app.py

import streamlit as st
import string
import pickle
import nltk
from nltk.corpus import stopwords
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('corpus')
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()


def transform_text(input_sms):
    text = input_sms.lower()
    text = nltk.word_tokenize(text)

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

    text = y[:]  # proper method to clone a list
    y.clear()

    for i in text:
        if i not in stopwords.words('english') and i not in string.punctuation:
            y.append(i)
    text = y[:]
    y.clear()
    for i in text:
        y.append(ps.stem(i))

    return " ".join(y)

tfidf = pickle.load(open('vectorizer.pkl', 'rb'))
model = pickle.load(open('model.pkl', 'rb'))

st.title("Email/SMS Spam Classifier")

input_sms = st.text_input("Enter the message: ")

if st.button('Predict'):
    # 1. Pre-Process
    transformed_sms = transform_text(input_sms)
    # 2. Vectorize
    vector_input = tfidf.transform([transformed_sms])
    # 3. Predict
    result = model.predict(vector_input)[0]
    # 4. Display
    if result == 1:
        st.header("Spam")
    if result == 0:
        st.header("Not Spam/Ham")