Bump to 0.8.2

* Remove arctic from Qlib core to Contrib

* fix empty df bug

.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/workflows/python-publish.yml

@@ -12,8 +12,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, macos-latest]
-        python-version: [3.6, 3.7, 3.8]
+        os: [windows-latest, macos-latest, macos-11]
+        # 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 +45,8 @@ 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/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
@@ -25,96 +26,41 @@ 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 numpy==1.19.5
-          $CONDA\\python.exe -m pip install pyqlib --ignore-installed ruamel.yaml numpy --user
-        else
-          sudo $CONDA/bin/python -m pip install numpy==1.19.5
-          sudo $CONDA/bin/python -m pip install pyqlib --ignore-installed ruamel.yaml numpy
-        fi
-      shell: bash
-    
-    - name: Install Lightgbm for MacOS
-      if: runner.os == 'macOS'
-      run: |
-        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
-        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
+        pip install numpy==1.19.5 ruamel.yaml
+        pip install pyqlib --ignore-installed 
 
     - 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 --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
 
     - 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 -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: |
         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 +1,75 @@
+# There are some issues (in the downloading data phase) on MacOS when running with other tests. So we split it into an individual config.
+name: Test MacOS
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-11, macos-latest]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Lint with Black
+      run: |
+        cd ..
+        python -m pip install pip --upgrade
+        python -m pip install wheel --upgrade
+        python -m pip install black
+        python -m black qlib -l 120 --check --diff
+    # Test Qlib installed with pip
+
+    - name: Install Qlib with pip
+      run: |
+          python -m pip install numpy==1.19.5
+          python -m pip install pyqlib --ignore-installed ruamel.yaml numpy
+    - name: Install Lightgbm for MacOS
+      run: |
+        /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
+        HOMEBREW_NO_AUTO_UPDATE=1 brew install lightgbm
+        # FIX MacOS error: Segmentation fault
+        # reference: https://github.com/microsoft/LightGBM/issues/4229
+        wget https://raw.githubusercontent.com/Homebrew/homebrew-core/fb8323f2b170bd4ae97e1bac9bf3e2983af3fdb0/Formula/libomp.rb
+        brew unlink libomp
+        brew install libomp.rb
+    - name: Test data downloads
+      run: |
+        python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+    - name: Test workflow by config (install from pip)
+      run: |
+        python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
+        python -m pip uninstall -y pyqlib
+    # Test Qlib installed from source
+    - name: Install Qlib from source
+      run: |
+        python -m pip install --upgrade cython
+        python -m pip install numpy jupyter jupyter_contrib_nbextensions
+        python -m pip install -U scipy scikit-learn # installing without this line will cause errors on GitHub Actions, while instsalling locally won't
+        pip install -e .
+    - name: Install test dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install -U pyopenssl idna
+        python -m pip install black pytest
+    - name: Unit tests with Pytest
+      run: |
+        cd tests
+        python -m pytest . --durations=0
+    - name: Test workflow by config (install from source)
+      run: |
+          python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

.gitignore

@@ -20,6 +20,7 @@ dist/
 .nvimrc
 .vscode
 
+qlib/VERSION.txt
 qlib/data/_libs/expanding.cpp
 qlib/data/_libs/rolling.cpp
 examples/estimator/estimator_example/

.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

@@ -11,19 +11,29 @@
 Recent released features
 | Feature | Status |
 | --                      | ------    |
-| Online serving and automatic model rolling | :star: [Released](https://github.com/microsoft/qlib/pull/290) on May 17, 2021 | 
-| DoubleEnsemble Model | [Released](https://github.com/microsoft/qlib/pull/286) on Mar 2, 2021 | 
-| High-frequency data processing example | [Released](https://github.com/microsoft/qlib/pull/257) on Feb 5, 2021  |
-| High-frequency trading example | [Part of code released](https://github.com/microsoft/qlib/pull/227) on Jan 28, 2021  | 
-| High-frequency data(1min) | [Released](https://github.com/microsoft/qlib/pull/221) on Jan 27, 2021 |
-| Tabnet Model | [Released](https://github.com/microsoft/qlib/pull/205) on Jan 22, 2021 | 
+| Arctic Provider Backend & Orderbook data example | :hammer: [Rleased](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>
 
 
@@ -42,9 +52,12 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
   - [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)
+- [Main Challenges & Solutions in Quant Research](#main-challenges--solutions-in-quant-research)
+  - [Forecasting: Finding Valuable Signals/Patterns](#forecasting-finding-valuable-signalspatterns)
+    - [**Quant Model (Paper) Zoo**](#quant-model-paper-zoo)
+      - [Run a Single Model](#run-a-single-model)
+      - [Run Multiple Models](#run-multiple-models)
+  - [Adapting to Market Dynamics](#adapting-to-market-dynamics)
 - [**Quant Dataset Zoo**](#quant-dataset-zoo)
 - [More About Qlib](#more-about-qlib)
 - [Offline Mode and Online Mode](#offline-mode-and-online-mode)
@@ -59,16 +72,12 @@ New features under development(order by estimated release time).
 Your feedbacks about the features are very important.
 | Feature                        | Status      |
 | --                      | ------    |
-| Planning-based portfolio optimization | Under review:  https://github.com/microsoft/qlib/pull/280 | 
-| Fund data supporting and analysis  |  Under review: https://github.com/microsoft/qlib/pull/292 |
 | Point-in-Time database | Under review: https://github.com/microsoft/qlib/pull/343 |
-| High-frequency trading | Under review: https://github.com/microsoft/qlib/pull/408 | 
-| Meta-Learning-based data selection | Initial opensource version under development |
 
