optimize log

finetune prompts

.github/workflows/python-publish.yml

@@ -38,7 +38,7 @@ jobs:
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
         twine upload dist/*
-        
+
   deploy_with_manylinux:
     runs-on: ubuntu-latest
     steps:

.github/workflows/stale.yml

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

.github/workflows/test_qlib_from_pip.yml

@@ -8,6 +8,7 @@ on:
 
 jobs:
   build:
+    if: ${{ false }}  #  FIXME: temporarily disable... Due to we are rushing a feature
     timeout-minutes: 120
 
     runs-on: ${{ matrix.os }}
@@ -19,10 +20,20 @@ jobs:
 
     steps:
     - name: Test qlib from pip
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
+
+    # Since version 3.7 of python for MacOS is installed in CI, version 3.7.17, this version causes "_bz not found error".
+    # So we make the version number of python 3.7 for MacOS more specific.
+    # refs: https://github.com/actions/setup-python/issues/682
+    - name: Set up Python ${{ matrix.python-version }}
+      if: (matrix.os == 'macos-latest' && matrix.python-version == '3.7') || (matrix.os == 'macos-11' && matrix.python-version == '3.7')
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.7.16"
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      if: (matrix.os != 'macos-latest' || matrix.python-version != '3.7') && (matrix.os != 'macos-11' || matrix.python-version != '3.7')
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -50,7 +61,9 @@ jobs:
 
     - name: Downloads dependencies data
       run: |
-        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+        cd ..
+        python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+        cd qlib
 
     - name: Test workflow by config
       run: |

.github/workflows/test_qlib_from_source.yml

@@ -64,7 +64,10 @@ jobs:
         python -m pip install -e .[dev]
 
     - name: Lint with Black
+      # Python 3.7 will use a black with low level. So we use python with higher version for black check
+      if: (matrix.python-version != '3.7')
       run: |
+        pip install -U black  # follow the latest version of black, previous Qlib dependency will downgrade black
         black . -l 120 --check --diff
 
     - name: Make html with sphinx

.gitignore

@@ -22,6 +22,10 @@ dist/
 qlib/VERSION.txt
 qlib/data/_libs/expanding.cpp
 qlib/data/_libs/rolling.cpp
+qlib/finco/prompt_cache.json
+qlib/finco/finco_workspace/
+qlib/finco/knowledge/*/knowledge.pkl
+qlib/finco/knowledge/*/storage.yml
 examples/estimator/estimator_example/
 examples/rl/data/
 examples/rl/checkpoints/

.pre-commit-config.yaml

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

README.md

@@ -91,6 +91,7 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
               </ul>
             </li>
           <li type="circle"><a href="#adapting-to-market-dynamics">Adapting to Market Dynamics</a></li>
+          <li type="circle"><a href="#reinforcement-learning-modeling-continuous-decisions">Reinforcement Learning: modeling continuous decisions</a></li>
           </ul>
         </li>
       </td>
@@ -392,6 +393,17 @@ Here is a list of solutions built on `Qlib`.
 - [Rolling Retraining](examples/benchmarks_dynamic/baseline/)
 - [DDG-DA on pytorch (Wendi, et al. AAAI 2022)](examples/benchmarks_dynamic/DDG-DA/)
 
+##  Reinforcement Learning: modeling continuous decisions
+Qlib now supports reinforcement learning, a feature designed to model continuous investment decisions. This functionality assists investors in optimizing their trading strategies by learning from interactions with the environment to maximize some notion of cumulative reward.
+
+Here is a list of solutions built on `Qlib` categorized by scenarios.
+
+### [RL for order execution](examples/rl_order_execution)
+[Here](https://qlib.readthedocs.io/en/latest/component/rl/overall.html#order-execution) is the introduction of this scenario.  All the methods below are compared [here](examples/rl_order_execution).
+- [TWAP](examples/rl_order_execution/exp_configs/backtest_twap.yml)
+- [PPO: "An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization", IJCAL 2020](examples/rl_order_execution/exp_configs/backtest_ppo.yml)
+- [OPDS: "Universal Trading for Order Execution with Oracle Policy Distillation", AAAI 2021](examples/rl_order_execution/exp_configs/backtest_opds.yml)
+
 # Quant Dataset Zoo
 Dataset plays a very important role in Quant. Here is a list of the datasets built on `Qlib`:
 

docs/component/rl/guidance.rst

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

docs/component/rl/overall.rst

@@ -4,7 +4,7 @@ Reinforcement Learning in Quantitative Trading
 
 Reinforcement Learning
 ======================
-Different from supervised learning tasks such as classification tasks and regression tasks. Another important paradigm in machine learning is Reinforcement Learning, 
+Different from supervised learning tasks such as classification tasks and regression tasks. Another important paradigm in machine learning is Reinforcement Learning(RL), 
 which attempts to optimize an accumulative numerical reward signal by directly interacting with the environment under a few assumptions such as Markov Decision Process(MDP).
 
 As demonstrated in the following figure, an RL system consists of four elements, 1)the agent 2) the environment the agent interacts with 3) the policy that the agent follows to take actions on the environment and 4)the reward signal from the environment to the agent. 
@@ -25,26 +25,46 @@ The Qlib Reinforcement Learning toolkit (QlibRL) is an RL platform for quantitat
 
 Potential Application Scenarios in Quantitative Trading
 =======================================================
-RL methods have already achieved outstanding achievement in many applications, such as game playing, resource allocating, recommendation, marketing and advertising, etc.
-Investment is always a continuous process, taking the stock market as an example, investors need to control their positions and stock holdings by one or more buying and selling behaviors, to maximize the investment returns.
-Besides, each buy and sell decision is made by investors after fully considering the overall market information and stock information. 
-From the view of an investor, the process could be described as a continuous decision-making process generated according to interaction with the market, such problems could be solved by the RL algorithms. 
-Following are some scenarios where RL can potentially be used in quantitative investment.
-
-Portfolio Construction
-----------------------
-Portfolio construction is a process of selecting securities optimally by taking a minimum risk to achieve maximum returns. With an RL-based solution, an agent allocates stocks at every time step by obtaining information for each stock and the market. The key is to develop of policy for building a portfolio and make the policy able to pick the optimal portfolio. 
+RL methods have demonstrated remarkable achievements in various applications, including game playing, resource allocation, recommendation systems, marketing, and advertising.
+In the context of investment, which involves continuous decision-making, let's consider the example of the stock market. Investors strive to optimize their investment returns by effectively managing their positions and stock holdings through various buying and selling behaviors.
+Furthermore, investors carefully evaluate market conditions and stock-specific information before making each buying or selling decision. From an investor's perspective, this process can be viewed as a continuous decision-making process driven by interactions with the market. RL algorithms offer a promising approach to tackle such challenges.
+Here are several scenarios where RL holds potential for application in quantitative investment.
 
 Order Execution
 ---------------
-As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument. Essentially, the goal of order execution is twofold: it not only requires to fulfill the whole order but also targets a more economical execution with maximizing profit gain (or minimizing capital loss). The order execution with only one order of liquidation or acquirement is called single-asset order execution.
+The order execution task is to execute orders efficiently while considering multiple factors, including optimal prices, minimizing trading costs, reducing market impact, maximizing order fullfill rates, and achieving execution within a specified time frame. RL can be applied to such tasks by incorporating these objectives into the reward function and action selection process. Specifically, the RL agent interacts with the market environment, observes the state from market information, and makes decisions on next step execution. The RL algorithm learns an optimal execution strategy through trial and error, aiming to maximize the expected cumulative reward, which incorporates the desired objectives.
 
