Remove Summarization

Remove summarization function as it takes too long to load.
The Top 5 Positive and Negative Comments remain.

app.py

@@ -13,7 +13,7 @@ import time
 
 
 sentiment_task = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment-latest", tokenizer="cardiffnlp/twitter-roberta-base-sentiment-latest")
-summarization_task = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+# summarization_task = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
 
 def extract_youtube_video_id(url_or_id):
@@ -175,19 +175,19 @@ def comments_analyzer(comments_df):
     end_time = time.time()
     print(f"Time taken for finding top n positive/negative comments: {end_time - start_time} seconds")
 
-    #Summarize the texts from positive and negative comments
-    start_time = time.time()
-    if top_positive_comments == "No positive comments available.":
-      top_positive_comments_summary = top_positive_comments
-    else:
-      top_positive_comments_summary = summarization_task(top_positive_comments)[0]['summary_text']
+    # #Summarize the texts from positive and negative comments
+    # start_time = time.time()
+    # if top_positive_comments == "No positive comments available.":
+    #   top_positive_comments_summary = top_positive_comments
+    # else:
+    #   top_positive_comments_summary = summarization_task(top_positive_comments)[0]['summary_text']
     
-    if top_negative_comments == "No negative comments available.":
-      top_negative_comments_summary = top_negative_comments
-    else:
-      top_negative_comments_summary = summarization_task(top_negative_comments)[0]['summary_text']
-    end_time = time.time()
-    print(f"Time taken for summarizing the top n positive/negative comments: {end_time - start_time} seconds")
+    # if top_negative_comments == "No negative comments available.":
+    #   top_negative_comments_summary = top_negative_comments
+    # else:
+    #   top_negative_comments_summary = summarization_task(top_negative_comments)[0]['summary_text']
+    # end_time = time.time()
+    # print(f"Time taken for summarizing the top n positive/negative comments: {end_time - start_time} seconds")
 
     data = {}
     #Categorize the comments by sentiment and count them
@@ -200,7 +200,7 @@ def comments_analyzer(comments_df):
     data['blended_comments'] = comments_df['content'].str.cat(sep=' ')
     data['pct_positive'] = 100 * round(data['num_positive']/data['total_comments'], 2)
 
-  return data, top_positive_comments_summary, top_negative_comments_summary
+  return data, top_positive_comments, top_negative_comments
 
 def generate_wordcloud(long_text, additional_stopwords=['Timestamps', 'timestamps']):
   # This function generates a word cloud image from a given text and returns it as a PIL image object.
@@ -300,7 +300,7 @@ def process_youtube_comments(youtube_link, max_comments, stop_words):
     print(f"Time taken for loading comments: {end_time - start_time} seconds")
 
     # Analyze
-    analysis_dict, top_positive_comments_summary, top_negative_comments_summary = comments_analyzer(comments_df)
+    analysis_dict, top_positive_comments, top_positive_comments = comments_analyzer(comments_df)
 
     long_text = analysis_dict['blended_comments']
 
@@ -334,8 +334,8 @@ interface = gr.Interface(
     ],
     outputs=[
         gr.Image(label="Word Cloud ☁️"),
-        gr.Textbox(label="Summary of the Top 5 Positive Comments 👍🏻"),
-        gr.Textbox(label="Summary of the Top 5 Negative Comments 👎🏻"),
+        gr.Textbox(label="Top 5 Positive Comments 👍🏻"),
+        gr.Textbox(label="Top 5 Negative Comments 👎🏻"),
         gr.Image(label="Sentiment Analysis Chart 📊")
     ],
     title="YouTube Comments Analyzer 📈",