 # 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>
 
 
@@ -77,7 +86,7 @@ At the module level, Qlib is a platform that consists of the above components. T
 | Name                   | Description                                                                                                                                                                                                                                                                                                                                                             |
 | ------                 | -----                                                                                                                                                                                                                                                                                                                                                                   |
 | `Infrastructure` layer | `Infrastructure` layer provides underlying support for Quant research. `DataServer` provides a high-performance infrastructure for users to manage and retrieve raw data. `Trainer` provides a flexible interface to control the training process of models, which enable algorithms to control the training process.                                                       |
-| `Workflow` layer       | `Workflow` layer covers the whole workflow of quantitative investment. `Information Extractor` extracts data for models. `Forecast Model` focuses on producing all kinds of forecast signals (e.g. _alpha_, risk) for other modules. With these signals `Portfolio Generator` will generate the target portfolio and produce orders to be executed by `Order Executor`. |
+| `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.
@@ -98,14 +107,15 @@ 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.
@@ -127,17 +137,11 @@ 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.
 
@@ -154,18 +158,42 @@ Load and prepare data by running the following code:
 
 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)
+
+
 <!-- 
 - Run the initialization code and get stock data:
 
   ```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
@@ -222,19 +250,19 @@ 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)
@@ -250,48 +278,74 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
 ## Building 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.
 
-# [Quant Model Zoo](examples/benchmarks)
+## 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 (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)
-- [DoubleEnsemble based on LightGBM (Chuheng Zhang, et al. 2020)](qlib/contrib/model/double_ensemble.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/)
 
 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:
 - 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.
 
-- 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 --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`:
@@ -346,9 +400,7 @@ 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
-- [【华泰金工林晓明团队】图神经网络选股与Qlib实践——华泰人工智能系列之四十二](https://mp.weixin.qq.com/s/w5fDB6oAv9dO6vlhf1kmhA)
 - [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)
 
@@ -361,11 +413,40 @@ Qlib data are stored in a compact format, which is efficient to be combined into
 Join IM discussion groups:
 |[Gitter](https://gitter.im/Microsoft/qlib)|
 |----|
-|![image](http://fintech.msra.cn/images_v060/qrcode/gitter_qr.png)|
+|![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) | 
+
+If you would like to become one of Qlib's maintainers to contribute more (e.g. help merge PR, triage issues), please contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).  We are glad to help you to set the right permission.
+
+## 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

@@ -97,4 +97,57 @@ Also, feel free to post a new issue in our GitHub repository. We always check ea
 
         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.
+- 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/task_management.rst

@@ -11,7 +11,10 @@ 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.
+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>`_.
 
@@ -74,6 +77,8 @@ If you do not want to use ``Task Manager`` to manage tasks, then use TrainerR to
 
 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).
@@ -82,8 +87,10 @@ To collect the results of ``task`` after training, ``Qlib`` provides `Collector
 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
+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>`_.
+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
 ============================
@@ -46,6 +52,7 @@ Also, ``Qlib`` provides a high-frequency dataset. Users can run a high-frequency
 Qlib Format Dataset
 --------------------
 ``Qlib`` has provided an off-the-shelf dataset in `.bin` format, users could use the script ``scripts/get_data.py`` to download the China-Stock dataset as follows.
+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.
 
 .. code-block:: bash
 
@@ -67,6 +74,34 @@ After running the above command, users can find china-stock and us-stock data in
 
 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
 -------------------------------------------
 
@@ -151,6 +186,7 @@ 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)
