app.py

import re
import emoji
import nltk
import numpy as np
import streamlit as st
import pickle  # To load the tokenizer

from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.sequence import pad_sequences

# Ensure necessary downloads
nltk.download("punkt")
nltk.download("wordnet")
nltk.download("omw-1.4")
nltk.download("averaged_perceptron_tagger")

lemmatizer = WordNetLemmatizer()

# Function to preprocess text
def pre_process(x):
    x = x.lower()
    x = re.sub("<.*?>", "", x)
    x = re.sub("http[s]?://.+?\\S+", "", x)
    x = re.sub("[@#].+?\\S", "", x)
    x = re.sub(r"\\_+", " ", x)
    x = re.sub("^[A-Za-z.].*\\s-\\s", "", x)
    x = emoji.demojize(x)
    x = re.sub(":.*?:", "", x)
    x = re.sub("[^a-zA-Z0-9\\s_]", "", x)
    words = word_tokenize(x)
    x = " ".join([lemmatizer.lemmatize(word) for word in words])
    return x

# Load trained model
model = load_model("best_rnn_model.h5")

# Load the same tokenizer used during training
with open("tokenizer.pickle", "rb") as handle:
    tokenizer = pickle.load(handle)

# Maximum length (must match training settings)
MAX_LENGTH = 100  

# Class labels
class_labels = ['Sports', 'Business', 'SciTech', 'World']

# Function to predict category
def predict_category(text):
    processed_text = pre_process(text)
    seq = tokenizer.texts_to_sequences([processed_text])
    padded_seq = pad_sequences(seq, maxlen=MAX_LENGTH, padding='post')
    prediction = model.predict(padded_seq)
    predicted_label = class_labels[np.argmax(prediction)]
    return predicted_label

# Streamlit UI
st.title("📰 News Category Classifier")
st.write("Enter a news headline or article snippet, and the model will predict its category.")

user_input = st.text_area("✍ Enter text here:")

if st.button("🔍 Predict"):
    if user_input.strip():
        prediction = predict_category(user_input)
        st.success(f"📌 Predicted Category: **{prediction}**")
    else:
        st.warning("⚠️ Please enter some text to classify.")