app.py

import pandas as pd
import numpy as np
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import gradio as gr

def load_data():
    df = pd.read_csv("spam.csv", encoding="latin-1")
    df = df[['v1', 'v2']]
    df.columns = ['label', 'message']
    df['spam'] = df['label'].apply(lambda x: 1 if x == 'spam' else 0)
    return df

def train_model(df):
    X_train, X_test, y_train, y_test = train_test_split(df.message, df.spam, test_size=0.2, random_state=42)

    vectorizer = CountVectorizer()
    X_train_cv = vectorizer.fit_transform(X_train)
    X_test_cv = vectorizer.transform(X_test)

    model = MultinomialNB()
    model.fit(X_train_cv, y_train)

    y_pred = model.predict(X_test_cv)
    print("Model performance on test set:")
    print(classification_report(y_test, y_pred))

    return model, vectorizer

def predict_spam(email_text):
    email_count = vectorizer.transform([email_text])
    prediction = model.predict(email_count)[0]
    return "Spam ❌" if prediction == 1 else "Not Spam"
df = load_data()
model, vectorizer = train_model(df)

interface = gr.Interface(
    fn=predict_spam,
    inputs=gr.Textbox(lines=5, placeholder="Paste your email text here..."),
    outputs="text",
    title="Email Spam Detector",
    description="A machine learning model using Naive Bayes to detect whether an email is spam or not."
)
interface.launch()