fix(security): use RestrictedUnpickler in load_instance (#2153)

* fix(security): enforce RestrictedUnpickler for load_instance to prevent unsafe pickle deserialization

* fix: lint error

examples/benchmarks/TFT/tft.py

@@ -19,7 +19,6 @@ from qlib.model.base import ModelFT
 from qlib.data.dataset import DatasetH
 from qlib.data.dataset.handler import DataHandlerLP
 
-
 # To register new datasets, please add them here.
 ALLOW_DATASET = ["Alpha158", "Alpha360"]
 # To register new datasets, please add their configurations here.

examples/benchmarks/TRA/src/dataset.py

@@ -8,7 +8,6 @@ import pandas as pd
 
 from qlib.data.dataset import DatasetH
 
-
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 

examples/benchmarks_dynamic/DDG-DA/vis_data.py

@@ -1,9 +1,10 @@
-import pickle
 import numpy as np
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
 
+from qlib.utils.pickle_utils import restricted_pickle_load
+
 sns.set(color_codes=True)
 plt.rcParams["font.sans-serif"] = "SimHei"
 plt.rcParams["axes.unicode_minus"] = False
@@ -18,7 +19,7 @@ from tqdm.auto import tqdm
 
 # +
 with open("./internal_data_s20.pkl", "rb") as f:
-    data = pickle.load(f)
+    data = restricted_pickle_load(f)
 
 data.data_ic_df.columns.names = ["start_date", "end_date"]
 
@@ -52,7 +53,7 @@ pd.DataFrame(meta_m.tn.twm.linear.weight.detach().numpy()).T[0].rolling(5).mean(
 
 # +
 with open("./tasks_s20.pkl", "rb") as f:
-    tasks = pickle.load(f)
+    tasks = restricted_pickle_load(f)
 
 task_df = {}
 for t in tasks:

examples/highfreq/workflow.py

@@ -4,11 +4,11 @@
 import fire
 
 import qlib
-import pickle
 from qlib.constant import REG_CN
 from qlib.config import HIGH_FREQ_CONFIG
 
 from qlib.utils import init_instance_by_config
+from qlib.utils.pickle_utils import restricted_pickle_load
 from qlib.data.dataset.handler import DataHandlerLP
 from qlib.data.ops import Operators
 from qlib.data.data import Cal
@@ -125,10 +125,10 @@ class HighfreqWorkflow:
         del dataset, dataset_backtest
         ##=============reload dataset=============
         with open("dataset.pkl", "rb") as file_dataset:
-            dataset = pickle.load(file_dataset)
+            dataset = restricted_pickle_load(file_dataset)
 
         with open("dataset_backtest.pkl", "rb") as file_dataset_backtest:
-            dataset_backtest = pickle.load(file_dataset_backtest)
+            dataset_backtest = restricted_pickle_load(file_dataset_backtest)
 
         self._prepare_calender_cache()
         ##=============reinit dataset=============

examples/model_interpreter/feature.py

@@ -9,7 +9,6 @@ from qlib.utils import init_instance_by_config
 from qlib.tests.data import GetData
 from qlib.tests.config import CSI300_GBDT_TASK
 
-
 if __name__ == "__main__":
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir

examples/nested_decision_execution/workflow.py

@@ -95,7 +95,6 @@ pos  0.000000
 [1706497:MainThread](2021-12-07 14:08:30,627) INFO - qlib.timer - [log.py:113] - Time cost: 0.014s | waiting `async_log` Done
 """
 
-
 from copy import deepcopy
 import qlib
 import fire

examples/online_srv/update_online_pred.py

@@ -7,6 +7,7 @@ There are two parts including first_train and update_online_pred.
 Firstly, we will finish the training and set the trained models to the `online` models.
 Next, we will finish updating online predictions.
 """
+
 import copy
 import fire
 import qlib

examples/orderbook_data/create_dataset.py

@@ -6,6 +6,7 @@ NOTE:
 - !!!!!!!!!!!!!!!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
 from pathlib import Path

examples/rl_order_execution/scripts/merge_orders.py

@@ -1,13 +1,15 @@
-import pickle
 import os
 import pandas as pd
 from tqdm import tqdm
 
+from qlib.utils.pickle_utils import restricted_pickle_load
+
 for tag in ["test", "valid"]:
     files = os.listdir(os.path.join("data/orders/", tag))
     dfs = []
     for f in tqdm(files):
-        df = pickle.load(open(os.path.join("data/orders/", tag, f), "rb"))
+        with open(os.path.join("data/orders/", tag, f), "rb") as fr:
+            df = restricted_pickle_load(fr)
         df = df.drop(["$close0"], axis=1)
         dfs.append(df)
 

examples/rolling_process_data/workflow.py

@@ -3,12 +3,12 @@
 
 import qlib
 import fire
-import pickle
 
 from datetime import datetime
 from qlib.constant import REG_CN
 from qlib.data.dataset.handler import DataHandlerLP
 from qlib.utils import init_instance_by_config
+from qlib.utils.pickle_utils import restricted_pickle_load
 from qlib.tests.data import GetData
 
 
@@ -42,7 +42,7 @@ class RollingDataWorkflow:
 
     def _load_pre_handler(self, path):
         with open(path, "rb") as file_dataset:
-            pre_handler = pickle.load(file_dataset)
+            pre_handler = restricted_pickle_load(file_dataset)
         return pre_handler
 
     def rolling_process(self):

examples/workflow_by_code.py

@@ -7,6 +7,7 @@ Qlib provides two kinds of interfaces.
 
 The interface of (1) is `qrun XXX.yaml`.  The interface of (2) is script like this, which nearly does the same thing as `qrun XXX.yaml`
 """
+
 import qlib
 from qlib.constant import REG_CN
 from qlib.utils import init_instance_by_config, flatten_dict
@@ -15,7 +16,6 @@ from qlib.workflow.record_temp import SignalRecord, PortAnaRecord, SigAnaRecord
 from qlib.tests.data import GetData
 from qlib.tests.config import CSI300_BENCH, CSI300_GBDT_TASK
 
-
 if __name__ == "__main__":
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir