Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import gradio as gr
 import pandas as pd
 import torch
@@ -8,16 +7,15 @@ from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 import re
 import string
-import torch
 
-# ====================== PREPROCESSING ======================
+# ====================== NLTK SETUP ======================
 nltk.download('wordnet', quiet=True)
 nltk.download('punkt', quiet=True)
-nltk.download('punkt_tab', quiet=True)   # ← THIS FIXES YOUR ERROR
-
+nltk.download('punkt_tab', quiet=True)
 
 lemmatizer = WordNetLemmatizer()
 
+
 def preprocess_text(text):
     if not isinstance(text, str):
         return ""
@@ -31,24 +29,23 @@ def preprocess_text(text):
     return ' '.join(tokens)
 
 
-# ====================== LOAD YOUR FINE-TUNED MODEL ======================
-model_name = "Ginidu2003/Distilbert-Base-News-classifier"   # ← Change if your model name is different
 
+# ====================== MODELS ======================
+classifier_model = "Ginidu2003/Distilbert-Base-News-classifier"
+qa_model = "deepset/roberta-base-squad2"   # Best for news Q&A
+
+# ====================== CLASSIFICATION FUNCTION ======================
 @torch.no_grad()
 def classify_csv(file):
     try:
         df = pd.read_csv(file)
-        
         if 'content' not in df.columns:
             return "Error: CSV must have a column named 'content'", None
         
-        # Preprocess
         df['clean_content'] = df['content'].apply(preprocess_text)
         
-        # Load classifier
-        classifier = pipeline("text-classification", model=model_name, device=-1)
+        classifier = pipeline("text-classification", model=classifier_model, device=-1)
         
-        # Predict
         predictions = []
         for text in df['clean_content']:
             if not text.strip():
@@ -60,33 +57,58 @@ def classify_csv(file):
         df['class'] = predictions
         df = df.drop(columns=['clean_content'], errors='ignore')
         
-        # Save output
         output_file = "output.csv"
         df.to_csv(output_file, index=False)
         
         return f"✅ Success! Classified {len(df)} rows", output_file
-        
     except Exception as e:
         return f"❌ Error: {str(e)}", None
 
+# ====================== Q&A FUNCTION ======================
+qa_pipeline = pipeline("question-answering", model=qa_model, device=-1)
+
+def answer_question(news_content, question):
+    if not news_content or not question:
+        return "Please enter both news content and a question."
+    try:
+        result = qa_pipeline(question=question, context=news_content)
+        return f"**Answer:** {result['answer']}\n\n**Confidence:** {result['score']:.2%}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
 # ====================== GRADIO INTERFACE ======================
 with gr.Blocks(title="Daily Mirror News Classifier") as demo:
     gr.Markdown("# 📰 Daily Mirror News Classifier")
-    gr.Markdown("### Classify news into Business, Opinion, Political Gossip, Sports, or World News")
-    
-    with gr.Row():
-        file_input = gr.File(label="Upload CSV file", file_types=[".csv"])
-    
-    classify_btn = gr.Button("🚀 Classify News", variant="primary")
-    
-    output_text = gr.Textbox(label="Status")
-    output_file = gr.File(label="Download output.csv")
-    
-    classify_btn.click(
-        fn=classify_csv,
-        inputs=file_input,
-        outputs=[output_text, output_file]
-    )
+    gr.Markdown("### Section 02 - Text Analytics Assignment")
+
+    with gr.Tabs():
+        # Tab 1: Classification
+        with gr.Tab("📊 Text Classification"):
+            gr.Markdown("Upload a CSV file with a `content` column")
+            file_input = gr.File(label="Upload CSV", file_types=[".csv"])
+            classify_btn = gr.Button("🚀 Classify News", variant="primary")
+            output_text = gr.Textbox(label="Status")
+            output_file = gr.File(label="Download output.csv")
+            
+            classify_btn.click(
+                fn=classify_csv,
+                inputs=file_input,
+                outputs=[output_text, output_file]
+            )
+
+        # Tab 2: Q&A Pipeline
+        with gr.Tab("❓ Question Answering"):
+            gr.Markdown("Ask any question about a news article")
+            news_input = gr.Textbox(lines=10, 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 issue discussed?")
+            qa_btn = gr.Button("🔍 Get Answer", variant="primary")
+            qa_output = gr.Textbox(label="Answer", lines=4)
+            
+            qa_btn.click(
+                fn=answer_question,
+                inputs=[news_input, question_input],
+                outputs=qa_output
+            )
 
     gr.Markdown("Built for Text Analytics Assignment - Section 02")