[FIX] enable the code pass the flake8 test

examples/dataset_table_workflow/base.py

@@ -1,6 +1,5 @@
 import os
 import time
-import torch
 import random
 import requests
 import tempfile
@@ -12,8 +11,8 @@ from learnware.market import instantiate_learnware_market
 from learnware.reuse.utils import fill_data_with_mean
 from learnware.tests.benchmarks import LearnwareBenchmark
 
-from config import *
-from methods import *
+from config import market_mapping_params
+from methods import loss_func_rmse, test_methods
 from utils import set_seed
 
 logger = get_module_logger("base_table", level="INFO")
@@ -26,14 +25,14 @@ class TableWorkflow:
         self.curves_result_path = os.path.join(self.result_path, "curves")
         os.makedirs(self.result_path, exist_ok=True)
         os.makedirs(self.curves_result_path, exist_ok=True)
-        self._prepare_market(benchmark_config, name, rebuild, retrain)    
-    
+        self._prepare_market(benchmark_config, name, rebuild, retrain)
+
     @staticmethod
     def _limited_data(method, test_info, loss_func):
         def subset_generator():
             for subset in test_info["train_subsets"]:
                 yield subset
-                
+
         all_scores = []
         for subset in subset_generator():
             subset_scores = []
@@ -43,7 +42,7 @@ class TableWorkflow:
                 subset_scores.append(loss_func(model.predict(test_info["test_x"]), test_info["test_y"]))
             all_scores.append(subset_scores)
         return all_scores
-    
+
     @staticmethod
     def get_train_subsets(n_labeled_list, n_repeat_list, train_x, train_y):
         np.random.seed(1)
@@ -56,9 +55,11 @@ class TableWorkflow:
                 n_label = len(train_x)
             for _ in range(repeated):
                 subset_idxs = np.random.choice(len(train_x), n_label, replace=False)
-                train_subsets[-1].append({"x_train": np.array(train_x[subset_idxs]), "y_train": np.array(train_y[subset_idxs])})
+                train_subsets[-1].append(
+                    {"x_train": np.array(train_x[subset_idxs]), "y_train": np.array(train_y[subset_idxs])}
+                )
         return train_subsets
-    
+
     def _prepare_market(self, benchmark_config, name, rebuild, retrain):
         client = LearnwareClient()
         self.benchmark = LearnwareBenchmark().get_benchmark(benchmark_config)
@@ -69,14 +70,17 @@ class TableWorkflow:
             organizer_kwargs={
                 "auto_update": True,
                 "auto_update_limit": len(self.benchmark.learnware_ids),
-                **market_mapping_params
-            } if retrain else None
+                **market_mapping_params,
+            }
+            if retrain
+            else None,
         )
         self.user_semantic = client.get_semantic_specification(self.benchmark.learnware_ids[0])
         self.user_semantic["Name"]["Values"] = ""
-        
-        if len(self.market) == 0 or rebuild == True:
-            if retrain: set_seed(0)
+
+        if len(self.market) == 0 or rebuild is True:
+            if retrain:
+                set_seed(0)
             for learnware_id in self.benchmark.learnware_ids:
                 with tempfile.TemporaryDirectory(prefix="table_benchmark_") as tempdir:
                     zip_path = os.path.join(tempdir, f"{learnware_id}.zip")
@@ -87,24 +91,28 @@ class TableWorkflow:
                             self.market.add_learnware(zip_path, semantic_spec)
                             break
                         except (requests.exceptions.RequestException, IOError, Exception) as e:
-                            logger.info(f"An error occurred when downloading {learnware_id}: {e}\n{traceback.format_exc()}, retrying...")
+                            logger.info(
+                                f"An error occurred when downloading {learnware_id}: {e}\n{traceback.format_exc()}, retrying..."
+                            )
                             time.sleep(1)
                             continue
-        
+
     def test_method(self, test_info, recorders, loss_func=loss_func_rmse):
         method_name_full = test_info["method_name"]
-        method_name = method_name_full if method_name_full == "user_model" else "_".join(method_name_full.split("_")[1:])
+        method_name = (
+            method_name_full if method_name_full == "user_model" else "_".join(method_name_full.split("_")[1:])
+        )
         method = test_methods[method_name_full]
         user, idx = test_info["user"], test_info["idx"]
         recorder = recorders[method_name_full]
-        
+
         save_root_path = os.path.join(self.curves_result_path, f"{user}/{user}_{idx}")
         os.makedirs(save_root_path, exist_ok=True)
         save_path = os.path.join(save_root_path, f"{method_name}.json")
-        
+
         if recorder.should_test_method(user, idx, save_path):
             scores = self._limited_data(method, test_info, loss_func)
             recorder.record(user, scores)
             recorder.save(save_path)
-        
-        logger.info(f"Method {method_name} on {user}_{idx} finished")
+
+        logger.info(f"Method {method_name} on {user}_{idx} finished")

examples/dataset_table_workflow/config.py

@@ -17,23 +17,23 @@ user_semantic = {
 }
 
 styles = {
-    'user_model': {"color": "navy", "marker": "o", "linestyle": "-"},  
-    'select_score': {'color': 'gold', 'marker': 's', 'linestyle': '--'},  
-    'oracle_score': {'color': 'darkorange', 'marker': '^', 'linestyle': '-.'},  
-    'mean_score': {'color': 'gray', 'marker': 'x', 'linestyle': ':'},
-    'single_aug': {'color': 'gold', 'marker': 's', 'linestyle': '--'},
-    'multiple_avg': {'color': 'blue', 'marker': '*', 'linestyle': '-'},  
-    'multiple_aug': {'color': 'purple', 'marker': 'd', 'linestyle': '--'},  
-    'ensemble_pruning': {"color": "magenta", "marker": "d", "linestyle": "-."} 
+    "user_model": {"color": "navy", "marker": "o", "linestyle": "-"},
+    "select_score": {"color": "gold", "marker": "s", "linestyle": "--"},
+    "oracle_score": {"color": "darkorange", "marker": "^", "linestyle": "-."},
+    "mean_score": {"color": "gray", "marker": "x", "linestyle": ":"},
+    "single_aug": {"color": "gold", "marker": "s", "linestyle": "--"},
+    "multiple_avg": {"color": "blue", "marker": "*", "linestyle": "-"},
+    "multiple_aug": {"color": "purple", "marker": "d", "linestyle": "--"},
+    "ensemble_pruning": {"color": "magenta", "marker": "d", "linestyle": "-."},
 }
 
 labels = {
-    'user_model': "User Model",  
-    'single_aug': "Single Learnware Reuse (FeatAug)",
+    "user_model": "User Model",
+    "single_aug": "Single Learnware Reuse (FeatAug)",
     "select_score": "Single Learnware Reuse (FeatAug)",
-    'multiple_aug': "Multiple Learnware Reuse (FeatAug)",
-    'ensemble_pruning': "Multiple Learnware Reuse (EnsemblePrune)",
-    'multiple_avg': "Multiple Learnware Reuse (Averaging)"
+    "multiple_aug": "Multiple Learnware Reuse (FeatAug)",
+    "ensemble_pruning": "Multiple Learnware Reuse (EnsemblePrune)",
+    "multiple_avg": "Multiple Learnware Reuse (Averaging)",
 }
 
 align_model_params = {
@@ -47,9 +47,9 @@ align_model_params = {
 }
 
 market_mapping_params = {
-    "lr": 1e-4, 
+    "lr": 1e-4,
     "num_epoch": 50,
-    "batch_size": 64,  
+    "batch_size": 64,
     "num_partition": 2,  # num of column partitions for pos/neg sampling
     "overlap_ratio": 0.7,  # specify the overlap ratio of column partitions during the CL
     "hidden_dim": 256,  # the dimension of hidden embeddings
@@ -73,10 +73,10 @@ user_model_params = {
                 "n_estimators": 100000,
                 "boost_from_average": False,
                 "num_threads": 32,
-                "verbose": -1
+                "verbose": -1,
             },
             "MAX_ROUNDS": 1000,
-            "early_stopping_rounds": 1000
+            "early_stopping_rounds": 1000,
         }
     },
     "PFS": {
@@ -95,7 +95,7 @@ user_model_params = {
                 "n_estimators": 100000,
             },
             "MAX_ROUNDS": 1000,
-            "early_stopping_rounds": 1000
+            "early_stopping_rounds": 1000,
         }
     },
     "PFS_HOMO": {
@@ -114,185 +114,620 @@ user_model_params = {
                 "n_estimators": 100000,
             },
             "MAX_ROUNDS": 1000,
-            "early_stopping_rounds": 1000
+            "early_stopping_rounds": 1000,
         }
-    }
+    },
 }
 
 homo_table_benchmark_config = BenchmarkConfig(
     name="PFS_HOMO",
     user_num=53,
     learnware_ids=[
-        "00002265", "00002266", "00002267", "00002268",
-        "00002269", "00002270", "00002271", "00002272",
-        "00002273", "00002274", "00002275", "00002276",
-        "00002277", "00002278", "00002279", "00002280",
-        "00002281", "00002282", "00002283", "00002284",
-        "00002285", "00002286", "00002287", "00002288",
-        "00002289", "00002290", "00002291", "00002292",
-        "00002293", "00002294", "00002295", "00002296",
-        "00002297", "00002298", "00002299", "00002300",
-        "00002301", "00002302", "00002303", "00002304",
-        "00002305", "00002306", "00002307", "00002308",
-        "00002309", "00002310", "00002311", "00002312",
-        "00002313", "00002314", "00002315", "00002316",
-        "00002317"
+        "00002265",
+        "00002266",
+        "00002267",
+        "00002268",
+        "00002269",
+        "00002270",
+        "00002271",
+        "00002272",
+        "00002273",
+        "00002274",
+        "00002275",
+        "00002276",
+        "00002277",
+        "00002278",
+        "00002279",
+        "00002280",
+        "00002281",
+        "00002282",
+        "00002283",
+        "00002284",
+        "00002285",
+        "00002286",
+        "00002287",
+        "00002288",
+        "00002289",
+        "00002290",
+        "00002291",
+        "00002292",
+        "00002293",
+        "00002294",
+        "00002295",
+        "00002296",
+        "00002297",
+        "00002298",
+        "00002299",
+        "00002300",
+        "00002301",
+        "00002302",
+        "00002303",
+        "00002304",
+        "00002305",
+        "00002306",
+        "00002307",
+        "00002308",
+        "00002309",
+        "00002310",
+        "00002311",
+        "00002312",
+        "00002313",
+        "00002314",
+        "00002315",
+        "00002316",
+        "00002317",
     ],
     test_data_path="PFS_HOMO/test_data.zip",
     train_data_path="PFS_HOMO/train_data.zip",
-    extra_info_path="PFS_HOMO/extra_info.zip"
+    extra_info_path="PFS_HOMO/extra_info.zip",
 )
 
