fixed pytest error in CI

examples/data_demo/data_cache_demo.py

@@ -1,8 +1,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 """
-    The motivation of this demo
-    - To show the data modules of Qlib is Serializable, users can dump processed data to disk to avoid duplicated data preprocessing
+The motivation of this demo
+- To show the data modules of Qlib is Serializable, users can dump processed data to disk to avoid duplicated data preprocessing
 """
 
 from copy import deepcopy

examples/data_demo/data_mem_resuse_demo.py

@@ -1,8 +1,8 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 """
-    The motivation of this demo
-    - To show the data modules of Qlib is Serializable, users can dump processed data to disk to avoid duplicated data preprocessing
+The motivation of this demo
+- To show the data modules of Qlib is Serializable, users can dump processed data to disk to avoid duplicated data preprocessing
 """
 
 from copy import deepcopy

examples/orderbook_data/create_dataset.py

@@ -1,10 +1,10 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 """
-    NOTE:
-    - This scripts is a demo to import example data import Qlib
-    - !!!!!!!!!!!!!!!TODO!!!!!!!!!!!!!!!!!!!:
-        - Its structure is not well designed and very ugly, your contribution is welcome to make importing dataset easier
+NOTE:
+- This scripts is a demo to import example data import Qlib
+- !!!!!!!!!!!!!!!TODO!!!!!!!!!!!!!!!!!!!:
+    - Its structure is not well designed and very ugly, your contribution is welcome to make importing dataset easier
 """
 from datetime import date, datetime as dt
 import os

examples/workflow_by_code.py

@@ -1,7 +1,7 @@
 #  Copyright (c) Microsoft Corporation.
 #  Licensed under the MIT License.
 """
-Qlib provides two kinds of interfaces. 
+Qlib provides two kinds of interfaces.
 (1) Users could define the Quant research workflow by a simple configuration.
 (2) Qlib is designed in a modularized way and supports creating research workflow by code just like building blocks.
 

pyproject.toml

@@ -79,6 +79,7 @@ package = [
 test = [
   "yahooquery",
   "baostock",
+  "akshare",
 ]
 analysis = [
   "plotly",

qlib/contrib/torch.py

@@ -1,9 +1,9 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 """
-    This module is not a necessary part of Qlib.
-    They are just some tools for convenience
-    It is should not imported into the core part of qlib
+This module is not a necessary part of Qlib.
+They are just some tools for convenience
+It is should not imported into the core part of qlib
 """
 import torch
 import numpy as np

qlib/rl/trainer/trainer.py

@@ -200,7 +200,7 @@ class Trainer:
 
         if ckpt_path is not None:
             _logger.info("Resuming states from %s", str(ckpt_path))
-            self.load_state_dict(torch.load(ckpt_path))
+            self.load_state_dict(torch.load(ckpt_path, weights_only=False))
         else:
             self.initialize()
 

scripts/data_collector/utils.py

@@ -13,6 +13,7 @@ import functools
 from pathlib import Path
 from typing import Iterable, Tuple, List
 
+import akshare as ak
 import numpy as np
 import pandas as pd
 from loguru import logger
@@ -202,18 +203,9 @@ def get_hs_stock_symbols() -> list:
         -------
             {600000.ss, 600001.ss, 600002.ss, 600003.ss, ...}
         """
-        url = "http://99.push2.eastmoney.com/api/qt/clist/get?pn=1&pz=10000&po=1&np=1&fs=m:0+t:6,m:0+t:80,m:1+t:2,m:1+t:23,m:0+t:81+s:2048&fields=f12"
-        try:
-            resp = requests.get(url, timeout=None)
-            resp.raise_for_status()
-        except requests.exceptions.HTTPError as e:
-            raise requests.exceptions.HTTPError(f"Request to {url} failed with status code {resp.status_code}") from e
-
-        try:
-            _symbols = [_v["f12"] for _v in resp.json()["data"]["diff"]]
-        except Exception as e:
-            logger.warning("An error occurred while extracting data from the response.")
-            raise
+        stock_info_a_code_name_df = ak.stock_info_a_code_name()
+        stock_codes = stock_info_a_code_name_df["code"].tolist()
+        _symbols = [code for code in stock_codes if code and code.strip()]
 
         if len(_symbols) < 3900:
             raise ValueError("The complete list of stocks is not available.")

scripts/data_collector/yahoo/README.md

@@ -50,12 +50,6 @@ pip install -r requirements.txt
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data_1min --region cn --interval 1min
     # us 1d
     python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/us_data --region us --interval 1d
-    # us 1min
-    python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/us_data_1min --region us --interval 1min
-    # in 1d
-    python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/in_data --region in --interval 1d
-    # in 1min
-    python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/in_data_1min --region in --interval 1min
     ```
 
 ### Collector *YahooFinance* data to qlib

tests/rl/test_trainer.py

@@ -194,7 +194,7 @@ def test_trainer_checkpoint():
     assert (output_dir / "002.pth").exists()
     assert os.readlink(output_dir / "latest.pth") == str(output_dir / "002.pth")
 
-    trainer.load_state_dict(torch.load(output_dir / "001.pth"))
+    trainer.load_state_dict(torch.load(output_dir / "001.pth", weights_only=False))
     assert trainer.current_iter == 1
     assert trainer.current_episode == 100