Update relation_extraction.py

relation_extraction.py

@@ -13,21 +13,19 @@ year={2020}
 
 # TODO: Add description of the module here
 _DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+This metric is used for evaluating the quality of relation extraction output. By calculating the Micro and Macro F1 score of every relation extraction outputs to ensure the quality.
 """
 
 
-# TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
+Calculates how good are predictions given some references, using Precision, Recall, F1 Score.
 Args:
-    predictions (list of list of dictionary): relation and its type of prediction
-       
-    references (list of list of dictionary): references for each relation and its type
+    predictions (list of list of dictionary): A list of predicted relations from the model.
+    references (list of list of dictionary): A list of ground-truth or reference relations to compare the predictions against.
     
 Returns:
-    **output** (`dictionary` of `dictionary`s) with multiple key-value pairs
-- **entity type** (`dictionary`): score of all of the type 
+    **output** (`dictionary` of `dictionary`s) A dictionary mapping each entity type to its respective scoring metrics such as Precision, Recall, F1 Score.
+- **entity type** (`dictionary`): score of selected relation type
   - **tp** : true positive count
   - **fp** : false positive count
   - **fn** : false negative count
@@ -38,12 +36,24 @@ Returns:
   - **Macro_p** : macro precision
   - **Macro_r** : macro recall
 Examples:
-    Examples should be written in doctest format, and should illustrate how
-    to use the function.
-    my_new_module = evaluate.load("my_new_module")
-    results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
-    print(results)
-    {'accuracy': 1.0}
+    metric_path = "Ikala-allen/relation_extraction"
+    module = evaluate.load(metric_path)
+    references = [
+      [
+        {"head": "phipigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+        {'head': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
+      ]
+    ]
+    predictions = [
+      [
+        {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+      ]
+    ]
+    evaluation_scores = module.compute(predictions=predictions, references=references, mode="strict", detailed_scores=False, relation_types=[])
+    print(evaluation_scores)
+    {'tp': 1, 'fp': 1, 'fn': 2, 'p': 50.0, 'r': 33.333333333333336, 'f1': 40.0, 'Macro_f1': 25.0, 'Macro_p': 25.0, 'Macro_r': 25.0}
 """
 
 
@@ -66,6 +76,7 @@ def convert_format(data:list):
         'tail_type': ['product', 'product'...]}
         ...
         ]
+        
     """
     predictions = []
     for item in data:
@@ -84,7 +95,7 @@ def convert_format(data:list):
 
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class relation_extraction(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
+    """evaluating the quality of relation extraction output"""
 
     def _info(self):
         # TODO: Specifies the evaluate.EvaluationModuleInfo object
@@ -119,8 +130,6 @@ class relation_extraction(evaluate.Metric):
         )
 
     def _download_and_prepare(self, dl_manager):
-        """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
         pass
 
     def _compute(self, predictions, references, mode, detailed_scores=False, relation_types=[]):