temporarily fix create exp conflicts for remote mlflow

* Auto injecting model and dataset for Recorder

* Support using Feature in expression

.deepsource.toml

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

.github/stale.yml

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

.github/workflows/python-publish.yml

@@ -12,8 +12,9 @@ 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/stale.yml

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

.github/workflows/test.yml

@@ -1,4 +1,4 @@
-name: Test 
+name: Test
 
 on:
   push:
@@ -12,8 +12,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-16.04, ubuntu-18.04, ubuntu-20.04, macos-latest]
-        python-version: [3.6, 3.7, 3.8, 3.9]
+        os: [windows-latest, ubuntu-18.04, ubuntu-20.04]
+        # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
+        python-version: [3.7, 3.8]
 
     steps:
     - uses: actions/checkout@v2
@@ -25,94 +26,41 @@ 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 pyqlib --ignore-installed ruamel.yaml --user
-        else
-          sudo $CONDA/bin/python -m pip install pyqlib --ignore-installed ruamel.yaml
-        fi
-      shell: bash
-    
-    - name: Install Lightgbm for MacOS
-      if: runner.os == 'macOS'
-      run: |
-        /bin/bash -c "$(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
+        python setup.py install
+    - 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/
@@ -34,3 +35,7 @@ tags
 
 .pytest_cache/
 .vscode/
+
+*.swp
+
+./pretrain

CHANGES.rst

@@ -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 verison <https://github.com/microsoft/qlib/blob/7c31012b507a3823117bddcc693fc64899460b2a/qlib/backtest/exchange.py#L304>`_, the trading limitation is different between loging 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 chec kout the backtesting results between  `Current version <https://github.com/microsoft/qlib/tree/7c31012b507a3823117bddcc693fc64899460b2a/examples/benchmarks>`_ and `previous version <https://github.com/microsoft/qlib/tree/v0.7.2/examples/benchmarks>`_
+
+
+Other Versions
 ----------------------------------
 Please refer to `Github release Notes <https://github.com/microsoft/qlib/releases>`_

MANIFEST.in

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

README.md

@@ -7,9 +7,25 @@
 [![License](https://img.shields.io/pypi/l/pyqlib)](LICENSE)
 [![Join the chat at https://gitter.im/Microsoft/qlib](https://badges.gitter.im/Microsoft/qlib.svg)](https://gitter.im/Microsoft/qlib?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
 
+## :newspaper: **What's NEW!**     :sparkling_heart: 
+Recent released features
+| Feature | Status |
+| --                      | ------    |
+|Temporal Routing Adaptor (TRA) | [Released](https://github.com/microsoft/qlib/pull/531) on July 30, 2021 |
+| Transformer & Localformer | [Released](https://github.com/microsoft/qlib/pull/508) on July 22, 2021 |
+| Release Qlib v0.7.0 | [Released](https://github.com/microsoft/qlib/releases/tag/v0.7.0) on July 12, 2021 |
+| TCTS Model | [Released](https://github.com/microsoft/qlib/pull/491) on July 1, 2021 |
+| 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 | 
+
+Features released before 2021 are not listed here.
 
 <p align="center">
-  <img src="http://fintech.msra.cn/images_v060/logo/1.png" />
+  <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
 </p>
 
 
@@ -17,17 +33,18 @@ Qlib is an AI-oriented quantitative investment platform, which aims to realize t
 
 It contains the full ML pipeline of data processing, model training, back-testing; and covers the entire chain of quantitative investment: alpha seeking, risk modeling, portfolio optimization, and order execution. 
 
-With Qlib, user can easily try ideas to create better Quant investment strategies.
+With Qlib, users can easily try ideas to create better Quant investment strategies.
 
 For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative Investment Platform"](https://arxiv.org/abs/2009.11189).
 
+- [**Plans**](#plans)
 - [Framework of Qlib](#framework-of-qlib)
 - [Quick Start](#quick-start)
   - [Installation](#installation)
   - [Data Preparation](#data-preparation)
   - [Auto Quant Research Workflow](#auto-quant-research-workflow)
   - [Building Customized Quant Research Workflow by Code](#building-customized-quant-research-workflow-by-code)
-- [**Quant Model Zoo**](#quant-model-zoo)
+- [**Quant Model(Paper) Zoo**](#quant-model-paper-zoo)
   - [Run a single model](#run-a-single-model)
   - [Run multiple models](#run-multiple-models)
 - [**Quant Dataset Zoo**](#quant-dataset-zoo)
@@ -35,22 +52,33 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
 - [Offline Mode and Online Mode](#offline-mode-and-online-mode)
   - [Performance of Qlib Data Server](#performance-of-qlib-data-server)
 - [Related Reports](#related-reports)
+- [Contact Us](#contact-us)
 - [Contributing](#contributing)
 
 
+# Plans
+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>
 
 
-At the module level, Qlib is a platform that consists of the above components. The components are designed as loose-coupled modules and each component could be used stand-alone.
+At the module level, Qlib is a platform that consists of the above components. The components are designed as loose-coupled modules, and each component could be used stand-alone.
 
 | Name                   | Description                                                                                                                                                                                                                                                                                                                                                             |
 | ------                 | -----                                                                                                                                                                                                                                                                                                                                                                   |
-| `Infrastructure` layer | `Infrastructure` layer provides underlying support for Quant research. `DataServer` provides high-performance infrastructure for users to manage and retrieve raw data. `Trainer` provides flexible interface to control the training process of models which enable algorithms controlling the training process.                                                       |
+| `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`. |
 | `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                                                                                                                                                                 |
 
@@ -72,14 +100,14 @@ 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.
 
 ### Install with pip
 Users can easily install ``Qlib`` by pip according to the following command.
@@ -118,14 +146,42 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 ## Data Preparation
 Load and prepare data by running the following code:
   ```bash
+  # get 1d data
   python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+
+  # get 1min data
+  python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --region cn --interval 1min
+
   ```
 
 This dataset is created by public data collected by [crawler scripts](scripts/data_collector/), which have been released in
 the same repository.
 Users could create the same dataset with it. 
 
-*Please pay **ATTENTION** that the data is collected from [Yahoo Finance](https://finance.yahoo.com/lookup) and the data might not be perfect. We recommend users to prepare their own data if they have high-quality dataset. For more information, users can refer to the [related document](https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format)*.
+*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)
+  > 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-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:
@@ -190,19 +246,19 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
 2. Graphical Reports Analysis: Run `examples/workflow_by_code.ipynb` with `jupyter notebook` to get graphical reports
     - Forecasting signal (model prediction) analysis
       - Cumulative Return of groups
-      ![Cumulative Return](http://fintech.msra.cn/images_v060/analysis/analysis_model_cumulative_return.png?v=0.1)
+      ![Cumulative Return](http://fintech.msra.cn/images_v070/analysis/analysis_model_cumulative_return.png?v=0.1)
       - Return distribution
-      ![long_short](http://fintech.msra.cn/images_v060/analysis/analysis_model_long_short.png?v=0.1)
+      ![long_short](http://fintech.msra.cn/images_v070/analysis/analysis_model_long_short.png?v=0.1)
       - Information Coefficient (IC)
-      ![Information Coefficient](http://fintech.msra.cn/images_v060/analysis/analysis_model_IC.png?v=0.1)        
-      ![Monthly IC](http://fintech.msra.cn/images_v060/analysis/analysis_model_monthly_IC.png?v=0.1)
-      ![IC](http://fintech.msra.cn/images_v060/analysis/analysis_model_NDQ.png?v=0.1)
+      ![Information Coefficient](http://fintech.msra.cn/images_v070/analysis/analysis_model_IC.png?v=0.1)
+      ![Monthly IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_monthly_IC.png?v=0.1)
+      ![IC](http://fintech.msra.cn/images_v070/analysis/analysis_model_NDQ.png?v=0.1)
       - Auto Correlation of forecasting signal (model prediction)
-      ![Auto Correlation](http://fintech.msra.cn/images_v060/analysis/analysis_model_auto_correlation.png?v=0.1)
+      ![Auto Correlation](http://fintech.msra.cn/images_v070/analysis/analysis_model_auto_correlation.png?v=0.1)
 
     - Portfolio analysis
       - Backtest return
-      ![Report](http://fintech.msra.cn/images_v060/analysis/report.png?v=0.1)
+      ![Report](http://fintech.msra.cn/images_v070/analysis/report.png?v=0.1)
       <!-- 
       - Score IC
       ![Score IC](docs/_static/img/score_ic.png)
@@ -213,25 +269,31 @@ Qlib provides a tool named `qrun` to run the whole workflow automatically (inclu
       - Rank Label
       ![Rank Label](docs/_static/img/rank_label.png)
       -->
+   - [Explanation](https://qlib.readthedocs.io/en/latest/component/report.html) of above results
 
 ## Building Customized Quant Research Workflow by Code
-The automatic workflow may not suite the research workflow of all Quant researchers. To support a flexible Quant research workflow, Qlib also provides a modularized interface to allow researchers to build their own workflow by code. [Here](examples/workflow_by_code.ipynb) is a demo for customized Quant research workflow by code.
+The automatic workflow may not suit the research workflow of all Quant researchers. To support a flexible Quant research workflow, Qlib also provides a modularized interface to allow researchers to build their own workflow by code. [Here](examples/workflow_by_code.ipynb) is a demo for customized Quant research workflow by code.
 
 
-# [Quant Model Zoo](examples/benchmarks)
+# [Quant Model (Paper) Zoo](examples/benchmarks)
 
 Here is a list of models built on `Qlib`.
-- [GBDT based on XGBoost (Tianqi Chen, et al. 2016)](qlib/contrib/model/xgboost.py)
-- [GBDT based on LightGBM (Guolin Ke, et al. 2017)](qlib/contrib/model/gbdt.py)
-- [GBDT based on Catboost (Liudmila Prokhorenkova, et al. 2017)](qlib/contrib/model/catboost_model.py)
+- [GBDT based on XGBoost (Tianqi Chen, et al. KDD 2016)](qlib/contrib/model/xgboost.py)
+- [GBDT based on LightGBM (Guolin Ke, et al. NIPS 2017)](qlib/contrib/model/gbdt.py)
+- [GBDT based on Catboost (Liudmila Prokhorenkova, et al. NIPS 2018)](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)
+- [LSTM based on pytorch (Sepp Hochreiter, et al. Neural omputation 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)
+- [ALSTM based on pytorch (Yao Qin, et al. IJCAI 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)
+- [SFM based on pytorch (Liheng Zhang, et al. KDD 2017)](qlib/contrib/model/pytorch_sfm.py)
+- [TFT based on tensorflow (Bryan Lim, et al. International Journal of Forecasting 2019)](examples/benchmarks/TFT/tft.py)
+- [TabNet based on pytorch (Sercan O. Arik, et al. AAAI 2019)](qlib/contrib/model/pytorch_tabnet.py)
+- [DoubleEnsemble based on LightGBM (Chuheng Zhang, et al. ICDM 2020)](qlib/contrib/model/double_ensemble.py)
+- [TCTS based on pytorch (Xueqing Wu, et al. ICML 2021)](qlib/contrib/model/pytorch_tcts.py)
+- [Transformer based on pytorch (Ashish Vaswani, et al. NeurIPS 2017)](qlib/contrib/model/pytorch_transformer.py)
+- [Localformer based on pytorch (Juyong Jiang, et al.)](qlib/contrib/model/pytorch_localformer.py)
+- [TRA based on pytorch (Hengxu, Dong, et al. KDD 2021)](qlib/contrib/model/pytorch_tra.py)
 
 Your PR of new Quant models is highly welcomed.
 
@@ -241,19 +303,20 @@ The performance of each model on the `Alpha158` and `Alpha360` dataset can be fo
 All the models listed above are runnable with ``Qlib``. Users can find the config files we provide and some details about the model through the [benchmarks](examples/benchmarks) folder. More information can be retrieved at the model files listed above.
 
 `Qlib` provides three different ways to run a single model, users can pick the one that fits their cases best:
-- User can use the tool `qrun` mentioned above to run a model's workflow based from a config file.
-- User can create a `workflow_by_code` python script based on the [one](examples/workflow_by_code.py) listed in the `examples` folder.
+- Users can use the tool `qrun` mentioned above to run a model's workflow based from a config file.
+- Users can create a `workflow_by_code` python script based on the [one](examples/workflow_by_code.py) listed in the `examples` folder.
 
-- User can use the script [`run_all_model.py`](examples/run_all_model.py) listed in the `examples` folder to run a model. Here is an example of the specific shell command to be used: `python run_all_model.py --models=lightgbm`, where the `--models` arguments can take any number of models listed above(the available models can be found  in [benchmarks](examples/benchmarks/)). For more use cases, please refer to the file's [docstrings](examples/run_all_model.py).
+- Users can use the script [`run_all_model.py`](examples/run_all_model.py) listed in the `examples` folder to run a model. Here is an example of the specific shell command to be used: `python run_all_model.py run --models=lightgbm`, where the `--models` arguments can take any number of models listed above(the available models can be found  in [benchmarks](examples/benchmarks/)). For more use cases, please refer to the file's [docstrings](examples/run_all_model.py).
+    - **NOTE**: Each baseline has different environment dependencies, please make sure that your python version aligns with the requirements(e.g. TFT only supports Python 3.6~3.7 due to the limitation of `tensorflow==1.15.0`)
 
 ## Run multiple models
-`Qlib` also provides a script [`run_all_model.py`](examples/run_all_model.py) which can run multiple models for several iterations. (**Note**: the script only support *Linux* for now. Other OS will be supported in the future. Besides, it doesn't support parrallel running the same model for multiple times as well, and this will be fixed in the future development too.)
+`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). 
@@ -307,21 +370,39 @@ which creates a dataset (14 features/factors) from the basic OHLCV daily data of
 * `+(-)E` indicates with (out) `ExpressionCache`
 * `+(-)D` indicates with (out) `DatasetCache`
 
-Most general-purpose databases take too much time on loading data. After looking into the underlying implementation, we find that data go through too many layers of interfaces and unnecessary format transformations in general-purpose database solutions.
+Most general-purpose databases take too much time to load data. After looking into the underlying implementation, we find that data go through too many layers of interfaces and unnecessary format transformations in general-purpose database solutions.
 Such overheads greatly slow down the data loading process.
 Qlib data are stored in a compact format, which is efficient to be combined into arrays for scientific computation.
 
-
 # Related Reports
 - [Guide To Qlib: Microsoft’s AI Investment Platform](https://analyticsindiamag.com/qlib/)
-- [【华泰金工林晓明团队】微软AI量化投资平台Qlib体验——华泰人工智能系列之四十](https://mp.weixin.qq.com/s/Brcd7im4NibJOJzZfMn6tQ)
 - [微软也搞AI量化平台？还是开源的！](https://mp.weixin.qq.com/s/47bP5YwxfTp2uTHjUBzJQQ)
 - [微矿Qlib：业内首个AI量化投资开源平台](https://mp.weixin.qq.com/s/vsJv7lsgjEi-ALYUz4CvtQ)
 
+# Contact Us
+- If you have any issues, please create issue [here](https://github.com/microsoft/qlib/issues/new/choose) or send messages in [gitter](https://gitter.im/Microsoft/qlib).
+- If you want to make contributions to `Qlib`, please [create pull requests](https://github.com/microsoft/qlib/compare). 
+- For other reasons, you are welcome to contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).
+  - We are recruiting new members(both FTEs and interns), your resumes are welcome!
+
+Join IM discussion groups:
+|[Gitter](https://gitter.im/Microsoft/qlib)|
+|----|
+|![image](http://fintech.msra.cn/images_v070/qrcode/gitter_qr.png)|
 
 # Contributing
 
-This project welcomes contributions and suggestions.  Most contributions require you to agree to a
+This project welcomes contributions and suggestions.  
+**Here are some 
+[code standards](docs/developer/code_standard.rst) when you submit a pull request.**
+
+If you want to contribute to Qlib's document, 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>
+
+
+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.
 