 --------------------------------
@@ -184,7 +220,7 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
         
         .. 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)
         
 
@@ -309,7 +345,7 @@ 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

docs/component/highfreq.rst

@@ -0,0 +1,31 @@
+.. _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>`_.

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

@@ -21,6 +21,12 @@ which including `Online Manager <#Online Manager>`_, `Online Strategy <#Online S
 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
 =============
 
@@ -43,4 +49,4 @@ Updater
 =============
 
 .. automodule:: qlib.workflow.online.update
-    :members:
+    :members:

docs/component/recorder.rst

@@ -37,7 +37,7 @@ Here is a general view of the structure of the system:
         
 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
 ===================
@@ -123,7 +123,6 @@ Here is a simple exampke of what is done in ``PortAnaRecord``, which users can r
         "n_drop": 5,
     }
     BACKTEST_CONFIG = {
-        "verbose": False,
         "limit_threshold": 0.095,
         "account": 100000000,
         "benchmark": BENCHMARK,

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 +22,22 @@ 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. 
+    Return the order list.
+    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.
 
@@ -69,52 +73,229 @@ TopkDropoutStrategy
 
         - `Topk`: The number of stocks held
         - `Drop`: The number of stocks sold on each trading day
-        
+
         Currently, the number of held stocks is `Topk`.
         On each trading day, the `Drop` number of held stocks with the worst `prediction score` will be sold, and the same number of unheld stocks with the best `prediction score` will be bought.
-        
+
         .. 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>`_.
 
-To know more about the `prediction score` `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
+Normally, the prediction score is the output of the models. But some models are learned from a label with a different scale. So the scale of the prediction score may be different from your expectation(e.g. the return of instruments).
+
+Qlib didn't add a step to scale the prediction score to a unified scale. Because not every trading strategy cares about the scale(e.g. TopkDropoutStrategy only cares about the order).  So the strategy is responsible for rescaling the prediction score(e.g. some portfolio-optimization-based strategies may require a meaningful scale).
+
+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()
+        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
+        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"
+        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:: 
         
@@ -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/developer/code_standard.rst

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

docs/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

@@ -36,10 +36,11 @@ 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>

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

@@ -241,6 +241,7 @@ Online Tool
 .. automodule:: qlib.workflow.online.utils
     :members:
 
+
 RecordUpdater
 --------------------
 .. automodule:: qlib.workflow.online.update
@@ -257,4 +258,4 @@ Serializable
     :members:
 
 
-    
+    

docs/requirements.txt

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

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)
     
@@ -42,12 +42,13 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
 - `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/main/qlib/config.py#L239>`_. 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.
@@ -77,7 +78,8 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
         })
 - `mongo`
     Type: dict, optional parameter, the setting of `MongoDB <https://www.mongodb.com/>`_ which will be used in some features such as `Task Management <../advanced/task_management.html>`_, with high performance and clustered processing. 
-    Users need finished `installation <https://www.mongodb.com/try/download/community>`_ firstly, and run it in a fixed URL.
+    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
 

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/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/requirements.txt

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_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: DEnsembleModel
@@ -75,16 +80,18 @@ task:
                 train: [2008-01-01, 2014-12-31]
                 valid: [2015-01-01, 2016-12-31]
                 test: [2017-01-01, 2020-08-01]
-    record:
+    record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: 
             ana_long_short: False
             ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: 
             config: *port_analysis_config

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_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: DEnsembleModel
@@ -82,10 +87,12 @@ task:
                 train: [2008-01-01, 2014-12-31]
                 valid: [2015-01-01, 2016-12-31]
                 test: [2017-01-01, 2020-08-01]
-    record:
+    record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
