app.py

import streamlit as st
import pandas as pd
import re
import io
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
from transformers import AutoModelForQuestionAnswering
from streamlit_extras.app_logo import add_logo  # For adding a logo

# Custom Styling
st.set_page_config(page_title="News Classifier & Q&A", page_icon="📰", layout="wide")

# CSS for styling
st.markdown(
    """
    <style>
        body {
            background-color: #f5f5f5;
        }
        .stApp {
            background-color: white;
            border-radius: 10px;
            padding: 20px;
            box-shadow: 2px 2px 10px rgba(0, 0, 0, 0.1);
        }
        .stTitle, .stHeader {
            color: #0073e6;
            text-align: center;
        }
        .stButton>button {
            background-color: #0073e6 !important;
            color: white !important;
            border-radius: 8px !important;
            font-size: 16px !important;
        }
        .stDownloadButton>button {
            background-color: #28a745 !important;
            color: white !important;
            border-radius: 8px !important;
        }
    </style>
    """,
    unsafe_allow_html=True,
)

# Add a logo (optional, replace with your logo URL)
# add_logo("https://your-logo-url.png", height=50)

st.title("📰 News Classification & 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")
    except UnicodeDecodeError:
        df = pd.read_csv(uploaded_file, encoding="ISO-8859-1")

    if 'content' not in df.columns:
        st.error("❌ The uploaded CSV must contain a 'content' column.")
    else:
        st.success("✅ File uploaded successfully!")
        st.write("Preview of uploaded data:")
        st.dataframe(df.head())

        # Preprocessing function
        def preprocess_text(text):
            text = text.lower()
            text = re.sub(r'\s+', ' ', text)
            text = re.sub(r'[^a-z\s]', '', text)
            return text

        # Apply preprocessing
        df['processed_content'] = df['content'].apply(preprocess_text)

        # Load Model
        model_name_classification = "TAgroup5/news-classification-model"
        model = AutoModelForSequenceClassification.from_pretrained(model_name_classification)
        tokenizer = AutoTokenizer.from_pretrained(model_name_classification)
        text_classification_pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)

        # Classify each record
        df['class'] = df['processed_content'].apply(lambda x: text_classification_pipeline(x)[0]['label'] if x.strip() else "Unknown")

        # Display 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="classified_news.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 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.success(f"**🗣 Answer:** {result['answer']}")
    else:
        st.warning("⚠️ No answer found in the provided content.")