commit

hpo/magellan_hpo.py

@@ -8,11 +8,11 @@ import py_entitymatching.catalog.catalog_manager as cm
 import pandas as pd
 from smac import HyperparameterOptimizationFacade, Scenario
 
-from ml_er.magellan_new import matching
+from ml_er.magellan_er import matching
 from settings import *
 
 
-class Classifier:
+class Optimization:
     @property
     def configspace(self) -> ConfigurationSpace:
         cs = ConfigurationSpace(seed=0)
@@ -68,8 +68,8 @@ class Classifier:
 
 
 def ml_er_hpo():
-    classifier = Classifier()
-    cs = classifier.configspace
+    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
@@ -88,7 +88,7 @@ def ml_er_hpo():
 
     smac = HyperparameterOptimizationFacade(
         scenario,
-        classifier.train,
+        optimization.train,
         initial_design=initial_design,
         overwrite=True,  # If the run exists, we overwrite it; alternatively, we can continue from last state
     )

ml_er/magellan_er.py

@@ -155,6 +155,7 @@ def matching(config: Configuration, blocking_result_):
 
     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+gold+predicted
     sim_tensor_dict = build_col_pairs_sim_tensor_dict(predictions)
     predictions['confidence'] = 0
 

ml_er/magellan_start.py

@@ -1,4 +1,4 @@
-from ml_er.magellan_new import blocking_mining
+from ml_er.magellan_er import blocking_mining
 
 if __name__ == '__main__':
     blocking_mining()