import gradio as gr import joblib import re import nltk from nltk.corpus import stopwords from nltk.stem import PorterStemmer # Download NLTK stopwords nltk.download('stopwords') # Load the saved pipeline pipeline = joblib.load('spam_classifier_pipeline.joblib') # Preprocessing function (must match your training preprocessing) def preprocess_text(text): text = text.lower() text = re.sub(r'[^a-zA-Z\s]', '', text) words = text.split() stop_words = set(stopwords.words('english')) words = [word for word in words if word not in stop_words] stemmer = PorterStemmer() words = [stemmer.stem(word) for word in words] return ' '.join(words) # Prediction function def classify_email(subject, body): combined_text = preprocess_text(f"{subject} {body}") prediction = pipeline.predict([combined_text])[0] labels = ["ham", "not_spam", "spam"] return labels[prediction] # Create Gradio interface with gr.Blocks() as demo: gr.Markdown("# 📧 Spam Email Classifier") gr.Markdown("Classify emails into **ham (personal)**, **not_spam (promotional)**, or **spam (junk)**") with gr.Row(): with gr.Column(): subject = gr.Textbox(label="Email Subject", placeholder="e.g., 'Win a free prize!'") body = gr.Textbox(label="Email Body", placeholder="e.g., 'Click here to claim...'", lines=5) submit_btn = gr.Button("Classify Email") with gr.Column(): output = gr.Label(label="Prediction") examples = gr.Examples( examples=[ ["Meeting tomorrow", "Hi team, let's discuss the project at 10 AM."], ["Exclusive offer!", "Get 50% off on our new product. Limited time!"], ["You won $1,000,000!", "Claim your prize now by clicking this link!"], ["Newsletter", "This month's updates and new features"], ["Urgent: Account Suspension", "Your account will be closed unless you verify now"] ], inputs=[subject, body] ) submit_btn.click( fn=classify_email, inputs=[subject, body], outputs=output ) # For Hugging Face Spaces deployment demo.launch()