Update gradio_app.py

gradio_app.py

@@ -60,6 +60,56 @@ def toggle_feedback(request_data, response_data, like_clicked, dislike_clicked):
     else:
         return "Feedback sent successfully!"
 
+def preprocess_and_flatten(json_results, nested_fields, meta_fields=None):
+    # Ensure 'meta_fields' is a list or set default fields
+    if meta_fields is None:
+        meta_fields = ['doc_id', 'details', 'domain']
+
+    # Check if json_results is a valid dictionary
+    if not isinstance(json_results, dict):
+        print(f"Invalid JSON results: Expected a dictionary but got {type(json_results)}")
+        return pd.DataFrame()  # Return an empty DataFrame if json_results is not a dictionary
+
+    # Preprocess each field in the nested_fields list
+    for field in nested_fields:
+        if field in json_results:
+            nested_field = json_results.get(field)
+            if isinstance(nested_field, dict):
+                json_results[field] = [nested_field]  # Wrap dict in a list if it's a dict
+            elif not isinstance(nested_field, list):
+                json_results[field] = []  # Default to empty list if not a list or dict
+
+    # Flatten the JSON for each field in nested_fields
+    dataframes = []
+    for field in nested_fields:
+        # Check if the field exists in json_results
+        if field not in json_results or not isinstance(json_results[field], list):
+            print(f"Field '{field}' not found or is not a list in the JSON results.")
+            continue  # Skip this field if it's missing or not a list
+
+        try:
+            # Flatten the JSON for the specified nested field
+            dataframe_results = pd.json_normalize(
+                json_results,
+                record_path=[field],                     # Nested array to flatten
+                meta=meta_fields,                        # Top-level fields to retain
+                sep='_',                                 # Separator for nested fields
+                errors='ignore'                          # To handle cases with missing keys
+            )
+            if not dataframe_results.empty:
+                dataframes.append(dataframe_results)     # Append the flattened DataFrame
+        except Exception as e:
+            print(f"Error while flattening field '{field}': {e}")
+            continue  # Skip this field if an error occurs
+
+    # Concatenate all the DataFrames if there are any
+    if dataframes:
+        final_dataframe = pd.concat(dataframes, ignore_index=True)
+    else:
+        final_dataframe = pd.DataFrame()  # Return an empty DataFrame if nothing was flattened
+
+    return final_dataframe
+    
 # Define the functions to handle the inputs and outputs
 def news_analysis(text):
     try:
@@ -75,8 +125,8 @@ def news_analysis(text):
         response.raise_for_status()
         # Prepare results for JSON output
         json_results = response.json()
-        # Normalize the JSON data
-        dataframe_results = pd.json_normalize(json_results, sep='_')
+        # Flatten 'claim_objects' field
+        dataframe_results = preprocess_and_flatten(json_results, ['claim_objects'], ['doc_id', 'details', 'domain'])
         return json_results, dataframe_results
     except Exception as e:
         results = {'error': str(e)}
@@ -96,8 +146,8 @@ def claim_verification(text):
         response.raise_for_status()
         # Prepare results for JSON output
         json_results = response.json()
-        # Normalize the JSON data
-        dataframe_results = pd.json_normalize(json_results, sep='_')
+        # Call preprocess_and_flatten to flatten 'support', 'refute', and 'no_info' fields
+        dataframe_results = preprocess_and_flatten(json_results, ['support', 'refute', 'no_info'], ['doc_id', 'details'])
         return json_results, dataframe_results
     except Exception as e:
         results = {'error': str(e)}