| import pandas as pd |
| from sklearn.feature_extraction.text import TfidfVectorizer |
| from sklearn.naive_bayes import MultinomialNB |
| import gradio as gr |
|
|
| |
| df = pd.read_csv("spam.csv", encoding='latin-1')[['v1', 'v2']] |
| df.columns = ['label', 'message'] |
| df['label'] = df['label'].map({'ham': 0, 'spam': 1}) |
|
|
| |
| X = df['message'] |
| y = df['label'] |
| vectorizer = TfidfVectorizer(stop_words='english') |
| X_vec = vectorizer.fit_transform(X) |
| model = MultinomialNB() |
| model.fit(X_vec, y) |
|
|
| |
| def predict_spam(text): |
| vec = vectorizer.transform([text]) |
| pred = model.predict(vec)[0] |
| return "SPAM ❌" if pred else "HAM ✅ (Bukan Spam)" |
|
|
| |
| gr.Interface( |
| fn=predict_spam, |
| inputs=gr.Textbox(lines=4, placeholder="Masukkan pesan..."), |
| outputs="text", |
| title="Klasifikasi Spam SMS", |
| description="Aplikasi klasifikasi pesan spam menggunakan Naive Bayes + TF-IDF" |
| ).launch() |
|
|
