microsoft · you-n-g · Sep 30, 2021 · Mar 19, 2021 · Apr 21, 2021 · Apr 21, 2021
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -49,6 +49,15 @@ jobs:
         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: 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
+
     - name: Install test dependencies
       run: |
         pip install --upgrade pip

diff --git a/.github/workflows/test_macos.yml b/.github/workflows/test_macos.yml
@@ -31,6 +31,7 @@ jobs:
         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

diff --git a/.gitignore b/.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/

diff --git a/README.md b/README.md
@@ -25,7 +25,7 @@ Recent released features
 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>
 
 
@@ -70,7 +70,7 @@ Your feedbacks about the features are very important.
 # Framework of Qlib
 
 <div style="align: center">
-<img src="http://fintech.msra.cn/images_v060/framework.png?v=0.2" />
+<img src="docs/_static/img/framework.svg" />
 </div>
 
 
@@ -247,19 +247,19 @@ 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)
@@ -389,7 +389,7 @@ Qlib data are stored in a compact format, which is efficient to be combined into
 Join IM discussion groups:
 |[Gitter](https://gitter.im/Microsoft/qlib)|
 |----|
-|![image](http://fintech.msra.cn/images_v060/qrcode/gitter_qr.png)|
+|![image](http://fintech.msra.cn/images_v070/qrcode/gitter_qr.png)|
 
 # Contributing
 

diff --git a/docs/_static/img/analysis/analysis_model_IC.png b/docs/_static/img/analysis/analysis_model_IC.png
diff --git a/docs/_static/img/analysis/analysis_model_NDQ.png b/docs/_static/img/analysis/analysis_model_NDQ.png
diff --git a/docs/_static/img/analysis/analysis_model_auto_correlation.png b/docs/_static/img/analysis/analysis_model_auto_correlation.png
diff --git a/docs/_static/img/analysis/analysis_model_cumulative_return.png b/docs/_static/img/analysis/analysis_model_cumulative_return.png
diff --git a/docs/_static/img/analysis/analysis_model_long_short.png b/docs/_static/img/analysis/analysis_model_long_short.png
diff --git a/docs/_static/img/analysis/analysis_model_monthly_IC.png b/docs/_static/img/analysis/analysis_model_monthly_IC.png
diff --git a/docs/_static/img/analysis/report.png b/docs/_static/img/analysis/report.png
diff --git a/docs/_static/img/analysis/risk_analysis_annualized_return.png b/docs/_static/img/analysis/risk_analysis_annualized_return.png
diff --git a/docs/_static/img/analysis/risk_analysis_bar.png b/docs/_static/img/analysis/risk_analysis_bar.png
diff --git a/docs/_static/img/analysis/risk_analysis_information_ratio.png b/docs/_static/img/analysis/risk_analysis_information_ratio.png
diff --git a/docs/_static/img/analysis/risk_analysis_max_drawdown.png b/docs/_static/img/analysis/risk_analysis_max_drawdown.png
diff --git a/docs/_static/img/analysis/risk_analysis_std.png b/docs/_static/img/analysis/risk_analysis_std.png
diff --git a/docs/_static/img/analysis/score_ic.png b/docs/_static/img/analysis/score_ic.png
diff --git a/docs/_static/img/framework.svg b/docs/_static/img/framework.svg
diff --git a/docs/component/backtest.rst b/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>`_.
 

diff --git a/docs/component/highfreq.rst b/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.
diff --git a/docs/component/recorder.rst b/docs/component/recorder.rst
@@ -123,7 +123,6 @@ Here is a simple exampke of what is done in ``PortAnaRecord``, which users can r
         "n_drop": 5,
     }
     BACKTEST_CONFIG = {
-        "verbose": False,
         "limit_threshold": 0.095,
         "account": 100000000,
         "benchmark": BENCHMARK,

diff --git a/docs/component/strategy.rst b/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,

diff --git a/docs/component/workflow.rst b/docs/component/workflow.rst
@@ -54,7 +54,6 @@ Below is a typical config file of ``qrun``.
                 topk: 50
                 n_drop: 5
         backtest:
-            verbose: False
             limit_threshold: 0.095
             account: 100000000
             benchmark: *benchmark
@@ -242,7 +241,6 @@ The following script is the configuration of `backtest` and the `strategy` used
                 topk: 50
                 n_drop: 5
         backtest:
-            verbose: False
             limit_threshold: 0.095
             account: 100000000
             benchmark: *benchmark

diff --git a/docs/hidden/tuner.rst b/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

diff --git a/docs/introduction/introduction.rst b/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
 
 

diff --git a/examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml b/examples/benchmarks/ALSTM/workflow_config_alstm_Alpha158.yaml
@@ -34,19 +34,23 @@ 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: ALSTM
@@ -81,7 +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: 

diff --git a/examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml b/examples/benchmarks/ALSTM/workflow_config_alstm_Alpha360.yaml
@@ -26,19 +26,23 @@ 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: ALSTM
@@ -71,7 +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: 

diff --git a/examples/benchmarks/CatBoost/workflow_config_catboost_Alpha158.yaml b/examples/benchmarks/CatBoost/workflow_config_catboost_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: CatBoostModel
@@ -53,7 +57,9 @@ 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: