Update app.py

app.py

@@ -5,8 +5,7 @@ import io
 from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
 from transformers import AutoModelForQuestionAnswering
 
-
-# Load fine-tuned models and tokenizers for both functions 
+# Load fine-tuned models and tokenizers for both functions
 model_name_classification = "TAgroup5/news-classification-model"  # Replace with the correct model name
 model = AutoModelForSequenceClassification.from_pretrained(model_name_classification)
 tokenizer = AutoTokenizer.from_pretrained(model_name_classification)
@@ -17,68 +16,81 @@ tokenizer_qa = AutoTokenizer.from_pretrained(model_name_qa)
 
 # Initialize pipelines
 text_classification_pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
-qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
-
-
-# Streamlit App
-st.title("News Classification and Q&A")
-
-## ====================== Component 1: News Classification ====================== ##
-st.header("Classify News Articles")
-st.markdown("Upload a CSV file with a 'content' column to classify news into categories.")
-
-uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-
-if uploaded_file is not None:
-    try:
-        df = pd.read_csv(uploaded_file, encoding="utf-8")  # Handle encoding issues
-    except UnicodeDecodeError:
-        df = pd.read_csv(uploaded_file, encoding="ISO-8859-1")
-
-    if 'content' not in df.columns:
-        st.error("Error: The uploaded CSV must contain a 'content' column.")
-    else:
-        st.write("Preview of uploaded data:")
-        st.dataframe(df.head())
-
-        # Preprocessing function to clean the text
-        def preprocess_text(text):
-            text = text.lower()  # Convert to lowercase
-            text = re.sub(r'\s+', ' ', text)  # Remove extra spaces
-            text = re.sub(r'[^a-z\s]', '', text)  # Remove special characters & numbers
-            # You don't need tokenization here, as the model tokenizer will handle it
-            return text
-
-
-        # Apply preprocessing and classification
-        df['processed_content'] = df['content'].apply(preprocess_text)
+qa_pipeline = pipeline("question-answering", model=model)
+
+# Streamlit App 
+st.set_page_config(page_title="News Classification & Q&A", page_icon="📰", layout="wide")
+st.markdown(
+    """
+    <style>
+        body {background-color: #f4f4f4;}
+        .title {text-align: center; font-size: 36px; font-weight: bold; color: #ff4b4b;}
+        .subheader {font-size: 24px; color: #333; margin-bottom: 20px; text-align: right;}
+        .stTextInput>div>div>input {border-radius: 10px;}
+        .stTextArea>div>div>textarea {border-radius: 10px;}
+        .stButton>button {border-radius: 10px; background-color: #ff4b4b; color: white; font-weight: bold;}
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+
+st.markdown('<h1 class="title">📰 News Classification & Q&A App</h1>', unsafe_allow_html=True)
+
+col1, col2 = st.columns([2, 1])
+with col2:
+    # ====================== Component 1: News Classification ====================== #
+    st.markdown('<h2 class="subheader">📌 Classify News Articles</h2>', unsafe_allow_html=True)
+    st.markdown("Upload a CSV file with a 'content' column to classify news into categories.")
+
+    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+
+    if uploaded_file is not None:
+        try:
+            df = pd.read_csv(uploaded_file, encoding="utf-8")  # Handle encoding issues
+        except UnicodeDecodeError:
+            df = pd.read_csv(uploaded_file, encoding="ISO-8859-1")
         
-        # Classify each record into one of the five classes
-        df['class'] = df['processed_content'].apply(lambda x: text_classification_pipeline(x)[0]['label'] if x.strip() else "Unknown")
-
-        # Show results
-        st.write("Classification Results:")
-        st.dataframe(df[['content', 'class']])
-
-        # Provide CSV download
-        output = io.BytesIO()
-        df.to_csv(output, index=False, encoding="utf-8-sig")
-        st.download_button(label="Download classified news", data=output.getvalue(), file_name="output.csv", mime="text/csv")
-
-## ====================== Component 2: Q&A ====================== ##
-st.header("Ask a Question About the News")
-st.markdown("Enter a question and provide a news article to get an answer.")
-
-question = st.text_input("Ask a question:")
-context = st.text_area("Provide the news article or content for the Q&A:", height=150)
-
-if question and context.strip():
-    model_name_qa = "distilbert-base-uncased-distilled-squad"  # Example of a common Q&A model
-    qa_pipeline = pipeline("question-answering", model=model_name_qa, tokenizer=model_name_qa)
-    result = qa_pipeline(question=question, context=context)
-    
-    # Check if the result contains an answer
-    if 'answer' in result and result['answer']:
-        st.write("Answer:", result['answer'])
-    else:
-        st.write("No answer found in the provided content.")
+        if 'content' not in df.columns:
+            st.error("❌ Error: The uploaded CSV must contain a 'content' column.")
+        else:
+            st.success("✅ File successfully uploaded!")
+            st.write("Preview of uploaded data:")
+            st.dataframe(df.head())
+            
+            # Preprocessing function to clean the text
+            def preprocess_text(text):
+                text = text.lower()  # Convert to lowercase
+                text = re.sub(r'\s+', ' ', text)  # Remove extra spaces
+                text = re.sub(r'[^a-z\s]', '', text)  # Remove special characters & numbers
+                return text
+
+            # Apply preprocessing and classification
+            df['processed_content'] = df['content'].apply(preprocess_text)
+            df['class'] = df['processed_content'].apply(lambda x: text_classification_pipeline(x)[0]['label'] if x.strip() else "Unknown")
+            
+            # Show results
+            st.markdown("### 🔹 Classification Results:")
+            st.dataframe(df[['content', 'class']])
+            
+            # Provide CSV download
+            output = io.BytesIO()
+            df.to_csv(output, index=False, encoding="utf-8-sig")
+            st.download_button(label="⬇️ Download classified news", data=output.getvalue(), file_name="classified_news.csv", mime="text/csv")
+
+    # ====================== Component 2: Q&A ====================== #
+    st.markdown('<h2 class="subheader">❓ Ask a Question About the News</h2>', unsafe_allow_html=True)
+    st.markdown("Enter a question and provide a news article to get an answer.")
+
+    question = st.text_input("🔍 Ask a question:")
+    context = st.text_area("📝 Provide the news article or content:", height=150)
+
+    if question and context.strip():
+        model_name_qa = "distilbert-base-uncased-distilled-squad"
+        qa_pipeline = pipeline("question-answering", model=model_name_qa, tokenizer=model_name_qa)
+        result = qa_pipeline(question=question, context=context)
+        
+        # Display Answer
+        if 'answer' in result and result['answer']:
+            st.markdown(f"### ✅ Answer: {result['answer']}")
+        else:
+            st.markdown("### ❌ No answer found in the provided content.")