prepare data by running the following code:
 
 This dataset is created by public data collected by crawler scripts in ``scripts/data_collector/``, which have been released in the same repository. Users could create the same dataset with it.
 
-To kown more about `prepare data`, please refer to `Data Preparation <../component/data.html#data-preparation>`_.
+To known more about `prepare data`, please refer to `Data Preparation <../component/data.html#data-preparation>`_.
 
 Auto Quant Research Workflow
 ====================================

docs/reference/api.rst

@@ -53,6 +53,34 @@ Cache
 .. autoclass:: qlib.data.cache.DiskDatasetCache
     :members:
 
+
+Storage
+-------------
+.. autoclass:: qlib.data.storage.storage.BaseStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.storage.CalendarStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.storage.InstrumentStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.storage.FeatureStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.file_storage.FileStorageMixin
+    :members:
+
+.. autoclass:: qlib.data.storage.file_storage.FileCalendarStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.file_storage.FileInstrumentStorage
+    :members:
+
+.. autoclass:: qlib.data.storage.file_storage.FileFeatureStorage
+    :members:
+
+
 Dataset
 ---------------
 
@@ -152,4 +180,82 @@ Recorder
 Record Template
 --------------------
 .. automodule:: qlib.workflow.record_temp
-    :members:
+    :members:
+
+Task Management
+====================
+
+
+TaskGen
+--------------------
+.. automodule:: qlib.workflow.task.gen
+    :members:
+
+TaskManager
+--------------------
+.. automodule:: qlib.workflow.task.manage
+    :members:
+
+Trainer
+--------------------
+.. automodule:: qlib.model.trainer
+    :members:
+
+Collector
+--------------------
+.. automodule:: qlib.workflow.task.collect
+    :members:
+
+Group
+--------------------
+.. automodule:: qlib.model.ens.group
+    :members:
+
+Ensemble
+--------------------
+.. automodule:: qlib.model.ens.ensemble
+    :members:
+
+Utils
+--------------------
+.. automodule:: qlib.workflow.task.utils
+    :members:
+
+
+Online Serving
+====================
+
+
+Online Manager
+--------------------
+.. automodule:: qlib.workflow.online.manager
+    :members:
+
+Online Strategy
+--------------------
+.. automodule:: qlib.workflow.online.strategy
+    :members:
+
+Online Tool
+--------------------
+.. automodule:: qlib.workflow.online.utils
+    :members:
+
+
+RecordUpdater
+--------------------
+.. automodule:: qlib.workflow.online.update
+    :members:
+
+
+Utils
+====================
+
+Serializable
+--------------------
+
+.. automodule:: qlib.utils.serial.Serializable
+    :members:
+
+
+    

docs/requirements.txt

@@ -3,3 +3,4 @@ cmake
 numpy
 scipy
 scikit-learn
+pandas

docs/start/getdata.rst

@@ -120,6 +120,32 @@ For more details about features, please refer `Feature API <../component/data.ht
 
 .. note:: When calling `D.features()` at the client, use parameter `disk_cache=0` to skip dataset cache, use `disk_cache=1` to generate and use dataset cache. In addition, when calling at the server, users can use `disk_cache=2` to update the dataset cache.
 
+
+When you are building complicated expressions, implementing all the expressions in a single string may not be easy.
+For example, it looks quite long and complicated:
+
+.. code-block:: python
+
+   >> from qlib.data import D
+   >> data = D.features(["sh600519"], ["(($high / $close) + ($open / $close)) * (($high / $close) + ($open / $close)) / ($high / $close) + ($open / $close)"], start_time="20200101")
+
+
+But using string is not the only way to implement the expression. You can also implement expression by code.
+Here is an exmaple which does the same thing as above examples.
+
+
+.. code-block:: python
+
+   >> from qlib.data.ops import *
+   >> f1 = Feature("high") / Feature("close")
+   >> f2 = Feature("open") / Feature("close")
+   >> f3 = f1 + f2
+   >> f4 = f3 * f3 / f3
+
+   >> data = D.features(["sh600519"], [f4], start_time="20200101")
+   >> data.head()
+
+
 API
 ====================
 To know more about how to use the Data, go to API Reference: `Data API <../reference/api.html#data>`_

docs/start/initialization.rst

@@ -27,7 +27,7 @@ Initialize Qlib before calling other APIs: run following code in python.
 
