app.py

import streamlit as st
import pickle
import tensorflow as tf
import numpy as np
import re
import emoji
import nltk
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords  

# Ensure necessary downloads
nltk.download("punkt")
nltk.download("wordnet")
nltk.download('stopwords')  

lemmatizer = WordNetLemmatizer()
stop_words = set(stopwords.words('english'))  

def pre_process(text):
    text = text.lower()
    text = re.sub("<.*?>", "", text)
    text = re.sub("http[s]?://\\S+", "", text)
    text = re.sub("[@#]\\S+", "", text)
    text = re.sub(r"\\_+", " ", text)
    text = re.sub("^[A-Za-z.].*\\s-\\s", "", text)
    text = emoji.demojize(text)
    text = re.sub(":.*?:", "", text)
    text = re.sub("[^a-zA-Z0-9\\s_]", "", text)
    words = word_tokenize(text)
    words = [lemmatizer.lemmatize(word) for word in words if word not in stop_words]
    return " ".join(words)

# Load the label encoder
with open("label_encoder.pkl", "rb") as f:
    label_encoder = pickle.load(f)

# Load the text vectorization model
text_vectorizer = tf.keras.models.load_model("news_tv_model.keras")

# Load the news classification model
news_model = tf.keras.models.load_model("news_model.keras")

def predict_category(text):
    processed_text = [pre_process(text)]
    vectorized_text = text_vectorizer(processed_text)
    prediction = news_model.predict(vectorized_text)
    predicted_label_index = np.argmax(prediction, axis=1)[0]
    return label_encoder.inverse_transform([predicted_label_index])[0]

# Streamlit UI
st.title("News Classification App")

# User input
user_text = st.text_area("Enter your news content for classification.")

if st.button("Predict Category"):
    if user_text.strip():
        category = predict_category(user_text)
        st.success(f"Predicted Category: {category}")
    else:
        st.warning("Please enter some text to classify.")