-Considering stock investment always aim to pursue long-term maximized profits, it usually manifests as a sequential process of continuously adjusting the asset portfolios, execution for multiple orders, including order of liquidation and acquirement, brings more constraints and makes the sequence of execution for different orders should be considered, e.g. before executing an order to buy some stocks, we have to sell at least one stock. The order execution with multiple assets is called multi-asset order execution. 
+ - General Setting
+    - Environment: The environment represents the financial market where order execution takes place. It encompasses variables such as the order book dynamics, liquidity, price movements, and market conditions.
 
-According to the order execution’s trait of sequential decision-making, an RL-based solution could be applied to solve the order execution. With an RL-based solution, an agent optimizes execution strategy by interacting with the market environment. 
+    - State: The state refers to the information available to the RL agent at a given time step. It typically includes features such as the current order book state (bid-ask spread, order depth), historical price data, historical trading volume, market volatility, and any other relevant information that can aid in decision-making.
 
-With QlibRL, the RL algorithm in the above scenarios can be easily implemented.
+    - Action: The action is the decision made by the RL agent based on the observed state. In order execution, actions can include selecting the order size, price, and timing of execution.
 
-Nested Portfolio Construction and Order Executor
-------------------------------------------------
-QlibRL makes it possible to jointly optimize different levels of strategies/models/agents. Take `Nested Decision Execution Framework <https://github.com/microsoft/qlib/blob/main/examples/nested_decision_execution>`_ as an example, the optimization of order execution strategy and portfolio management strategies can interact with each other to maximize returns.
+    - Reward: The reward is a scalar signal that indicates the performance of the RL agent's action in the environment. The reward function is designed to encourage actions that lead to efficient and cost-effective order execution. It typically considers multiple objectives, such as maximizing price advantages, minimizing trading costs (including transaction fees and slippage), reducing market impact (the effect of the order on the market price) and maximizing order fullfill rates. 
+
+ - Scenarios
+    - Single-asset order execution: Single-asset order execution focuses on the task of executing a single order for a specific asset, such as a stock or a cryptocurrency. The primary objective is to execute the order efficiently while considering factors such as maximizing price advantages, minimizing trading costs, reducing market impact, and achieving a high fullfill rate. The RL agent interacts with the market environment and makes decisions on order size, price, and timing of execution for that particular asset. The goal is to learn an optimal execution strategy for the single asset, maximizing the expected cumulative reward while considering the specific dynamics and characteristics of that asset.
+
+    - Multi-asset order execution: Multi-asset order execution expands the order execution task to involve multiple assets or securities. It typically involves executing a portfolio of orders across different assets simultaneously or sequentially. Unlike single-asset order execution, the focus is not only on the execution of individual orders but also on managing the interactions and dependencies between different assets within the portfolio. The RL agent needs to make decisions on the order sizes, prices, and timings for each asset in the portfolio, considering their interdependencies, cash constraints, market conditions, and transaction costs. The goal is to learn an optimal execution strategy that balances the execution efficiency for each asset while considering the overall performance and objectives of the portfolio as a whole.
+   
+The choice of settings and RL algorithm depends on the specific requirements of the task, available data, and desired performance objectives. 
+
+Portfolio Construction
+----------------------
+Portfolio construction is a process of selecting and allocating assets in an investment portfolio. RL provides a framework to optimize portfolio management decisions by learning from interactions with the market environment and maximizing long-term returns while considering risk management.
+ - General Setting
+    - State: The state represents the current information about the market and the portfolio. It typically includes historical prices and volumes, technical indicators, and other relevant data.
+
+    - Action: The action corresponds to the decision of allocating capital to different assets in the portfolio. It determines the weights or proportions of investments in each asset.
+
+    - Reward: The reward is a metric that evaluates the performance of the portfolio. It can be defined in various ways, such as total return, risk-adjusted return, or other objectives like maximizing Sharpe ratio or minimizing drawdown.
+
+ - Scenarios
+    - Stock market: RL can be used to construct portfolios of stocks, where the agent learns to allocate capital among different stocks.
+
+    - Cryptocurrency market: RL can be applied to construct portfolios of cryptocurrencies, where the agent learns to make allocation decisions.
+
+    - Foreign exchange (Forex) market: RL can be used to construct portfolios of currency pairs, where the agent learns to allocate capital across different currencies based on exchange rate data, economic indicators, and other factors.
+
+Similarly, the choice of basic setting and algorithm depends on the specific requirements of the problem and the characteristics of the market.

docs/component/rl/toctree.rst

@@ -5,6 +5,7 @@ Reinforcement Learning in Quantitative Trading
 ========================================================================
 
 .. toctree::
+    Guidance <guidance>
     Overall <overall>
     Quick Start <quickstart>
     Framework <framework>

docs/component/workflow.rst

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

examples/benchmarks/ADARNN/workflow_config_adarnn_Alpha360.yaml

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

examples/benchmarks/ADD/workflow_config_add_Alpha360.yaml

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

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml

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

examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158_csi500.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360.yaml

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

examples/benchmarks/CatBoost/workflow_config_catboost_Alpha360_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360_csi500.yaml

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

examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_early_stop_Alpha158.yaml

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

examples/benchmarks/GATs/workflow_config_gats_Alpha158.yaml

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

examples/benchmarks/GATs/workflow_config_gats_Alpha360.yaml

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

examples/benchmarks/GRU/workflow_config_gru_Alpha158.yaml

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

examples/benchmarks/GRU/workflow_config_gru_Alpha360.yaml

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

examples/benchmarks/HIST/workflow_config_hist_Alpha360.yaml

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

examples/benchmarks/IGMTF/workflow_config_igmtf_Alpha360.yaml

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

examples/benchmarks/KRNN/workflow_config_krnn_Alpha360.yaml

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

examples/benchmarks/LSTM/workflow_config_lstm_Alpha158.yaml

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

examples/benchmarks/LSTM/workflow_config_lstm_Alpha360.yaml

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

examples/benchmarks/LightGBM/multi_freq_handler.py

@@ -48,7 +48,6 @@ class Avg15minHandler(DataHandlerLP):
         )
 
     def loader_config(self):
-
         # Results for dataset: df: pd.DataFrame
         #   len(df.columns) == 6 + 6 * 16, len(df.index.get_level_values(level="datetime").unique()) == T
         #   df.columns: close0, close1, ..., close16, open0, ..., open16, ..., vwap16

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_csi500.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158_multi_freq.yaml

@@ -33,9 +33,7 @@ port_analysis_config: &port_analysis_config
         kwargs:
             topk: 50
             n_drop: 5
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
     backtest:
         verbose: False
         limit_threshold: 0.095

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha360_csi500.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_configurable_dataset.yaml

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

examples/benchmarks/LightGBM/workflow_config_lightgbm_multi_freq.yaml

@@ -31,9 +31,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/Linear/workflow_config_linear_Alpha158.yaml

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

examples/benchmarks/Linear/workflow_config_linear_Alpha158_csi500.yaml

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

examples/benchmarks/Localformer/workflow_config_localformer_Alpha158.yaml

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

examples/benchmarks/Localformer/workflow_config_localformer_Alpha360.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha158.yaml

@@ -41,9 +41,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/MLP/workflow_config_mlp_Alpha158_csi500.yaml

@@ -41,9 +41,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/MLP/workflow_config_mlp_Alpha360.yaml

