unit testing

README.md

@@ -82,7 +82,7 @@ print(metric.inputs_description)
 [//]: # (- **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*)
 
 ### Output Values
-List of `Scores` dataclass corresponding to each sample - 
+Singleton/List of `Scores` dataclass corresponding to each sample - 
 
  - `precision: float`: Precision score, which ranges from 0.0 to 1.0.
  - `recall: List[float]`: Recall score corresponding to each reference

tests.py

@@ -249,7 +249,7 @@ class TestSemF1(unittest.TestCase):
             'this is the second prediction sample',
         ]
     
-    def test_aggregate_flag(self):
+    def test_aggregate_multi_sample(self):
         """
         check if a `Scores` class is returned instead of a list of 
         `Scores`
@@ -266,6 +266,70 @@ class TestSemF1(unittest.TestCase):
         )
         self.assertIsInstance(scores, Scores)
 
+    def test_aggregate_untokenized_single_ref(self):
+        scores = self.semf1_metric.compute(
+            predictions=self.untokenized_single_reference_predictions,
+            references=self.untokenized_single_reference_references,
+            tokenize_sentences=True,
+            multi_references=False,
+            gpu=False,
+            batch_size=32,
+            verbose=False,
+            aggregate=True,
+        )
+        self.assertIsInstance(scores, Scores)
+
+    def test_aggregate_tokenized_single_ref(self):
+        scores = self.semf1_metric.compute(
+            predictions=self.tokenized_single_reference_predictions,
+            references=self.tokenized_single_reference_references,
+            tokenize_sentences=True,
+            multi_references=False,
+            gpu=False,
+            batch_size=32,
+            verbose=False,
+            aggregate=True,
+        )
+        self.assertIsInstance(scores, Scores)
+
+    def test_aggregate_untokenized_multi_ref(self):
+        scores = self.semf1_metric.compute(
+            predictions=self.untokenized_multi_reference_predictions,
+            references=self.untokenized_multi_reference_references,
+            tokenize_sentences=True,
+            multi_references=False,
+            gpu=False,
+            batch_size=32,
+            verbose=False,
+            aggregate=True,
+        )
+        self.assertIsInstance(scores, Scores)
+
+    def test_aggregate_tokenized_multi_ref(self):
+        scores = self.semf1_metric.compute(
+            predictions=self.tokenized_multi_reference_predictions,
+            references=self.tokenized_multi_reference_references,
+            tokenize_sentences=True,
+            multi_references=False,
+            gpu=False,
+            batch_size=32,
+            verbose=False,
+            aggregate=True,
+        )
+        self.assertIsInstance(scores, Scores)
+
+    def test_aggregate_same_pred_and_ref(self):
+        scores = self.semf1_metric.compute(
+            predictions=self.tokenized_single_reference_predictions,
+            references=self.tokenized_single_reference_predictions,
+            tokenize_sentences=True,
+            multi_references=False,
+            gpu=False,
+            batch_size=32,
+            verbose=False,
+            aggregate=True,
+        )
+        self.assertIsInstance(scores, Scores)
 
     def test_untokenized_single_reference(self):
         scores = self.semf1_metric.compute(