         import qlib
         # region in [REG_CN, REG_US]
-        from qlib.config import REG_CN
+        from qlib.constant import REG_CN
         provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
         qlib.init(provider_uri=provider_uri, region=REG_CN)
     
@@ -37,17 +37,19 @@ Initialize Qlib before calling other APIs: run following code in python.
 Parameters
 -------------------
 
-Besides `provider_uri` and `region`, `qlib.init` has other parameters. The following are several important parameters of `qlib.init`:
+Besides `provider_uri` and `region`, `qlib.init` has other parameters.
+The following are several important parameters of `qlib.init` (`Qlib` has a lot of config. Only part of parameters are limited here. More detailed setting can be found `here <https://github.com/microsoft/qlib/blob/main/qlib/config.py>`_):
 
 - `provider_uri`
     Type: str. The URI of the Qlib data. For example, it could be the location where the data loaded by ``get_data.py`` are stored.
 - `region`
-    Type: str, optional parameter(default: `qlib.config.REG_CN`).
-        Currently: ``qlib.config.REG_US`` ('us') and ``qlib.config.REG_CN`` ('cn') is supported. Different value of  `region` will result in different stock market mode.
-        - ``qlib.config.REG_US``: US stock market.
-        - ``qlib.config.REG_CN``: China stock market.
+    Type: str, optional parameter(default: `qlib.constant.REG_CN`).
+        Currently: ``qlib.constant.REG_US`` ('us') and ``qlib.constant.REG_CN`` ('cn') is supported. Different value of  `region` will result in different stock market mode.
+        - ``qlib.constant.REG_US``: US stock market.
+        - ``qlib.constant.REG_CN``: China stock market.
 
         Different modes will result in different trading limitations and costs.
+        The region is just `shortcuts for defining a batch of configurations <https://github.com/microsoft/qlib/blob/528f74af099bf6156e9480bcd2bb28e453231212/qlib/config.py#L249>`_, which include minimal trading order unit (``trade_unit``),  trading limitation (``limit_threshold``) , etc.  It is not a necessary part and users can set the key configurations manually if the existing region setting can't meet their requirements.
 - `redis_host`
     Type: str, optional parameter(default: "127.0.0.1"), host of `redis`
         The lock and cache mechanism relies on redis.
@@ -75,3 +77,21 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
                 "default_exp_name": "Experiment",
             }
         })
+- `mongo`
+    Type: dict, optional parameter, the setting of `MongoDB <https://www.mongodb.com/>`_ which will be used in some features such as `Task Management <../advanced/task_management.html>`_, with high performance and clustered processing. 
+    Users need to follow the steps in  `installation <https://www.mongodb.com/try/download/community>`_  to install MongoDB firstly and then access it via a URI.
+    Users can access mongodb with credential by setting "task_url"  to a string like `"mongodb://%s:%s@%s" % (user, pwd, host + ":" + port)`.
+
+    .. code-block:: Python
+
+        # For example, you can initialize qlib below
+        qlib.init(provider_uri=provider_uri, region=REG_CN, mongo={
+            "task_url": "mongodb://localhost:27017/",  # your mongo url
+            "task_db_name": "rolling_db", # the database name of Task Management
+        })
+
+- `logging_level`
+    The logging level for the system.
+
+- `kernels`
+    The number of processes used when calculating features in Qlib's expression engine. It is very helpful to set it to 1 when you are debuggin an expression calculating exception

docs/start/integration.rst

@@ -82,7 +82,7 @@ The Custom models need to inherit `qlib.model.base.Model <../reference/api.html#
             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, and when users one to use this method on their own models, they should inherit the ``ModelFT`` base class, which includes the interface of `finetune`.
+    - 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

examples/benchmarks/ADARNN/README.md

@@ -0,0 +1,4 @@
+# AdaRNN
+* Code: [https://github.com/jindongwang/transferlearning/tree/master/code/deep/adarnn](https://github.com/jindongwang/transferlearning/tree/master/code/deep/adarnn)
+* Paper: [AdaRNN: Adaptive Learning and Forecasting for Time Series](https://arxiv.org/pdf/2108.04443.pdf).
+

examples/benchmarks/ADARNN/requirements.txt

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

examples/benchmarks/ADARNN/workflow_config_adarnn_Alpha360.yaml

@@ -0,0 +1,88 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            model: <MODEL>
+            dataset: <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: ADARNN
+        module_path: qlib.contrib.model.pytorch_adarnn
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0.0
+            n_epochs: 200
+            lr: 1e-3
+            early_stop: 20
+            batch_size: 800
+            metric: loss
+            loss: mse
+            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/ADD/README.md