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

examples/benchmarks/MLP/workflow_config_mlp_Alpha360_csi500.yaml

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

examples/benchmarks/SFM/workflow_config_sfm_Alpha360.yaml

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

examples/benchmarks/Sandwich/workflow_config_sandwich_Alpha360.yaml

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

examples/benchmarks/TCN/workflow_config_tcn_Alpha158.yaml

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

examples/benchmarks/TCN/workflow_config_tcn_Alpha360.yaml

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

examples/benchmarks/TCTS/workflow_config_tcts_Alpha360.yaml

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

examples/benchmarks/TFT/data_formatters/base.py

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

examples/benchmarks/TFT/expt_settings/configs.py

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

examples/benchmarks/TFT/libs/hyperparam_opt.py

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

examples/benchmarks/TFT/libs/tft_model.py

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

examples/benchmarks/TFT/workflow_config_tft_Alpha158.yaml

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

examples/benchmarks/TRA/example.py

@@ -6,7 +6,6 @@ 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)
@@ -30,7 +29,6 @@ def main(seed, config_file="configs/config_alstm.yaml"):
 
 
 if __name__ == "__main__":
-
     # set params from cmd
     parser = argparse.ArgumentParser(allow_abbrev=False)
     parser.add_argument("--seed", type=int, default=1000, help="random seed")

examples/benchmarks/TRA/src/dataset.py

@@ -96,7 +96,6 @@ class MTSDatasetH(DatasetH):
         drop_last=False,
         **kwargs,
     ):
-
         assert horizon > 0, "please specify `horizon` to avoid data leakage"
 
         self.seq_len = seq_len
@@ -111,7 +110,6 @@ class MTSDatasetH(DatasetH):
         super().__init__(handler, segments, **kwargs)
 
     def setup_data(self, handler_kwargs: dict = None, **kwargs):
-
         super().setup_data()
 
         # change index to <code, date>

examples/benchmarks/TRA/src/model.py

@@ -45,7 +45,6 @@ class TRAModel(Model):
         avg_params=True,
         **kwargs,
     ):
-
         np.random.seed(seed)
         torch.manual_seed(seed)
 
@@ -93,7 +92,6 @@ class TRAModel(Model):
         self.global_step = -1
 
     def train_epoch(self, data_set):
-
         self.model.train()
         self.tra.train()
 
@@ -146,7 +144,6 @@ class TRAModel(Model):
         return total_loss
 
     def test_epoch(self, data_set, return_pred=False):
-
         self.model.eval()
         self.tra.eval()
         data_set.eval()
@@ -204,7 +201,6 @@ class TRAModel(Model):
         return metrics, preds
 
     def fit(self, dataset, evals_result=dict()):
-
         train_set, valid_set, test_set = dataset.prepare(["train", "valid", "test"])
 
         best_score = -1
@@ -380,7 +376,6 @@ class LSTM(nn.Module):
             self.output_size = hidden_size
 
     def forward(self, x):
-
         x = self.input_drop(x)
 
         if self.training and self.noise_level > 0:
@@ -464,7 +459,6 @@ class Transformer(nn.Module):
         self.output_size = hidden_size
 
     def forward(self, x):
-
         x = self.input_drop(x)
 
         if self.training and self.noise_level > 0:
@@ -514,7 +508,6 @@ class TRA(nn.Module):
         self.predictors = nn.Linear(input_size, num_states)
 
     def forward(self, hidden, hist_loss):
-
         preds = self.predictors(hidden)
 
         if self.num_states == 1:

examples/benchmarks/TRA/workflow_config_tra_Alpha158.yaml

@@ -57,9 +57,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TRA/workflow_config_tra_Alpha158_full.yaml

@@ -51,9 +51,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TRA/workflow_config_tra_Alpha360.yaml

@@ -51,9 +51,7 @@ port_analysis_config: &port_analysis_config
         class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy
         kwargs:
-            signal:
-                - <MODEL> 
-                - <DATASET>
+            signal: <PRED>
             topk: 50
             n_drop: 5
     backtest:

examples/benchmarks/TabNet/workflow_config_TabNet_Alpha158.yaml

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

examples/benchmarks/TabNet/workflow_config_TabNet_Alpha360.yaml

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

examples/benchmarks/Transformer/workflow_config_transformer_Alpha158.yaml

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

examples/benchmarks/Transformer/workflow_config_transformer_Alpha360.yaml

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

examples/benchmarks/XGBoost/workflow_config_xgboost_Alpha158.yaml

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

examples/benchmarks/XGBoost/workflow_config_xgboost_Alpha360.yaml

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

examples/benchmarks_dynamic/DDG-DA/README.md

@@ -16,12 +16,12 @@ Though the dataset is different, the conclusion remains the same. By applying `D
 # Run the Code
 Users can try `DDG-DA` by running the following command:
 ```bash
-    python workflow.py run_all
+    python workflow.py run
 ```
 
 The default forecasting models are `Linear`. Users can choose other forecasting models by changing the `forecast_model` parameter when `DDG-DA` initializes. For example, users can try `LightGBM` forecasting models by running the following command:
 ```bash
-    python workflow.py --forecast_model="gbdt" run_all
+    python workflow.py --conf_path=../workflow_config_lightgbm_Alpha158.yaml run
 ```
 
 # Results

examples/benchmarks_dynamic/DDG-DA/workflow.py

@@ -1,305 +1,40 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 from pathlib import Path
-from qlib.model.meta.task import MetaTask
-from qlib.contrib.meta.data_selection.model import MetaModelDS
-from qlib.contrib.meta.data_selection.dataset import InternalData, MetaDatasetDS
-from qlib.data.dataset.handler import DataHandlerLP
+from typing import Union
 
-import pandas as pd
 import fire
-import sys
-import pickle
-from typing import Optional
+
 from qlib import auto_init
-from qlib.model.trainer import TrainerR
-from qlib.typehint import Literal
-from qlib.utils import init_instance_by_config
-from qlib.workflow import R
+from qlib.contrib.rolling.ddgda import DDGDA
 from qlib.tests.data import GetData
 
 DIRNAME = Path(__file__).absolute().resolve().parent
-sys.path.append(str(DIRNAME.parent / "baseline"))
-from rolling_benchmark import RollingBenchmark  # NOTE: sys.path is changed for import RollingBenchmark
+BENCH_DIR = DIRNAME.parent / "baseline"
 
 
-class DDGDA:
-    """
-    please run `python workflow.py run_all` to run the full workflow of the experiment
+class DDGDABench(DDGDA):
+    # The config in the README.md
+    CONF_LIST = [
+        BENCH_DIR / "workflow_config_linear_Alpha158.yaml",
+        BENCH_DIR / "workflow_config_lightgbm_Alpha158.yaml",
+    ]
 
-    **NOTE**
-    before running the example, please clean your previous results with following command
-    - `rm -r mlruns`
-    """
+    DEFAULT_CONF = CONF_LIST[0]  # Linear by default due to efficiency
 
-    def __init__(
-        self,
-        sim_task_model: Literal["linear", "gbdt"] = "gbdt",
-        forecast_model: Literal["linear", "gbdt"] = "linear",
-        h_path: Optional[str] = None,
-        test_end: Optional[str] = None,
-        train_start: Optional[str] = None,
-        meta_1st_train_end: Optional[str] = None,
-        task_ext_conf: Optional[dict] = None,
-        alpha: float = 0.01,
-        proxy_hd: str = "handler_proxy.pkl",
-    ):
-        """
+    def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwargs) -> None:
+        # This code is for being compatible with the previous old code
+        conf_path = Path(conf_path)
+        super().__init__(conf_path=conf_path, horizon=horizon, working_dir=DIRNAME, **kwargs)
 
