change get_data url (#1558)

* change_url

* fix_CI

* fix_CI_2

* fix_CI_3

* fix_CI_4

* fix_CI_5

* fix_CI_6

* fix_CI_7

* fix_CI_8

* fix_CI_9

* fix_CI_10

* fix_CI_11

* fix_CI_12

* fix_CI_13

* fix_CI_13

* fix_CI_14

* fix_CI_15

* fix_CI_16

* fix_CI_17

* fix_CI_18

* fix_CI_19

* fix_CI_20

* fix_CI_21

* fix_CI_22

* fix_CI_23

* fix_CI_24

* fix_CI_25

* fix_CI_26

* fix_CI_27

* fix_get_data_error

* fix_get_data_error2

* modify_get_data

* modify_get_data2

* modify_get_data3

* modify_get_data4

* fix_CI_28

* fix_CI_29

* fix_CI_30

---------

Co-authored-by: Linlang <v-linlanglv@microsoft.com>

.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 }}
+      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 }}
 
     - 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
+        python scripts/get_data.py download_data --file_name rl_data.zip --target_dir tests/.data/rl
-        mv /tmp/qlibpublic/data tests/.data
 
     - 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 }}
+      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 }}
 
     - 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]
 

docs/component/data.rst

@@ -119,7 +119,7 @@ Here are some example:
 for daily data:
   .. code-block:: bash
 
-    python scripts/get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
+    python scripts/get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
 
 for 1min data:
   .. code-block:: bash

qlib/tests/data.py

@@ -1,6 +1,7 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
+import os
 import re
 import sys
 import qlib
@@ -11,13 +12,15 @@ import datetime
 from tqdm import tqdm
 from pathlib import Path
 from loguru import logger
+from cryptography.fernet import Fernet
 from qlib.utils import exists_qlib_data
 
 
 class GetData:
-    DATASET_VERSION = "v2"
     REMOTE_URL = "https://qlibpublic.blob.core.windows.net/data/default/stock_data"
-    QLIB_DATA_NAME = "{dataset_name}_{region}_{interval}_{qlib_version}.zip"
+    # "?" is not included in the token.
+    TOKEN = "gAAAAABkmDhojHc0VSCDdNK1MqmRzNLeDFXe5hy8obHpa6SDQh4de6nW5gtzuD-fa6O_WZb0yyqYOL7ndOfJX_751W3xN5YB4-n-P22jK-t6ucoZqhT70KPD0Lf0_P328QPJVZ1gDnjIdjhi2YLOcP4BFTHLNYO0mvzszR8TKm9iT5AKRvuysWnpi8bbYwGU9zAcJK3x9EPL43hOGtxliFHcPNGMBoJW4g_ercdhi0-Qgv5_JLsV-29_MV-_AhuaYvJuN2dEywBy"
+    KEY = "EYcA8cgorA8X9OhyMwVfuFxn_1W3jGk6jCbs3L2oPoA="
 
     def __init__(self, delete_zip_file=False):
         """
@@ -29,24 +32,44 @@ class GetData:
         """
         self.delete_zip_file = delete_zip_file
 
-    def normalize_dataset_version(self, dataset_version: str = None):
+    def merge_remote_url(self, file_name: str):
-        if dataset_version is None:
+        fernet = Fernet(self.KEY)
-            dataset_version = self.DATASET_VERSION
+        token = fernet.decrypt(self.TOKEN).decode()
-        return dataset_version
+        return f"{self.REMOTE_URL}/{file_name}?{token}"
 
-    def merge_remote_url(self, file_name: str, dataset_version: str = None):
+    def download_data(self, file_name: str, target_dir: [Path, str], delete_old: bool = True):
-        return f"{self.REMOTE_URL}/{self.normalize_dataset_version(dataset_version)}/{file_name}"
+        """
+        Download the specified file to the target folder.
 
-    def _download_data(
+        Parameters
-        self, file_name: str, target_dir: [Path, str], delete_old: bool = True, dataset_version: str = None
+        ----------
-    ):
+        target_dir: str
+            data save directory
+        file_name: str
+            dataset name, needs to endwith .zip, value from [rl_data.zip, csv_data_cn.zip, ...]
+            may contain folder names, for example: v2/qlib_data_simple_cn_1d_latest.zip
+        delete_old: bool
+            delete an existing directory, by default True
+
+        Examples
+        ---------
+        # get rl data
+        python get_data.py download_data --file_name rl_data.zip --target_dir ~/.qlib/qlib_data/rl_data
+        When this command is run, the data will be downloaded from this link: https://qlibpublic.blob.core.windows.net/data/default/stock_data/rl_data.zip?{token}
+
+        # get cn csv data
+        python get_data.py download_data --file_name csv_data_cn.zip --target_dir ~/.qlib/csv_data/cn_data
+        When this command is run, the data will be downloaded from this link: https://qlibpublic.blob.core.windows.net/data/default/stock_data/csv_data_cn.zip?{token}
+        -------
+
+        """
         target_dir = Path(target_dir).expanduser()
         target_dir.mkdir(exist_ok=True, parents=True)
         # saved file name
-        _target_file_name = datetime.datetime.now().strftime("%Y%m%d%H%M%S") + "_" + file_name
+        _target_file_name = datetime.datetime.now().strftime("%Y%m%d%H%M%S") + "_" + os.path.basename(file_name)
         target_path = target_dir.joinpath(_target_file_name)
 