@@ -0,0 +1,3 @@
+# ADD
+* Paper: [ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting](https://arxiv.org/abs/2012.06289).
+

examples/benchmarks/ADD/requirements.txt

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

examples/benchmarks/ADD/workflow_config_add_Alpha360.yaml

@@ -0,0 +1,94 @@
+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:
+                - <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: ADD
+        module_path: qlib.contrib.model.pytorch_add
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0.1
+            dec_dropout: 0.0
+            n_epochs: 200
+            lr: 1e-3
+            early_stop: 20
+            batch_size: 5000
+            metric: ic
+            base_model: GRU
+            gamma: 0.1
+            gamma_clip: 0.2
+            optimizer: adam
+            mu: 0.2
+            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/ALSTM/README.md

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

examples/benchmarks/ALSTM/requirements.txt

@@ -1,4 +1,4 @@
-numpy==1.17.4
+numpy==1.21.0
 pandas==1.1.2
 scikit_learn==0.23.2
 torch==1.7.0

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml

@@ -34,19 +34,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: ALSTM
@@ -81,7 +86,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml

@@ -26,19 +26,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: ALSTM
@@ -71,7 +76,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -80,4 +87,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/CatBoost/requirements.txt

@@ -1,3 +1,3 @@
 pandas==1.1.2
-numpy==1.17.4
+numpy==1.21.0
 catboost==0.24.3

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158.yaml

@@ -12,19 +12,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: CatBoostModel
@@ -53,7 +58,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360.yaml

@@ -19,19 +19,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: CatBoostModel
@@ -60,7 +65,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 

examples/benchmarks/DoubleEnsemble/README.md

@@ -0,0 +1,4 @@
+# DoubleEnsemble
+* DoubleEnsemble is an ensemble framework leveraging learning trajectory based sample reweighting and shuffling based feature selection, to solve both the low signal-to-noise ratio and increasing number of features problems. They identify the key samples based on the training dynamics on each sample and elicit key features based on the ablation impact of each feature via shuffling. The model is applicable to a wide range of base models, capable of extracting complex patterns, while mitigating the overfitting and instability issues for financial market prediction.
+* This code used in Qlib is implemented by ourselves.
+* Paper: DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis [https://arxiv.org/pdf/2010.01265.pdf](https://arxiv.org/pdf/2010.01265.pdf).

examples/benchmarks/DoubleEnsemble/requirements.txt

@@ -0,0 +1,3 @@
+pandas==1.1.2
+numpy==1.21.0
+lightgbm==3.1.0

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml

@@ -0,0 +1,97 @@
+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:
+                - <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: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 28
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml

@@ -0,0 +1,104 @@
+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: []
+    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:
+                - <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: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 136
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/GATs/requirements.txt

@@ -1,4 +1,4 @@
 pandas==1.1.2
-numpy==1.17.4
+numpy==1.21.0
 scikit_learn==0.23.2
 torch==1.7.0

examples/benchmarks/GATs/workflow_config_gats_Alpha158.yaml

@@ -33,19 +33,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: GATs
@@ -61,7 +66,6 @@ task:
             metric: loss
             loss: mse
             base_model: LSTM
-            with_pretrain: True
             model_path: "benchmarks/LSTM/csi300_lstm_ts.pkl"
             GPU: 0
     dataset:
@@ -80,7 +84,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -89,4 +95,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/GATs/workflow_config_gats_Alpha360.yaml

@@ -26,19 +26,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: GATs
@@ -54,7 +59,6 @@ task:
             metric: loss
             loss: mse
             base_model: LSTM
-            with_pretrain: True
             model_path: "benchmarks/LSTM/model_lstm_csi300.pkl"
             GPU: 0
     dataset:
@@ -72,7 +76,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -81,4 +87,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/GRU/README.md

@@ -0,0 +1,2 @@
+# Gated Recurrent Unit (GRU)
+* Paper: [Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation](https://aclanthology.org/D14-1179.pdf).