VERSION.txt

@@ -0,0 +1 @@
+0.7.2.99

docs/FAQ/FAQ.rst

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

docs/advanced/serial.rst

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

docs/advanced/task_management.rst

@@ -0,0 +1,89 @@
+.. _task_management:
+
+=================================
+Task Management
+=================================
+.. currentmodule:: qlib
+
+
+Introduction
+=============
+
+The `Workflow <../component/introduction.html>`_ part introduces how to run research workflow in a loosely-coupled way. But it can only execute one ``task`` when you use ``qrun``.
+To automatically generate and execute different tasks, ``Task Management`` provides a whole process including `Task Generating`_, `Task Storing`_, `Task Training`_ and `Task Collecting`_. 
+With this module, users can run their ``task`` automatically at different periods, in different losses, or even by different models.
+
+This whole process can be used in `Online Serving <../component/online.html>`_.
+
+An example of the entire process is shown `here <https://github.com/microsoft/qlib/tree/main/examples/model_rolling/task_manager_rolling.py>`_.
+
+Task Generating
+===============
+A ``task`` consists of `Model`, `Dataset`, `Record`, or anything added by users. 
+The specific task template can be viewed in 
+`Task Section <../component/workflow.html#task-section>`_.
+Even though the task template is fixed, users can customize their ``TaskGen`` to generate different ``task`` by task template.
+
+Here is the base class of ``TaskGen``:
+
+.. autoclass:: qlib.workflow.task.gen.TaskGen
+    :members:
+
+``Qlib`` provides a class `RollingGen <https://github.com/microsoft/qlib/tree/main/qlib/workflow/task/gen.py>`_ to generate a list of ``task`` of the dataset in different date segments.
+This class allows users to verify the effect of data from different periods on the model in one experiment. More information is `here <../reference/api.html#TaskGen>`_.
+
+Task Storing
+===============
+To achieve higher efficiency and the possibility of cluster operation, ``Task Manager`` will store all tasks in `MongoDB <https://www.mongodb.com/>`_.
+``TaskManager`` can fetch undone tasks automatically and manage the lifecycle of a set of tasks with error handling.
+Users **MUST** finish the configuration of `MongoDB <https://www.mongodb.com/>`_ when using this module.
+
+Users need to provide the MongoDB URL and database name for using ``TaskManager`` in `initialization <../start/initialization.html#Parameters>`_ or make a statement like this.
+
+    .. code-block:: python
+
+        from qlib.config import C
+        C["mongo"] = {
+            "task_url" : "mongodb://localhost:27017/", # your MongoDB url
+            "task_db_name" : "rolling_db" # database name
+        }
+
+.. autoclass:: qlib.workflow.task.manage.TaskManager
+    :members:
+
+More information of ``Task Manager`` can be found in `here <../reference/api.html#TaskManager>`_.
+
+Task Training
+===============
+After generating and storing those ``task``, it's time to run the ``task`` which is in the *WAITING* status.
+``Qlib`` provides a method called ``run_task`` to run those ``task`` in task pool, however, users can also customize how tasks are executed.
+An easy way to get the ``task_func`` is using ``qlib.model.trainer.task_train`` directly.
+It will run the whole workflow defined by ``task``, which includes *Model*, *Dataset*, *Record*.
+
+.. autofunction:: qlib.workflow.task.manage.run_task
+
+Meanwhile, ``Qlib`` provides a module called ``Trainer``. 
+
+.. autoclass:: qlib.model.trainer.Trainer
+    :members:
+
+``Trainer`` will train a list of tasks and return a list of model recorders.
+``Qlib`` offer two kinds of Trainer, TrainerR is the simplest way and TrainerRM is based on TaskManager to help manager tasks lifecycle automatically. 
+If you do not want to use ``Task Manager`` to manage tasks, then use TrainerR to train a list of tasks generated by ``TaskGen`` is enough.
+`Here <../reference/api.html#Trainer>`_ are the details about different ``Trainer``.
+
+Task Collecting
+===============
+To collect the results of ``task`` after training, ``Qlib`` provides `Collector <../reference/api.html#Collector>`_, `Group <../reference/api.html#Group>`_ and `Ensemble <../reference/api.html#Ensemble>`_ to collect the results in a readable, expandable and loosely-coupled way.
+
+`Collector <../reference/api.html#Collector>`_ can collect objects from everywhere and process them such as merging, grouping, averaging and so on. It has 2 step action including ``collect`` (collect anything in a dict) and ``process_collect`` (process collected dict).
+
+`Group <../reference/api.html#Group>`_ also has 2 steps including ``group`` (can group a set of object based on `group_func` and change them to a dict) and ``reduce`` (can make a dict become an ensemble based on some rule).
+For example: {(A,B,C1): object, (A,B,C2): object} ---``group``---> {(A,B): {C1: object, C2: object}} ---``reduce``---> {(A,B): object}
+
+`Ensemble <../reference/api.html#Ensemble>`_ can merge the objects in an ensemble. 
+For example: {C1: object, C2: object} ---``Ensemble``---> object
+
+So the hierarchy is ``Collector``'s second step corresponds to ``Group``. And ``Group``'s second step correspond to ``Ensemble``.
+
+For more information, please see `Collector <../reference/api.html#Collector>`_, `Group <../reference/api.html#Group>`_ and `Ensemble <../reference/api.html#Ensemble>`_, or the `example <https://github.com/microsoft/qlib/tree/main/examples/model_rolling/task_manager_rolling.py>`_.

docs/component/backtest.rst

@@ -30,7 +30,7 @@ The simple example of the default strategy is as follows.
 
     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)
+    report, positions = backtest(pred_score, topk=50, n_drop=0.5, limit_threshold=0.0095)
 
 To know more about backtesting with a specific ``Strategy``, please refer to `Portfolio Strategy <strategy.html>`_.
 

docs/component/data.rst

@@ -31,7 +31,7 @@ Qlib Format Data
 We've specially designed a data structure to manage financial data, please refer to the `File storage design section in Qlib paper <https://arxiv.org/abs/2009.11189>`_ for detailed information.
 Such data will be stored with filename suffix `.bin` (We'll call them `.bin` file, `.bin` format, or qlib format). `.bin` file is designed for scientific computing on finance data.
 
-``Qlib`` provides two different off-the-shelf dataset, which can be accessed through this `link <https://github.com/microsoft/qlib/blob/main/qlib/contrib/data/handler.py>`_:
+``Qlib`` provides two different off-the-shelf datasets, which can be accessed through this `link <https://github.com/microsoft/qlib/blob/main/qlib/contrib/data/handler.py>`_:
 
 ========================  =================  ================
 Dataset                   US Market          China Market
@@ -41,6 +41,7 @@ Alpha360                  √                  √
 Alpha158                  √                  √
 ========================  =================  ================
 
+Also, ``Qlib`` provides a high-frequency dataset. Users can run a high-frequency dataset example through this `link <https://github.com/microsoft/qlib/tree/main/examples/highfreq>`_.
 
 Qlib Format Dataset
 --------------------
@@ -48,31 +49,70 @@ Qlib Format Dataset
 
 .. code-block:: bash
 
+    # download 1d
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
 
+    # download 1min
+    python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/qlib_cn_1min --region cn --interval 1min
+
 In addition to China-Stock data, ``Qlib`` also includes a US-Stock dataset, which can be downloaded with the following command:
 
 .. code-block:: bash
 
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/us_data --region us
 
-After running the above command, users can find china-stock and us-stock data in ``Qlib`` format in the ``~/.qlib/csv_data/cn_data`` directory and ``~/.qlib/csv_data/us_data`` directory respectively.
+After running the above command, users can find china-stock and us-stock data in ``Qlib`` format in the ``~/.qlib/qlib_data/cn_data`` directory and ``~/.qlib/qlib_data/us_data`` directory respectively.
 
 ``Qlib`` also provides the scripts in ``scripts/data_collector`` to help users crawl the latest data on the Internet and convert it to qlib format.
 
 When ``Qlib`` is initialized with this dataset, users could build and evaluate their own models with it.  Please refer to `Initialization <../start/initialization.html>`_ for more details.
 
+Automatic update of daily frequency data
+----------------------------------------
+
+  **It is recommended that users update the data manually once (\-\-trading_date 2021-05-25) and then set it to update automatically.**
+
+  For more information refer to: `yahoo collector <https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#Automatic-update-of-daily-frequency-data>`_
+
+  - Automatic update of data to the "qlib" directory each trading day(Linux)
+      - use *crontab*: `crontab -e`
+      - set up timed tasks:
+
+        .. code-block:: bash
+
+            * * * * 1-5 python <script path> update_data_to_bin --qlib_data_1d_dir <user data dir>
+
+        - **script path**: *scripts/data_collector/yahoo/collector.py*
+
+  - Manual update of data
+
+      .. code-block:: bash
+
+        python scripts/data_collector/yahoo/collector.py update_data_to_bin --qlib_data_1d_dir <user data dir> --trading_date <start date> --end_date <end date>
+
+      - *trading_date*: start of trading day
+      - *end_date*: end of trading day(not included)
+
+
+
 Converting CSV Format into Qlib Format
 -------------------------------------------
 
 ``Qlib`` has provided the script ``scripts/dump_bin.py`` to convert **any** data in CSV format into `.bin` files (``Qlib`` format) as long as they are in the correct format.
 
-Users can download the demo china-stock data in CSV format as follows for reference to the CSV format.
+Besides downloading the prepared demo data, users could download demo data directly from the Collector as follows for reference to the CSV format.
+Here are some example:
 
-.. code-block:: bash
+for daily data:
+  .. code-block:: bash
 
     python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
 
+for 1min data:
+  .. code-block:: bash
+
+    python scripts/data_collector/yahoo/collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1min --region CN --start 2021-05-20 --end 2021-05-23 --delay 0.1 --interval 1min --limit_nums 10
+
 Users can also provide their own data in CSV format. However, the CSV data **must satisfies** following criterions:
 
 - CSV file is named after a specific stock *or* the CSV file includes a column of the stock name
@@ -139,6 +179,17 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
         The Restoration factor. Normally, ``factor = adjusted_price / original_price``, `adjusted price` reference: `split adjusted <https://www.investopedia.com/terms/s/splitadjusted.asp>`_
 
     In the convention of `Qlib` data processing, `open, close, high, low, volume, money and factor` will be set to NaN if the stock is suspended. 
+    If you want to use your own alpha-factor which can't be calculate by OCHLV, like PE, EPS and so on, you could add it to the CSV files with OHCLV together and then dump it to the Qlib format data.
+
+Stock Pool (Market)
+--------------------------------
+
+``Qlib`` defines `stock pool <https://github.com/microsoft/qlib/blob/main/examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml#L4>`_ as stock list and their date ranges. Predefined stock pools (e.g. csi300) may be imported as follows.
+
+.. code-block:: bash
+
+    python collector.py --index_name CSI300 --qlib_dir <user qlib data dir> --method parse_instruments
+
 
 Multiple Stock Modes
 --------------------------------
@@ -158,7 +209,7 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
 - If users use ``Qlib`` in china-stock mode, china-stock data is required. Users can use ``Qlib`` in china-stock mode according to the following steps:
     - Download china-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in china-stock mode
-        Supposed that users download their Qlib format data in the directory ``~/.qlib/csv_data/cn_data``. Users only need to initialize ``Qlib`` as follows.
+        Supposed that users download their Qlib format data in the directory ``~/.qlib/qlib_data/cn_data``. Users only need to initialize ``Qlib`` as follows.
         
