app.py

import streamlit as st
import pickle
import string
import nltk
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer

# 🧠 Download required NLTK resources only once
try:
    nltk.data.find('tokenizers/punkt')
except LookupError:
    nltk.download('punkt')

try:
    nltk.data.find('corpora/stopwords')
except LookupError:
    nltk.download('stopwords')

# 🔤 Initialize stemmer
ps = PorterStemmer()

# 🔍 Preprocessing function
def transform_text(text):
    text = text.lower()
    text = nltk.word_tokenize(text)

    y = []
    for word in text:
        if word.isalnum():
            y.append(word)

    text = y[:]
    y.clear()

    for word in text:
        if word not in stopwords.words('english') and word not in string.punctuation:
            y.append(ps.stem(word))

    return " ".join(y)

# 📦 Load model and vectorizer
tfidf = pickle.load(open('vectorizer.pkl', 'rb'))
model = pickle.load(open('model.pkl', 'rb'))

# 💬 Streamlit UI
st.title("📩 SMS Spam Classifier")

input_sms = st.text_area("Enter the message")

if st.button('Predict'):
    # 1. Preprocess
    transformed_sms = transform_text(input_sms)

    # 2. Vectorize
    vector_input = tfidf.transform([transformed_sms])

    # 3. Predict
    result = model.predict(vector_input)[0]

    # 4. Show result
    if result == 1:
        st.error("🚫 Spam")
    else:
        st.success("✅ Not Spam")