-        Parameters
-        ----------
-
-        train_start: Optional[str]
-            the start datetime for data.  It is used in training start time (for both tasks & meta learing)
-        test_end: Optional[str]
-            the end datetime for data. It is used in test end time
-        meta_1st_train_end: Optional[str]
-            the datetime of training end of the first meta_task
-        alpha: float
-            Setting the L2 regularization for ridge
-            The `alpha` is only passed to MetaModelDS (it is not passed to sim_task_model currently..)
-        """
-        self.step = 20
-        # NOTE:
-        # the horizon must match the meaning in the base task template
-        self.horizon = 20
-        self.meta_exp_name = "DDG-DA"
-        self.sim_task_model = sim_task_model  # The model to capture the distribution of data.
-        self.forecast_model = forecast_model  # downstream forecasting models' type
-        self.rb_kwargs = {
-            "h_path": h_path,
-            "test_end": test_end,
-            "train_start": train_start,
-            "task_ext_conf": task_ext_conf,
-        }
-        self.alpha = alpha
-        self.meta_1st_train_end = meta_1st_train_end
-        self.proxy_hd = proxy_hd
-
-    def get_feature_importance(self):
-        # this must be lightGBM, because it needs to get the feature importance
-        rb = RollingBenchmark(model_type="gbdt", **self.rb_kwargs)
-        task = rb.basic_task()
-
-        with R.start(experiment_name="feature_importance"):
-            model = init_instance_by_config(task["model"])
-            dataset = init_instance_by_config(task["dataset"])
-            model.fit(dataset)
-
-        fi = model.get_feature_importance()
-
-        # Because the model use numpy instead of dataframe for training lightgbm
-        # So the we must use following extra steps to get the right feature importance
-        df = dataset.prepare(segments=slice(None), col_set="feature", data_key=DataHandlerLP.DK_R)
-        cols = df.columns
-        fi_named = {cols[int(k.split("_")[1])]: imp for k, imp in fi.to_dict().items()}
-
-        return pd.Series(fi_named)
-
-    def dump_data_for_proxy_model(self):
-        """
-        Dump data for training meta model.
-        The meta model will be trained upon the proxy forecasting model.
-        This dataset is for the proxy forecasting model.
-        """
-        topk = 30
-        fi = self.get_feature_importance()
-        col_selected = fi.nlargest(topk)
-
-        rb = RollingBenchmark(model_type=self.sim_task_model, **self.rb_kwargs)
-        task = rb.basic_task()
-        dataset = init_instance_by_config(task["dataset"])
-        prep_ds = dataset.prepare(slice(None), col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
-
-        feature_df = prep_ds["feature"]
-        label_df = prep_ds["label"]
-
-        feature_selected = feature_df.loc[:, col_selected.index]
-
-        feature_selected = feature_selected.groupby("datetime", group_keys=False).apply(
-            lambda df: (df - df.mean()).div(df.std())
-        )
-        feature_selected = feature_selected.fillna(0.0)
-
-        df_all = {
-            "label": label_df.reindex(feature_selected.index),
-            "feature": feature_selected,
-        }
-        df_all = pd.concat(df_all, axis=1)
-        df_all.to_pickle(DIRNAME / "fea_label_df.pkl")
-
-        # dump data in handler format for aligning the interface
-        handler = DataHandlerLP(
-            data_loader={
-                "class": "qlib.data.dataset.loader.StaticDataLoader",
-                "kwargs": {"config": DIRNAME / "fea_label_df.pkl"},
-            }
-        )
-        handler.to_pickle(DIRNAME / self.proxy_hd, dump_all=True)
-
-    @property
-    def _internal_data_path(self):
-        return DIRNAME / f"internal_data_s{self.step}.pkl"
-
-    def dump_meta_ipt(self):
-        """
-        Dump data for training meta model.
-        This function will dump the input data for meta model
-        """
-        # According to the experiments, the choice of the model type is very important for achieving good results
-        rb = RollingBenchmark(model_type=self.sim_task_model, **self.rb_kwargs)
-        sim_task = rb.basic_task()
-
-        if self.sim_task_model == "gbdt":
-            sim_task["model"].setdefault("kwargs", {}).update({"early_stopping_rounds": None, "num_boost_round": 150})
-
-        exp_name_sim = f"data_sim_s{self.step}"
-
-        internal_data = InternalData(sim_task, self.step, exp_name=exp_name_sim)
-        internal_data.setup(trainer=TrainerR)
-
-        with self._internal_data_path.open("wb") as f:
-            pickle.dump(internal_data, f)
-
-    def train_meta_model(self, fill_method="max"):
-        """
-        training a meta model based on a simplified linear proxy model;
-        """
-
-        # 1) leverage the simplified proxy forecasting model to train meta model.
-        # - Only the dataset part is important, in current version of meta model will integrate the
-        rb = RollingBenchmark(model_type=self.sim_task_model, **self.rb_kwargs)
-        sim_task = rb.basic_task()
-        # the train_start for training meta model does not necessarily align with final rolling
-        train_start = "2008-01-01" if self.rb_kwargs.get("train_start") is None else self.rb_kwargs.get("train_start")
-        train_end = "2010-12-31" if self.meta_1st_train_end is None else self.meta_1st_train_end
-        test_start = (pd.Timestamp(train_end) + pd.Timedelta(days=1)).strftime("%Y-%m-%d")
-        proxy_forecast_model_task = {
-            # "model": "qlib.contrib.model.linear.LinearModel",
-            "dataset": {
-                "class": "qlib.data.dataset.DatasetH",
-                "kwargs": {
-                    "handler": f"file://{(DIRNAME / self.proxy_hd).absolute()}",
-                    "segments": {
-                        "train": (train_start, train_end),
-                        "test": (test_start, sim_task["dataset"]["kwargs"]["segments"]["test"][1]),
-                    },
-                },
-            },
-            # "record": ["qlib.workflow.record_temp.SignalRecord"]
-        }
-        # the proxy_forecast_model_task will be used to create meta tasks.
-        # The test date of first task will be 2011-01-01. Each test segment will be about 20days
-        # The tasks include all training tasks and test tasks.
-
-        # 2) preparing meta dataset
-        kwargs = dict(
-            task_tpl=proxy_forecast_model_task,
-            step=self.step,
-            segments=0.62,  # keep test period consistent with the dataset yaml
-            trunc_days=1 + self.horizon,
-            hist_step_n=30,
-            fill_method=fill_method,
-            rolling_ext_days=0,
-        )
-        # NOTE:
-        # the input of meta model (internal data) are shared between proxy model and final forecasting model
-        # but their task test segment are not aligned! It worked in my previous experiment.
-        # So the misalignment will not affect the effectiveness of the method.
-        with self._internal_data_path.open("rb") as f:
-            internal_data = pickle.load(f)
-
-        md = MetaDatasetDS(exp_name=internal_data, **kwargs)
-
-        # 3) train and logging meta model
-        with R.start(experiment_name=self.meta_exp_name):
-            R.log_params(**kwargs)
-            mm = MetaModelDS(
-                step=self.step, hist_step_n=kwargs["hist_step_n"], lr=0.001, max_epoch=30, seed=43, alpha=self.alpha
-            )
-            mm.fit(md)
-            R.save_objects(model=mm)
-
-    @property
-    def _task_path(self):
-        return DIRNAME / f"tasks_s{self.step}.pkl"
-
-    def meta_inference(self):
-        """
-        Leverage meta-model for inference:
-        - Given
-            - baseline tasks
-            - input for meta model(internal data)
-            - meta model (its learnt knowledge on proxy forecasting model is expected to transfer to normal forecasting model)
-        """
-        # 1) get meta model
-        exp = R.get_exp(experiment_name=self.meta_exp_name)
-        rec = exp.list_recorders(rtype=exp.RT_L)[0]
-        meta_model: MetaModelDS = rec.load_object("model")
-
-        # 2)
-        # we are transfer to knowledge of meta model to final forecasting tasks.
-        # Create MetaTaskDataset for the final forecasting tasks
-        # Aligning the setting of it to the MetaTaskDataset when training Meta model is necessary
-
-        # 2.1) get previous config
-        param = rec.list_params()
-        trunc_days = int(param["trunc_days"])
-        step = int(param["step"])
-        hist_step_n = int(param["hist_step_n"])
-        fill_method = param.get("fill_method", "max")
-
-        rb = RollingBenchmark(model_type=self.forecast_model, **self.rb_kwargs)
-        task_l = rb.create_rolling_tasks()
-
-        # 2.2) create meta dataset for final dataset
-        kwargs = dict(
-            task_tpl=task_l,
-            step=step,
-            segments=0.0,  # all the tasks are for testing
-            trunc_days=trunc_days,
-            hist_step_n=hist_step_n,
-            fill_method=fill_method,
-            task_mode=MetaTask.PROC_MODE_TRANSFER,
-        )
-
-        with self._internal_data_path.open("rb") as f:
-            internal_data = pickle.load(f)
-        mds = MetaDatasetDS(exp_name=internal_data, **kwargs)
-
-        # 3) meta model make inference and get new qlib task
-        new_tasks = meta_model.inference(mds)
-        with self._task_path.open("wb") as f:
-            pickle.dump(new_tasks, f)
-
-    def train_and_eval_tasks(self):
-        """
-        Training the tasks generated by meta model
-        Then evaluate it
-        """
-        with self._task_path.open("rb") as f:
-            tasks = pickle.load(f)
-        rb = RollingBenchmark(rolling_exp="rolling_ds", model_type=self.forecast_model, **self.rb_kwargs)
-        rb.train_rolling_tasks(tasks)
-        rb.ens_rolling()
-        rb.update_rolling_rec()
-
-    def run_all(self):
-        # 1) file: handler_proxy.pkl (self.proxy_hd)
-        self.dump_data_for_proxy_model()
-        # 2)
-        # file: internal_data_s20.pkl
-        # mlflow: data_sim_s20, models for calculating meta_ipt
-        self.dump_meta_ipt()
-        # 3) meta model will be stored in `DDG-DA`
-        self.train_meta_model()
-        # 4) new_tasks are saved in "tasks_s20.pkl" (reweighter is added)
-        self.meta_inference()
-        # 5) load the saved tasks and train model
-        self.train_and_eval_tasks()
+        for f in self.CONF_LIST:
+            if conf_path.samefile(f):
+                break
+        else:
+            self.logger.warning("Model type is not in the benchmark!")
 