@@ -93,5 +100,5 @@ task:
             ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
-            config: *port_analysis_config
+          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/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

@@ -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: 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

examples/benchmarks/LightGBM/workflow_config_lightgbm_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: LGBModel
@@ -61,7 +66,9 @@ 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: 
@@ -70,4 +77,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/LightGBM/workflow_config_lightgbm_configurable_dataset.yaml

@@ -27,19 +27,24 @@ 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: LGBModel
@@ -69,7 +74,9 @@ 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: 
@@ -78,4 +85,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/LightGBM/workflow_config_lightgbm_multi_freq.yaml

@@ -0,0 +1,90 @@
+qlib_init:
+    provider_uri:
+        day: "~/.qlib/qlib_data/cn_data"
+        1min: "~/.qlib/qlib_data/cn_data_1min"
+    region: cn
+    dataset_cache: null
+    maxtasksperchild: null
+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_15min: 1min
+        feature_day: day
+    # with label as reference
+    inst_processor:
+        feature_15min:
+            - class: ResampleNProcessor
+              module_path: features_resample_N.py
+              kwargs:
+                  target_frq: 1d
+
+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: 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: Avg15minHandler
+                module_path: multi_freq_handler.py
+                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/Linear/workflow_config_linear_Alpha158.yaml

@@ -22,23 +22,27 @@ data_handler_config: &data_handler_config
         - 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.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: LinearModel
@@ -57,16 +61,18 @@ task:
                 train: [2008-01-01, 2014-12-31]
                 valid: [2015-01-01, 2016-12-31]
                 test: [2017-01-01, 2020-08-01]
-    record:
+    record: 
         - class: SignalRecord
           module_path: qlib.workflow.record_temp
-          kwargs: {}
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
         - class: SigAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: 
             ana_long_short: True
             ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
-          kwargs:
+          kwargs: 
             config: *port_analysis_config

examples/benchmarks/Localformer/README.md

@@ -0,0 +1 @@
+# Localformer

examples/benchmarks/Localformer/requirements.txt

@@ -0,0 +1,3 @@
+numpy==1.21.0
+pandas==1.1.2
+torch==1.2.0

examples/benchmarks/Localformer/workflow_config_localformer_Alpha158.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: FilterCol
+          kwargs:
+              fields_group: feature
+              col_list: ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", 
+                            "ROC60", "RESI10", "VSTD5", "RSQR60", "CORR60", "WVMA60", "STD5", 
+                            "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"
+                        ]
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"] 
+
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <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: LocalformerModel
+        module_path: qlib.contrib.model.pytorch_localformer_ts
+        kwargs:
+            seed: 0
+            n_jobs: 20
+    dataset:
+        class: TSDatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+            step_len: 20
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+              model: <MODEL>
+              dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+              ana_long_short: False
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+              config: *port_analysis_config

examples/benchmarks/Localformer/workflow_config_localformer_Alpha360.yaml

@@ -0,0 +1,80 @@
+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: LocalformerModel
+        module_path: qlib.contrib.model.pytorch_localformer
+        kwargs:
+            d_feat: 6
+            seed: 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/MLP/README.md

@@ -0,0 +1 @@
+# Multi-Layer Perceptron (MLP)

examples/benchmarks/MLP/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/MLP/workflow_config_mlp_Alpha158.yaml

@@ -39,19 +39,24 @@ 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: DNNModelPytorch
@@ -83,7 +88,9 @@ 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: 
@@ -92,4 +99,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

examples/benchmarks/MLP/workflow_config_mlp_Alpha360.yaml

@@ -27,19 +27,24 @@ 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: DNNModelPytorch
@@ -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/README.md

@@ -1,39 +1,68 @@
 # Benchmarks Performance
+This page lists a batch of methods designed for alpha seeking. Each method tries to give scores/predictions for all stocks each day(e.g. forecasting the future excess return of stocks). The scores/predictions of the models will be used as the mined alpha. Investing in stocks with higher scores is expected to yield more profit.  
 