examples/benchmarks/GRU/requirements.txt

@@ -1,4 +1,4 @@
-numpy==1.17.4
+numpy==1.21.0
 pandas==1.1.2
 scikit_learn==0.23.2
 torch==1.7.0

examples/benchmarks/GRU/workflow_config_gru_Alpha158.yaml

@@ -34,19 +34,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: GRU
@@ -80,7 +85,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 

examples/benchmarks/GRU/workflow_config_gru_Alpha360.yaml

@@ -26,19 +26,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: GRU
@@ -70,7 +75,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -79,4 +86,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/HIST/README.md

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

examples/benchmarks/HIST/requirements.txt

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

examples/benchmarks/HIST/workflow_config_hist_Alpha360.yaml

@@ -0,0 +1,92 @@
+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:
+                - <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: HIST
+        module_path: qlib.contrib.model.pytorch_hist
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0
+            n_epochs: 200
+            lr: 1e-4
+            early_stop: 20
+            metric: ic
+            loss: mse
+            base_model: LSTM
+            model_path: "benchmarks/LSTM/model_lstm_csi300.pkl"
+            stock2concept: "benchmarks/HIST/qlib_csi300_stock2concept.npy"
+            stock_index: "benchmarks/HIST/qlib_csi300_stock_index.npy"
+            GPU: 0
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/IGMTF/README.md

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

examples/benchmarks/IGMTF/requirements.txt

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

examples/benchmarks/IGMTF/workflow_config_igmtf_Alpha360.yaml

@@ -0,0 +1,89 @@
+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:
+            model: <MODEL>
+            dataset: <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: IGMTF
+        module_path: qlib.contrib.model.pytorch_igmtf
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0
+            n_epochs: 200
+            lr: 1e-4
+            early_stop: 20
+            metric: ic
+            loss: mse
+            base_model: LSTM
+            model_path: "benchmarks/LSTM/model_lstm_csi300.pkl"
+            GPU: 0
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/LSTM/README.md

@@ -0,0 +1,2 @@
+# Long Short-Term Memory (LSTM)
+* Paper: [Long Short-Term Memory](https://direct.mit.edu/neco/article-abstract/9/8/1735/6109/Long-Short-Term-Memory?redirectedFrom=fulltext).

examples/benchmarks/LSTM/requirements.txt

@@ -1,4 +1,4 @@
-numpy==1.17.4
+numpy==1.21.0
 pandas==1.1.2
 scikit_learn==0.23.2
 torch==1.7.0

examples/benchmarks/LSTM/workflow_config_lstm_Alpha158.yaml

@@ -29,24 +29,29 @@ data_handler_config: &data_handler_config
         - class: CSRankNorm
           kwargs:
               fields_group: label
-    label: ["Ref($close, -2) / Ref($close, -1) - 1"] 
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
 
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: LSTM
@@ -80,7 +85,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 

examples/benchmarks/LSTM/workflow_config_lstm_Alpha360.yaml

@@ -26,19 +26,24 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: LSTM
@@ -70,7 +75,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -79,4 +86,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/LightGBM/features_resample_N.py

@@ -0,0 +1,18 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+import pandas as pd
+
+from qlib.data.inst_processor import InstProcessor
+from qlib.utils.resam import resam_calendar
+
+
+class ResampleNProcessor(InstProcessor):
+    def __init__(self, target_frq: str, **kwargs):
+        self.target_frq = target_frq
+
+    def __call__(self, df: pd.DataFrame, *args, **kwargs):
+        df.index = pd.to_datetime(df.index)
+        res_index = resam_calendar(df.index, "1min", self.target_frq)
+        df = df.resample(self.target_frq).last().reindex(res_index)
+        return df

examples/benchmarks/LightGBM/features_sample.py

@@ -0,0 +1,16 @@
+import datetime
+import pandas as pd
+
+from qlib.data.inst_processor import InstProcessor
+
+
+class Resample1minProcessor(InstProcessor):
+    def __init__(self, hour: int, minute: int, **kwargs):
+        self.hour = hour
+        self.minute = minute
+
+    def __call__(self, df: pd.DataFrame, *args, **kwargs):
+        df.index = pd.to_datetime(df.index)
+        df = df.loc[df.index.time == datetime.time(self.hour, self.minute)]
+        df.index = df.index.normalize()
+        return df

