Simple Spam Filtering using Naive Bayes

app.py

@@ -0,0 +1,59 @@
+import pandas as pd
+import numpy as np
+import streamlit as st
+from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import Pipeline
+from sklearn.metrics import accuracy_score, classification_report
+
+# Sample dataset (email, label)
+data = {'text': [
+    'Congratulations! You have won a free lottery ticket.',
+    'Important meeting scheduled for tomorrow.',
+    'Limited-time offer! Get a discount now!',
+    'Your bank account needs urgent verification.',
+    'Lunch meeting at 1 PM.',
+    'Win a free trip to the Bahamas!',
+    'Project deadline extended to next week.',
+    'Exclusive deal just for you! Buy now!',
+    'Reminder: Your doctor appointment is at 10 AM tomorrow.',
+    'Earn money fast with this simple trick!',
+    'Meeting rescheduled to 3 PM.',
+    'Verify your email to secure your account.',
+    'Huge discount on your favorite products!',
+    'Team outing planned for this weekend.',
+    'Act now! Limited seats available for the webinar.',
+    'Your order has been shipped successfully.',
+    'Congratulations! You have been selected for a special reward.',
+    'Last chance to claim your exclusive offer!',
+    'Monthly budget report attached.',
+    'Reminder: Submit your timesheet by Friday.'
+],
+'label': ['spam', 'legit', 'spam', 'spam', 'legit', 'spam', 'legit', 'spam', 'legit', 'spam', 'legit', 'spam', 'spam', 'legit', 'spam', 'legit', 'spam', 'spam', 'legit', 'legit']}
+
+df = pd.DataFrame(data)
+
+# Splitting data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(df['text'], df['label'], test_size=0.2, random_state=42)
+
+# Building the spam filter model using a pipeline
+model = Pipeline([
+    ('vectorizer', CountVectorizer()),
+    ('tfidf', TfidfTransformer()),
+    ('classifier', MultinomialNB())
+])
+
+# Train the model
+model.fit(X_train, y_train)
+
+# Streamlit App
+st.title("Spam Filter Email Classifier")
+
+email_input = st.text_area("Enter email content:")
+if st.button("Classify Email"):
+    if email_input:
+        prediction = model.predict([email_input])[0]
+        st.write(f"The email is classified as: {prediction}")
+    else:
+        st.write("Please enter an email to classify.")