-hetero_cross_feat_eng_benchmark_config = BenchmarkConfig(  
+hetero_cross_feat_eng_benchmark_config = BenchmarkConfig(
     name="PFS",
     user_num=41,
-    learnware_ids = [
-        "00000342", "00000343", "00000344", "00000345",
-        "00000346", "00000347", "00000348", "00000349",
-        "00000350", "00000351", "00000352", "00000353",
-        "00000354", "00000355", "00000356", "00000357",
-        "00000358", "00000359", "00000360", "00000361",
-        "00000362", "00000363", "00000364", "00000365",
-        "00000366", "00000367", "00000368", "00000369",
-        "00000370", "00000371", "00000372", "00000373",
-        "00000374", "00000375", "00000376", "00000377",
-        "00000378", "00000379", "00000380", "00000381",
-        "00000382", "00000383", "00000384", "00000385",
-        "00000386", "00000387", "00000388", "00000389",
-        "00000390", "00000391", "00000392", "00000393",
-        "00000394", "00000395", "00000396", "00000397",
-        "00000398", "00000399", "00000400", "00000401",
-        "00000402", "00000403", "00000404", "00000405",
-        "00000406", "00000407", "00000408", "00000409",
-        "00000410", "00000411", "00000412", "00000413",
-        "00000414", "00000415", "00000416", "00000417",
-        "00000418", "00000419", "00000420", "00000421",
-        "00000422", "00000423", "00000424", "00000425",
-        "00000426", "00000427", "00000428", "00000429",
-        "00000430", "00000431", "00000432", "00000433",
-        "00000434", "00000435", "00000436", "00000437",
-        "00000438", "00000439", "00000440", "00000441",
-        "00000442", "00000443", "00000444", "00000730",
-        "00000731", "00000732", "00000733", "00000734",
-        "00000735", "00000736", "00000737", "00000738",
-        "00000739", "00000740", "00000741", "00000742",
-        "00000743", "00000744", "00000745", "00000746",
-        "00000747", "00000748", "00000749", "00000750",
-        "00000751", "00000752", "00000753", "00000754",
-        "00000755", "00000756", "00000757", "00000758",
-        "00000759", "00000760", "00000761", "00000762",
-        "00000763", "00000764", "00000765", "00000766",
-        "00000767", "00000768", "00000769", "00000770",
-        "00000771", "00000772", "00000773", "00000774",
-        "00000775", "00000776", "00000777", "00000778",
-        "00000779", "00000780", "00000781", "00000782",
-        "00000783", "00000786", "00000787", "00000788",
-        "00000789", "00000790", "00000791", "00000792",
-        "00000793", "00000794", "00000795", "00000796",
-        "00000797", "00000798", "00000799", "00000800",
-        "00000801", "00000802", "00000803", "00000804",
-        "00000805", "00000806", "00000807", "00000808",
-        "00000809", "00000810", "00000811", "00000812",
-        "00000813", "00000814", "00000815", "00000816",
-        "00000817", "00000818", "00000819", "00000820",
-        "00000821", "00000822", "00000823", "00000824",
-        "00000825", "00000826", "00000827", "00000828",
-        "00000829", "00000830", "00000831", "00000832",
-        "00000833", "00000834", "00000835", "00000836",
-        "00000837", "00000838", "00000839", "00000859",
-        "00000860", "00000861", "00000862", "00000863",
-        "00000864", "00000865", "00000866", "00000867",
-        "00000868", "00000869", "00000870", "00000871",
-        "00000872", "00000873", "00000874", "00000875",
-        "00000876", "00000877", "00000878", "00000879",
-        "00000880", "00000881", "00000882", "00000883",
-        "00000884", "00000885", "00000886", "00000887",
-        "00000888", "00000889", "00000890", "00000891",
-        "00000892", "00000893", "00000894", "00000895",
-        "00000896", "00000897", "00000898", "00000899",
-        "00000900", "00000901", "00000902", "00000903",
-        "00000904", "00000905", "00000906", "00000907",
-        "00000908", "00000909", "00000910", "00000911",
-        "00000912"
+    learnware_ids=[
+        "00000342",
+        "00000343",
+        "00000344",
+        "00000345",
+        "00000346",
+        "00000347",
+        "00000348",
+        "00000349",
+        "00000350",
+        "00000351",
+        "00000352",
+        "00000353",
+        "00000354",
+        "00000355",
+        "00000356",
+        "00000357",
+        "00000358",
+        "00000359",
+        "00000360",
+        "00000361",
+        "00000362",
+        "00000363",
+        "00000364",
+        "00000365",
+        "00000366",
+        "00000367",
+        "00000368",
+        "00000369",
+        "00000370",
+        "00000371",
+        "00000372",
+        "00000373",
+        "00000374",
+        "00000375",
+        "00000376",
+        "00000377",
+        "00000378",
+        "00000379",
+        "00000380",
+        "00000381",
+        "00000382",
+        "00000383",
+        "00000384",
+        "00000385",
+        "00000386",
+        "00000387",
+        "00000388",
+        "00000389",
+        "00000390",
+        "00000391",
+        "00000392",
+        "00000393",
+        "00000394",
+        "00000395",
+        "00000396",
+        "00000397",
+        "00000398",
+        "00000399",
+        "00000400",
+        "00000401",
+        "00000402",
+        "00000403",
+        "00000404",
+        "00000405",
+        "00000406",
+        "00000407",
+        "00000408",
+        "00000409",
+        "00000410",
+        "00000411",
+        "00000412",
+        "00000413",
+        "00000414",
+        "00000415",
+        "00000416",
+        "00000417",
+        "00000418",
+        "00000419",
+        "00000420",
+        "00000421",
+        "00000422",
+        "00000423",
+        "00000424",
+        "00000425",
+        "00000426",
+        "00000427",
+        "00000428",
+        "00000429",
+        "00000430",
+        "00000431",
+        "00000432",
+        "00000433",
+        "00000434",
+        "00000435",
+        "00000436",
+        "00000437",
+        "00000438",
+        "00000439",
+        "00000440",
+        "00000441",
+        "00000442",
+        "00000443",
+        "00000444",
+        "00000730",
+        "00000731",
+        "00000732",
+        "00000733",
+        "00000734",
+        "00000735",
+        "00000736",
+        "00000737",
+        "00000738",
+        "00000739",
+        "00000740",
+        "00000741",
+        "00000742",
+        "00000743",
+        "00000744",
+        "00000745",
+        "00000746",
+        "00000747",
+        "00000748",
+        "00000749",
+        "00000750",
+        "00000751",
+        "00000752",
+        "00000753",
+        "00000754",
+        "00000755",
+        "00000756",
+        "00000757",
+        "00000758",
+        "00000759",
+        "00000760",
+        "00000761",
+        "00000762",
+        "00000763",
+        "00000764",
+        "00000765",
+        "00000766",
+        "00000767",
+        "00000768",
+        "00000769",
+        "00000770",
+        "00000771",
+        "00000772",
+        "00000773",
+        "00000774",
+        "00000775",
+        "00000776",
+        "00000777",
+        "00000778",
+        "00000779",
+        "00000780",
+        "00000781",
+        "00000782",
+        "00000783",
+        "00000786",
+        "00000787",
+        "00000788",
+        "00000789",
+        "00000790",
+        "00000791",
+        "00000792",
+        "00000793",
+        "00000794",
+        "00000795",
+        "00000796",
+        "00000797",
+        "00000798",
+        "00000799",
+        "00000800",
+        "00000801",
+        "00000802",
+        "00000803",
+        "00000804",
+        "00000805",
+        "00000806",
+        "00000807",
+        "00000808",
+        "00000809",
+        "00000810",
+        "00000811",
+        "00000812",
+        "00000813",
+        "00000814",
+        "00000815",
+        "00000816",
+        "00000817",
+        "00000818",
+        "00000819",
+        "00000820",
+        "00000821",
+        "00000822",
+        "00000823",
+        "00000824",
+        "00000825",
+        "00000826",
+        "00000827",
+        "00000828",
+        "00000829",
+        "00000830",
+        "00000831",
+        "00000832",
+        "00000833",
+        "00000834",
+        "00000835",
+        "00000836",
+        "00000837",
+        "00000838",
+        "00000839",
+        "00000859",
+        "00000860",
+        "00000861",
+        "00000862",
+        "00000863",
+        "00000864",
+        "00000865",
+        "00000866",
+        "00000867",
+        "00000868",
+        "00000869",
+        "00000870",
+        "00000871",
+        "00000872",
+        "00000873",
+        "00000874",
+        "00000875",
+        "00000876",
+        "00000877",
+        "00000878",
+        "00000879",
+        "00000880",
+        "00000881",
+        "00000882",
+        "00000883",
+        "00000884",
+        "00000885",
+        "00000886",
+        "00000887",
+        "00000888",
+        "00000889",
+        "00000890",
+        "00000891",
+        "00000892",
+        "00000893",
+        "00000894",
+        "00000895",
+        "00000896",
+        "00000897",
+        "00000898",
+        "00000899",
+        "00000900",
+        "00000901",
+        "00000902",
+        "00000903",
+        "00000904",
+        "00000905",
+        "00000906",
+        "00000907",
+        "00000908",
+        "00000909",
+        "00000910",
+        "00000911",
+        "00000912",
     ],
     test_data_path="PFS/test_data.zip",
     train_data_path="PFS/train_data.zip",
-    extra_info_path="PFS/extra_info.zip"
+    extra_info_path="PFS/extra_info.zip",
 )
 