examples/benchmarks/LightGBM/multi_freq_handler.py

@@ -0,0 +1,135 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+import pandas as pd
+
+from qlib.data.dataset.loader import QlibDataLoader
+from qlib.contrib.data.handler import DataHandlerLP, _DEFAULT_LEARN_PROCESSORS, check_transform_proc
+
+
+class Avg15minLoader(QlibDataLoader):
+    def load(self, instruments=None, start_time=None, end_time=None) -> pd.DataFrame:
+        df = super(Avg15minLoader, self).load(instruments, start_time, end_time)
+        if self.is_group:
+            # feature_day(day freq) and feature_15min(1min freq, Average every 15 minutes) renamed feature
+            df.columns = df.columns.map(lambda x: ("feature", x[1]) if x[0].startswith("feature") else x)
+        return df
+
+
+class Avg15minHandler(DataHandlerLP):
+    def __init__(
+        self,
+        instruments="csi500",
+        start_time=None,
+        end_time=None,
+        freq="day",
+        infer_processors=[],
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
+        fit_start_time=None,
+        fit_end_time=None,
+        process_type=DataHandlerLP.PTYPE_A,
+        filter_pipe=None,
+        inst_processor=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
+        )
+        super().__init__(
+            instruments=instruments,
+            start_time=start_time,
+            end_time=end_time,
+            data_loader=data_loader,
+            infer_processors=infer_processors,
+            learn_processors=learn_processors,
+            process_type=process_type,
+        )
+
+    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
+        #       freq == day:
+        #           close0, open0, low0, high0, volume0, vwap0
+        #       freq == 1min:
+        #           close1, ..., close16, ..., vwap1, ..., vwap16
+        #   df.index.name == ["datetime", "instrument"]: pd.MultiIndex
+        # Example:
+        #                          feature                        ...                  label
+        #                           close0      open0       low0  ... vwap1 vwap16    LABEL0
+        # datetime   instrument                                   ...
+        # 2020-10-09 SH600000    11.794546  11.819587  11.769505  ...   NaN    NaN -0.005214
+        # 2020-10-15 SH600000    12.044961  11.944795  11.932274  ...   NaN    NaN -0.007202
+        # ...                          ...        ...        ...  ...   ...    ...       ...
+        # 2021-05-28 SZ300676     6.369684   6.495406   6.306568  ...   NaN    NaN -0.001321
+        # 2021-05-31 SZ300676     6.601626   6.465643   6.465130  ...   NaN    NaN -0.023428
+
+        # features day: len(columns) == 6, freq = day
+        # $close is the closing price of the current trading day:
+        #   if the user needs to get the `close` before the last T days, use Ref($close, T-1), for example:
+        #                                    $close  Ref($close, 1)  Ref($close, 2)  Ref($close, 3)  Ref($close, 4)
+        #         instrument datetime
+        #         SH600519   2021-06-01  244.271530
+        #                    2021-06-02  242.205917      244.271530
+        #                    2021-06-03  242.229889      242.205917      244.271530
+        #                    2021-06-04  245.421524      242.229889      242.205917      244.271530
+        #                    2021-06-07  247.547089      245.421524      242.229889      242.205917      244.271530
+
+        # WARNING: Ref($close, N), if N == 0, Ref($close, N) ==> $close
+
+        fields = ["$close", "$open", "$low", "$high", "$volume", "$vwap"]
+        # names: close0, open0, ..., vwap0
+        names = list(map(lambda x: x.strip("$") + "0", fields))
+
+        config = {"feature_day": (fields, names)}
+
+        # features 15min: len(columns) == 6 * 16, freq = 1min
+        #   $close is the closing price of the current trading day:
+        #       if the user gets 'close' for the i-th 15min of the last T days, use `Ref(Mean($close, 15), (T-1) * 240 + i * 15)`, for example:
+        #                                    Ref(Mean($close, 15), 225)  Ref(Mean($close, 15), 465)  Ref(Mean($close, 15), 705)
+        #             instrument datetime
+        #             SH600519   2021-05-31                  241.769897                  243.077942                  244.712997
+        #                        2021-06-01                  244.271530                  241.769897                  243.077942
+        #                        2021-06-02                  242.205917                  244.271530                  241.769897
+
+        # WARNING: Ref(Mean($close, 15), N), if N == 0, Ref(Mean($close, 15), N) ==> Mean($close, 15)
+
+        # Results of the current script:
+        #   time:   09:00 --> 09:14,            ..., 14:45 --> 14:59
+        #   fields: Ref(Mean($close, 15), 225), ..., Mean($close, 15)
+        #   name:   close1,                     ..., close16
+        #
+
+        # Expression description: take close as an example
+        #   Mean($close, 15) ==> df["$close"].rolling(15, min_periods=1).mean()
+        #   Ref(Mean($close, 15), 15) ==> df["$close"].rolling(15, min_periods=1).mean().shift(15)
+
+        #   NOTE: The last data of each trading day, which is the average of the i-th 15 minutes
+
+        # Average:
+        #   Average of the i-th 15-minute period of each trading day: 1 <= i <= 250 // 16
+        #       Avg(15minutes): Ref(Mean($close, 15), 240 - i * 15)
+        #
+        #   Average of the first 15 minutes of each trading day; i = 1
+        #       Avg(09:00 --> 09:14), df.index.loc["09:14"]: Ref(Mean($close, 15), 240- 1 * 15) ==> Ref(Mean($close, 15), 225)
+        #   Average of the last 15 minutes of each trading day; i = 16
+        #       Avg(14:45 --> 14:59), df.index.loc["14:59"]: Ref(Mean($close, 15), 240 - 16 * 15) ==> Ref(Mean($close, 15), 0) ==> Mean($close, 15)
+
+        # 15min resample to day
+        #   df.resample("1d").last()
+        tmp_fields = []
+        tmp_names = []
+        for i, _f in enumerate(fields):
+            _fields = [f"Ref(Mean({_f}, 15), {j * 15})" for j in range(1, 240 // 15)]
+            _names = [f"{names[i][:-1]}{int(names[i][-1])+j}" for j in range(240 // 15 - 1, 0, -1)]
+            _fields.append(f"Mean({_f}, 15)")
+            _names.append(f"{names[i][:-1]}{int(names[i][-1])+240 // 15}")
+            tmp_fields += _fields
+            tmp_names += _names
+        config["feature_15min"] = (tmp_fields, tmp_names)
+        # label
+        config["label"] = (["Ref($close, -2)/Ref($close, -1) - 1"], ["LABEL0"])
+        return config