-Here are the results of each benchmark model running on Qlib's `Alpha360` and `Alpha158` dataset with China's A shared-stock & CSI300 data respectively. The values of each metric are the mean and std calculated based on 20 runs.
+The alpha is evaluated in two ways.
+1. The correlation between the alpha and future return.
+1. Constructing portfolio based on the alpha and evaluating the final total return.
+
+Here are the results of each benchmark model running on Qlib's `Alpha360` and `Alpha158` dataset with China's A shared-stock & CSI300 data respectively. The values of each metric are the mean and std calculated based on 20 runs with different random seeds.
 
 The numbers shown below demonstrate the performance of the entire `workflow` of each model. We will update the `workflow` as well as models in the near future for better results.
+<!-- 
+> If you need to reproduce the results below, please use the **v1** dataset: `python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn --version v1`
+>
+> In the new version of qlib, the default dataset is **v2**. Since the data is collected from the YahooFinance API (which is not very stable), the results of *v2* and *v1* may differ -->
+
+> NOTE:
+> The backtest start from 0.8.0 is quite different from previous version. Please check out the changelog for the difference.
 
-## Alpha360 dataset
-| Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown |
-|---|---|---|---|---|---|---|---|---|
-| Linear | Alpha360 | 0.0150±0.00 | 0.1049±0.00| 0.0284±0.00 | 0.1970±0.00 | -0.0659±0.00 | -0.7072±0.00| -0.2955±0.00 |
-| CatBoost (Liudmila Prokhorenkova, et al.) | Alpha360 | 0.0397±0.00 | 0.2878±0.00| 0.0470±0.00 | 0.3703±0.00 | 0.0342±0.00 | 0.4092±0.00| -0.1057±0.00 |
-| XGBoost (Tianqi Chen, et al.) | Alpha360 | 0.0400±0.00 | 0.3031±0.00| 0.0461±0.00 | 0.3862±0.00 | 0.0528±0.00 | 0.6307±0.00| -0.1113±0.00 |
-| LightGBM (Guolin Ke, et al.) | Alpha360 | 0.0399±0.00 | 0.3075±0.00| 0.0492±0.00 | 0.4019±0.00 | 0.0323±0.00 | 0.4370±0.00| -0.0917±0.00 |
-| MLP | Alpha360 | 0.0285±0.00 | 0.1981±0.02| 0.0402±0.00 | 0.2993±0.02 | 0.0073±0.02 | 0.0880±0.22| -0.1446±0.03 |
-| GRU (Kyunghyun Cho, et al.) | Alpha360 | 0.0490±0.01 | 0.3787±0.05| 0.0581±0.00 | 0.4664±0.04 | 0.0726±0.02 | 0.9817±0.34| -0.0902±0.03 |
-| LSTM (Sepp Hochreiter, et al.) | Alpha360 | 0.0443±0.01 | 0.3401±0.05| 0.0536±0.01 | 0.4248±0.05 | 0.0627±0.03 | 0.8441±0.48| -0.0882±0.03 |
-| ALSTM (Yao Qin, et al.) | Alpha360 | 0.0493±0.01 | 0.3778±0.06| 0.0585±0.00 | 0.4606±0.04 | 0.0513±0.03 | 0.6727±0.38| -0.1085±0.02 |
-| GATs (Petar Velickovic, et al.) | Alpha360 | 0.0475±0.00 | 0.3515±0.02| 0.0592±0.00 | 0.4585±0.01 | 0.0876±0.02 | 1.1513±0.27| -0.0795±0.02 |
-| DoubleEnsemble (Chuheng Zhang, et al.) | Alpha360 | 0.0407±0.00| 0.3053±0.00 | 0.0490±0.00 | 0.3840±0.00 | 0.0380±0.02 | 0.5000±0.21 | -0.0984±0.02 |
-| TabNet (Sercan O. Arik, et al.)| Alpha360 | 0.0192±0.00 | 0.1401±0.00| 0.0291±0.00 | 0.2163±0.00 | -0.0258±0.00 | -0.2961±0.00| -0.1429±0.00 |
 
 ## Alpha158 dataset
-| Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown |
-|---|---|---|---|---|---|---|---|---|
-| Linear | Alpha158 | 0.0393±0.00 | 0.2980±0.00| 0.0475±0.00 | 0.3546±0.00 | 0.0795±0.00 | 1.0712±0.00| -0.1449±0.00 |
-| CatBoost (Liudmila Prokhorenkova, et al.) | Alpha158 | 0.0503±0.00 | 0.3586±0.00| 0.0483±0.00 | 0.3667±0.00 | 0.1080±0.00 | 1.1561±0.00| -0.0787±0.00 |
-| XGBoost (Tianqi Chen, et al.) | Alpha158 | 0.0481±0.00 | 0.3659±0.00| 0.0495±0.00 | 0.4033±0.00 | 0.1111±0.00 | 1.2915±0.00| -0.0893±0.00 |
-| LightGBM (Guolin Ke, et al.) | Alpha158 | 0.0475±0.00 | 0.3979±0.00| 0.0485±0.00 | 0.4123±0.00 | 0.1143±0.00 | 1.2744±0.00| -0.0800±0.00 |
-| MLP | Alpha158 | 0.0358±0.00 | 0.2738±0.03| 0.0425±0.00 | 0.3221±0.01 | 0.0836±0.02 | 1.0323±0.25| -0.1127±0.02 |
-| TFT (Bryan Lim, et al.) | Alpha158 (with selected 20 features) | 0.0343±0.00 | 0.2071±0.02| 0.0107±0.00 | 0.0660±0.02 | 0.0623±0.02 | 0.5818±0.20| -0.1762±0.01 |
-| GRU (Kyunghyun Cho, et al.) | Alpha158 (with selected 20 features) | 0.0311±0.00 | 0.2418±0.04| 0.0425±0.00 | 0.3434±0.02 | 0.0330±0.02 | 0.4805±0.30| -0.1021±0.02 |
-| LSTM (Sepp Hochreiter, et al.) | Alpha158 (with selected 20 features) | 0.0312±0.00 | 0.2394±0.04| 0.0418±0.00 | 0.3324±0.03 | 0.0298±0.02 | 0.4198±0.33| -0.1348±0.03 |
-| ALSTM (Yao Qin, et al.) | Alpha158 (with selected 20 features) | 0.0385±0.01 | 0.3022±0.06| 0.0478±0.00 | 0.3874±0.04 | 0.0486±0.03 | 0.7141±0.45| -0.1088±0.03 |
-| GATs (Petar Velickovic, et al.) | Alpha158 (with selected 20 features) | 0.0349±0.00 | 0.2511±0.01| 0.0457±0.00 | 0.3537±0.01 | 0.0578±0.02 | 0.8221±0.25| -0.0824±0.02 |
-| DoubleEnsemble (Chuheng Zhang, et al.) | Alpha158 | 0.0544±0.00 | 0.4338±0.01 | 0.0523±0.00 | 0.4257±0.01 | 0.1253±0.01 | 1.4105±0.14 | -0.0902±0.01 |
-| TabNet (Sercan O. Arik, et al.)| Alpha158 | 0.0383±0.00 | 0.3414±0.00| 0.0388±0.00 | 0.3460±0.00 | 0.0226±0.00 | 0.2652±0.00| -0.1072±0.00 |
+
+| Model Name                               | Dataset                             | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
+|------------------------------------------|-------------------------------------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
+| TCN(Shaojie Bai, et al.)                 | Alpha158                            | 0.0275±0.00 | 0.2157±0.01 | 0.0411±0.00 | 0.3379±0.01 | 0.0190±0.02       | 0.2887±0.27       | -0.1202±0.03 |
+| TabNet(Sercan O. Arik, et al.)           | Alpha158                            | 0.0204±0.01 | 0.1554±0.07 | 0.0333±0.00 | 0.2552±0.05 | 0.0227±0.04       | 0.3676±0.54       | -0.1089±0.08 |
+| Transformer(Ashish Vaswani, et al.)      | Alpha158                            | 0.0264±0.00 | 0.2053±0.02 | 0.0407±0.00 | 0.3273±0.02 | 0.0273±0.02       | 0.3970±0.26       | -0.1101±0.02 |
+| GRU(Kyunghyun Cho, et al.)               | Alpha158(with selected 20 features) | 0.0315±0.00 | 0.2450±0.04 | 0.0428±0.00 | 0.3440±0.03 | 0.0344±0.02       | 0.5160±0.25       | -0.1017±0.02 |
+| LSTM(Sepp Hochreiter, et al.)            | Alpha158(with selected 20 features) | 0.0318±0.00 | 0.2367±0.04 | 0.0435±0.00 | 0.3389±0.03 | 0.0381±0.03       | 0.5561±0.46       | -0.1207±0.04 |
+| Localformer(Juyong Jiang, et al.)        | Alpha158                            | 0.0356±0.00 | 0.2756±0.03 | 0.0468±0.00 | 0.3784±0.03 | 0.0438±0.02       | 0.6600±0.33       | -0.0952±0.02 |
+| SFM(Liheng Zhang, et al.)                | Alpha158                            | 0.0379±0.00 | 0.2959±0.04 | 0.0464±0.00 | 0.3825±0.04 | 0.0465±0.02       | 0.5672±0.29       | -0.1282±0.03 |
+| ALSTM (Yao Qin, et al.)                  | Alpha158(with selected 20 features) | 0.0362±0.01 | 0.2789±0.06 | 0.0463±0.01 | 0.3661±0.05 | 0.0470±0.03       | 0.6992±0.47       | -0.1072±0.03 |
+| GATs (Petar Velickovic, et al.)          | Alpha158(with selected 20 features) | 0.0349±0.00 | 0.2511±0.01 | 0.0462±0.00 | 0.3564±0.01 | 0.0497±0.01       | 0.7338±0.19       | -0.0777±0.02 |
+| TRA(Hengxu Lin, et al.)                  | Alpha158(with selected 20 features) | 0.0404±0.00 | 0.3197±0.05 | 0.0490±0.00 | 0.4047±0.04 | 0.0649±0.02       | 1.0091±0.30       | -0.0860±0.02 |
+| Linear                                   | Alpha158                            | 0.0397±0.00 | 0.3000±0.00 | 0.0472±0.00 | 0.3531±0.00 | 0.0692±0.00       | 0.9209±0.00       | -0.1509±0.00 |
+| TRA(Hengxu Lin, et al.)                  | Alpha158                            | 0.0440±0.00 | 0.3535±0.05 | 0.0540±0.00 | 0.4451±0.03 | 0.0718±0.02       | 1.0835±0.35       | -0.0760±0.02 |
+| CatBoost(Liudmila Prokhorenkova, et al.) | Alpha158                            | 0.0481±0.00 | 0.3366±0.00 | 0.0454±0.00 | 0.3311±0.00 | 0.0765±0.00       | 0.8032±0.01       | -0.1092±0.00 |
+| XGBoost(Tianqi Chen, et al.)             | Alpha158                            | 0.0498±0.00 | 0.3779±0.00 | 0.0505±0.00 | 0.4131±0.00 | 0.0780±0.00       | 0.9070±0.00       | -0.1168±0.00 |
+| TFT (Bryan Lim, et al.)                  | Alpha158(with selected 20 features) | 0.0358±0.00 | 0.2160±0.03 | 0.0116±0.01 | 0.0720±0.03 | 0.0847±0.02       | 0.8131±0.19       | -0.1824±0.03 |
+| MLP                                      | Alpha158                            | 0.0376±0.00 | 0.2846±0.02 | 0.0429±0.00 | 0.3220±0.01 | 0.0895±0.02       | 1.1408±0.23       | -0.1103±0.02 |
+| LightGBM(Guolin Ke, et al.)              | Alpha158                            | 0.0448±0.00 | 0.3660±0.00 | 0.0469±0.00 | 0.3877±0.00 | 0.0901±0.00       | 1.0164±0.00       | -0.1038±0.00 |
+| DoubleEnsemble(Chuheng Zhang, et al.)    | Alpha158                            | 0.0544±0.00 | 0.4340±0.00 | 0.0523±0.00 | 0.4284±0.01 | 0.1168±0.01       | 1.3384±0.12       | -0.1036±0.01 |
+
+
+## Alpha360 dataset
+
+| Model Name                                | Dataset  | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
+|-------------------------------------------|----------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
+| Transformer(Ashish Vaswani, et al.)       | Alpha360 | 0.0114±0.00 | 0.0716±0.03 | 0.0327±0.00 | 0.2248±0.02 | -0.0270±0.03      | -0.3378±0.37      | -0.1653±0.05 |
+| TabNet(Sercan O. Arik, et al.)            | Alpha360 | 0.0099±0.00 | 0.0593±0.00 | 0.0290±0.00 | 0.1887±0.00 | -0.0369±0.00      | -0.3892±0.00      | -0.2145±0.00 |
+| MLP                                       | Alpha360 | 0.0273±0.00 | 0.1870±0.02 | 0.0396±0.00 | 0.2910±0.02 | 0.0029±0.02       | 0.0274±0.23       | -0.1385±0.03 |
+| Localformer(Juyong Jiang, et al.)         | Alpha360 | 0.0404±0.00 | 0.2932±0.04 | 0.0542±0.00 | 0.4110±0.03 | 0.0246±0.02       | 0.3211±0.21       | -0.1095±0.02 |
+| CatBoost((Liudmila Prokhorenkova, et al.) | Alpha360 | 0.0378±0.00 | 0.2714±0.00 | 0.0467±0.00 | 0.3659±0.00 | 0.0292±0.00       | 0.3781±0.00       | -0.0862±0.00 |
+| XGBoost(Tianqi Chen, et al.)              | Alpha360 | 0.0394±0.00 | 0.2909±0.00 | 0.0448±0.00 | 0.3679±0.00 | 0.0344±0.00       | 0.4527±0.02       | -0.1004±0.00 |
+| DoubleEnsemble(Chuheng Zhang, et al.)     | Alpha360 | 0.0404±0.00 | 0.3023±0.00 | 0.0495±0.00 | 0.3898±0.00 | 0.0468±0.01       | 0.6302±0.20       | -0.0860±0.01 |
+| LightGBM(Guolin Ke, et al.)               | Alpha360 | 0.0400±0.00 | 0.3037±0.00 | 0.0499±0.00 | 0.4042±0.00 | 0.0558±0.00       | 0.7632±0.00       | -0.0659±0.00 |
+| TCN(Shaojie Bai, et al.)                  | Alpha360 | 0.0441±0.00 | 0.3301±0.02 | 0.0519±0.00 | 0.4130±0.01 | 0.0604±0.02       | 0.8295±0.34       | -0.1018±0.03 |
+| ALSTM (Yao Qin, et al.)                   | Alpha360 | 0.0497±0.00 | 0.3829±0.04 | 0.0599±0.00 | 0.4736±0.03 | 0.0626±0.02       | 0.8651±0.31       | -0.0994±0.03 |
+| LSTM(Sepp Hochreiter, et al.)             | Alpha360 | 0.0448±0.00 | 0.3474±0.04 | 0.0549±0.00 | 0.4366±0.03 | 0.0647±0.03       | 0.8963±0.39       | -0.0875±0.02 |
+| ADD                                       | Alpha360 | 0.0430±0.00 | 0.3188±0.04 | 0.0559±0.00 | 0.4301±0.03 | 0.0667±0.02       | 0.8992±0.34       | -0.0855±0.02 |
+| GRU(Kyunghyun Cho, et al.)                | Alpha360 | 0.0493±0.00 | 0.3772±0.04 | 0.0584±0.00 | 0.4638±0.03 | 0.0720±0.02       | 0.9730±0.33       | -0.0821±0.02 |
+| AdaRNN(Yuntao Du, et al.)                 | Alpha360 | 0.0464±0.01 | 0.3619±0.08 | 0.0539±0.01 | 0.4287±0.06 | 0.0753±0.03       | 1.0200±0.40       | -0.0936±0.03 |
+| GATs (Petar Velickovic, et al.)           | Alpha360 | 0.0476±0.00 | 0.3508±0.02 | 0.0598±0.00 | 0.4604±0.01 | 0.0824±0.02       | 1.1079±0.26       | -0.0894±0.03 |
+| TCTS(Xueqing Wu, et al.)                  | Alpha360 | 0.0508±0.00 | 0.3931±0.04 | 0.0599±0.00 | 0.4756±0.03 | 0.0893±0.03       | 1.2256±0.36       | -0.0857±0.02 |
+| TRA(Hengxu Lin, et al.)                   | Alpha360 | 0.0485±0.00 | 0.3787±0.03 | 0.0587±0.00 | 0.4756±0.03 | 0.0920±0.03       | 1.2789±0.42       | -0.0834±0.02 |
 
 - The selected 20 features are based on the feature importance of a lightgbm-based model.
 - The base model of DoubleEnsemble is LGBM.
+- The base model of TCTS is GRU.

examples/benchmarks/SFM/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
+torch==1.7.0

examples/benchmarks/SFM/workflow_config_sfm_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: SFM
@@ -73,7 +78,9 @@ 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/TCN/README.md

@@ -0,0 +1,4 @@
+# TCN
+* Code: [https://github.com/locuslab/TCN](https://github.com/locuslab/TCN)
+* Paper: [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://arxiv.org/abs/1803.01271).
+

examples/benchmarks/TCN/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/TCN/workflow_config_tcn_Alpha158.yaml

@@ -0,0 +1,100 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: FilterCol
+          kwargs:
+              fields_group: feature
+              col_list: ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", 
+                            "ROC60", "RESI10", "VSTD5", "RSQR60", "CORR60", "WVMA60", "STD5", 
+                            "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"
+                        ]
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            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: TCN
+        module_path: qlib.contrib.model.pytorch_tcn_ts
+        kwargs:
+            d_feat: 20
+            num_layers: 5
+            n_chans: 32
+            kernel_size: 7
+            dropout: 0.5
+            n_epochs: 200
+            lr: 1e-4
+            early_stop: 20
+            batch_size: 2000
+            metric: loss
+            loss: mse
+            optimizer: adam
+            n_jobs: 20
+            GPU: 0
+    dataset:
+        class: TSDatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+            step_len: 20
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/TCN/workflow_config_tcn_Alpha360.yaml

@@ -0,0 +1,90 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: RobustZScoreNorm
+          kwargs:
+              fields_group: feature
+              clip_outlier: true
+        - class: Fillna
+          kwargs:
+              fields_group: feature
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            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: TCN
+        module_path: qlib.contrib.model.pytorch_tcn
+        kwargs:
+            d_feat: 6
+            num_layers: 5
+            n_chans: 128
+            kernel_size: 3
+            dropout: 0.5
+            n_epochs: 200
+            lr: 1e-3
+            early_stop: 20
+            batch_size: 2000
+            metric: loss
+            loss: mse
+            optimizer: adam
+            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/TCTS/README.md

@@ -0,0 +1,38 @@
+# Temporally Correlated Task Scheduling for Sequence Learning
+### Background
+Sequence learning has attracted much research attention from the machine learning community in recent years. In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are different in terms of how much input information to use or which future step to predict. In stock trend forecasting, as demonstrated in Figure1, one can predict the price of a stock in different future days (e.g., tomorrow, the day after tomorrow). In this paper, we propose a framework to make use of those temporally correlated tasks to help each other. 
+
+### Method
+Given that there are usually multiple temporally correlated tasks, the key challenge lies in which tasks to use and when to use them in the training process. This work introduces a learnable task scheduler for sequence learning, which adaptively selects temporally correlated tasks during the training process. The scheduler accesses the model status and the current training data (e.g., in the current minibatch) and selects the best auxiliary task to help the training of the main task. The scheduler and the model for the main task are jointly trained through bi-level optimization: the scheduler is trained to maximize the validation performance of the model, and the model is trained to minimize the training loss guided by the scheduler. The process is demonstrated in Figure2.