 
 if __name__ == "__main__":
     GetData().qlib_data(exists_skip=True)
     auto_init()
-    fire.Fire(DDGDA)
+    fire.Fire(DDGDABench)

examples/benchmarks_dynamic/baseline/README.md

@@ -5,11 +5,12 @@ This is the framework of periodically Rolling Retrain (RR) forecasting models. R
 ## Run the Code
 Users can try RR by running the following command:
 ```bash
-    python rolling_benchmark.py run_all
+    python rolling_benchmark.py run
 ```
 
 The default forecasting models are `Linear`. Users can choose other forecasting models by changing the `model_type` parameter.
 For example, users can try `LightGBM` forecasting models by running the following command:
 ```bash
-    python rolling_benchmark.py --model_type="gbdt" run_all
-```
+    python rolling_benchmark.py --conf_path=workflow_config_lightgbm_Alpha158.yaml run
+
+```

examples/benchmarks_dynamic/baseline/rolling_benchmark.py

@@ -1,161 +1,33 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
-from typing import Optional
-from qlib.model.ens.ensemble import RollingEnsemble
-from qlib.utils import init_instance_by_config
-import fire
-import yaml
-import pandas as pd
-from qlib import auto_init
 from pathlib import Path
-from tqdm.auto import tqdm
-from qlib.model.trainer import TrainerR
-from qlib.log import get_module_logger
-from qlib.utils.data import update_config
-from qlib.workflow import R
+from typing import Union
+
+import fire
+
+from qlib import auto_init
+from qlib.contrib.rolling.base import Rolling
 from qlib.tests.data import GetData
 
 DIRNAME = Path(__file__).absolute().resolve().parent
-from qlib.workflow.task.gen import task_generator, RollingGen
-from qlib.workflow.task.collect import RecorderCollector
-from qlib.workflow.record_temp import PortAnaRecord, SigAnaRecord
 
 
-class RollingBenchmark:
-    """
-    **NOTE**
-    before running the example, please clean your previous results with following command
-    - `rm -r mlruns`
+class RollingBenchmark(Rolling):
+    # The config in the README.md
+    CONF_LIST = [DIRNAME / "workflow_config_linear_Alpha158.yaml", DIRNAME / "workflow_config_lightgbm_Alpha158.yaml"]
 
-    """
+    DEFAULT_CONF = CONF_LIST[0]
 
-    def __init__(
-        self,
-        rolling_exp: str = "rolling_models",
-        model_type: str = "linear",
-        h_path: Optional[str] = None,
-        train_start: Optional[str] = None,
-        test_end: Optional[str] = None,
-        task_ext_conf: Optional[dict] = None,
-    ) -> None:
-        """
-        Parameters
-        ----------
-        rolling_exp : str
-            The name for the experiments for rolling
-        model_type : str
-            The model to be boosted.
-        h_path : Optional[str]
-            the dumped data handler;
-        test_end : Optional[str]
-            the test end for the data. It is typically used together with the handler
-        train_start : Optional[str]
-            the train start for the data.  It is typically used together with the handler.
-        task_ext_conf : Optional[dict]
-            some option to update the
-        """
-        self.step = 20
-        self.horizon = 20
-        self.rolling_exp = rolling_exp
-        self.model_type = model_type
-        self.h_path = h_path
-        self.train_start = train_start
-        self.test_end = test_end
-        self.logger = get_module_logger("RollingBenchmark")
-        self.task_ext_conf = task_ext_conf
+    def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwargs) -> None:
+        # This code is for being compatible with the previous old code
+        conf_path = Path(conf_path)
+        super().__init__(conf_path=conf_path, horizon=horizon, **kwargs)
 
-    def basic_task(self):
-        """For fast training rolling"""
-        if self.model_type == "gbdt":
-            conf_path = DIRNAME / "workflow_config_lightgbm_Alpha158.yaml"
-            # dump the processed data on to disk for later loading to speed up the processing
-            h_path = DIRNAME / "lightgbm_alpha158_handler_horizon{}.pkl".format(self.horizon)
-        elif self.model_type == "linear":
-            # We use ridge regression to stabilize the performance
-            conf_path = DIRNAME / "workflow_config_linear_Alpha158.yaml"
-            h_path = DIRNAME / "linear_alpha158_handler_horizon{}.pkl".format(self.horizon)
+        for f in self.CONF_LIST:
+            if conf_path.samefile(f):
+                break
         else:
-            raise AssertionError("Model type is not supported!")
-
-        if self.h_path is not None:
-            h_path = Path(self.h_path)
-
-        with conf_path.open("r") as f:
-            conf = yaml.safe_load(f)
-
-        # modify dataset horizon
-        conf["task"]["dataset"]["kwargs"]["handler"]["kwargs"]["label"] = [
-            "Ref($close, -{}) / Ref($close, -1) - 1".format(self.horizon + 1)
-        ]
-
-        task = conf["task"]
-
-        if self.task_ext_conf is not None:
-            task = update_config(task, self.task_ext_conf)
-
-        if not h_path.exists():
-            h_conf = task["dataset"]["kwargs"]["handler"]
-            h = init_instance_by_config(h_conf)
-            h.to_pickle(h_path, dump_all=True)
-
-        task["dataset"]["kwargs"]["handler"] = f"file://{h_path}"
-        task["record"] = ["qlib.workflow.record_temp.SignalRecord"]
-
-        if self.train_start is not None:
-            seg = task["dataset"]["kwargs"]["segments"]["train"]
-            task["dataset"]["kwargs"]["segments"]["train"] = pd.Timestamp(self.train_start), seg[1]
-
-        if self.test_end is not None:
-            seg = task["dataset"]["kwargs"]["segments"]["test"]
-            task["dataset"]["kwargs"]["segments"]["test"] = seg[0], pd.Timestamp(self.test_end)
-        self.logger.info(task)
-        return task
-
-    def create_rolling_tasks(self):
-        task = self.basic_task()
-        task_l = task_generator(
-            task, RollingGen(step=self.step, trunc_days=self.horizon + 1)
-        )  # the last two days should be truncated to avoid information leakage
-        return task_l
-
-    def train_rolling_tasks(self, task_l=None):
-        if task_l is None:
-            task_l = self.create_rolling_tasks()
-        trainer = TrainerR(experiment_name=self.rolling_exp)
-        trainer(task_l)
-
-    COMB_EXP = "rolling"
-
-    def ens_rolling(self):
-        rc = RecorderCollector(
-            experiment=self.rolling_exp,
-            artifacts_key=["pred", "label"],
-            process_list=[RollingEnsemble()],
-            # rec_key_func=lambda rec: (self.COMB_EXP, rec.info["id"]),
-            artifacts_path={"pred": "pred.pkl", "label": "label.pkl"},
-        )
-        res = rc()
-        with R.start(experiment_name=self.COMB_EXP):
-            R.log_params(exp_name=self.rolling_exp)
-            R.save_objects(**{"pred.pkl": res["pred"], "label.pkl": res["label"]})