examples/benchmarks/LightGBM/requirements.txt

@@ -1,3 +1,3 @@
 pandas==1.1.2
-numpy==1.17.4
+numpy==1.21.0
 lightgbm==3.1.0

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

@@ -12,19 +12,23 @@ data_handler_config: &data_handler_config
 port_analysis_config: &port_analysis_config
     strategy:
         class: TopkDropoutStrategy
-        module_path: qlib.contrib.strategy.strategy
+        module_path: qlib.contrib.strategy
         kwargs:
+            model: <MODEL> 
+            dataset: <DATASET>
             topk: 50
             n_drop: 5
     backtest:
-        verbose: False
-        limit_threshold: 0.095
+        start_time: 2017-01-01
+        end_time: 2020-08-01
         account: 100000000
         benchmark: *benchmark
-        deal_price: close
-        open_cost: 0.0005
-        close_cost: 0.0015
-        min_cost: 5
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
 task:
     model:
         class: LGBModel
@@ -54,7 +58,9 @@ task:
     record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
@@ -63,4 +69,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_multi_freq.yaml

@@ -0,0 +1,86 @@
+qlib_init:
+    provider_uri:
+        day: "~/.qlib/qlib_data/cn_data"
+        1min: "~/.qlib/qlib_data/cn_data_1min"
+    region: cn
+    dataset_cache: null
+    maxtasksperchild: 1
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    # 1min closing time is 15:00:00
+    end_time: "2020-08-01 15:00:00"
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    freq:
+        label: day
+        feature: 1min
+    # with label as reference
+    inst_processor:
+        feature:
+            - class: Resample1minProcessor
+              module_path: features_sample.py
+              kwargs:
+                  hour: 14
+                  minute: 56
+
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy.strategy
+        kwargs:
+            topk: 50
+            n_drop: 5
+            signal:
+                - <MODEL> 
+                - <DATASET>
+    backtest:
+        verbose: False
+        limit_threshold: 0.095
+        account: 100000000
+        benchmark: *benchmark
+        deal_price: close
+        open_cost: 0.0005
+        close_cost: 0.0015
+        min_cost: 5
+task:
+    model:
+        class: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - 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