         .. code-block:: python
 
@@ -167,9 +218,9 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
         
 
 - If users use ``Qlib`` in US-stock mode, US-stock data is required. ``Qlib`` also provides a script to download US-stock data. Users can use ``Qlib`` in US-stock mode according to the following steps:
-    - Download china-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
+    - Download us-stock in qlib format, please refer to section `Qlib Format Dataset <#qlib-format-dataset>`_.
     - Initialize ``Qlib`` in US-stock mode
-        Supposed that users prepare their Qlib format data in the directory ``~/.qlib/csv_data/us_data``. Users only need to initialize ``Qlib`` as follows.
+        Supposed that users prepare their Qlib format data in the directory ``~/.qlib/qlib_data/us_data``. Users only need to initialize ``Qlib`` as follows.
         
         .. code-block:: python
 
@@ -177,6 +228,11 @@ The `trade unit` defines the unit number of stocks can be used in a trade, and t
             qlib.init(provider_uri='~/.qlib/qlib_data/us_data', region=REG_US)
         
 
+.. note::
+
+    PRs for new data source are highly welcome! Users could commit the code to crawl data as a PR like `the examples here  <https://github.com/microsoft/qlib/tree/main/scripts>`_. And then we will use the code to create data cache on our server which other users could use directly.
+
+
 Data API
 ========================
 
@@ -213,6 +269,25 @@ Filter
     - `cross-sectional features filter` \: rule_expression = '$rank($close)<10'
     - `time-sequence features filter`: rule_expression = '$Ref($close, 3)>100'
 
+Here is a simple example showing how to use filter in a basic ``Qlib`` workflow configuration file:
+
+.. code-block:: yaml
+
+    filter: &filter
+        filter_type: ExpressionDFilter
+        rule_expression: "Ref($close, -2) / Ref($close, -1) > 1"
+        filter_start_time: 2010-01-01
+        filter_end_time: 2010-01-07
+        keep: False
+
+    data_handler_config: &data_handler_config
+        start_time: 2010-01-01
+        end_time: 2021-01-22
+        fit_start_time: 2010-01-01
+        fit_end_time: 2015-12-31
+        instruments: *market
+        filter_pipe: [*filter]
+
 To know more about ``Filter``, please refer to `Filter API <../reference/api.html#module-qlib.data.filter>`_.
 
 Reference
@@ -274,9 +349,10 @@ Here are some important interfaces that ``DataHandlerLP`` provides:
 .. autoclass:: qlib.data.dataset.handler.DataHandlerLP
     :members: __init__, fetch, get_cols
 
-If users want to load features and labels by config, users can inherit ``qlib.data.dataset.handler.ConfigDataHandler``, ``Qlib`` also provides some preprocess method in this subclass.
 
-If users want to use qlib data, `QLibDataHandler` is recommended. Users can inherit their custom class from `QLibDataHandler`, which is also a subclass of `ConfigDataHandler`.
+If users want to load features and labels by config, users can define a new handler and call the static method `parse_config_to_fields` of ``qlib.contrib.data.handler.Alpha158``.
+
+Also, users can pass ``qlib.contrib.data.processor.ConfigSectionProcessor`` that provides some preprocess methods for features defined by config into the new handler.
 
 
 Processor
@@ -313,7 +389,6 @@ Qlib provides implemented data handler `Alpha158`. The following example shows h
 
 .. note:: Users need to initialize ``Qlib`` with `qlib.init` first, please refer to `initialization <../start/initialization.html>`_.
 
-
 .. code-block:: Python
 
     import qlib
@@ -340,6 +415,9 @@ Qlib provides implemented data handler `Alpha158`. The following example shows h
         # fetch all the features
         print(h.fetch(col_set="feature"))
 
+
+.. note:: In the ``Alpha158``, ``Qlib`` uses the label `Ref($close, -2)/Ref($close, -1) - 1` that means the change from T+1 to T+2, rather than `Ref($close, -1)/$close - 1`, of which the reason is that when getting the T day close price of a china stock, the stock can be bought on T+1 day and sold on T+2 day.
+
 API
 ---------
 
@@ -364,8 +442,7 @@ The ``DatasetH`` class is the `dataset` with `Data Handler`. Here is the most im
 API
 ---------
 
-To know more about ``Dataset``, please refer to `Dataset API <../reference/api.html#module-qlib.data.dataset.__init__>`_.
-
+To know more about ``Dataset``, please refer to `Dataset API <../reference/api.html#dataset>`_.
 
 
 Cache

docs/component/highfreq.rst

@@ -0,0 +1,120 @@
+.. _highfreq:
+
+============================================
+Design of hierarchical order execution framework
+============================================
+.. currentmodule:: qlib
+
+Introduction
+===================
+
+In order to support reinforcement learning algorithms for high-frequency trading, a corresponding framework is required. None of the publicly available high-frequency trading frameworks now consider multi-layer trading mechanisms, and the currently designed algorithms cannot directly use existing frameworks.
+In addition to supporting the basic intraday multi-layer trading, the linkage with the day-ahead strategy is also a factor that affects the performance evaluation of the strategy. Different day strategies generate different order distributions and different patterns on different stocks. To verify that high-frequency trading strategies perform well on real trading orders, it is necessary to support day-frequency and high-frequency multi-level linkage trading. In addition to more accurate backtesting of high-frequency trading algorithms, if the distribution of day-frequency orders is considered when training a high-frequency trading model, the algorithm can also be optimized more for product-specific day-frequency orders.
+Therefore, innovation in the high-frequency trading framework is necessary to solve the various problems mentioned above, for which we designed a hierarchical order execution framework that can link daily-frequency and intra-day trading at different granularities.
+
+.. image:: ../_static/img/framework.svg
+
+The design of the framework is shown in the figure above. At each layer consists of Trading Agent and Execution Env. The Trading Agent has its own data processing module (Information Extractor), forecasting module (Forecast Model) and decision generator (Decision Generator). The trading algorithm generates the corresponding 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. Here the frequency of trading algorithm, decision content and execution environment can be customized by users (e.g. intra-day 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 hierarchical order execution framework is user-defined in terms of hierarchy division and decision frequency, making it easy for users to explore the effects of combining different levels of trading algorithms and breaking down the barriers between different levels of trading algorithm optimization.
+In addition to the innovation in the framework, the hierarchical order execution framework also takes into account various details of the real backtesting environment, minimizing the differences with the final real environment as much as possible. At the same time, the framework is designed to unify the interface between online and offline (e.g. data pre-processing level supports using the same set of code to process both offline and online data) to reduce the cost of strategy go-live as much as possible.
+
+Prepare Data
+===================
+.. _data:: ../../examples/highfreq/README.md
+
+
+Example
+===========================
+
+Here is an example of highfreq execution.
+
+.. code-block:: python
+
+    import qlib
+    # init qlib
+    provider_uri_day = "~/.qlib/qlib_data/cn_data"
+    provider_uri_1min = "~/.qlib/qlib_data/cn_data_1min"
+    provider_uri_map = {"1min": provider_uri_1min, "day": provider_uri_day}
+    qlib.init(provider_uri=provider_uri_day, expression_cache=None, dataset_cache=None)
+
+    # data freq and backtest time
+    freq = "1min"
+    inst_list = D.list_instruments(D.instruments("all"), as_list=True)
+    start_time = "2020-01-01"
+    start_time = "2020-01-31"
+
+When initializing qlib, if the default data is used, then both daily and minute frequency data need to be passed in.
+
+.. code-block:: python
+
+    # random order strategy config
+    strategy_config = {
+        "class": "RandomOrderStrategy",
+        "module_path": "qlib.contrib.strategy.rule_strategy",
+        "kwargs": {
+            "trade_range": TradeRangeByTime("9:30", "15:00"),
+            "sample_ratio": 1.0,
+            "volume_ratio": 0.01,
+            "market": market,
+        },
+    }
+
+.. code-block:: python
+    # backtest config
+    backtest_config = {
+        "start_time": start_time,
+        "end_time": end_time,
+        "account": 100000000,
+        "benchmark": None,
+        "exchange_kwargs": {
+            "freq": freq,
+            "limit_threshold": 0.095,
+            "deal_price": "close",
+            "open_cost": 0.0005,
+            "close_cost": 0.0015,
+            "min_cost": 5,
+            "codes": market,
+        },
+        "pos_type": "InfPosition",  # Position with infinitive position
+    }
+
+please refer to "../../qlib/backtest".
+
+.. code-block:: python
+    # excutor config
+    executor_config = {
+        "class": "NestedExecutor",
+        "module_path": "qlib.backtest.executor",
+        "kwargs": {
+            "time_per_step": "day",
+            "inner_executor": {
+                "class": "SimulatorExecutor",
+                "module_path": "qlib.backtest.executor",
+                "kwargs": {
+                    "time_per_step": freq,
+                    "generate_portfolio_metrics": True,
+                    "verbose": False,
+                    # "verbose": True,
+                    "indicator_config": {
+                        "show_indicator": False,
+                    },
+                },
+            },
+            "inner_strategy": {
+                "class": "TWAPStrategy",
+                "module_path": "qlib.contrib.strategy.rule_strategy",
+            },
+            "track_data": True,
+            "generate_portfolio_metrics": True,
+            "indicator_config": {
+                "show_indicator": True,
+            },
+        },
+    }
+
+NestedExecutor represents not the innermost layer, the initialization parameters should contain inner_executor and inner_strategy. simulatorExecutor represents the current excutor is the innermost layer, the innermost strategy used here is the TWAP strategy, the framework currently also supports the VWAP strategy
+
+.. code-block:: python
+    # backtest
+    portfolio_metrics_dict, indicator_dict = backtest(executor=executor_config, strategy=strategy_config, **backtest_config)
+
+The metrics of backtest are included in the portfolio_metrics_dict and indicator_dict.

