Merge branch 'main' of github.com:microsoft/qlib into fix_yahoo_colle…

…ctor_last_day_format

.github/workflows/python-publish.yml

@@ -51,8 +51,8 @@ jobs:
         python setup.py bdist_wheel
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/*
 
@@ -72,10 +72,10 @@ jobs:
         python-version: 3.7
     - name: Install dependencies
       run: |
-        pip install twine  
+        pip install twine
     - name: Build and publish
       env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
       run: |
         twine upload dist/pyqlib-*-manylinux*.whl

.github/workflows/release-drafter.yml

@@ -6,8 +6,14 @@ on:
     branches:
       - main
 
+permissions:
+  contents: read
+
 jobs:
   update_release_draft:
+    permissions:
+      contents: write
+      pull-requests: read
     runs-on: ubuntu-latest
     steps:
       # Drafts your next Release notes as Pull Requests are merged into "master"

.github/workflows/test_qlib_from_pip.yml

@@ -13,7 +13,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 
@@ -42,6 +45,9 @@ jobs:
 
     - name: Qlib installation test
       run: |
+        # 2024-05-30 scs has released a new version: 3.2.4.post2,
+        # This will cause the CI to fail, so we have limited the version of scs for now.
+        python -m pip install "scs<=3.2.4"
         python -m pip install pyqlib
 
     - name: Install Lightgbm for MacOS

.github/workflows/test_qlib_from_source.yml

@@ -14,7 +14,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 

.github/workflows/test_qlib_from_source_slow.yml

@@ -14,7 +14,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-latest]
+        # Since macos-latest changed from 12.7.4 to 14.4.1,
+        # the minimum python version that matches a 14.4.1 version of macos is 3.10,
+        # so we limit the macos version to macos-12.
+        os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-11, macos-12]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
         python-version: [3.7, 3.8]
 

.gitignore

@@ -48,4 +48,4 @@ tags
 *.swp
 
 ./pretrain
-.idea/
+.idea/

.readthedocs.yml → .readthedocs.yaml

@@ -5,6 +5,12 @@
 # Required
 version: 2
 
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.7"
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py
@@ -14,7 +20,6 @@ formats: all
 
 # Optionally set the version of Python and requirements required to build your docs
 python:
-  version: 3.7
   install:
     - requirements: docs/requirements.txt
     - method: pip

README.md

@@ -40,7 +40,7 @@ Recent released features
 Features released before 2021 are not listed here.
 
 <p align="center">
-  <img src="http://fintech.msra.cn/images_v070/logo/1.png" />
+  <img src="docs/_static/img/logo/1.png" />
 </p>
 
 Qlib is an open-source, AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms, including supervised learning, market dynamics modeling, and reinforcement learning.
@@ -166,13 +166,29 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 * Clone the repository and install ``Qlib`` as follows.
     ```bash
     git clone https://github.com/microsoft/qlib.git && cd qlib
-    pip install .
+    pip install .  # `pip install -e .[dev]` is recommended for development. check details in docs/developer/code_standard_and_dev_guide.rst
     ```
   **Note**:  You can install Qlib with `python setup.py install` as well. But it is not the recommended approach. It will skip `pip` and cause obscure problems. For example, **only** the command ``pip install .`` **can** overwrite the stable version installed by ``pip install pyqlib``, while the command ``python setup.py install`` **can't**.
 
 **Tips**: If you fail to install `Qlib` or run the examples in your environment,  comparing your steps and the [CI workflow](.github/workflows/test_qlib_from_source.yml) may help you find the problem.
 
