change get_data url

.github/workflows/test_qlib_from_source.yml

@@ -20,18 +20,28 @@ jobs:
 
     steps:
     - name: Test qlib from source
-      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 }}
-      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: "3.7.16"
+
+    - 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: ${{ matrix.python-version }}
 
     - name: Update pip to the latest version
       # pip release version 23.1 on Apr.15 2023, CI failed to run, Please refer to #1495 ofr detailed logs.
-      # The pip version has been temporarily fixed to 23.0.1
+      # The pip version has been temporarily fixed to 23.0
       run: |
-        python -m pip install pip==23.0.1
+        python -m pip install pip==23.0
 
     - name: Installing pytorch for macos
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}
@@ -129,8 +139,7 @@ jobs:
     - name: Test data downloads
       run: |
         python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        azcopy copy https://qlibpublic.blob.core.windows.net/data/rl /tmp/qlibpublic/data --recursive
-        mv /tmp/qlibpublic/data tests/.data
+        python scripts/get_data.py rl_data --target_dir tests/.data/rl
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-11' || matrix.os == 'macos-latest' }}

.github/workflows/test_qlib_from_source_slow.yml

@@ -20,18 +20,28 @@ jobs:
 
     steps:
     - name: Test qlib from source slow
-      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 }}
-      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: "3.7.16"
+
+    - 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: ${{ matrix.python-version }}
 
     - name: Set up Python tools
       # pip release version 23.1 on Apr.15 2023, CI failed to run, Please refer to #1495 ofr detailed logs.
-      # The pip version has been temporarily fixed to 23.0.1
+      # The pip version has been temporarily fixed to 23.0
       run: |
-        python -m pip install pip==23.0.1
+        python -m pip install pip==23.0
         pip install --upgrade cython numpy
         pip install -e .[dev]
 

qlib/tests/data.py

@@ -16,7 +16,7 @@
 
 class GetData:
     DATASET_VERSION = "v2"
-    REMOTE_URL = "https://qlibpublic.blob.core.windows.net/data/default/stock_data"
+    REMOTE_URL = "http://fintech.msra.cn/stock_data/downloads"
     QLIB_DATA_NAME = "{dataset_name}_{region}_{interval}_{qlib_version}.zip"
 
     def __init__(self, delete_zip_file=False):
@@ -165,6 +165,43 @@ def _get_file_name(v):
             file_name = _get_file_name("latest")
         self._download_data(file_name.lower(), target_dir, delete_old, dataset_version=version)
 
+    def rl_data(
+        self,
+        target_dir="~/.qlib/qlib_data/rl_data",
+        version=None,
+        delete_old=True,
+        exists_skip=False,
+    ):
+        """download cn qlib data from remote
+
+        Parameters
+        ----------
+        target_dir: str
+            data save directory
+        version: str
+            data version, value from [v1, ...], by default None(use script to specify version)
+        delete_old: bool
+            delete an existing directory, by default True
+        exists_skip: bool
+            exists skip, by default False
+
+        Examples
+        ---------
+        # get rl data
+        python get_data.py rl_data --target_dir ~/.qlib/qlib_data/rl_data
+        -------
+
+        """
+        if exists_skip and exists_qlib_data(target_dir):
+            logger.warning(
+                f"Data already exists: {target_dir}, the data download will be skipped\n"
+                f"\tIf downloading is required: `exists_skip=False` or `change target_dir`"
+            )
+            return
+
+        file_name = "rl.zip"
+        self._download_data(file_name.lower(), target_dir, delete_old, dataset_version=version)
+
     def csv_data_cn(self, target_dir="~/.qlib/csv_data/cn_data"):
         """download cn csv data from remote