docs/component/online.rst

@@ -0,0 +1,48 @@
+.. _online:
+
+=================================
+Online Serving
+=================================
+.. currentmodule:: qlib
+
+
+Introduction
+=============
+
+.. image:: ../_static/img/online_serving.png
+    :align: center
+
+
+In addition to backtesting, one way to test a model is effective is to make predictions in real market conditions or even do real trading based on those predictions.
+``Online Serving`` is a set of modules for online models using the latest data,
+which including `Online Manager <#Online Manager>`_, `Online Strategy <#Online Strategy>`_, `Online Tool <#Online Tool>`_, `Updater <#Updater>`_. 
+
+`Here <https://github.com/microsoft/qlib/tree/main/examples/online_srv>`_ are several examples for reference, which demonstrate different features of ``Online Serving``.
+If you have many models or `task` needs to be managed, please consider `Task Management <../advanced/task_management.html>`_.
+The `examples <https://github.com/microsoft/qlib/tree/main/examples/online_srv>`_ are based on some components in `Task Management <../advanced/task_management.html>`_ such as ``TrainerRM`` or ``Collector``.
+
+**NOTE**: User should keep his data source updated to support online serving. For example, Qlib provides `a batch of scripts <https://github.com/microsoft/qlib/blob/main/scripts/data_collector/yahoo/README.md#automatic-update-of-daily-frequency-datafrom-yahoo-finance>`_ to help users update Yahoo daily data.
+
+Online Manager
+=============
+
+.. automodule:: qlib.workflow.online.manager
+    :members:
+
+Online Strategy
+=============
+
+.. automodule:: qlib.workflow.online.strategy
+    :members:
+
+Online Tool
+=============
+
+.. automodule:: qlib.workflow.online.utils
+    :members:
+
+Updater
+=============
+
+.. automodule:: qlib.workflow.online.update
+    :members:

docs/component/recorder.rst

@@ -34,6 +34,7 @@ Here is a general view of the structure of the system:
             - Recorder 2
             - ...
         - ...
+        
 This experiment management system defines a set of interface and provided a concrete implementation ``MLflowExpManager``, which is based on the machine learning platform: ``MLFlow`` (`link <https://mlflow.org/>`_). 
 
 If users set the implementation of ``ExpManager`` to be ``MLflowExpManager``, they can use the command `mlflow ui` to visualize and check the experiment results. For more information, pleaes refer to the related documents `here <https://www.mlflow.org/docs/latest/cli.html#mlflow-ui>`_.
@@ -94,6 +95,51 @@ The ``RecordTemp`` class is a class that enables generate experiment results suc
 
 - ``SignalRecord``: This class generates the `prediction` results of the model.
 - ``SigAnaRecord``: This class generates the `IC`, `ICIR`, `Rank IC` and `Rank ICIR` of the model.
+
+Here is a simple example of what is done in ``SigAnaRecord``, which users can refer to if they want to calculate IC, Rank IC, Long-Short Return with their own prediction and label.
+
+.. code-block:: Python
+
+    from qlib.contrib.eva.alpha import calc_ic, calc_long_short_return
+
+    ic, ric = calc_ic(pred.iloc[:, 0], label.iloc[:, 0])
+    long_short_r, long_avg_r = calc_long_short_return(pred.iloc[:, 0], label.iloc[:, 0])
+
 - ``PortAnaRecord``: This class generates the results of `backtest`. The detailed information about `backtest` as well as the available `strategy`, users can refer to `Strategy <../component/strategy.html>`_ and `Backtest <../component/backtest.html>`_.
 
+Here is a simple exampke of what is done in ``PortAnaRecord``, which users can refer to if they want to do backtest based on their own prediction and label.
+
+.. code-block:: Python
+
+    from qlib.contrib.strategy.strategy import TopkDropoutStrategy
+    from qlib.contrib.evaluate import (
+        backtest as normal_backtest,
+        risk_analysis,
+    )
+
+    # backtest
+    STRATEGY_CONFIG = {
+        "topk": 50,
+        "n_drop": 5,
+    }
+    BACKTEST_CONFIG = {
+        "limit_threshold": 0.095,
+        "account": 100000000,
+        "benchmark": BENCHMARK,
+        "deal_price": "close",
+        "open_cost": 0.0005,
+        "close_cost": 0.0015,
+        "min_cost": 5,
+    }
+    
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
+    report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
+
+    # analysis
+    analysis = dict()
+    analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+    analysis["excess_return_with_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"] - report_normal["cost"])
+    analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+    print(analysis_df)
+
 For more information about the APIs, please refer to `Record Template API <../reference/api.html#module-qlib.workflow.record_temp>`_.

docs/component/report.rst

@@ -101,7 +101,7 @@ Graphical Result
     - Axis Y: 
         - `ic`
             The `Pearson correlation coefficient` series between `label` and `prediction score`.
-            In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. Please refer to `Data Featrue <data.html#feature>`_ for more details.
+            In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. Please refer to `Data Feature <data.html#feature>`_ for more details.
                 
         - `rank_ic`
             The `Spearman's rank correlation coefficient` series between `label` and `prediction score`.

docs/component/strategy.rst

@@ -93,7 +93,6 @@ Usage & Example
         "n_drop": 5,
     }
     BACKTEST_CONFIG = {
-        "verbose": False,
         "limit_threshold": 0.095,
         "account": 100000000,
         "benchmark": BENCHMARK,
@@ -111,8 +110,6 @@ Usage & Example
         pred_score, strategy=strategy, **BACKTEST_CONFIG
     )
 
-Also, the above example has been given in ``examples/train_backtest_analyze.ipynb``.
-
 To know more about the `prediction score` `pred_score` output by ``Forecast Model``, please refer to `Forecast Model: Model Training & Prediction <model.html>`_.
 
 To know more about ``Intraday Trading``, please refer to `Intraday Trading: Model&Strategy Testing <backtest.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.
 
@@ -142,7 +144,7 @@ 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 +243,10 @@ 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

@@ -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
@@ -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

@@ -42,6 +42,7 @@ Document Structure
    Intraday Trading: Model&Strategy Testing <component/backtest.rst>
    Qlib Recorder: Experiment Management <component/recorder.rst>
    Analysis: Evaluation & Results Analysis <component/report.rst>
+   Online Serving: Online Management & Strategy & Tool <component/online.rst>
 
 .. toctree::
    :maxdepth: 3
@@ -49,6 +50,8 @@ Document Structure
    
    Building Formulaic Alphas <advanced/alpha.rst>
    Online & Offline mode <advanced/server.rst>
+   Serialization <advanced/serial.rst>
+   Task Management <advanced/task_management.rst>
 
 .. toctree::
    :maxdepth: 3

docs/introduction/introduction.rst

@@ -15,7 +15,7 @@ With ``Qlib``, users can easily try their ideas to create better Quant investmen
 Framework
 ===================
    
-.. image:: ../_static/img/framework.png
+.. image:: ../_static/img/framework.svg
     :align: center
 
 

docs/reference/api.rst

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

docs/start/initialization.rst

@@ -75,3 +75,15 @@ Besides `provider_uri` and `region`, `qlib.init` has other parameters. The follo
                 "default_exp_name": "Experiment",
             }
         })
+- `mongo`
+    Type: dict, optional parameter, the setting of `MongoDB <https://www.mongodb.com/>`_ which will be used in some features such as `Task Management <../advanced/task_management.html>`_, with high performance and clustered processing. 
+    Users need to follow the steps in  `installation <https://www.mongodb.com/try/download/community>`_  to install MongoDB firstly and then access it via a URI.
+    Users can access mongodb with credential by setting "task_url"  to a string like `"mongodb://%s:%s@%s" % (user, pwd, host + ":" + port)`.
+
+    .. code-block:: Python
+
+        # For example, you can initialize qlib below
+        qlib.init(provider_uri=provider_uri, region=REG_CN, mongo={
+            "task_url": "mongodb://localhost:27017/",  # your mongo url
+            "task_db_name": "rolling_db", # the database name of Task Management
+        })

docs/start/integration.rst

@@ -82,7 +82,7 @@ The Custom models need to inherit `qlib.model.base.Model <../reference/api.html#
             return pd.Series(self.model.predict(x_test.values), index=x_test.index)
 
 - Override the `finetune` method (Optional)
-    - This method is optional to the users, and when users one to use this method on their own models, they should inherit the ``ModelFT`` base class, which includes the interface of `finetune`.
+    - This method is optional to the users. When users want to use this method on their own models, they should inherit the ``ModelFT`` base class, which includes the interface of `finetune`.
     - The parameters must include the parameter `dataset`.
     - Code Example: In the following example, users will use `LightGBM` as the model and finetune it.
     .. code-block:: Python

examples/benchmarks/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/workflow_config_catboost_Alpha158.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360.yaml

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

examples/benchmarks/DoubleEnsemble/README.md

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

examples/benchmarks/DoubleEnsemble/requirements.txt

@@ -0,0 +1,3 @@
+pandas==1.1.2
+numpy==1.17.4
+lightgbm==3.1.0

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml

@@ -0,0 +1,97 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 28
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha158
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml

@@ -0,0 +1,104 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors: []
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 136
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/GATs/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/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/workflow_config_lstm_Alpha158.yaml

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

examples/benchmarks/LSTM/workflow_config_lstm_Alpha360.yaml

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

examples/benchmarks/LightGBM/features_resample_N.py

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

examples/benchmarks/LightGBM/features_sample.py

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

examples/benchmarks/LightGBM/multi_freq_handler.py

@@ -0,0 +1,135 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+import pandas as pd
+
+from qlib.data.dataset.loader import QlibDataLoader
+from qlib.contrib.data.handler import DataHandlerLP, _DEFAULT_LEARN_PROCESSORS, check_transform_proc
+
+
+class Avg15minLoader(QlibDataLoader):
+    def load(self, instruments=None, start_time=None, end_time=None) -> pd.DataFrame:
+        df = super(Avg15minLoader, self).load(instruments, start_time, end_time)
+        if self.is_group:
+            # feature_day(day freq) and feature_15min(1min freq, Average every 15 minutes) renamed feature
+            df.columns = df.columns.map(lambda x: ("feature", x[1]) if x[0].startswith("feature") else x)
+        return df
+
+
+class Avg15minHandler(DataHandlerLP):
+    def __init__(
+        self,
+        instruments="csi500",
+        start_time=None,
+        end_time=None,
+        freq="day",
+        infer_processors=[],
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
+        fit_start_time=None,
+        fit_end_time=None,
+        process_type=DataHandlerLP.PTYPE_A,
+        filter_pipe=None,
+        inst_processor=None,
+        **kwargs,
+    ):
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
+        data_loader = Avg15minLoader(
+            config=self.loader_config(), filter_pipe=filter_pipe, freq=freq, inst_processor=inst_processor
+        )
+        super().__init__(
+            instruments=instruments,
+            start_time=start_time,
+            end_time=end_time,
+            data_loader=data_loader,
+            infer_processors=infer_processors,
+            learn_processors=learn_processors,
+            process_type=process_type,
+        )
+
+    def loader_config(self):
+
+        # Results for dataset: df: pd.DataFrame
+        #   len(df.columns) == 6 + 6 * 16, len(df.index.get_level_values(level="datetime").unique()) == T
+        #   df.columns: close0, close1, ..., close16, open0, ..., open16, ..., vwap16
+        #       freq == day:
+        #           close0, open0, low0, high0, volume0, vwap0
+        #       freq == 1min:
+        #           close1, ..., close16, ..., vwap1, ..., vwap16
+        #   df.index.name == ["datetime", "instrument"]: pd.MultiIndex
+        # Example:
+        #                          feature                        ...                  label
+        #                           close0      open0       low0  ... vwap1 vwap16    LABEL0
+        # datetime   instrument                                   ...
+        # 2020-10-09 SH600000    11.794546  11.819587  11.769505  ...   NaN    NaN -0.005214
+        # 2020-10-15 SH600000    12.044961  11.944795  11.932274  ...   NaN    NaN -0.007202
+        # ...                          ...        ...        ...  ...   ...    ...       ...
+        # 2021-05-28 SZ300676     6.369684   6.495406   6.306568  ...   NaN    NaN -0.001321
+        # 2021-05-31 SZ300676     6.601626   6.465643   6.465130  ...   NaN    NaN -0.023428
+
+        # features day: len(columns) == 6, freq = day
+        # $close is the closing price of the current trading day:
+        #   if the user needs to get the `close` before the last T days, use Ref($close, T-1), for example:
+        #                                    $close  Ref($close, 1)  Ref($close, 2)  Ref($close, 3)  Ref($close, 4)
+        #         instrument datetime
+        #         SH600519   2021-06-01  244.271530
+        #                    2021-06-02  242.205917      244.271530
+        #                    2021-06-03  242.229889      242.205917      244.271530
+        #                    2021-06-04  245.421524      242.229889      242.205917      244.271530
+        #                    2021-06-07  247.547089      245.421524      242.229889      242.205917      244.271530
+
+        # WARNING: Ref($close, N), if N == 0, Ref($close, N) ==> $close
+
+        fields = ["$close", "$open", "$low", "$high", "$volume", "$vwap"]
+        # names: close0, open0, ..., vwap0
+        names = list(map(lambda x: x.strip("$") + "0", fields))
+
+        config = {"feature_day": (fields, names)}
+
+        # features 15min: len(columns) == 6 * 16, freq = 1min
+        #   $close is the closing price of the current trading day:
+        #       if the user gets 'close' for the i-th 15min of the last T days, use `Ref(Mean($close, 15), (T-1) * 240 + i * 15)`, for example:
+        #                                    Ref(Mean($close, 15), 225)  Ref(Mean($close, 15), 465)  Ref(Mean($close, 15), 705)
+        #             instrument datetime
+        #             SH600519   2021-05-31                  241.769897                  243.077942                  244.712997
+        #                        2021-06-01                  244.271530                  241.769897                  243.077942
+        #                        2021-06-02                  242.205917                  244.271530                  241.769897
+
+        # WARNING: Ref(Mean($close, 15), N), if N == 0, Ref(Mean($close, 15), N) ==> Mean($close, 15)
+
+        # Results of the current script:
+        #   time:   09:00 --> 09:14,            ..., 14:45 --> 14:59
+        #   fields: Ref(Mean($close, 15), 225), ..., Mean($close, 15)
+        #   name:   close1,                     ..., close16
+        #
+
+        # Expression description: take close as an example
+        #   Mean($close, 15) ==> df["$close"].rolling(15, min_periods=1).mean()
+        #   Ref(Mean($close, 15), 15) ==> df["$close"].rolling(15, min_periods=1).mean().shift(15)
+
+        #   NOTE: The last data of each trading day, which is the average of the i-th 15 minutes
+
+        # Average:
+        #   Average of the i-th 15-minute period of each trading day: 1 <= i <= 250 // 16
+        #       Avg(15minutes): Ref(Mean($close, 15), 240 - i * 15)
+        #
+        #   Average of the first 15 minutes of each trading day; i = 1
+        #       Avg(09:00 --> 09:14), df.index.loc["09:14"]: Ref(Mean($close, 15), 240- 1 * 15) ==> Ref(Mean($close, 15), 225)
+        #   Average of the last 15 minutes of each trading day; i = 16
+        #       Avg(14:45 --> 14:59), df.index.loc["14:59"]: Ref(Mean($close, 15), 240 - 16 * 15) ==> Ref(Mean($close, 15), 0) ==> Mean($close, 15)
+
+        # 15min resample to day
+        #   df.resample("1d").last()
+        tmp_fields = []
+        tmp_names = []
+        for i, _f in enumerate(fields):
+            _fields = [f"Ref(Mean({_f}, 15), {j * 15})" for j in range(1, 240 // 15)]
+            _names = [f"{names[i][:-1]}{int(names[i][-1])+j}" for j in range(240 // 15 - 1, 0, -1)]
+            _fields.append(f"Mean({_f}, 15)")
+            _names.append(f"{names[i][:-1]}{int(names[i][-1])+240 // 15}")
+            tmp_fields += _fields
+            tmp_names += _names
+        config["feature_15min"] = (tmp_fields, tmp_names)
+        # label
+        config["label"] = (["Ref($close, -2)/Ref($close, -1) - 1"], ["LABEL0"])
+        return config

examples/benchmarks/LightGBM/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