+**Tips for Mac**: If you are using Mac with M1, you might encounter issues in building the wheel for LightGBM, which is due to missing dependencies from OpenMP. To solve the problem, install openmp first with ``brew install libomp`` and then run ``pip install .`` to build it successfully. 
+
 ## Data Preparation
+❗ Due to more restrict data security policy. The offical dataset is disabled temporarily. You can try [this data source](https://github.com/chenditc/investment_data/releases) contributed by the community.
+Here is an example to download the data updated on 20220720.
+```bash
+wget https://github.com/chenditc/investment_data/releases/download/20220720/qlib_bin.tar.gz
+mkdir -p ~/.qlib/qlib_data/cn_data
+tar -zxvf qlib_bin.tar.gz -C ~/.qlib/qlib_data/cn_data --strip-components=2
+rm -f qlib_bin.tar.gz
+```
+
+The official dataset below will resume in short future.
+
+
+----
+
 Load and prepare data by running the following code:
 
 ### Get with module

docs/requirements.txt

@@ -5,3 +5,4 @@ scipy
 scikit-learn
 pandas
 tianshou
+sphinx_rtd_theme

examples/benchmarks/TRA/src/model.py

@@ -324,7 +324,6 @@ def predict(self, dataset, segment="test"):
 
 
 class LSTM(nn.Module):
-
     """LSTM Model
 
     Args:
@@ -414,7 +413,6 @@ def forward(self, x):
 
 
 class Transformer(nn.Module):
-
     """Transformer Model
 
     Args:
@@ -475,7 +473,6 @@ def forward(self, x):
 
 
 class TRA(nn.Module):
-
     """Temporal Routing Adaptor (TRA)
 
     TRA takes historical prediction errors & latent representation as inputs,

examples/orderbook_data/README.md

@@ -16,7 +16,7 @@ Current version of script with default value tries to connect localhost **via de
 
 Run following command to install necessary libraries
 ```
-pip install pytest coverage
+pip install pytest coverage gdown
 pip install arctic  # NOTE: pip may fail to resolve the right package dependency !!! Please make sure the dependency are satisfied.
 ```
 
@@ -27,13 +27,12 @@ pip install arctic  # NOTE: pip may fail to resolve the right package dependency
 2. Please follow following steps to download example data
 ```bash
 cd examples/orderbook_data/
-wget http://fintech.msra.cn/stock_data/downloads/highfreq_orderboook_example_data.tar.bz2
-tar xf highfreq_orderboook_example_data.tar.bz2
+gdown https://drive.google.com/uc?id=15nZF7tFT_eKVZAcMFL1qPS4jGyJflH7e  # Proxies may be necessary here.
+python ../../scripts/get_data.py _unzip --file_path highfreq_orderbook_example_data.zip --target_dir .
 ```
 
 3. Please import the example data to your mongo db
 ```bash
-cd examples/orderbook_data/
 python create_dataset.py initialize_library  # Initialization Libraries
 python create_dataset.py import_data  # Initialization Libraries
 ```
@@ -42,7 +41,6 @@ python create_dataset.py import_data  # Initialization Libraries
 
 After importing these data, you run `example.py` to create some high-frequency features.
 ```bash
-cd examples/orderbook_data/
 pytest -s --disable-warnings example.py   # If you want run all examples
 pytest -s --disable-warnings example.py::TestClass::test_exp_10  # If you want to run specific example
 ```

qlib/__init__.py

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 from pathlib import Path
 
-__version__ = "0.9.3.99"
+__version__ = "0.9.5.99"
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
 import os
 from typing import Union

qlib/backtest/__init__.py

@@ -162,13 +162,15 @@ def create_account_instance(
         init_cash=init_cash,
         position_dict=position_dict,
         pos_type=pos_type,
-        benchmark_config={}
-        if benchmark is None
-        else {
-            "benchmark": benchmark,
-            "start_time": start_time,
-            "end_time": end_time,
-        },
+        benchmark_config=(
+            {}
+            if benchmark is None
+            else {
+                "benchmark": benchmark,
+                "start_time": start_time,
+                "end_time": end_time,
+            }
+        ),
     )
 
