update version

* fix get data error

* fix get v0 data error

* optimize get_data code

* fix pylint error

* add comments

.gitignore

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

.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

@@ -175,6 +175,20 @@ Also, users can install the latest dev version ``Qlib`` by the source code accor
 **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/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.
 ```
 
@@ -27,7 +27,8 @@ 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/
-python ../../scripts/get_data.py download_data --target_dir . --file_name highfreq_orderbook_example_data.zip
+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

qlib/__init__.py

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 from pathlib import Path
 
-__version__ = "0.9.4"
+__version__ = "0.9.5"
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
 import os
 from typing import Union

qlib/data/data.py

@@ -536,7 +536,6 @@ class DatasetProvider(abc.ABC):
         """
         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/tests/data.py

@@ -12,15 +12,11 @@ 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:
-    REMOTE_URL = "https://qlibpublic.blob.core.windows.net/data/default/stock_data"
-    # "?" is not included in the token.
-    TOKEN = b"gAAAAABkmDhojHc0VSCDdNK1MqmRzNLeDFXe5hy8obHpa6SDQh4de6nW5gtzuD-fa6O_WZb0yyqYOL7ndOfJX_751W3xN5YB4-n-P22jK-t6ucoZqhT70KPD0Lf0_P328QPJVZ1gDnjIdjhi2YLOcP4BFTHLNYO0mvzszR8TKm9iT5AKRvuysWnpi8bbYwGU9zAcJK3x9EPL43hOGtxliFHcPNGMBoJW4g_ercdhi0-Qgv5_JLsV-29_MV-_AhuaYvJuN2dEywBy"
-    KEY = "EYcA8cgorA8X9OhyMwVfuFxn_1W3jGk6jCbs3L2oPoA="
+    REMOTE_URL = "https://github.com/SunsetWolf/qlib_dataset/releases/download"
 
     def __init__(self, delete_zip_file=False):
         """
@@ -33,9 +29,45 @@ class GetData:
         self.delete_zip_file = delete_zip_file
 
     def merge_remote_url(self, file_name: str):
-        fernet = Fernet(self.KEY)
-        token = fernet.decrypt(self.TOKEN).decode()
-        return f"{self.REMOTE_URL}/{file_name}?{token}"
+        """
+        Generate download links.
+
+        Parameters
+        ----------
+        file_name: str
+            The name of the file to be downloaded.
+            The file name can be accompanied by a version number, (e.g.: v2/qlib_data_simple_cn_1d_latest.zip),
+            if no version number is attached, it will be downloaded from v0 by default.
+        """
+        return f"{self.REMOTE_URL}/{file_name}" if "/" in file_name else f"{self.REMOTE_URL}/v0/{file_name}"
+
+    def download(self, url: str, target_path: [Path, str]):
+        """
+        Download a file from the specified url.
+
+        Parameters
+        ----------
+        url: str
+            The url of the data.
+        target_path: str
+            The location where the data is saved, including the file name.
+        """
+        file_name = str(target_path).rsplit("/", maxsplit=1)[-1]
+        resp = requests.get(url, stream=True, timeout=60)
+        resp.raise_for_status()
+        if resp.status_code != 200:
+            raise requests.exceptions.HTTPError()
+
+        chunk_size = 1024
+        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"{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):
+                    fp.write(chunk)
+                    p_bar.update(chunk_size)
 
     def download_data(self, file_name: str, target_dir: [Path, str], delete_old: bool = True):
         """
@@ -70,21 +102,7 @@ class GetData:
         target_path = target_dir.joinpath(_target_file_name)
 
         url = self.merge_remote_url(file_name)
-        resp = requests.get(url, stream=True, timeout=60)
-        resp.raise_for_status()
-        if resp.status_code != 200:
-            raise requests.exceptions.HTTPError()
-
-        chunk_size = 1024
-        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"{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):
-                    fp.write(chunk)
-                    p_bar.update(chunk_size)
+        self.download(url=url, target_path=target_path)
 
         self._unzip(target_path, target_dir, delete_old)
         if self.delete_zip_file:
@@ -99,7 +117,9 @@ class GetData:
         return status
 
     @staticmethod
-    def _unzip(file_path: Path, target_dir: Path, delete_old: bool = True):
+    def _unzip(file_path: [Path, str], target_dir: [Path, str], delete_old: bool = True):
+        file_path = Path(file_path)
+        target_dir = Path(target_dir)
         if delete_old:
             logger.warning(
                 f"will delete the old qlib data directory(features, instruments, calendars, features_cache, dataset_cache): {target_dir}"

qlib/utils/__init__.py

@@ -25,7 +25,12 @@ import pandas as pd
 from pathlib import Path
 from typing import List, Union, Optional, Callable
 from packaging import version
-from .file import get_or_create_path, save_multiple_parts_file, unpack_archive_with_buffer, get_tmp_file_with_buffer
