Remove print statments and reformat the results

Nested/utils/data.py

@@ -118,9 +118,7 @@ def get_dataloaders(
     """
     dataloaders = list()
 
-    print("data_config Before: ", data_config, type(data_config))
     data_config = data_config["data_config"]
-    print("data_config After: ", data_config)
     for i, examples in enumerate(datasets):
         data_config["kwargs"].update({"examples": examples, "vocab": vocab})
         dataset = load_object(data_config["fn"], data_config["kwargs"])

app.py

@@ -73,11 +73,28 @@ dataloader = get_dataloaders(
 
 # Perform inference on the text and get back the tagged segments
 segments = tagger.infer(dataloader)
+segments_lists = []
+
 
 # Print results
+# for segment in segments:
+#     s = [
+#         f"{token.text} ({'|'.join([t['tag'] for t in token.pred_tag])})"
+#         for token in segment
+#     ]
+#     print(" ".join(s))
+
+
 for segment in segments:
-    s = [
-        f"{token.text} ({'|'.join([t['tag'] for t in token.pred_tag])})"
-        for token in segment
-    ]
-    print(" ".join(s))
+    for token in segment:
+        segments_list = {}
+        segments_list["token"] = token.text
+        list_of_tags = [t['tag'] for t in token.pred_tag]
+        list_of_tags = [i for i in list_of_tags if i not in('O',' ','')]
+        if list_of_tags == []:
+            segments_list["tags"] = ' '.join(['O'])
+        else:
+            segments_list["tags"] = ' '.join(list_of_tags)
+        segments_lists.append(segments_list)  
+
+print(segments_lists)