import subprocess

# Install NLTK and download required data
subprocess.run(["pip", "install", "nltk"])
subprocess.run(["pip", "install", "scikit-learn"])
import nltk
nltk.download('punkt')
nltk.download('stopwords')
import gradio as gr
import pickle
import nltk
import string
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer

# Load pre-trained model and vectorizer
ps = PorterStemmer()
tf = pickle.load(open('vectorizerr.pkl', 'rb'))
model = pickle.load(open('modell.pkl', 'rb'))

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

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

    text = y[:]
    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)

def predict_spam(input_sms):
    transform_sms = transform_text(input_sms)
    vector_input = tf.transform([transform_sms])
    result = model.predict(vector_input)[0]

    if result == 1:
        return 'Alert! This message is likely spam.'
    else:
        return 'This message is safe and not spam!'

# Gradio interface
input_text = gr.Textbox(lines=5, label="Enter the message")
output_text = gr.Textbox(label="Prediction")

gr.Interface(fn=predict_spam, inputs=input_text, outputs=output_text, title="SMS Spam Classifier", description="Enter a message below to check if it's spam or not.").launch()