Update app.py

app.py

@@ -94,34 +94,17 @@ def answer_question(news_content, question):
         start_idx = torch.argmax(outputs.start_logits)
         end_idx = torch.argmax(outputs.end_logits) + 1
         
+        # Clean answer - remove question repetition and special tokens
         answer = qa_tokenizer.decode(inputs.input_ids[0][start_idx:end_idx], 
                                     skip_special_tokens=True, 
                                     clean_up_tokenization_spaces=True)
         
         confidence = torch.max(torch.softmax(outputs.start_logits, dim=1)).item()
-
-        # ====== Useful Statistics ======
-        words = nltk.word_tokenize(news_content)
-        sentences = nltk.sent_tokenize(news_content)
-        word_count = len(words)
-        sentence_count = len(sentences)
-        reading_time = round(word_count / 200, 2)  # ~200 words/minute
-
-        stats = f"Word count: {word_count}\nSentences: {sentence_count}\nEstimated reading time: {reading_time} min"
-
-        # ====== Word Cloud ======
-        wc = WordCloud(width=800, height=400, background_color="white").generate(news_content)
-        fig, ax = plt.subplots()
-        ax.imshow(wc, interpolation="bilinear")
-        ax.axis("off")
-        buf = io.BytesIO()
-        plt.savefig(buf, format="png")
-        buf.seek(0)
-
-        return f"**Answer:** {answer.strip()}\n\n**Confidence:** {confidence:.2%}\n\n{stats}", buf
+        
+        return f"**Answer:** {answer.strip()}\n\n**Confidence:** {confidence:.2%}"
     
     except Exception as e:
-        return f"Error: {str(e)}", None
+        return f"Error: {str(e)}"
 
 
 # ====================== GRADIO INTERFACE ======================
@@ -149,18 +132,18 @@ with gr.Blocks(title="Daily Mirror News Classifier") as demo:
                 outputs=[output_text, output_file,bar_chart]
             )
 
-        with gr.Tab("❓ Question Answering"):
+         with gr.Tab("❓ Question Answering"):
             gr.Markdown("Ask any question about a news article")
             news_input = gr.Textbox(lines=12, label="Paste News Content", placeholder="Paste the full news article here...")
             question_input = gr.Textbox(label="Your Question", placeholder="e.g. What is the main topic?")
             qa_btn = gr.Button("🔍 Get Answer", variant="primary")
-            qa_output = gr.Textbox(label="Answer + Stats", lines=8)
-            wc_output = gr.Image(label="Word Cloud")
-
+            qa_output = gr.Textbox(label="Answer", lines=5)
+            
             qa_btn.click(
-            fn=answer_question,
-            inputs=[news_input, question_input],
-            outputs=[qa_output, wc_output])
+                fn=answer_question,
+                inputs=[news_input, question_input],
+                outputs=qa_output
+            )
 
     gr.Markdown("Built for Text Analytics Assignment - Section 02")