app.py

import base64
import streamlit as st
import numpy as np
import re
import emoji
import os
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

# Download necessary resources
nltk.download('punkt_tab')
nltk.download('stopwords')
nltk.download('wordnet')

import tensorflow as tf
import keras
from keras.preprocessing.sequence import pad_sequences
import pickle

# ✅ Enable full-width mode for Hugging Face
st.set_page_config(page_title="Intelligent News Classifier", page_icon="🧠", layout="wide")

# ✅ Function to set background image
def set_background(image_path):
    if not os.path.exists(image_path):
        st.error(f"❌ Background image not found: {image_path}")
        return

    with open(image_path, "rb") as img_file:
        encoded_img = base64.b64encode(img_file.read()).decode()

    bg_image_style = f"""
    <style>
        .stApp {{
            background-image: url("data:image/png;base64,{encoded_img}");
            background-size: cover;
            background-repeat: no-repeat;
            background-position: center;
            background-attachment: fixed;
        }}
    </style>
    """
    st.markdown(bg_image_style, unsafe_allow_html=True)

# ✅ Set background image
set_background("Images/picture.png")

# ✅ Initialize stopwords and lemmatizer
stop_words = set(stopwords.words('english')).union({"pm"})
lemmatizer = WordNetLemmatizer()

# ✅ Text Preprocessing Function
def pre_process(text):
    text = text.lower()
    text = re.sub("<.*?>", "", text)  # Remove HTML tags
    text = re.sub("http[s]?://\\S+", "", text)  # Remove URLs
    text = re.sub("[@#]\\S+", "", text)  # Remove mentions and hashtags
    text = re.sub(r"\\_+", " ", text)  # Replace underscores with spaces
    text = emoji.demojize(text)  # Convert emojis to text
    text = re.sub(":.*?:", "", text)  # Remove emoji text
    text = re.sub("[^a-zA-Z0-9\\s_]", "", text)  # Remove special characters
    words = word_tokenize(text)
    words = [word for word in words if word not in stop_words]
    text = " ".join([lemmatizer.lemmatize(word) for word in words])
    return text

# ✅ Cache Model Loading for Performance
@st.cache_resource
def load_model():
    model_path = "news_model.keras"
    vectorizer_path = "news_tv_model.keras"
    label_encoder_path = "label_encoder.pkl"

    model = keras.models.load_model(model_path)
    vectorizer = keras.models.load_model(vectorizer_path)

    with open(label_encoder_path, 'rb') as file:
        label_encoder = pickle.load(file)

    return model, vectorizer, label_encoder

# ✅ Load the models
model, vectorizer, label_encoder = load_model()

# ✅ Prediction Function
def predict_category(text):
    processed_text = [pre_process(text)]
    text_vectorized = pad_sequences(vectorizer(processed_text).numpy().tolist(), padding='pre', maxlen=82)
    prediction = model.predict(text_vectorized)
    category_idx = np.argmax(prediction, axis=1)[0]
    return label_encoder.inverse_transform([category_idx])[0]

# ✅ Category Color Mapping
category_colors = {
    "Sports": "#27ae60",  # Green
    "Politics": "#2980b9",  # Blue
    "Entertainment": "#8e44ad",  # Purple
    "Technology": "#e67e22",  # Orange
    "Business": "#c0392b",  # Red
    "Default": "#ffffff"  # White
}

# ✅ Streamlit UI Design
st.markdown("""
    <style>
    .title {
        color: #ffffff;
        font-size: 2.8em;
        text-align: center;
        font-weight: 700;
        text-transform: uppercase;
        text-shadow: 2px 2px 8px rgba(0, 0, 0, 1.0);
        padding: 15px;
    }
    .subtitle {
        color: #ffffff;
        font-size: 1.5em;
        text-align: center;
        font-weight: 600;
        text-shadow: 1px 1px 6px rgba(0, 0, 0, 1.0);
        padding: 10px;
    }
    .result-box {
        padding: 25px;
        border-radius: 12px;
        text-align: center;
        margin-top: 30px;
        font-size: 2em;
        font-weight: 900;
        text-shadow: 3px 3px 10px rgba(0, 0, 0, 0.5);
    }
    </style>
    """, unsafe_allow_html=True)

# ✅ Page Title
st.markdown("<div class='title'>🧠 Intelligent News Classifier</div>", unsafe_allow_html=True)
st.markdown("<div class='subtitle'>Find out what type of news you're reading!.</div>", unsafe_allow_html=True)

# ✅ User Input
user_input = st.text_area("Enter text here:", height=150, placeholder="Type your news text here...")

# ✅ Analyze Button
if st.button("Analyze 🧐"): 
    if user_input.strip():
        category = predict_category(user_input)
        color = category_colors.get(category, category_colors["Default"])
        st.markdown(
            f"""
            <div class='result-box' style='color: {color};'>
                🗂️ Predicted Category: <strong>{category}</strong>
            </div>
            """,
            unsafe_allow_html=True
        )
    else:
        st.warning("⚠️ Please enter some text to analyze.")