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.pipeline import Pipeline
from sklearn import metrics
import joblib

url = "https://raw.githubusercontent.com/justmarkham/pycon-2016-tutorial/master/data/sms.tsv"
df = pd.read_csv(url, sep='\t', header=None, names=['label', 'message'])

# Encode labels
df['label_num'] = df.label.map({'ham': 0, 'spam': 1})

# Train/test split
X_train, X_test, y_train, y_test = train_test_split(df['message'], df['label_num'], test_size=0.2, random_state=42)

# Build pipeline
model = Pipeline([
    ('tfidf', TfidfVectorizer()),
    ('nb', MultinomialNB())
])

# Train
model.fit(X_train, y_train)

# Evaluate
preds = model.predict(X_test)
print("Accuracy:", metrics.accuracy_score(y_test, preds))

# Save model
joblib.dump(model, "spam_classifier_model.joblib")