在预测结果中记录对应MD

打印运行时间

.gitignore

@@ -1 +1,3 @@
-/md_discovery/output/mds.txt
+/md_discovery/output/*
+/ml_er/output/*
+/hpo/output/*

hpo/deepmatcher_hpo.py

@@ -1,8 +1,10 @@
 import json
+import time
+from colorama import init, Fore
 from ConfigSpace import Categorical, Configuration, ConfigurationSpace, Integer, Float
 from ConfigSpace.conditions import InCondition, EqualsCondition, AndConjunction
 from ConfigSpace.read_and_write import json as csj
-from smac import Scenario, HyperparameterOptimizationFacade
+from smac import Scenario, BlackBoxFacade
 
 from ml_er.deepmatcher_er import matching
 from setting import hpo_output_dir
@@ -31,31 +33,32 @@ class Optimization:
 
         return cs
 
-    def train(self, config: Configuration, seed: int = 0) -> float:
+    def train(self, config: Configuration, seed: int = 0, ) -> float:
         indicators = matching(config)
         return 1 - indicators['performance']
 
 
 def ml_er_hpo():
+    # init(autoreset=True)
     optimization = Optimization()
     cs = optimization.configspace
     str_configspace = csj.write(cs)
     dict_configspace = json.loads(str_configspace)
     # 将超参数空间保存本地
-    with open(hpo_output_dir + "configspace.json", "w") as f:
+    with open(hpo_output_dir + r"\configspace.json", "w") as f:
         json.dump(dict_configspace, f, indent=4)
 
     scenario = Scenario(
         cs,
         crash_cost=1.0,
         deterministic=True,
-        n_trials=20,
+        n_trials=16,
         n_workers=1
     )
 
-    initial_design = HyperparameterOptimizationFacade.get_initial_design(scenario, n_configs=5)
+    initial_design = BlackBoxFacade.get_initial_design(scenario, n_configs=5)
 
-    smac = HyperparameterOptimizationFacade(
+    smac = BlackBoxFacade(
         scenario,
         optimization.train,
         initial_design=initial_design,
@@ -66,19 +69,21 @@ def ml_er_hpo():
     incumbent_cost = smac.validate(incumbent)
     default = cs.get_default_configuration()
     default_cost = smac.validate(default)
-    print(f"Default Cost: {default_cost}")
-    print(f"Incumbent Cost: {incumbent_cost}")
+    print(Fore.BLUE + f"Default Cost: {default_cost}")
+    print(Fore.BLUE + f"Incumbent Cost: {incumbent_cost}")
 
     if incumbent_cost > default_cost:
         incumbent = default
-        print(f"Updated Incumbent Cost: {default_cost}")
+        print(Fore.RED + f'Updated Incumbent Cost: {default_cost}')
 
-    print(f"Optimized Configuration:{incumbent.values()}")
+    print(Fore.BLUE + f"Optimized Configuration:{incumbent.values()}")
 
-    with open(hpo_output_dir + "incumbent.json", "w") as f:
+    with open(hpo_output_dir + r"\incumbent.json", "w") as f:
         json.dump(dict(incumbent), f, indent=4)
     return incumbent
 
 
 if __name__ == '__main__':
+    init(autoreset=True)
+    print(Fore.CYAN + f'Start Time: {time.time()}')
     ml_er_hpo()

md_discovery/md_mining.py

@@ -18,6 +18,7 @@ from setting import *
 def mining(train: pd.DataFrame):
     # data is train set, in which each row represents a tuple pair
     train = train.astype(str)
+    # 将label列移到最后
     train = pd.concat([train, pd.DataFrame({'label': train.pop('label')})], axis=1)
 
     # 尝试不将左右表key手动调整相同，而是只看gold属性是否为1
@@ -217,5 +218,5 @@ def merge_mds(md_list_):
 if __name__ == '__main__':
     _train = pd.read_csv(directory_path + r'\train_whole.csv')
     result = mining(_train)
-    with open(md_output_dir + "mds.pickle", "wb") as file_:
+    with open(md_output_dir + r"\mds.pickle", "wb") as file_:
         pickle.dump(result, file_)

ml_er/deepmatcher_er.py

@@ -10,16 +10,17 @@ import ConfigSpace
 from ConfigSpace import Configuration
 from ConfigSpace.read_and_write import json as csj
 import torch.nn.functional
+from colorama import init, Fore
 from tqdm import tqdm
 
 from setting import *
 
 
 def matching(config):
-    print(f'\033[33mConfig: {config}\033[0m')
-    start = time.time()
+    # init(autoreset=True)
+    print(Fore.BLUE + f'Config: {config}')
 
-    with open(md_output_dir + "mds.pickle", "rb") as file:
+    with open(md_output_dir + r"\mds.pickle", "rb") as file:
         md_list = pickle.load(file)
 
     train, valid, test = dm.data.process(
@@ -30,9 +31,9 @@ def matching(config):
         use_magellan_convention=True,  # 与Magellan命名风格相同
         embeddings=config['embeddings'])
 