-
-    def update_rolling_rec(self):
-        """
-        Evaluate the combined rolling results
-        """
-        for _, rec in R.list_recorders(experiment_name=self.COMB_EXP).items():
-            for rt_cls in SigAnaRecord, PortAnaRecord:
-                rt = rt_cls(recorder=rec, skip_existing=True)
-                rt.generate()
-        print(f"Your evaluation results can be found in the experiment named `{self.COMB_EXP}`.")
-
-    def run_all(self):
-        # the results will be  save in mlruns.
-        # 1) each rolling task is saved in rolling_models
-        self.train_rolling_tasks()
-        # 2) combined rolling tasks and evaluation results are saved in rolling
-        self.ens_rolling()
-        self.update_rolling_rec()
+            self.logger.warning("Model type is not in the benchmark!")
 
 
 if __name__ == "__main__":

examples/benchmarks_dynamic/baseline/workflow_config_lightgbm_Alpha158.yaml

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

examples/benchmarks_dynamic/baseline/workflow_config_linear_Alpha158.yaml

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

examples/highfreq/highfreq_handler.py

@@ -14,7 +14,6 @@ class HighFreqHandler(DataHandlerLP):
         fit_end_time=None,
         drop_raw=True,
     ):
-
         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)
 

examples/highfreq/workflow.py

@@ -18,7 +18,6 @@ from highfreq_ops import get_calendar_day, DayLast, FFillNan, BFillNan, Date, Se
 
 
 class HighfreqWorkflow:
-
     SPEC_CONF = {"custom_ops": [DayLast, FFillNan, BFillNan, Date, Select, IsNull, Cut], "expression_cache": None}
 
     MARKET = "all"

examples/hyperparameter/LightGBM/hyperparameter_158.py

@@ -35,7 +35,6 @@ def objective(trial):
 
 
 if __name__ == "__main__":
-
     provider_uri = "~/.qlib/qlib_data/cn_data"
     GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
     qlib.init(provider_uri=provider_uri, region="cn")

examples/hyperparameter/LightGBM/hyperparameter_360.py

@@ -38,7 +38,6 @@ def objective(trial):
 
 
 if __name__ == "__main__":
-
     provider_uri = "~/.qlib/qlib_data/cn_data"
     GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
     qlib.init(provider_uri=provider_uri, region=REG_CN)

examples/model_interpreter/feature.py

@@ -11,7 +11,6 @@ from qlib.tests.config import CSI300_GBDT_TASK
 
 
 if __name__ == "__main__":
-
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
     GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)

examples/portfolio/prepare_riskdata.py

@@ -9,7 +9,6 @@ from qlib.model.riskmodel import StructuredCovEstimator
 
 
 def prepare_data(riskdata_root="./riskdata", T=240, start_time="2016-01-01"):
-
     universe = D.features(D.instruments("csi300"), ["$close"], start_time=start_time).swaplevel().sort_index()
 
     price_all = (
@@ -20,7 +19,6 @@ def prepare_data(riskdata_root="./riskdata", T=240, start_time="2016-01-01"):
     riskmodel = StructuredCovEstimator()
 
     for i in range(T - 1, len(price_all)):
-
         date = price_all.index[i]
         ref_date = price_all.index[i - T + 1]
 
@@ -47,7 +45,6 @@ def prepare_data(riskdata_root="./riskdata", T=240, start_time="2016-01-01"):
 
 
 if __name__ == "__main__":
-
     import qlib
 
     qlib.init(provider_uri="~/.qlib/qlib_data/cn_data")

examples/rolling_process_data/workflow.py

@@ -13,7 +13,6 @@ from qlib.tests.data import GetData
 
 
 class RollingDataWorkflow:
-
     MARKET = "csi300"
     start_time = "2010-01-01"
     end_time = "2019-12-31"
@@ -93,7 +92,6 @@ class RollingDataWorkflow:
         dataset = init_instance_by_config(dataset_config)
 
         for rolling_offset in range(self.rolling_cnt):
-
             print(f"===========rolling{rolling_offset} start===========")
             if rolling_offset:
                 dataset.config(

examples/workflow_by_code.py

@@ -17,7 +17,6 @@ from qlib.tests.config import CSI300_BENCH, CSI300_GBDT_TASK
 
 
 if __name__ == "__main__":
-
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
     GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)

qlib/__init__.py

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 from pathlib import Path
 
-__version__ = "0.9.2"
+__version__ = "0.9.2.99"
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
 import os
 from typing import Union
@@ -77,7 +77,6 @@ def init(default_conf="client", **kwargs):
 
 
 def _mount_nfs_uri(provider_uri, mount_path, auto_mount: bool = False):
-
     LOG = get_module_logger("mount nfs", level=logging.INFO)
     if mount_path is None:
         raise ValueError(f"Invalid mount path: {mount_path}!")

qlib/backtest/__init__.py

@@ -182,7 +182,6 @@ def get_strategy_executor(
     exchange_kwargs: dict = {},
     pos_type: str = "Position",
 ) -> Tuple[BaseStrategy, BaseExecutor]:
-
     # NOTE:
     # - for avoiding recursive import
     # - typing annotations is not reliable

qlib/backtest/exchange.py

@@ -638,7 +638,6 @@ class Exchange:
         random.seed(0)
         random.shuffle(sorted_ids)
         for stock_id in sorted_ids:
-
             # Do not generate order for the non-tradable stocks
             if not self.is_stock_tradable(stock_id=stock_id, start_time=start_time, end_time=end_time):
                 continue

qlib/config.py

@@ -293,7 +293,6 @@ class QlibConfig(Config):
         """
 
         def __init__(self, provider_uri: Union[str, Path, dict], mount_path: Union[str, Path, dict]):
-
             """
             The relation of `provider_uri` and `mount_path`
             - `mount_path` is used only if provider_uri is an NFS path
@@ -487,5 +486,8 @@ class QlibConfig(Config):
         return self._registered
 
 
+DEFAULT_QLIB_DOT_PATH = Path("~/.qlib/").expanduser()
+
+
 # global config
 C = QlibConfig(_default_config)

qlib/contrib/analyzer.py

@@ -0,0 +1,111 @@
+import logging
+import matplotlib.pyplot as plt
+from pathlib import Path
+import numpy as np
+
+from ..log import get_module_logger
+from ..contrib.eva.alpha import calc_ic, calc_long_short_return, calc_long_short_prec
+
+logger = get_module_logger("analysis", logging.INFO)
+
+
+class AnalyzerTemp:
+    def __init__(self, recorder, output_dir=None, **kwargs):
+        self.recorder = recorder
+        self.output_dir = Path(output_dir) if output_dir else "./"
+
+    def load(self, name: str):
+        """
+        It behaves the same as self.recorder.load_object.
+        But it is an easier interface because users don't have to care about `get_path` and `artifact_path`
+
+        Parameters
+        ----------
+        name : str
+            the name for the file to be load.
+
+        Return
+        ------
+        The stored records.
+        """
+        return self.recorder.load_object(name)
+
+    def analyse(self, **kwargs):
+        """
+        Analyse data index, distribution .etc
+
+        Parameters
+        ----------