 hetero_cross_task_benchmark_config = BenchmarkConfig(
     name="M5",
     user_num=30,
-    learnware_ids = [
-        "00000342", "00000343", "00000344", "00000345",
-        "00000346", "00000347", "00000348", "00000349",
-        "00000350", "00000351", "00000352", "00000353",
-        "00000354", "00000355", "00000356", "00000357",
-        "00000358", "00000359", "00000360", "00000361",
-        "00000362", "00000363", "00000364", "00000365",
-        "00000366", "00000367", "00000368", "00000369",
-        "00000370", "00000371", "00000372", "00000373",
-        "00000374", "00000375", "00000376", "00000377",
-        "00000378", "00000379", "00000380", "00000381",
-        "00000382", "00000383", "00000384", "00000385",
-        "00000386", "00000387", "00000388", "00000389",
-        "00000390", "00000391", "00000392", "00000393",
-        "00000394", "00000395", "00000396", "00000397",
-        "00000398", "00000399", "00000400", "00000401",
-        "00000402", "00000403", "00000404", "00000405",
-        "00000406", "00000407", "00000408", "00000409",
-        "00000410", "00000411", "00000412", "00000413",
-        "00000414", "00000415", "00000416", "00000417",
-        "00000418", "00000419", "00000420", "00000421",
-        "00000422", "00000423", "00000424", "00000425",
-        "00000426", "00000427", "00000428", "00000429",
-        "00000430", "00000431", "00000432", "00000433",
-        "00000434", "00000435", "00000436", "00000437",
-        "00000438", "00000439", "00000440", "00000441",
-        "00000442", "00000443", "00000444", "00000730",
-        "00000731", "00000732", "00000733", "00000734",
-        "00000735", "00000736", "00000737", "00000738",
-        "00000739", "00000740", "00000741", "00000742",
-        "00000743", "00000744", "00000745", "00000746",
-        "00000747", "00000748", "00000749", "00000750",
-        "00000751", "00000752", "00000753", "00000754",
-        "00000755", "00000756", "00000757", "00000758",
-        "00000759", "00000760", "00000761", "00000762",
-        "00000763", "00000764", "00000765", "00000766",
-        "00000767", "00000768", "00000769", "00000770",
-        "00000771", "00000772", "00000773", "00000774",
-        "00000775", "00000776", "00000777", "00000778",
-        "00000779", "00000780", "00000781", "00000782",
-        "00000783", "00000786", "00000787", "00000788",
-        "00000789", "00000790", "00000791", "00000792",
-        "00000793", "00000794", "00000795", "00000796",
-        "00000797", "00000798", "00000799", "00000800",
-        "00000801", "00000802", "00000803", "00000804",
-        "00000805", "00000806", "00000807", "00000808",
-        "00000809", "00000810", "00000811", "00000812",
-        "00000813", "00000814", "00000815", "00000816",
-        "00000817", "00000818", "00000819", "00000820",
-        "00000821", "00000822", "00000823", "00000824",
-        "00000825", "00000826", "00000827", "00000828",
-        "00000829", "00000830", "00000831", "00000832",
-        "00000833", "00000834", "00000835", "00000836",
-        "00000837", "00000838", "00000839", "00000859",
-        "00000860", "00000861", "00000862", "00000863",
-        "00000864", "00000865", "00000866", "00000867",
-        "00000868", "00000869", "00000870", "00000871",
-        "00000872", "00000873", "00000874", "00000875",
-        "00000876", "00000877", "00000878", "00000879",
-        "00000880", "00000881", "00000882", "00000883",
-        "00000884", "00000885", "00000886", "00000887",
-        "00000888", "00000889", "00000890", "00000891",
-        "00000892", "00000893", "00000894", "00000895",
-        "00000896", "00000897", "00000898", "00000899",
-        "00000900", "00000901", "00000902", "00000903",
-        "00000904", "00000905", "00000906", "00000907",
-        "00000908", "00000909", "00000910", "00000911",
-        "00000912"
+    learnware_ids=[
+        "00000342",
+        "00000343",
+        "00000344",
+        "00000345",
+        "00000346",
+        "00000347",
+        "00000348",
+        "00000349",
+        "00000350",
+        "00000351",
+        "00000352",
+        "00000353",
+        "00000354",
+        "00000355",
+        "00000356",
+        "00000357",
+        "00000358",
+        "00000359",
+        "00000360",
+        "00000361",
+        "00000362",
+        "00000363",
+        "00000364",
+        "00000365",
+        "00000366",
+        "00000367",
+        "00000368",
+        "00000369",
+        "00000370",
+        "00000371",
+        "00000372",
+        "00000373",
+        "00000374",
+        "00000375",
+        "00000376",
+        "00000377",
+        "00000378",
+        "00000379",
+        "00000380",
+        "00000381",
+        "00000382",
+        "00000383",
+        "00000384",
+        "00000385",
+        "00000386",
+        "00000387",
+        "00000388",
+        "00000389",
+        "00000390",
+        "00000391",
+        "00000392",
+        "00000393",
+        "00000394",
+        "00000395",
+        "00000396",
+        "00000397",
+        "00000398",
+        "00000399",
+        "00000400",
+        "00000401",
+        "00000402",
+        "00000403",
+        "00000404",
+        "00000405",
+        "00000406",
+        "00000407",
+        "00000408",
+        "00000409",
+        "00000410",
+        "00000411",
+        "00000412",
+        "00000413",
+        "00000414",
+        "00000415",
+        "00000416",
+        "00000417",
+        "00000418",
+        "00000419",
+        "00000420",
+        "00000421",
+        "00000422",
+        "00000423",
+        "00000424",
+        "00000425",
+        "00000426",
+        "00000427",
+        "00000428",
+        "00000429",
+        "00000430",
+        "00000431",
+        "00000432",
+        "00000433",
+        "00000434",
+        "00000435",
+        "00000436",
+        "00000437",
+        "00000438",
+        "00000439",
+        "00000440",
+        "00000441",
+        "00000442",
+        "00000443",
+        "00000444",
+        "00000730",
+        "00000731",
+        "00000732",
+        "00000733",
+        "00000734",
+        "00000735",
+        "00000736",
+        "00000737",
+        "00000738",
+        "00000739",
+        "00000740",
+        "00000741",
+        "00000742",
+        "00000743",
+        "00000744",
+        "00000745",
+        "00000746",
+        "00000747",
+        "00000748",
+        "00000749",
+        "00000750",
+        "00000751",
+        "00000752",
+        "00000753",
+        "00000754",
+        "00000755",
+        "00000756",
+        "00000757",
+        "00000758",
+        "00000759",
+        "00000760",
+        "00000761",
+        "00000762",
+        "00000763",
+        "00000764",
+        "00000765",
+        "00000766",
+        "00000767",
+        "00000768",
+        "00000769",
+        "00000770",
+        "00000771",
+        "00000772",
+        "00000773",
+        "00000774",
+        "00000775",
+        "00000776",
+        "00000777",
+        "00000778",
+        "00000779",
+        "00000780",
+        "00000781",
+        "00000782",
+        "00000783",
+        "00000786",
+        "00000787",
+        "00000788",
+        "00000789",
+        "00000790",
+        "00000791",
+        "00000792",
+        "00000793",
+        "00000794",
+        "00000795",
+        "00000796",
+        "00000797",
+        "00000798",
+        "00000799",
+        "00000800",
+        "00000801",
+        "00000802",
+        "00000803",
+        "00000804",
+        "00000805",
+        "00000806",
+        "00000807",
+        "00000808",
+        "00000809",
+        "00000810",
+        "00000811",
+        "00000812",
+        "00000813",
+        "00000814",
+        "00000815",
+        "00000816",
+        "00000817",
+        "00000818",
+        "00000819",
+        "00000820",
+        "00000821",
+        "00000822",
+        "00000823",
+        "00000824",
+        "00000825",
+        "00000826",
+        "00000827",
+        "00000828",
+        "00000829",
+        "00000830",
+        "00000831",
+        "00000832",
+        "00000833",
+        "00000834",
+        "00000835",
+        "00000836",
+        "00000837",
+        "00000838",
+        "00000839",
+        "00000859",
+        "00000860",
+        "00000861",
+        "00000862",
+        "00000863",
+        "00000864",
+        "00000865",
+        "00000866",
+        "00000867",
+        "00000868",
+        "00000869",
+        "00000870",
+        "00000871",
+        "00000872",
+        "00000873",
+        "00000874",
+        "00000875",
+        "00000876",
+        "00000877",
+        "00000878",
+        "00000879",
+        "00000880",
+        "00000881",
+        "00000882",
+        "00000883",
+        "00000884",
+        "00000885",
+        "00000886",
+        "00000887",
+        "00000888",
+        "00000889",
+        "00000890",
+        "00000891",
+        "00000892",
+        "00000893",
+        "00000894",
+        "00000895",
+        "00000896",
+        "00000897",
+        "00000898",
+        "00000899",
+        "00000900",
+        "00000901",
+        "00000902",
+        "00000903",
+        "00000904",
+        "00000905",
+        "00000906",
+        "00000907",
+        "00000908",
+        "00000909",
+        "00000910",
+        "00000911",
+        "00000912",
     ],
     test_data_path="M5/test_data.zip",
     train_data_path="M5/train_data.zip",
-    extra_info_path="M5/extra_info.zip"
-)
+    extra_info_path="M5/extra_info.zip",
+)