-    train_table = train.get_raw_table()
-    test_table = test.get_raw_table()
-    valid_table = valid.get_raw_table()
+    # train_table = train.get_raw_table()
+    # test_table = test.get_raw_table()
+    # valid_table = valid.get_raw_table()
 
     attr_summarizer = config['attr_summarizer']
     if attr_summarizer == 'sif':
@@ -79,21 +80,25 @@ def matching(config):
 
     indicators = {}
     f1_score = model_.run_eval(test, device='cuda')
-    indicators["F1"] = f1_score
+    indicators["F1"] = f1_score.item() / 100
 
     predictions = model_.run_prediction(test, device='cuda', output_attributes=True)
     # predictions中没有predicted列, 根据match_score手动新增   deepmatcher在计算F1时的阈值为0.5
     predictions['predicted'] = predictions['match_score'].apply(lambda score: 1 if score >= 0.5 else 0)
+    predictions = predictions.reset_index(drop=True)
+    predictions = predictions.astype(str)
     # 目前predictions包含的属性：左右表全部属性+label+predicted+match_score+_id
     sim_tensor_dict = build_col_pairs_sim_tensor_dict(predictions)
     predictions['confidence'] = 0
+    predictions['md'] = ''
 
     epl_match = 0  # 可解释，预测match
     if len(md_list) > 0:
         for row in tqdm(predictions.itertuples()):
-            x = is_explicable(row, md_list, sim_tensor_dict)
-            if x > 0 and str(getattr(row, 'predicted')) == str(1):
-                predictions.loc[row[0], 'confidence'] = x
+            conf, md_dict = is_explicable(row, md_list, sim_tensor_dict)
+            if conf > 0 and str(getattr(row, 'predicted')) == str(1):
+                predictions.loc[row[0], 'confidence'] = conf
+                predictions.loc[row[0], 'md'] = str(md_dict)
                 epl_match += 1
 
     df = predictions[predictions['predicted'] == str(1)]
@@ -101,10 +106,10 @@ def matching(config):
     indicators['interpretability'] = interpretability
     performance = interpre_weight * interpretability + (1 - interpre_weight) * indicators["F1"]
     indicators['performance'] = performance
-    print(f'ER Indicators: {indicators}')
+    print(Fore.BLUE + f'ER Indicators: {indicators}')
 
     predictions.to_csv(er_output_dir + r'\predictions.csv', sep=',', index=False, header=True)
-    print(f'\033[33mTime consumed by matching in seconds: {time.time() - start}\033[0m')
+    print(Fore.CYAN + f'Finish Time: {time.time()}')
 
     return indicators
 
@@ -148,13 +153,13 @@ def is_explicable(row, all_mds: list, st_dict):
                 explicable = False  # 任意一个字段的相似度达不到阈值，这条md就不能解释当前元组
                 break  # 不再与当前md的其他相似度阈值比较，跳转到下一条md
         if explicable:
-            return md_tuple[2]  # 任意一条md能解释，直接返回
-    return -1.0  # 遍历结束，不能解释
+            return md_tuple[2], md_tuple[0]  # 任意一条md能解释，直接返回
+    return -1.0, {}  # 遍历结束，不能解释
 
 
 def ml_er(config: Configuration):
     indicators = matching(config)
-    output_path = er_output_dir + "eval_result.txt"
+    output_path = er_output_dir + r"\eval_result.txt"
     with open(output_path, 'w') as _f:
         _f.write('F1:' + str(indicators["F1"]) + '\n')
         _f.write('interpretability:' + str(indicators['interpretability']) + '\n')
@@ -162,12 +167,12 @@ def ml_er(config: Configuration):
 
 
 if __name__ == '__main__':
-    if os.path.isfile(hpo_output_dir + "incumbent.json"):
-        with open(hpo_output_dir + "configspace.json", 'r') as f:
+    if os.path.isfile(hpo_output_dir + r"\incumbent.json"):
+        with open(hpo_output_dir + r"\configspace.json", 'r') as f:
             dict_configspace = json.load(f)
         str_configspace = json.dumps(dict_configspace)
         configspace = csj.read(str_configspace)
-        with open(hpo_output_dir + "incumbent.json", 'r') as f:
+        with open(hpo_output_dir + r"\incumbent.json", 'r') as f:
             dic = json.load(f)
         configuration = ConfigSpace.Configuration(configspace, values=dic)
         ml_er(configuration)

setting.py

@@ -1,6 +1,6 @@
 from sentence_transformers import SentenceTransformer
 
-directory_path = r'E:\Data\Research\Datasets\DeepMatcher dataset\Textual\Abt-Buy'
+directory_path = r'E:\Data\Research\Datasets\DeepMatcher dataset\Structured\iTunes-Amazon'
 
 er_output_dir = r'E:\Data\Research\Projects\md_bayesian_er_deepmatcher\ml_er\output'
 md_output_dir = r'E:\Data\Research\Projects\md_bayesian_er_deepmatcher\md_discovery\output'