+
+
+        Return
+        ------
+        The handled data.
+        """
+        raise NotImplementedError(f"Please implement the `analysis` method.")
+
+
+class HFAnalyzer(AnalyzerTemp):
+    """
+    This is the Signal Analysis class that generates the analysis results such as IC and IR.
+
+    default output image filename is "HFAnalyzerTable.jpeg"
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def analyse(self):
+        pred = self.load("pred.pkl")
+        label = self.load("label.pkl")
+
+        long_pre, short_pre = calc_long_short_prec(pred.iloc[:, 0], label.iloc[:, 0], is_alpha=True)
+        ic, ric = calc_ic(pred.iloc[:, 0], label.iloc[:, 0])
+        metrics = {
+            "IC": ic.mean(),
+            "ICIR": ic.mean() / ic.std(),
+            "Rank IC": ric.mean(),
+            "Rank ICIR": ric.mean() / ric.std(),
+            "Long precision": long_pre.mean(),
+            "Short precision": short_pre.mean(),
+        }
+
+        long_short_r, long_avg_r = calc_long_short_return(pred.iloc[:, 0], label.iloc[:, 0])
+        metrics.update(
+            {
+                "Long-Short Average Return": long_short_r.mean(),
+                "Long-Short Average Sharpe": long_short_r.mean() / long_short_r.std(),
+            }
+        )
+
+        table = [[k, v] for (k, v) in metrics.items()]
+        plt.table(cellText=table, loc="center")
+        plt.axis("off")
+        plt.savefig(self.output_dir.joinpath("HFAnalyzerTable.jpeg"))
+        plt.clf()
+
+        plt.scatter(np.arange(0, len(pred)), pred.iloc[:, 0])
+        plt.scatter(np.arange(0, len(label)), label.iloc[:, 0])
+        plt.title("HFAnalyzer")
+        plt.savefig(self.output_dir.joinpath("HFAnalyzer.jpeg"))
+        return "HFAnalyzer.jpeg"
+
+
+class SignalAnalyzer(AnalyzerTemp):
+    """
+    This is the Signal Analysis class that generates the analysis results such as IC and IR.
+
+    default output image filename is "signalAnalysis.jpeg"
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def analyse(self, dataset=None, **kwargs):
+        label = self.load("label.pkl")
+
+        plt.hist(label)
+        plt.title("SignalAnalyzer")
+        plt.savefig(self.output_dir.joinpath("signalAnalysis.jpeg"))
+
+        return "signalAnalysis.jpeg"

qlib/contrib/data/dataset.py

@@ -130,7 +130,6 @@ class MTSDatasetH(DatasetH):
         input_size=None,
         **kwargs,
     ):
-
         assert num_states == 0 or horizon > 0, "please specify `horizon` to avoid data leakage"
         assert memory_mode in ["sample", "daily"], "unsupported memory mode"
         assert memory_mode == "sample" or batch_size < 0, "daily memory requires daily sampling (`batch_size < 0`)"
@@ -153,7 +152,6 @@ class MTSDatasetH(DatasetH):
         super().__init__(handler, segments, **kwargs)
 
     def setup_data(self, handler_kwargs: dict = None, **kwargs):
-
         super().setup_data(**kwargs)
 
         if handler_kwargs is not None:
@@ -288,7 +286,6 @@ class MTSDatasetH(DatasetH):
             daily_count = []  # store number of samples for each day
 
             for j in indices[i : i + batch_size]:
-
                 # normal sampling: self.batch_size > 0 => slices is a list => slices_subset is a slice
                 # daily sampling: self.batch_size < 0 => slices is a nested list => slices_subset is a list
                 slices_subset = slices[j]
@@ -297,7 +294,6 @@ class MTSDatasetH(DatasetH):
                 # each slices_subset contains a list of slices for multiple stocks
                 # NOTE: daily sampling is used in 1) eval mode, 2) train mode with self.batch_size < 0
                 if self.batch_size < 0:
-
                     # store daily index
                     idx = self._daily_index.index[j]  # daily_index.index is the index of the original data
                     daily_index.append(idx)
@@ -320,7 +316,6 @@ class MTSDatasetH(DatasetH):
                     slices_subset = [slices_subset]
 
                 for slc in slices_subset:
-
                     # legacy support for Alpha360 data by `input_size`
                     if self.input_size:
                         data.append(self._data[slc.stop - 1].reshape(self.input_size, -1).T)

qlib/contrib/data/handler.py

@@ -1,6 +1,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
+from typing import Optional
+from qlib.utils.data import update_config
 from ...data.dataset.handler import DataHandlerLP
 from ...data.dataset.processor import Processor
 from ...utils import get_callable_kwargs
@@ -57,12 +59,13 @@ class Alpha360(DataHandlerLP):
         fit_end_time=None,
         filter_pipe=None,
         inst_processors=None,
+        data_loader: Optional[dict] = 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 = {
+        _data_loader = {
             "class": "QlibDataLoader",
             "kwargs": {
                 "config": {
@@ -74,12 +77,14 @@ class Alpha360(DataHandlerLP):
                 "inst_processors": inst_processors,
             },
         }
+        if data_loader is not None:
+            update_config(_data_loader, data_loader)
 
         super().__init__(
             instruments=instruments,
             start_time=start_time,
             end_time=end_time,
-            data_loader=data_loader,
+            data_loader=_data_loader,
             learn_processors=learn_processors,
             infer_processors=infer_processors,
             **kwargs
@@ -153,12 +158,13 @@ class Alpha158(DataHandlerLP):
         process_type=DataHandlerLP.PTYPE_A,
         filter_pipe=None,
         inst_processors=None,
+        data_loader: Optional[dict] = 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 = {
+        _data_loader = {
             "class": "QlibDataLoader",
             "kwargs": {
                 "config": {
@@ -170,11 +176,13 @@ class Alpha158(DataHandlerLP):
                 "inst_processors": inst_processors,
             },
         }
+        if data_loader is not None:
+            update_config(_data_loader, data_loader)
         super().__init__(
             instruments=instruments,
             start_time=start_time,
             end_time=end_time,
-            data_loader=data_loader,
+            data_loader=_data_loader,
             infer_processors=infer_processors,
             learn_processors=learn_processors,
             process_type=process_type,

qlib/contrib/data/highfreq_handler.py

@@ -17,7 +17,6 @@ class HighFreqHandler(DataHandlerLP):
         fit_end_time=None,
         drop_raw=True,
     ):
-
         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)
 
@@ -318,7 +317,6 @@ class HighFreqOrderHandler(DataHandlerLP):
         inst_processors=None,
         drop_raw=True,
     ):
-
         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)
 

qlib/contrib/data/highfreq_processor.py

@@ -29,7 +29,6 @@ class HighFreqNorm(Processor):