+from .file import (
+    get_or_create_path,
+    save_multiple_parts_file,
+    unpack_archive_with_buffer,
+    get_tmp_file_with_buffer,
+)
 from ..config import C
 from ..log import get_module_logger, set_log_with_config
 
@@ -37,7 +42,12 @@ is_deprecated_lexsorted_pandas = version.parse(pd.__version__) > version.parse("
 #################### Server ####################
 def get_redis_connection():
     """get redis connection instance."""
-    return redis.StrictRedis(host=C.redis_host, port=C.redis_port, db=C.redis_task_db, password=C.redis_password)
+    return redis.StrictRedis(
+        host=C.redis_host,
+        port=C.redis_port,
+        db=C.redis_task_db,
+        password=C.redis_password,
+    )
 
 
 #################### Data ####################
@@ -96,7 +106,14 @@ def get_period_offset(first_year, period, quarterly):
     return offset
 
 
-def read_period_data(index_path, data_path, period, cur_date_int: int, quarterly, last_period_index: int = None):
+def read_period_data(
+    index_path,
+    data_path,
+    period,
+    cur_date_int: int,
+    quarterly,
+    last_period_index: int = None,
+):
     """
     At `cur_date`(e.g. 20190102), read the information at `period`(e.g. 201803).
     Only the updating info before cur_date or at cur_date will be used.
@@ -273,7 +290,10 @@ def parse_field(field):
     # \uff09 -> )
     chinese_punctuation_regex = r"\u3001\uff1a\uff08\uff09"
     for pattern, new in [
-        (rf"\$\$([\w{chinese_punctuation_regex}]+)", r'PFeature("\1")'),  # $$ must be before $
+        (
+            rf"\$\$([\w{chinese_punctuation_regex}]+)",
+            r'PFeature("\1")',
+        ),  # $$ must be before $
         (rf"\$([\w{chinese_punctuation_regex}]+)", r'Feature("\1")'),
         (r"(\w+\s*)\(", r"Operators.\1("),
     ]:  # Features  # Operators
@@ -383,7 +403,14 @@ def get_date_range(trading_date, left_shift=0, right_shift=0, future=False):
     return calendar
 
 
-def get_date_by_shift(trading_date, shift, future=False, clip_shift=True, freq="day", align: Optional[str] = None):
+def get_date_by_shift(
+    trading_date,
+    shift,
+    future=False,
+    clip_shift=True,
+    freq="day",
+    align: Optional[str] = None,
+):
     """get trading date with shift bias will cur_date
         e.g. : shift == 1,  return next trading date
                shift == -1, return previous trading date
@@ -569,7 +596,38 @@ def exists_qlib_data(qlib_dir):
     # check instruments
     code_names = set(map(lambda x: fname_to_code(x.name.lower()), features_dir.iterdir()))
     _instrument = instruments_dir.joinpath("all.txt")
-    miss_code = set(pd.read_csv(_instrument, sep="\t", header=None).loc[:, 0].apply(str.lower)) - set(code_names)
+    # Removed two possible ticker names "NA" and "NULL" from the default na_values list for column 0
+    miss_code = set(
+        pd.read_csv(
+            _instrument,
+            sep="\t",
+            header=None,
+            keep_default_na=False,
+            na_values={
+                0: [
+                    " ",
+                    "#N/A",
+                    "#N/A N/A",
+                    "#NA",
+                    "-1.#IND",
+                    "-1.#QNAN",
+                    "-NaN",
+                    "-nan",
+                    "1.#IND",
+                    "1.#QNAN",
+                    "<NA>",
+                    "N/A",
+                    "NaN",
+                    "None",
+                    "n/a",
+                    "nan",
+                    "null ",
+                ]
+            },
+        )
+        .loc[:, 0]
+        .apply(str.lower)
+    ) - set(code_names)
     if miss_code and any(map(lambda x: "sht" not in x, miss_code)):
         return False
 

scripts/data_collector/cn_index/collector.py

@@ -396,14 +396,7 @@ class CSI500Index(CSIIndex):
         today = pd.Timestamp.now()
         date_range = pd.DataFrame(pd.date_range(start="2007-01-15", end=today, freq="7D"))[0].dt.date
         ret_list = []
-        col = ["date", "symbol", "code_name"]
         for date in tqdm(date_range, desc="Download CSI500"):
-            rs = bs.query_zz500_stocks(date=str(date))
-            zz500_stocks = []
-            while (rs.error_code == "0") & rs.next():
-                zz500_stocks.append(rs.get_row_data())
-            result = pd.DataFrame(zz500_stocks, columns=col)
-            result["symbol"] = result["symbol"].apply(lambda x: x.replace(".", "").upper())
             result = self.get_data_from_baostock(date)
             ret_list.append(result[["date", "symbol"]])
         bs.logout()

scripts/data_collector/cn_index/requirements.txt

@@ -5,3 +5,5 @@ pandas
 lxml
 loguru
 tqdm
+yahooquery
+openpyxl

scripts/dump_pit.py

@@ -3,7 +3,7 @@
 """
 TODO:
 - A more well-designed PIT database is required.
-    - seperated insert, delete, update, query operations are required.
+    - separated insert, delete, update, query operations are required.
 """
 
 import shutil