Project_three.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, confusion_matrix


data = pd.read_csv("emails.csv")


X = data["text"]
y = data["label"]


X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)


vectorizer = TfidfVectorizer()
X_train_vec = vectorizer.fit_transform(X_train)
X_test_vec = vectorizer.transform(X_test)


model = MultinomialNB()
model.fit(X_train_vec, y_train)
y_pred = model.predict(X_test_vec)


print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))

email = input("\nEnter email text: ")
email_vec = vectorizer.transform([email])

prediction = model.predict(email_vec)[0]

print("Result:", prediction.upper())