         feature_save_dir: str,
         norm_groups: Dict[str, int],
     ):
-
         self.fit_start_time = fit_start_time
         self.fit_end_time = fit_end_time
         self.feature_save_dir = feature_save_dir

qlib/contrib/meta/data_selection/dataset.py

@@ -49,6 +49,8 @@ class InternalData:
 
         # 1) prepare the prediction of proxy models
         perf_task_tpl = deepcopy(self.task_tpl)  # this task is supposed to contains no complicated objects
+        # The only thing we want to save is the prediction
+        perf_task_tpl["record"] = ["qlib.workflow.record_temp.SignalRecord"]
 
         trainer = auto_filter_kwargs(trainer)(experiment_name=self.exp_name, **trainer_kwargs)
         # NOTE:

qlib/contrib/model/pytorch_adarnn.py

@@ -246,7 +246,6 @@ class ADARNN(Model):
         evals_result=dict(),
         save_path=None,
     ):
-
         df_train, df_valid = dataset.prepare(
             ["train", "valid"],
             col_set=["feature", "label"],
@@ -318,7 +317,6 @@ class ADARNN(Model):
         preds = []
 
         for begin in range(sample_num)[:: self.batch_size]:
-
             if sample_num - begin < self.batch_size:
                 end = sample_num
             else:

qlib/contrib/model/pytorch_alstm.py

@@ -146,7 +146,6 @@ class ALSTM(Model):
         raise ValueError("unknown loss `%s`" % self.loss)
 
     def metric_fn(self, pred, label):
-
         mask = torch.isfinite(label)
 
         if self.metric in ("", "loss"):
@@ -155,7 +154,6 @@ class ALSTM(Model):
         raise ValueError("unknown metric `%s`" % self.metric)
 
     def train_epoch(self, x_train, y_train):
-
         x_train_values = x_train.values
         y_train_values = np.squeeze(y_train.values)
 
@@ -165,7 +163,6 @@ class ALSTM(Model):
         np.random.shuffle(indices)
 
         for i in range(len(indices))[:: self.batch_size]:
-
             if len(indices) - i < self.batch_size:
                 break
 
@@ -181,7 +178,6 @@ class ALSTM(Model):
             self.train_optimizer.step()
 
     def test_epoch(self, data_x, data_y):
-
         # prepare training data
         x_values = data_x.values
         y_values = np.squeeze(data_y.values)
@@ -194,7 +190,6 @@ class ALSTM(Model):
         indices = np.arange(len(x_values))
 
         for i in range(len(indices))[:: self.batch_size]:
-
             if len(indices) - i < self.batch_size:
                 break
 
@@ -217,7 +212,6 @@ class ALSTM(Model):
         evals_result=dict(),
         save_path=None,
     ):
-
         df_train, df_valid, df_test = dataset.prepare(
             ["train", "valid", "test"],
             col_set=["feature", "label"],
@@ -282,7 +276,6 @@ class ALSTM(Model):
         preds = []
 
         for begin in range(sample_num)[:: self.batch_size]:
-
             if sample_num - begin < self.batch_size:
                 end = sample_num
             else:

qlib/contrib/model/pytorch_alstm_ts.py

@@ -156,7 +156,6 @@ class ALSTM(Model):
         raise ValueError("unknown loss `%s`" % self.loss)
 
     def metric_fn(self, pred, label):
-
         mask = torch.isfinite(label)
 
         if self.metric in ("", "loss"):
@@ -165,10 +164,9 @@ class ALSTM(Model):
         raise ValueError("unknown metric `%s`" % self.metric)
 
     def train_epoch(self, data_loader):
-
         self.ALSTM_model.train()
 
-        for (data, weight) in data_loader:
+        for data, weight in data_loader:
             feature = data[:, :, 0:-1].to(self.device)
             label = data[:, -1, -1].to(self.device)
 
@@ -181,14 +179,12 @@ class ALSTM(Model):
             self.train_optimizer.step()
 
     def test_epoch(self, data_loader):
-
         self.ALSTM_model.eval()
 
         scores = []
         losses = []
 
-        for (data, weight) in data_loader:
-
+        for data, weight in data_loader:
             feature = data[:, :, 0:-1].to(self.device)
             # feature[torch.isnan(feature)] = 0
             label = data[:, -1, -1].to(self.device)
@@ -295,7 +291,6 @@ class ALSTM(Model):
         preds = []
 
         for data in test_loader:
-
             feature = data[:, :, 0:-1].to(self.device)
 
             with torch.no_grad():

qlib/contrib/model/pytorch_gats.py

@@ -154,7 +154,6 @@ class GATs(Model):
         raise ValueError("unknown loss `%s`" % self.loss)
 
     def metric_fn(self, pred, label):
-
         mask = torch.isfinite(label)
 
         if self.metric in ("", "loss"):
@@ -175,7 +174,6 @@ class GATs(Model):
         return daily_index, daily_count
 
     def train_epoch(self, x_train, y_train):
-
         x_train_values = x_train.values
         y_train_values = np.squeeze(y_train.values)
         self.GAT_model.train()
@@ -197,7 +195,6 @@ class GATs(Model):
             self.train_optimizer.step()
 
     def test_epoch(self, data_x, data_y):
-
         # prepare training data
         x_values = data_x.values
         y_values = np.squeeze(data_y.values)
@@ -230,7 +227,6 @@ class GATs(Model):
         evals_result=dict(),
         save_path=None,
     ):
-
         df_train, df_valid, df_test = dataset.prepare(
             ["train", "valid", "test"],
             col_set=["feature", "label"],

qlib/contrib/model/pytorch_gats_ts.py

@@ -32,7 +32,6 @@ class DailyBatchSampler(Sampler):
         self.daily_index[0] = 0
 
     def __iter__(self):
-
         for idx, count in zip(self.daily_index, self.daily_count):
             yield np.arange(idx, idx + count)
 
@@ -173,7 +172,6 @@ class GATs(Model):
         raise ValueError("unknown loss `%s`" % self.loss)
 
     def metric_fn(self, pred, label):
-
         mask = torch.isfinite(label)
 
         if self.metric in ("", "loss"):
@@ -194,11 +192,9 @@ class GATs(Model):
         return daily_index, daily_count
 
     def train_epoch(self, data_loader):
-
         self.GAT_model.train()
 
         for data in data_loader:
-
             data = data.squeeze()
             feature = data[:, :, 0:-1].to(self.device)
             label = data[:, -1, -1].to(self.device)
@@ -212,14 +208,12 @@ class GATs(Model):
             self.train_optimizer.step()
 
     def test_epoch(self, data_loader):
-
         self.GAT_model.eval()
 
         scores = []
         losses = []
 
         for data in data_loader:
-
             data = data.squeeze()
             feature = data[:, :, 0:-1].to(self.device)
             # feature[torch.isnan(feature)] = 0
@@ -240,7 +234,6 @@ class GATs(Model):
         evals_result=dict(),
         save_path=None,
     ):
-
         dl_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
         dl_valid = dataset.prepare("valid", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
         if dl_train.empty or dl_valid.empty:
@@ -329,7 +322,6 @@ class GATs(Model):
         preds = []
 
         for data in test_loader:
-
             data = data.squeeze()
             feature = data[:, :, 0:-1].to(self.device)