fix: gen_training_orders.py bugs

* fix: the bug when auto_mount=True

* fix: the bug when auto_mount=True

README.md

@@ -324,7 +324,7 @@ We recommend users to prepare their own data if they have a high-quality dataset
     ```
 2. Start a new Docker container
     ```bash
-    docker run -it --name <container name> -v <Mounted local directory>:/app qlib_image_stable
+    docker run -it --name <container name> -v <Mounted local directory>:/app pyqlib/qlib_image_stable:stable
     ```
 3. At this point you are in the docker environment and can run the qlib scripts. An example:
     ```bash

examples/rl_order_execution/scripts/gen_training_orders.py

@@ -17,11 +17,11 @@ def generate_order(stock: str, start_idx: int, end_idx: int) -> bool:
     if len(df) == 0 or df.isnull().values.any() or min(df["$volume0"]) < 1e-5:
         return False
 
-    df["date"] = df["datetime"].dt.date.astype("datetime64")
+    df["date"] = df["datetime"].dt.date.astype("datetime64[ns]")
     df = df.set_index(["instrument", "datetime", "date"])
-    df = df.groupby("date", group_keys=False).take(range(start_idx, end_idx)).droplevel(level=0)
+    df = df.groupby("date", group_keys=True).take(range(start_idx, end_idx)).droplevel(level=0)
 
-    order_all = pd.DataFrame(df.groupby(level=(2, 0), group_keys=False).mean().dropna())
+    order_all = pd.DataFrame(df.groupby(level=(2, 0), group_keys=True).mean().dropna())
     order_all["amount"] = np.random.lognormal(-3.28, 1.14) * order_all["$volume0"]
     order_all = order_all[order_all["amount"] > 0.0]
     order_all["order_type"] = 0

pyproject.toml

@@ -45,7 +45,7 @@ dependencies = [
   "pymongo",
   "loguru",
   "lightgbm",
-  "gymnasium<=0.26.2",
+  "gym",
   "cvxpy",
   "joblib",
   "matplotlib",

qlib/__init__.py

@@ -140,7 +140,10 @@ def _mount_nfs_uri(provider_uri, mount_path, auto_mount: bool = False):
                     _command_log = [line for line in _command_log if _remote_uri in line]
                 if len(_command_log) > 0:
                     for _c in _command_log:
-                        _temp_mount = _c.decode("utf-8").split(" ")[2]
+                        if isinstance(_c, str):
+                            _temp_mount = _c.split(" ")[2]
+                        else:
+                            _temp_mount = _c.decode("utf-8").split(" ")[2]
                         _temp_mount = _temp_mount[:-1] if _temp_mount.endswith("/") else _temp_mount
                         if _temp_mount == _mount_path:
                             _is_mount = True

qlib/rl/interpreter.py

@@ -5,9 +5,9 @@ from __future__ import annotations
 
 from typing import Any, Generic, TypeVar
 
-import gymnasium as gym
+import gym
 import numpy as np
-from gymnasium import spaces
+from gym import spaces
 
 from qlib.typehint import final
 from .simulator import ActType, StateType

qlib/rl/order_execution/interpreter.py

@@ -8,7 +8,7 @@ from typing import Any, List, Optional, cast
 
 import numpy as np
 import pandas as pd
-from gymnasium import spaces
+from gym import spaces
 
 from qlib.constant import EPS
 from qlib.rl.data.base import ProcessedDataProvider

qlib/rl/order_execution/policy.py

@@ -6,11 +6,11 @@ from __future__ import annotations
 from pathlib import Path
 from typing import Any, Dict, Generator, Iterable, Optional, OrderedDict, Tuple, cast
 
-import gymnasium as gym
+import gym
 import numpy as np
 import torch
 import torch.nn as nn
-from gymnasium.spaces import Discrete
+from gym.spaces import Discrete
 from tianshou.data import Batch, ReplayBuffer, to_torch
 from tianshou.policy import BasePolicy, PPOPolicy, DQNPolicy
 

qlib/rl/utils/env_wrapper.py

@@ -6,8 +6,8 @@ from __future__ import annotations
 import weakref
 from typing import Any, Callable, cast, Dict, Generic, Iterable, Iterator, Optional, Tuple
 
-import gymnasium as gym
-from gymnasium import Space
+import gym
+from gym import Space
 
 from qlib.rl.aux_info import AuxiliaryInfoCollector
 from qlib.rl.interpreter import ActionInterpreter, ObsType, PolicyActType, StateInterpreter

qlib/rl/utils/finite_env.py

@@ -13,7 +13,7 @@ import warnings
 from contextlib import contextmanager
 from typing import Any, Callable, Dict, Generator, List, Optional, Set, Tuple, Type, Union, cast
 
-import gymnasium as gym
+import gym
 import numpy as np
 from tianshou.env import BaseVectorEnv, DummyVectorEnv, ShmemVectorEnv, SubprocVectorEnv
 

scripts/collect_info.py

@@ -45,7 +45,7 @@ class InfoCollector:
             "pymongo",
             "loguru",
             "lightgbm",
-            "gymnasium",
+            "gym",
             "cvxpy",
             "joblib",
             "matplotlib",

tests/rl/test_finite_env.py

@@ -3,7 +3,7 @@
 
 from collections import Counter
 
-import gymnasium as gym
+import gym
 import numpy as np
 from tianshou.data import Batch, Collector
 from tianshou.policy import BasePolicy

tests/rl/test_logger.py

@@ -7,10 +7,10 @@ import logging
 import re
 from typing import Any, Tuple
 
-import gymnasium as gym
+import gym
 import numpy as np
 import pandas as pd
-from gymnasium import spaces
+from gym import spaces
 from tianshou.data import Collector, Batch
 from tianshou.policy import BasePolicy
 

tests/rl/test_trainer.py

@@ -7,7 +7,7 @@ import pytest
 
 import torch
 import torch.nn as nn
-from gymnasium import spaces
+from gym import spaces
 from tianshou.policy import PPOPolicy
 
 from qlib.config import C