Update app.py

app.py

@@ -10,20 +10,25 @@ dataset_api = project.get_dataset_api()
 
 dataset = load_dataset("torileatherman/sentiment_analysis_batch_predictions", split='train')
 predictions_df = pd.DataFrame(dataset)
-predictions_df_url0 = predictions_df['Url'].iloc[0]
-predictions_df_url1 = predictions_df['Url'].iloc[1]
-predictions_df_url2 = predictions_df['Url'].iloc[2]
-predictions_df_urls = [[predictions_df_url0],
-                       [predictions_df_url1],
-                       [predictions_df_url2]]
+grouped_predictions = predictions_df.groupby(predictions_df.Sentiment)
+positive_preds = grouped_predictions.get_group(2)
+neutral_preds = grouped_predictions.get_group(1)
+negative_preds = grouped_predictions.get_group(0)
+
 
 def article_selection(sentiment):
     if sentiment == "Positive":
-            return predictions_df_urls #f"""The sentence you requested is Positive!"""
+        predictions = positive_preds
+        predictions_urls = predictions['Url'][0:3]
+        return predictions_urls
     elif sentiment == "Negative":
-        return f"""The sentence you requested is Negative!""" 
+        predictions = negative_preds
+        predictions_urls = predictions['Url'][0:3]
+        return predictions_urls
     else:
-        return f"""The sentence you requested is Neutral!""" 
+        predictions = neutral_preds
+        predictions_urls = predictions['Url'][0:3]
+        return predictions_urls
 
 def thanks(url, sentiment):
     thanks_text = "Thank you for making our model better!"
@@ -54,7 +59,7 @@ manual_label_demo = gr.Interface(
     inputs=[gr.Textbox(label = "Paste in URL of news article here."),
             gr.Dropdown(["Positive","Negative","Neutral"], label="Select the sentiment of the news article.")],
     outputs = gr.Textbox(label="Output"),
-    description = description1
+    description = description2
 )