Update app.py

app.py

@@ -19,7 +19,11 @@ def load_text_classifier():
 
 # Load Classifier & QA pipeline
 classifier = load_text_classifier()
-qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+qa_pipeline = pipeline(
+    "question-answering",
+    model="deepset/roberta-large-squad2",
+    tokenizer="deepset/roberta-large-squad2"
+)
 
 # ----------------- CSS Styling -----------------
 st.markdown(
@@ -45,7 +49,7 @@ uploaded_file = st.file_uploader("Choose a CSV file...", type=["csv"])
 
 if uploaded_file:
     # Read and preprocess
-    df = pd.read_csv(uploaded_file)
+    df = pd.read_csv(uploaded_file, encoding='utf-8')
     if "content" not in df.columns:
         st.error("❌ The uploaded CSV must contain a 'content' column.")
         st.stop()
@@ -63,7 +67,8 @@ if uploaded_file:
 
     # ----------------- Download -----------------
     st.subheader("📥 Download Results")
-    csv_output = df.to_csv(index=False).encode('utf-8')
+    output_df = df[['content', 'class']]
+    csv_output = output_df.to_csv(index=False, encoding='utf-8-sig').encode('utf-8-sig')
     st.download_button("Download Output CSV", data=csv_output, file_name="output.csv", mime="text/csv")
 
     # ----------------- Q&A Section -----------------
@@ -71,14 +76,14 @@ if uploaded_file:
     question = st.text_input("🔍 What do you want to know about the content?")
 
     if st.button("Get Answer"):
-        context = " ".join(df['cleaned_text'].tolist())
+        context = " ".join(df['content'].tolist())
         with st.spinner("Answering..."):
             result = qa_pipeline(question=question, context=context)
-        st.success(f"📝 **Answer:** {result['answer']}")
+        st.success(f"📝 Answer: {result['answer']}")
 
     # ----------------- Word Cloud -----------------
-    st.subheader("☁️ Word Cloud of News Text")
-    text = " ".join(df['cleaned_text'].tolist())
+    st.subheader("☁ Word Cloud of News Text")
+    text = " ".join(df['content'].tolist())
     wordcloud = WordCloud(width=800, height=400, background_color="white").generate(text)
 
     fig, ax = plt.subplots()