 

qlib/backtest/report.py

@@ -622,9 +622,11 @@ def cal_trade_indicators(
             print(
                 "[Indicator({}) {}]: FFR: {}, PA: {}, POS: {}".format(
                     freq,
-                    trade_start_time
-                    if isinstance(trade_start_time, str)
-                    else trade_start_time.strftime("%Y-%m-%d %H:%M:%S"),
+                    (
+                        trade_start_time
+                        if isinstance(trade_start_time, str)
+                        else trade_start_time.strftime("%Y-%m-%d %H:%M:%S")
+                    ),
                     fulfill_rate,
                     price_advantage,
                     positive_rate,

qlib/contrib/eva/alpha.py

@@ -3,6 +3,7 @@
 
 The interface should be redesigned carefully in the future.
 """
+
 import pandas as pd
 from typing import Tuple
 from qlib import get_module_logger

qlib/contrib/model/pytorch_tra.py

@@ -511,7 +511,6 @@ def predict(self, dataset, segment="test"):
 
 
 class RNN(nn.Module):
-
     """RNN Model
 
     Args:
@@ -601,7 +600,6 @@ def forward(self, x):
 
 
 class Transformer(nn.Module):
-
     """Transformer Model
 
     Args:
@@ -649,7 +647,6 @@ def forward(self, x):
 
 
 class TRA(nn.Module):
-
     """Temporal Routing Adaptor (TRA)
 
     TRA takes historical prediction errors & latent representation as inputs,

qlib/contrib/strategy/signal_strategy.py

@@ -373,7 +373,6 @@ def generate_trade_decision(self, execute_result=None):
 
 
 class EnhancedIndexingStrategy(WeightStrategyBase):
-
     """Enhanced Indexing Strategy
 
     Enhanced indexing combines the arts of active management and passive management,

qlib/data/client.py

@@ -35,7 +35,7 @@ def __init__(self, host, port):
     def connect_server(self):
         """Connect to server."""
         try:
-            self.sio.connect("ws://" + self.server_host + ":" + str(self.server_port))
+            self.sio.connect(f"ws://{self.server_host}:{self.server_port}")
         except socketio.exceptions.ConnectionError:
             self.logger.error("Cannot connect to server - check your network or server status")
 

qlib/data/data.py

@@ -536,7 +536,6 @@ def get_column_names(fields):
         """
         if len(fields) == 0:
             raise ValueError("fields cannot be empty")
-        fields = fields.copy()
         column_names = [str(f) for f in fields]
         return column_names
 

qlib/data/dataset/utils.py

@@ -9,7 +9,7 @@
     from qlib.data.dataset import DataHandler
 
 
-def get_level_index(df: pd.DataFrame, level=Union[str, int]) -> int:
+def get_level_index(df: pd.DataFrame, level: Union[str, int]) -> int:
     """
 
     get the level index of `df` given `level`

qlib/model/ens/ensemble.py

@@ -30,7 +30,6 @@ def __call__(self, ensemble_dict: dict, *args, **kwargs):
 
 
 class SingleKeyEnsemble(Ensemble):
-
     """
     Extract the object if there is only one key and value in the dict. Make the result more readable.
     {Only key: Only value} -> Only value
@@ -64,7 +63,6 @@ def __call__(self, ensemble_dict: Union[dict, object], recursion: bool = True) -
 
 
 class RollingEnsemble(Ensemble):
-
     """Merge a dict of rolling dataframe like `prediction` or `IC` into an ensemble.
 
     NOTE: The values of dict must be pd.DataFrame, and have the index "datetime".

qlib/model/riskmodel/shrink.py

@@ -247,9 +247,7 @@ def _get_shrink_param_lw_single_factor(self, X: np.ndarray, S: np.ndarray, F: np
         v1 = y.T.dot(z) / t - cov_mkt[:, None] * S
         roff1 = np.sum(v1 * cov_mkt[:, None].T) / var_mkt - np.sum(np.diag(v1) * cov_mkt) / var_mkt
         v3 = z.T.dot(z) / t - var_mkt * S
-        roff3 = (
-            np.sum(v3 * np.outer(cov_mkt, cov_mkt)) / var_mkt**2 - np.sum(np.diag(v3) * cov_mkt**2) / var_mkt**2
-        )
+        roff3 = np.sum(v3 * np.outer(cov_mkt, cov_mkt)) / var_mkt**2 - np.sum(np.diag(v3) * cov_mkt**2) / var_mkt**2
         roff = 2 * roff1 - roff3
         rho = rdiag + roff