examples/dataset_table_workflow/hetero.py

@@ -1,6 +1,5 @@
 import os
 import warnings
-warnings.filterwarnings("ignore")
 
 import numpy as np
 from learnware.logger import get_module_logger
@@ -8,11 +7,12 @@ from learnware.specification import generate_stat_spec
 from learnware.market import BaseUserInfo
 from learnware.reuse import AveragingReuser, FeatureAlignLearnware
 
-from methods import *
+from methods import loss_func_rmse
 from base import TableWorkflow
 from config import align_model_params, user_semantic, hetero_n_labeled_list, hetero_n_repeat_list
 from utils import Recorder, plot_performance_curves, set_seed
 
+warnings.filterwarnings("ignore")
 logger = get_module_logger("hetero_test", level="INFO")
 
 
@@ -24,7 +24,7 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
         single_score_list = []
         ensemble_score_list = []
         all_learnwares = self.market.get_learnwares()
-        
+
         user = self.benchmark.name
         for idx in range(self.benchmark.user_num):
             test_x, test_y = self.benchmark.get_test_data(user_ids=idx)
@@ -32,23 +32,21 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
             user_stat_spec = generate_stat_spec(type="table", X=test_x)
             input_description = {
                 "Dimension": len(feature_descriptions),
-                "Description": {str(i): feature_descriptions[i] for i in range(len(feature_descriptions))}
+                "Description": {str(i): feature_descriptions[i] for i in range(len(feature_descriptions))},
             }
             user_semantic["Input"] = input_description
-            user_info = BaseUserInfo(
-                semantic_spec=user_semantic, stat_info={user_stat_spec.type: user_stat_spec}
-            )
+            user_info = BaseUserInfo(semantic_spec=user_semantic, stat_info={user_stat_spec.type: user_stat_spec})
             logger.info(f"Searching Market for user: {user}_{idx}")
-            
+
             search_result = self.market.search_learnware(user_info, search_method="auto")
             single_result = search_result.get_single_results()
             multiple_result = search_result.get_multiple_results()
-            
+
             logger.info(f"hetero search result of user {user}_{idx}: {single_result[0].learnware.id}")
             logger.info(
                 f"single model num: {len(single_result)}, max_score: {single_result[0].score}, min_score: {single_result[-1].score}"
             )
-            
+
             single_hetero_learnware = FeatureAlignLearnware(single_result[0].learnware, **align_model_params)
             single_hetero_learnware.align(user_rkme=user_stat_spec)
             pred_y = single_hetero_learnware.predict(test_x)
@@ -59,11 +57,11 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
                 hetero_learnware = FeatureAlignLearnware(learnware, **align_model_params)
                 hetero_learnware.align(user_rkme=user_stat_spec)
                 pred_y = hetero_learnware.predict(test_x)
-                rmse_list.append(loss_func_rmse(pred_y, test_y)) 
+                rmse_list.append(loss_func_rmse(pred_y, test_y))
             logger.info(
                 f"Top1-score: {single_result[0].score}, learnware_id: {single_result[0].learnware.id}, rmse: {single_score_list[0]}"
             )
-            
+
             if len(multiple_result) > 0:
                 mixture_id = " ".join([learnware.id for learnware in multiple_result[0].learnwares])
                 logger.info(f"mixture_score: {multiple_result[0].score}, mixture_learnware: {mixture_id}")
@@ -85,11 +83,11 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
             logger.info(f"mixture reuse rmse (ensemble): {ensemble_score}")
 
             learnware_rmse_list.append(rmse_list)
-        
+
         single_list = np.array(learnware_rmse_list)
         avg_score_list = [np.mean(lst, axis=0) for lst in single_list]
         oracle_score_list = [np.min(lst, axis=0) for lst in single_list]
-        
+
         logger.info(
             "RMSE of selected learnware: %.3f +/- %.3f, Average performance: %.3f +/- %.3f, Oracle performace: %.3f +/- %.3f"
             % (
@@ -98,7 +96,7 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
                 np.mean(avg_score_list),
                 np.std(avg_score_list),
                 np.mean(oracle_score_list),
-                np.std(oracle_score_list)
+                np.std(oracle_score_list),
             )
         )
         logger.info(
@@ -106,33 +104,30 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
             % (np.mean(ensemble_score_list), np.std(ensemble_score_list))
         )
 
-
     def labeled_hetero_table_example(self, skip_test):
         set_seed(0)
         logger.info("Total Items: %d" % len(self.market))
         methods = ["user_model", "hetero_single_aug", "hetero_multiple_avg", "hetero_ensemble_pruning"]
         recorders = {method: Recorder() for method in methods}
         user = self.benchmark.name
-        
+
         if not skip_test:
             for idx in range(self.benchmark.user_num):
                 test_x, test_y = self.benchmark.get_test_data(user_ids=idx)
                 test_x, test_y = test_x.values, test_y.values
-                
+
                 train_x, train_y = self.benchmark.get_train_data(user_ids=idx)
                 train_x, train_y, feature_descriptions = train_x.values, train_y.values, train_x.columns
                 train_subsets = self.get_train_subsets(hetero_n_labeled_list, hetero_n_repeat_list, train_x, train_y)
-                
+
                 user_stat_spec = generate_stat_spec(type="table", X=test_x)
                 input_description = {
                     "Dimension": len(feature_descriptions),
-                    "Description": {str(i): feature_descriptions[i] for i in range(len(feature_descriptions))}
+                    "Description": {str(i): feature_descriptions[i] for i in range(len(feature_descriptions))},
                 }
                 user_semantic["Input"] = input_description
-                user_info = BaseUserInfo(
-                    semantic_spec=user_semantic, stat_info={user_stat_spec.type: user_stat_spec}
-                )
-                
+                user_info = BaseUserInfo(semantic_spec=user_semantic, stat_info={user_stat_spec.type: user_stat_spec})
+
                 logger.info(f"Searching Market for user: {user}_{idx}")
                 search_result = self.market.search_learnware(user_info)
                 single_result = search_result.get_single_results()
@@ -144,16 +139,25 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
                     mixture_learnware_list = multiple_result[0].learnwares
                 else:
                     mixture_learnware_list = [single_result[0].learnware]
-                
-                logger.info(f"Hetero search result of user {user}_{idx}: mixture learnware num: {len(mixture_learnware_list)}")
 
-                test_info = {"user": user, "idx": idx, "train_subsets": train_subsets, "test_x": test_x, "test_y": test_y, "n_labeled_list": hetero_n_labeled_list}
+                logger.info(
+                    f"Hetero search result of user {user}_{idx}: mixture learnware num: {len(mixture_learnware_list)}"
+                )
+
+                test_info = {
+                    "user": user,
+                    "idx": idx,
+                    "train_subsets": train_subsets,
+                    "test_x": test_x,
+                    "test_y": test_y,
+                    "n_labeled_list": hetero_n_labeled_list,
+                }
                 common_config = {"user_rkme": user_stat_spec, "learnwares": mixture_learnware_list}
                 method_configs = {
                     "user_model": {"dataset": self.benchmark.name, "model_type": "lgb"},
                     "hetero_single_aug": {"user_rkme": user_stat_spec, "single_learnware": single_result[0].learnware},
                     "hetero_multiple_avg": common_config,
-                    "hetero_ensemble_pruning": common_config
+                    "hetero_ensemble_pruning": common_config,
                 }
 
                 for method_name in methods:
@@ -161,8 +165,10 @@ class HeterogeneousDatasetWorkflow(TableWorkflow):
                     test_info["method_name"] = method_name
                     test_info.update(method_configs[method_name])
                     self.test_method(test_info, recorders, loss_func=loss_func_rmse)
-            
+
             for method, recorder in recorders.items():
                 recorder.save(os.path.join(self.curves_result_path, f"{user}/{user}_{method}_performance.json"))
-                
-        plot_performance_curves(self.curves_result_path, user, recorders, task="Hetero", n_labeled_list=hetero_n_labeled_list)
+
+        plot_performance_curves(
+            self.curves_result_path, user, recorders, task="Hetero", n_labeled_list=hetero_n_labeled_list
+        )

examples/dataset_table_workflow/homo.py

@@ -1,18 +1,18 @@
 import os
 import warnings
 import numpy as np
-warnings.filterwarnings("ignore")
 
 from learnware.market import BaseUserInfo
 from learnware.logger import get_module_logger
 from learnware.specification import generate_stat_spec
-from learnware.reuse import AveragingReuser, JobSelectorReuser, EnsemblePruningReuser
+from learnware.reuse import AveragingReuser, JobSelectorReuser
 
-from methods import *
+from methods import loss_func_rmse
 from base import TableWorkflow
 from config import homo_n_labeled_list, homo_n_repeat_list
 from utils import Recorder, plot_performance_curves
 
+warnings.filterwarnings("ignore")
 logger = get_module_logger("homo_table", level="INFO")
 
 
@@ -30,9 +30,7 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
             test_x, test_y = self.benchmark.get_test_data(user_ids=idx)
             test_x, test_y = test_x.values, test_y.values
             user_stat_spec = generate_stat_spec(type="table", X=test_x)
-            user_info = BaseUserInfo(
-                semantic_spec=self.user_semantic, stat_info={user_stat_spec.type: user_stat_spec}
-            )
+            user_info = BaseUserInfo(semantic_spec=self.user_semantic, stat_info={user_stat_spec.type: user_stat_spec})
             logger.info(f"Searching Market for user: {user}_{idx}")
 
             search_result = self.market.search_learnware(user_info, max_search_num=2)
@@ -43,7 +41,7 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
             logger.info(
                 f"single model num: {len(single_result)}, max_score: {single_result[0].score}, min_score: {single_result[-1].score}"
             )
-            
+
             pred_y = single_result[0].learnware.predict(test_x)
             single_score_list.append(loss_func_rmse(pred_y, test_y))
 
@@ -77,7 +75,7 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
             ensemble_score = loss_func_rmse(ensemble_predict_y, test_y)
             ensemble_score_list.append(ensemble_score)
             logger.info(f"mixture reuse rmse (ensemble): {ensemble_score}")
-            
+
             learnware_rmse_list.append(rmse_list)
 
         single_list = np.array(learnware_rmse_list)
@@ -103,19 +101,18 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
             "Averaging Ensemble Reuse Performance: %.3f +/- %.3f"
             % (np.mean(ensemble_score_list), np.std(ensemble_score_list))
         )
-        
-        
+
     def labeled_homo_table_example(self, skip_test):
         logger.info("Total Item: %d" % (len(self.market)))
         methods = ["user_model", "homo_single_aug", "homo_ensemble_pruning"]
         recorders = {method: Recorder() for method in methods}
         user = self.benchmark.name
-        
+
         if not skip_test:
             for idx in range(self.benchmark.user_num):
                 test_x, test_y = self.benchmark.get_test_data(user_ids=idx)
                 test_x, test_y = test_x.values, test_y.values
-                
+
                 train_x, train_y = self.benchmark.get_train_data(user_ids=idx)
                 train_x, train_y = train_x.values, train_y.values
                 train_subsets = self.get_train_subsets(homo_n_labeled_list, homo_n_repeat_list, train_x, train_y)
@@ -124,7 +121,7 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
                 user_info = BaseUserInfo(
                     semantic_spec=self.user_semantic, stat_info={"RKMETableSpecification": user_stat_spec}
                 )
-                
+
                 logger.info(f"Searching Market for user: {user}_{idx}")
                 search_result = self.market.search_learnware(user_info)
                 single_result = search_result.get_single_results()
@@ -142,12 +139,18 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
                 else:
                     mixture_learnware_list = [single_result[0].learnware]
 
-                test_info = {"user": user, "idx": idx, "train_subsets": train_subsets, "test_x": test_x, "test_y": test_y}
+                test_info = {
+                    "user": user,
+                    "idx": idx,
+                    "train_subsets": train_subsets,
+                    "test_x": test_x,
+                    "test_y": test_y,
+                }
                 common_config = {"learnwares": mixture_learnware_list}
                 method_configs = {
                     "user_model": {"dataset": self.benchmark.name, "model_type": "lgb"},
                     "homo_single_aug": {"single_learnware": [single_result[0].learnware]},
-                    "homo_ensemble_pruning": common_config
+                    "homo_ensemble_pruning": common_config,
                 }
 
                 for method_name in methods:
@@ -155,8 +158,10 @@ class HomogeneousDatasetWorkflow(TableWorkflow):
                     test_info["method_name"] = method_name
                     test_info.update(method_configs[method_name])
                     self.test_method(test_info, recorders, loss_func=loss_func_rmse)
-            
+
             for method, recorder in recorders.items():
                 recorder.save(os.path.join(self.curves_result_path, f"{user}/{user}_{method}_performance.json"))
 
-        plot_performance_curves(self.curves_result_path, user, recorders, task="Homo", n_labeled_list=homo_n_labeled_list)
+        plot_performance_curves(
+            self.curves_result_path, user, recorders, task="Homo", n_labeled_list=homo_n_labeled_list
+        )

examples/dataset_table_workflow/methods.py

@@ -31,7 +31,7 @@ class HomoScoringMethods:
         reuse_multiple_augment = FeatureAugmentReuser(multiple_learnwares, mode="regression")
         reuse_multiple_augment.fit(x_train=x_train, y_train=y_train)
         return reuse_multiple_augment
-    
+
     @staticmethod
     def multiple_avg_score(x_train, y_train, test_info):
         multiple_learnwares = test_info["learnwares"]
@@ -64,29 +64,35 @@ class HeteroMethods:
         reuse_single_augment = HeteroMapAlignLearnware(single_learnware, mode="regression", **align_model_params)
         reuse_single_augment.align(user_rkme=user_rkme, x_train=x_train, y_train=y_train)
         return reuse_single_augment
-    
+
     @staticmethod
     def multiple_aug_score(x_train, y_train, test_info):
         user_rkme, multiple_learnwares = test_info["user_rkme"], test_info["learnwares"]
-        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(multiple_learnwares, user_rkme, x_train, y_train)
+        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(
+            multiple_learnwares, user_rkme, x_train, y_train
+        )
         reuse_multiple_augment = FeatureAugmentReuser(hetero_learnware_list, mode="regression")
         reuse_multiple_augment.fit(x_train=x_train, y_train=y_train)
         return reuse_multiple_augment
-    
+
     @staticmethod
     def multiple_ensemble_pruning_score(x_train, y_train, test_info):
         user_rkme, multiple_learnwares = test_info["user_rkme"], test_info["learnwares"]
-        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(multiple_learnwares, user_rkme, x_train, y_train)
+        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(
+            multiple_learnwares, user_rkme, x_train, y_train
+        )
         if len(hetero_learnware_list) == 1:
             return hetero_learnware_list[0]
         reuse_pruning = EnsemblePruningReuser(hetero_learnware_list, mode="regression")
         reuse_pruning.fit(val_X=x_train, val_y=y_train)
         return reuse_pruning
-    
+
     @staticmethod
     def multiple_avg_score(x_train, y_train, test_info):
         user_rkme, multiple_learnwares = test_info["user_rkme"], test_info["learnwares"]
-        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(multiple_learnwares, user_rkme, x_train, y_train)
+        hetero_learnware_list = HeteroMethods.create_hetero_learnware_list(
+            multiple_learnwares, user_rkme, x_train, y_train
+        )
         reuse_multiple_avg = AveragingReuser(hetero_learnware_list, mode="mean")
         return reuse_multiple_avg
 
@@ -100,5 +106,5 @@ test_methods = {
     "homo_single_aug": HomoScoringMethods.single_aug_score,
     "homo_multiple_aug": HomoScoringMethods.multiple_aug_score,
     "homo_multiple_avg": HomoScoringMethods.multiple_avg_score,
-    "homo_ensemble_pruning": HomoScoringMethods.multiple_ensemble_pruning_score
-}
+    "homo_ensemble_pruning": HomoScoringMethods.multiple_ensemble_pruning_score,
+}

examples/dataset_table_workflow/train.py

@@ -1,7 +1,5 @@
-import numpy as np
 import lightgbm as lgb
 from lightgbm import early_stopping
-from sklearn.metrics import mean_squared_error
 
 from learnware.logger import get_module_logger
 from config import user_model_params
@@ -24,7 +22,7 @@ def train_lgb(X_train, y_train, X_val, y_val, dataset):
         dtrain,
         num_boost_round=MAX_ROUNDS,
         valid_sets=[dtrain, dval] if dataset == "Corporacion" else [dval],
-        callbacks=[early_stopping(model_param["early_stopping_rounds"], verbose=False)]
+        callbacks=[early_stopping(model_param["early_stopping_rounds"], verbose=False)],
     )
     val_pred.append(bst.predict(X_val, num_iteration=bst.best_iteration or MAX_ROUNDS))
     return bst
@@ -38,6 +36,6 @@ def train_model(X_train, y_train, X_val, y_val, test_info):
     dataset = test_info["dataset"]
     model_type = test_info["model_type"]
     assert model_type in ["lgb", "ridge"]
-    
+
     if model_type == "lgb":
-        return train_lgb(X_train, y_train, X_val, y_val, dataset)
+        return train_lgb(X_train, y_train, X_val, y_val, dataset)

examples/dataset_table_workflow/utils.py

@@ -8,7 +8,7 @@ import matplotlib.pyplot as plt
 from collections import defaultdict
 
 from learnware.logger import get_module_logger
-from config import *
+from config import styles, labels
 
 logger = get_module_logger("base_table", level="INFO")
 
@@ -29,46 +29,46 @@ class Recorder:
     def save(self, path):
         with open(path, "w") as f:
             json.dump(self.data, f, indent=4, default=list)
-            
+
     def load(self, path):
         with open(path, "r") as f:
             self.data = json.load(f, object_hook=lambda x: defaultdict(list, x))
-    
+
     def should_test_method(self, user, idx, path):
         if os.path.exists(path):
             self.load(path)
             return user not in self.data or idx > len(self.data[user]) - 1
         return True
-    
+
 
 def plot_performance_curves(path, user, recorders, task, n_labeled_list):
     plt.figure(figsize=(10, 6))
     plt.xticks(range(len(n_labeled_list)), n_labeled_list)
-    for method, recorder in recorders.items():    
+    for method, recorder in recorders.items():
         data_path = os.path.join(path, f"{user}/{user}_{method}_performance.json")
         recorder.load(data_path)
         scores_array = recorder.get_performance_data(user)
-            
+
         mean_curve, std_curve = [], []
         for i in range(len(n_labeled_list)):
             sub_scores_array = np.vstack([lst[i] for lst in scores_array])
-            sub_scores_mean = np.squeeze(np.mean(sub_scores_array, axis=0))                
+            sub_scores_mean = np.squeeze(np.mean(sub_scores_array, axis=0))
             mean_curve.append(np.mean(sub_scores_mean))
             std_curve.append(np.std(sub_scores_mean))
-            
+
         mean_curve = np.array(mean_curve)
         std_curve = np.array(std_curve)
 
-        method_plot = '_'.join(method.split('_')[1:]) if method not in ['user_model', 'oracle_score', 'select_score', 'mean_score'] else method
+        method_plot = (
+            "_".join(method.split("_")[1:])
+            if method not in ["user_model", "oracle_score", "select_score", "mean_score"]
+            else method
+        )
         style = styles.get(method_plot, {"color": "black", "linestyle": "-"})
         plt.plot(mean_curve, label=labels.get(method_plot), **style)
 
         plt.fill_between(
-            range(len(mean_curve)), 
-            mean_curve - std_curve, 
-            mean_curve + std_curve, 
-            color=style["color"], 
-            alpha=0.2
+            range(len(mean_curve)), mean_curve - std_curve, mean_curve + std_curve, color=style["color"], alpha=0.2
         )
 
     plt.xlabel("Amount of Labeled User Data", fontsize=14)
@@ -76,7 +76,7 @@ def plot_performance_curves(path, user, recorders, task, n_labeled_list):
     plt.title(f"Results on {task} Table Experimental Scenario", fontsize=16)
     plt.legend(fontsize=12)
     plt.tight_layout()
-    
+
     root_path = os.path.abspath(os.path.join(__file__, ".."))
     fig_path = os.path.join(root_path, "results", "figs")
     os.makedirs(fig_path, exist_ok=True)
@@ -91,4 +91,4 @@ def set_seed(seed):
     torch.cuda.manual_seed(seed)
     torch.cuda.manual_seed_all(seed)
     torch.backends.cudnn.benchmark = False
-    torch.backends.cudnn.deterministic = True
+    torch.backends.cudnn.deterministic = True