+
+<p align="center"> 
+<img src="workflow.png"/>
+</p>
+
+At step <img src="https://latex.codecogs.com/png.latex?s" title="s" />, with training data <img src="https://latex.codecogs.com/png.latex?x_s,y_s" title="x_s,y_s" />, the scheduler <img src="https://latex.codecogs.com/png.latex?\varphi" title="\varphi" /> chooses a suitable task <img src="https://latex.codecogs.com/png.latex?T_{i_s}" title="T_{i_s}" /> (green solid lines) to update the model <img src="https://latex.codecogs.com/png.latex?f" title="f" /> (blue solid lines). After <img src="https://latex.codecogs.com/png.latex?S" title="S" /> steps, we evaluate the model <img src="https://latex.codecogs.com/png.latex?f" title="f" /> on the validation set and update the scheduler <img src="https://latex.codecogs.com/png.latex?\varphi" title="\varphi" /> (green dashed lines).
+
+### Experiments
+Due to different data versions and different Qlib versions, the original data and data preprocessing methods of the experimental settings in the paper are different from those experimental settings in the existing Qlib version. Therefore, we provide two versions of the code according to the two kinds of settings, 1) the [code](https://github.com/lwwang1995/tcts) that can be used to reproduce the experimental results and 2) the [code](https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_tcts.py) in the current Qlib baseline.
+
+#### Setting1
+* Dataset: We use the historical transaction data for 300 stocks on [CSI300](http://www.csindex.com.cn/en/indices/index-detail/000300) from 01/01/2008 to 08/01/2020. We split the data into training (01/01/2008-12/31/2013), validation (01/01/2014-12/31/2015), and test sets (01/01/2016-08/01/2020) based on the transaction time. 
+
+* The main tasks <img src="https://latex.codecogs.com/png.latex?T_k" title="T_k" /> refers to forecasting return of stock <img src="https://latex.codecogs.com/png.latex?i" title="i" /> as following,
+<div align=center>
+<img src="https://latex.codecogs.com/png.image?\dpi{110}&space;r_{i}^{t,k}&space;=&space;\frac{price_i^{t&plus;k}}{price_i^{t&plus;k-1}}-1" title="r_{i}^{t,k} = \frac{price_i^{t+k}}{price_i^{t+k-1}}-1" />
+</div>
+
+* Temporally correlated task sets <img src="https://latex.codecogs.com/png.latex?\mathcal{T}_k&space;=&space;\{T_1,&space;T_2,&space;...&space;,&space;T_k\}" title="\mathcal{T}_k = \{T_1, T_2, ... , T_k\}" />, in this paper, <img src="https://latex.codecogs.com/png.latex?\mathcal{T}_3" title="\mathcal{T}_3" />, <img src="https://latex.codecogs.com/png.latex?\mathcal{T}_5" title="\mathcal{T}_5" /> and <img src="https://latex.codecogs.com/png.latex?\mathcal{T}_{10}" title="\mathcal{T}_{10}" /> are used in <img src="https://latex.codecogs.com/png.latex?T_1" title="T_1" />, <img src="https://latex.codecogs.com/png.latex?T_2" title="T_2" />, and <img src="https://latex.codecogs.com/png.latex?T_3" title="T_3" />.
+
+#### Setting2
+* Dataset: We use the historical transaction data for 300 stocks on [CSI300](http://www.csindex.com.cn/en/indices/index-detail/000300) from 01/01/2008 to 08/01/2020. We split the data into training (01/01/2008-12/31/2014), validation (01/01/2015-12/31/2016), and test sets (01/01/2017-08/01/2020) based on the transaction time. 
+
+* The main tasks <img src="https://latex.codecogs.com/png.latex?T_k" title="T_k" /> refers to forecasting return of stock <img src="https://latex.codecogs.com/png.latex?i" title="i" /> as following,
+<div align=center>
+<img src="https://latex.codecogs.com/png.image?\dpi{110}&space;r_{i}^{t,k}&space;=&space;\frac{price_i^{t&plus;1&plus;k}}{price_i^{t&plus;1}}-1" title="r_{i}^{t,k} = \frac{price_i^{t+1+k}}{price_i^{t+1}}-1" />
+</div>
+
+* In Qlib baseline, <img src="https://latex.codecogs.com/png.latex?\mathcal{T}_3" title="\mathcal{T}_3" />, is used in  <img src="https://latex.codecogs.com/png.latex?T_1" title="T_1" />.
+
+### Experimental Result
+You can find the experimental result of setting1 in the [paper](http://proceedings.mlr.press/v139/wu21e/wu21e.pdf) and the experimental result of setting2 in this [page](https://github.com/microsoft/qlib/tree/main/examples/benchmarks).

examples/benchmarks/TCTS/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/TCTS/workflow_config_tcts_Alpha360.yaml

@@ -0,0 +1,98 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors:
+        - class: 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", 
+            "Ref($close, -3) / Ref($close, -1) - 1", 
+            "Ref($close, -4) / Ref($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: TCTS
+        module_path: qlib.contrib.model.pytorch_tcts
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0.3
+            n_epochs: 200
+            early_stop: 20
+            batch_size: 800
+            metric: loss
+            loss: mse
+            GPU: 0
+            fore_optimizer: adam
+            weight_optimizer: adam
+            output_dim: 3
+            fore_lr: 2e-3
+            weight_lr: 2e-3
+            steps: 3
+            target_label: 0
+            lowest_valid_performance: 0.993
+    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