@@ -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
+    instruments: *market
+    data_loader:
+        class: QlibDataLoader
+        kwargs:
+            config:
+                feature:
+                    - ["Resi($close, 15)/$close", "Std(Abs($close/Ref($close, 1)-1)*$volume, 5)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, 5)+1e-12)", "Rsquare($close, 5)", "($high-$low)/$open", "Rsquare($close, 10)", "Corr($close, Log($volume+1), 5)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 5)", "Corr($close, Log($volume+1), 10)", "Rsquare($close, 20)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 60)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 10)", "Corr($close, Log($volume+1), 20)", "(Less($open, $close)-$low)/$open"]
+                    - ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"]
+                label:
+                    - ["Ref($close, -2)/Ref($close, -1) - 1"]
+                    - ["LABEL0"]
+            freq: day
+
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSZScoreNorm
+          kwargs:
+            fields_group: label
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy
+        kwargs:
+            signal:
+                - <MODEL> 
+                - <DATASET>
+            topk: 50
+            n_drop: 5
+    backtest:
+        start_time: 2017-01-01
+        end_time: 2020-08-01
+        account: 100000000
+        benchmark: *benchmark
+        exchange_kwargs:
+            limit_threshold: 0.095
+            deal_price: close
+            open_cost: 0.0005
+            close_cost: 0.0015
+            min_cost: 5
+task:
+    model:
+        class: 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: DataHandlerLP
+                module_path: qlib.data.dataset.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            model: <MODEL>
+            dataset: <DATASET>
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/LightGBM/workflow_config_lightgbm_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

@@ -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: LinearModel
@@ -57,16 +62,18 @@ 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/requirements.txt

@@ -0,0 +1,3 @@
+numpy==1.17.4
+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/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

@@ -1,35 +1,60 @@
 # Benchmarks Performance
 
-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.
+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/qlib_cn_1d --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 |
 
 ## 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 |
-| TabNet with pretrain (Sercan O. Arikm et al) | Alpha158 | 0.0344±0.00|0.205±0.11|0.0398±0.00 |0.3479±0.01|0.0827±0.02|1.1141±0.32 |-0.0925±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 |
+
+| Model Name                               | Dataset                             | IC          | ICIR        | Rank IC     | Rank ICIR   | Annualized Return | Information Ratio | Max Drawdown |
+|------------------------------------------|-------------------------------------|-------------|-------------|-------------|-------------|-------------------|-------------------|--------------|
+| 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 |
+| 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 |
+| 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 |
+| 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
 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/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==1.17.4
+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

examples/benchmarks/TFT/README.md

@@ -8,7 +8,7 @@
 Users can follow the ``workflow_by_code_tft.py`` to run the benchmark. 
 
 ### Notes
-1. Please be **aware** that this script can only support `Python 3.5 - 3.8`.
+1. Please be **aware** that this script can only support `Python 3.6 - 3.7`.
 2. If the CUDA version on your machine is not 10.0, please remember to run the following commands `conda install anaconda cudatoolkit=10.0` and `conda install cudnn` on your machine.
 3. The model must run in GPU, or an error will be raised.
 4. New datasets should be registered in ``data_formatters``, for detail please visit the source.

examples/benchmarks/TFT/data_formatters/base.py

@@ -132,7 +132,7 @@ class GenericDataFormatter(abc.ABC):
         return -1, -1
 
     def get_column_definition(self):
-        """"Returns formatted column definition in order expected by the TFT."""
+        """Returns formatted column definition in order expected by the TFT."""
 
         column_definition = self._column_definition
 

examples/benchmarks/TFT/data_formatters/qlib_Alpha158.py

@@ -195,7 +195,8 @@ class Alpha158Formatter(GenericDataFormatter):
 
         for col in column_names:
             if col not in {"forecast_time", "identifier"}:
-                output[col] = self._target_scaler.inverse_transform(predictions[col])
+                # Using [col] is for aligning with the format when fitting
+                output[col] = self._target_scaler.inverse_transform(predictions[[col]])
 
         return output
 

examples/benchmarks/TFT/requirements.txt

@@ -1,3 +1,2 @@
 tensorflow-gpu==1.15.0
-numpy == 1.19.4
-pandas==1.1.0
+pandas==1.1.0

examples/benchmarks/TFT/tft.py

@@ -1,6 +1,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
+from pathlib import Path
+from typing import Union
 import numpy as np
 import pandas as pd
 import tensorflow.compat.v1 as tf
@@ -243,7 +245,7 @@ class TFTModel(ModelFT):
             #    extract_numerical_data(targets), extract_numerical_data(p90_forecast),
             #    0.9)
             tf.keras.backend.set_session(default_keras_session)
-        print("Training completed.".format(dte.datetime.now()))
+        print("Training completed at {}.".format(dte.datetime.now()))
         # ===========================Training Process===========================
 
     def predict(self, dataset):
@@ -289,3 +291,31 @@ class TFTModel(ModelFT):
             dataset for finetuning
         """
         pass
+
+    def to_pickle(self, path: Union[Path, str]):
+        """
+        Tensorflow model can't be dumped directly.
+        So the data should be save seperatedly
+
+        **TODO**: Please implement the function to load the files
+
+        Parameters
+        ----------
+        path : Union[Path, str]
+            the target path to be dumped
+        """
+        # FIXME: implementing saving tensorflow models
+        # save tensorflow model
+        # path = Path(path)
+        # path.mkdir(parents=True)
+        # self.model.save(path)
+
+        # save qlib model wrapper
+        drop_attrs = ["model", "tf_graph", "sess", "data_formatter"]
+        orig_attr = {}
+        for attr in drop_attrs:
+            orig_attr[attr] = getattr(self, attr)
+            setattr(self, attr, None)
+        super(TFTModel, self).to_pickle(path)
+        for attr in drop_attrs:
+            setattr(self, attr, orig_attr[attr])

examples/benchmarks/TFT/workflow_config_tft_Alpha158.yaml

@@ -14,19 +14,24 @@ 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: TFTModel
@@ -46,7 +51,9 @@ 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/TRA/README.md