-        url = self.merge_remote_url(file_name, dataset_version)
+        url = self.merge_remote_url(file_name)
         resp = requests.get(url, stream=True, timeout=60)
         resp.raise_for_status()
         if resp.status_code != 200:
@@ -56,7 +79,7 @@ class GetData:
         logger.warning(
             f"The data for the example is collected from Yahoo Finance. Please be aware that the quality of the data might not be perfect. (You can refer to the original data source: https://finance.yahoo.com/lookup.)"
         )
-        logger.info(f"{file_name} downloading......")
+        logger.info(f"{os.path.basename(file_name)} downloading......")
         with tqdm(total=int(resp.headers.get("Content-Length", 0))) as p_bar:
             with target_path.open("wb") as fp:
                 for chunk in resp.iter_content(chunk_size=chunk_size):
@@ -67,8 +90,8 @@ class GetData:
         if self.delete_zip_file:
             target_path.unlink()
 
-    def check_dataset(self, file_name: str, dataset_version: str = None):
+    def check_dataset(self, file_name: str):
-        url = self.merge_remote_url(file_name, dataset_version)
+        url = self.merge_remote_url(file_name)
         resp = requests.get(url, stream=True, timeout=60)
         status = True
         if resp.status_code == 404:
@@ -140,9 +163,11 @@ class GetData:
         ---------
         # get 1d data
         python get_data.py qlib_data --name qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
+        When this command is run, the data will be downloaded from this link: https://qlibpublic.blob.core.windows.net/data/default/stock_data/v2/qlib_data_cn_1d_latest.zip?{token}
 
         # get 1min data
         python get_data.py qlib_data --name qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --interval 1min --region cn
+        When this command is run, the data will be downloaded from this link: https://qlibpublic.blob.core.windows.net/data/default/stock_data/v2/qlib_data_cn_1min_latest.zip?{token}
         -------
 
         """
@@ -155,29 +180,12 @@ class GetData:
 
         qlib_version = ".".join(re.findall(r"(\d+)\.+", qlib.__version__))
 
-        def _get_file_name(v):
+        def _get_file_name_with_version(qlib_version, dataset_version):
-            return self.QLIB_DATA_NAME.format(
+            dataset_version = "v2" if dataset_version is None else dataset_version
-                dataset_name=name, region=region.lower(), interval=interval.lower(), qlib_version=v
+            file_name_with_version = f"{dataset_version}/{name}_{region.lower()}_{interval.lower()}_{qlib_version}.zip"
-            )
+            return file_name_with_version
 
-        file_name = _get_file_name(qlib_version)
+        file_name = _get_file_name_with_version(qlib_version, dataset_version=version)
-        if not self.check_dataset(file_name, version):
+        if not self.check_dataset(file_name):
-            file_name = _get_file_name("latest")
+            file_name = _get_file_name_with_version("latest", dataset_version=version)
-        self._download_data(file_name.lower(), target_dir, delete_old, dataset_version=version)
+        self.download_data(file_name.lower(), target_dir, delete_old)
-
-    def csv_data_cn(self, target_dir="~/.qlib/csv_data/cn_data"):
-        """download cn csv data from remote
-
-        Parameters
-        ----------
-        target_dir: str
-            data save directory
-
-        Examples
-        ---------
-        python get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
-        -------
-
-        """
-        file_name = "csv_data_cn.zip"
-        self._download_data(file_name, target_dir)

setup.py

@@ -80,6 +80,7 @@ REQUIRED = [
     "gym",
     # Installing the latest version of protobuf for python versions below 3.8 will cause unit tests to fail.
     "protobuf<=3.20.1;python_version<='3.8'",
+    "cryptography",
 ]
 
 # Numpy include

tests/test_dump_data.py

@@ -35,7 +35,7 @@ class TestDumpData(unittest.TestCase):
 
     @classmethod
     def setUpClass(cls) -> None:
-        GetData().csv_data_cn(SOURCE_DIR)
+        GetData().download_data(file_name="csv_data_cn.zip", target_dir=SOURCE_DIR)
         TestDumpData.DUMP_DATA = DumpDataAll(csv_path=SOURCE_DIR, qlib_dir=QLIB_DIR, include_fields=cls.FIELDS)
         TestDumpData.STOCK_NAMES = list(map(lambda x: x.name[:-4].upper(), SOURCE_DIR.glob("*.csv")))
         provider_uri = str(QLIB_DIR.resolve())

tests/test_get_data.py

@@ -42,7 +42,7 @@ class TestGetData(unittest.TestCase):
         self.assertFalse(df.dropna().empty, "get qlib data failed")
 
     def test_1_csv_data(self):
-        GetData().csv_data_cn(SOURCE_DIR)
+        GetData().download_data(file_name="csv_data_cn.zip", target_dir=SOURCE_DIR)
         stock_name = set(map(lambda x: x.name[:-4].upper(), SOURCE_DIR.glob("*.csv")))
         self.assertEqual(len(stock_name), 85, "get csv data failed")