@@ -0,0 +1,93 @@
+# Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport
+
+Temporal Routing Adaptor (TRA) is designed to capture multiple trading patterns in the stock market data. Please refer to [our paper](http://arxiv.org/abs/2106.12950) for more details.
+
+If you find our work useful in your research, please cite:
+```
+@inproceedings{HengxuKDD2021,
+ author = {Hengxu Lin and Dong Zhou and Weiqing Liu and Jiang Bian},
+ title = {Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport},
+ booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},
+ series = {KDD '21},
+ year = {2021},
+ publisher = {ACM},
+}
+
+@article{yang2020qlib,
+  title={Qlib: An AI-oriented Quantitative Investment Platform},
+  author={Yang, Xiao and Liu, Weiqing and Zhou, Dong and Bian, Jiang and Liu, Tie-Yan},
+  journal={arXiv preprint arXiv:2009.11189},
+  year={2020}
+}
+```
+
+## Usage (Recommended)
+
+**Update**: `TRA` has been moved to `qlib.contrib.model.pytorch_tra` to support other `Qlib` components like  `qlib.workflow` and `Alpha158/Alpha360` dataset.
+
+Please follow the official [doc](https://qlib.readthedocs.io/en/latest/component/workflow.html) to use `TRA` with `workflow`. Here we also provide several example config files:
+
+- `workflow_config_tra_Alpha360.yaml`: running `TRA` with `Alpha360` dataset
+- `workflow_config_tra_Alpha158.yaml`: running `TRA` with `Alpha158` dataset (with feature subsampling)
+- `workflow_config_tra_Alpha158_full.yaml`: running `TRA` with `Alpha158` dataset (without feature subsampling)
+
+The performances of `TRA` are reported in [Benchmarks](https://github.com/microsoft/qlib/tree/main/examples/benchmarks).
+
+## Usage (Not Maintained)
+
+This section is used to reproduce the results in the paper.
+
+### Running
+
+We attach our running scripts for the paper in `run.sh`.
+
+And here are two ways to run the model:
+
+* Running from scripts with default parameters
+
+  You can directly run from Qlib command `qrun`:
+  ```
+  qrun configs/config_alstm.yaml
+  ```
+
+* Running from code with self-defined parameters
+
+  Setting different parameters is also allowed. See codes in `example.py`:
+  ```
+  python example.py --config_file configs/config_alstm.yaml
+  ```
+
+Here we trained TRA on a pretrained backbone model. Therefore we run `*_init.yaml` before TRA's scipts.
+
+### Results
+
+After running the scripts, you can find result files in path `./output`:
+
+* `info.json` - config settings and result metrics.
+* `log.csv` - running logs.
+* `model.bin` - the model parameter dictionary.
+* `pred.pkl` - the prediction scores and output for inference.
+
+Evaluation metrics reported in the paper:
+This result is generated by qlib==0.7.1.
+
+| Methods | MSE| MAE| IC | ICIR | AR | AV | SR | MDD |
+|-------|-------|------|-----|-----|-----|-----|-----|-----|
+|Linear|0.163|0.327|0.020|0.132|-3.2%|16.8%|-0.191|32.1%|
+|LightGBM|0.160(0.000)|0.323(0.000)|0.041|0.292|7.8%|15.5%|0.503|25.7%|
+|MLP|0.160(0.002)|0.323(0.003)|0.037|0.273|3.7%|15.3%|0.264|26.2%|
+|SFM|0.159(0.001)	|0.321(0.001)	|0.047	|0.381	|7.1%	|14.3%	|0.497	|22.9%|
+|ALSTM|0.158(0.001)	|0.320(0.001)	|0.053	|0.419	|12.3%	|13.7%	|0.897	|20.2%|
+|Trans.|0.158(0.001)	|0.322(0.001)	|0.051	|0.400	|14.5%	|14.2%	|1.028	|22.5%|
+|ALSTM+TS|0.160(0.002)	|0.321(0.002)	|0.039	|0.291	|6.7%	|14.6%	|0.480|22.3%|
+|Trans.+TS|0.160(0.004)	|0.324(0.005)	|0.037	|0.278	|10.4%	|14.7%	|0.722	|23.7%|
+|ALSTM+TRA(Ours)|0.157(0.000)	|0.318(0.000)	|0.059	|0.460	|12.4%	|14.0%	|0.885	|20.4%|
+|Trans.+TRA(Ours)|0.157(0.000)	|0.320(0.000)	|0.056	|0.442	|16.1%	|14.2%	|1.133	|23.1%|
+
+A more detailed demo for our experiment results in the paper can be found in `Report.ipynb`.
+
+## Common Issues
+
+For help or issues using TRA, please submit a GitHub issue.
+
+Sometimes we might encounter situation where the loss is `NaN`, please check the `epsilon` parameter in the sinkhorn algorithm, adjusting the `epsilon` according to input's scale is important.

examples/benchmarks/TRA/configs/config_alstm.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 256
+  num_layers: 2
+  num_heads: 2
+  use_attn: True
+  dropout: 0.1
+
+num_states: &num_states 1
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0002
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/alstm
+      model_type: LSTM
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 1.0
+      rho: 0.99
+      freeze_model: False
+      model_init_state: 
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 1024

examples/benchmarks/TRA/configs/config_alstm_tra.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 256
+  num_layers: 2
+  num_heads: 2
+  use_attn: True
+  dropout: 0.1
+
+num_states: &num_states 10
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0001
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/alstm_tra
+      model_type: LSTM
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 2.0
+      rho: 0.99
+      freeze_model: True
+      model_init_state: output/test/alstm_tra_init/model.bin
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 1024

examples/benchmarks/TRA/configs/config_alstm_tra_init.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 256
+  num_layers: 2
+  num_heads: 2
+  use_attn: True
+  dropout: 0.1
+
+num_states: &num_states 3
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0002
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/alstm_tra_init
+      model_type: LSTM
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 1.0
+      rho: 0.99
+      freeze_model: False
+      model_init_state: 
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 512

examples/benchmarks/TRA/configs/config_transformer.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 64
+  num_layers: 2
+  num_heads: 4
+  use_attn: False
+  dropout: 0.1
+
+num_states: &num_states 1
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0002
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/transformer
+      model_type: Transformer
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 1.0
+      rho: 0.99
+      freeze_model: False
+      model_init_state: 
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 1024

examples/benchmarks/TRA/configs/config_transformer_tra.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 64
+  num_layers: 2
+  num_heads: 4
+  use_attn: False
+  dropout: 0.1
+
+num_states: &num_states 3
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0005
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/transformer_tra
+      model_type: Transformer
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 1.0
+      rho: 0.99
+      freeze_model: True
+      model_init_state: output/test/transformer_tra_init/model.bin
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 512

examples/benchmarks/TRA/configs/config_transformer_tra_init.yaml

@@ -0,0 +1,63 @@
+qlib_init:
+  provider_uri: "~/.qlib/qlib_data/cn_data"
+  region: cn
+
+data_loader_config: &data_loader_config
+  class: StaticDataLoader
+  module_path: qlib.data.dataset.loader
+  kwargs:
+    config:
+      feature: data/feature.pkl
+      label: data/label.pkl
+
+model_config: &model_config
+  input_size: 16
+  hidden_size: 64
+  num_layers: 2
+  num_heads: 4
+  use_attn: False
+  dropout: 0.1
+
+num_states: &num_states 3
+
+tra_config: &tra_config
+  num_states: *num_states
+  hidden_size: 16
+  tau: 1.0
+  src_info: LR_TPE
+
+task:
+  model:
+    class: TRAModel
+    module_path: src/model.py
+    kwargs:
+      lr: 0.0002
+      n_epochs: 500
+      max_steps_per_epoch: 100
+      early_stop: 20
+      seed: 1000
+      logdir: output/test/transformer_tra_init
+      model_type: Transformer
+      model_config: *model_config
+      tra_config: *tra_config
+      lamb: 1.0
+      rho: 0.99
+      freeze_model: False
+      model_init_state: 
+  dataset:
+    class: MTSDatasetH
+    module_path: src/dataset.py
+    kwargs:
+      handler:
+        class: DataHandler
+        module_path: qlib.data.dataset.handler
+        kwargs:
+          data_loader: *data_loader_config
+      segments:
+        train: [2007-10-30, 2016-05-27]
+        valid: [2016-09-26, 2018-05-29]
+        test: [2018-09-21, 2020-06-30]
+      seq_len: 60
+      horizon: 21
+      num_states: *num_states
+      batch_size: 512

examples/benchmarks/TRA/data/README.md

@@ -0,0 +1 @@
+Data Link: https://drive.google.com/drive/folders/1fMqZYSeLyrHiWmVzygeI4sw3vp5Gt8cY?usp=sharing

examples/benchmarks/TRA/example.py

@@ -0,0 +1,39 @@
+import argparse
+
+import qlib
+import ruamel.yaml as yaml
+from qlib.utils import init_instance_by_config
+
+
+def main(seed, config_file="configs/config_alstm.yaml"):
+
+    # set random seed
+    with open(config_file) as f:
+        config = yaml.safe_load(f)
+
+    # seed_suffix = "/seed1000" if "init" in config_file else f"/seed{seed}"
+    seed_suffix = ""
+    config["task"]["model"]["kwargs"].update(
+        {"seed": seed, "logdir": config["task"]["model"]["kwargs"]["logdir"] + seed_suffix}
+    )
+
+    # initialize workflow
+    qlib.init(
+        provider_uri=config["qlib_init"]["provider_uri"],
+        region=config["qlib_init"]["region"],
+    )
+    dataset = init_instance_by_config(config["task"]["dataset"])
+    model = init_instance_by_config(config["task"]["model"])
+
+    # train model
+    model.fit(dataset)
+
+
+if __name__ == "__main__":
+
+    # set params from cmd
+    parser = argparse.ArgumentParser(allow_abbrev=False)
+    parser.add_argument("--seed", type=int, default=1000, help="random seed")
+    parser.add_argument("--config_file", type=str, default="configs/config_alstm.yaml", help="config file")
+    args = parser.parse_args()
+    main(**vars(args))

examples/benchmarks/TRA/requirements.txt

@@ -0,0 +1,5 @@
+pandas==1.1.2
+numpy==1.17.4
+scikit_learn==0.23.2
+torch==1.7.0
+seaborn

examples/benchmarks/TRA/run.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+# we used random seed(1 1000 2000 3000 4000 5000) in our experiments 
+
+# Directly run from Qlib command `qrun`
+qrun configs/config_alstm.yaml
+
+qrun configs/config_transformer.yaml
+
+qrun configs/config_transformer_tra_init.yaml
+qrun configs/config_transformer_tra.yaml
+
+qrun configs/config_alstm_tra_init.yaml
+qrun configs/config_alstm_tra.yaml
+
+
+# Or setting different parameters with example.py
+python example.py --config_file configs/config_alstm.yaml
+
+python example.py --config_file configs/config_transformer.yaml
+
+python example.py --config_file configs/config_transformer_tra_init.yaml
+python example.py --config_file configs/config_transformer_tra.yaml
+
+python example.py --config_file configs/config_alstm_tra_init.yaml
+python example.py --config_file configs/config_alstm_tra.yaml
+
+
+