import pandas as pd
import string
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from joblib import dump
import nltk
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer

# Download necessary NLTK resources
nltk.download('stopwords')

# Initialize stopwords and stemmer
stop_words = set(stopwords.words('english'))
stemmer = PorterStemmer()

def preprocess(text):
    """Clean and preprocess text for model input."""
    # Lowercase and remove punctuation
    text = text.lower()
    text = ''.join([char for char in text if char not in string.punctuation])
    # Remove stopwords and apply stemming
    words = text.split()
    return ' '.join([stemmer.stem(word) for word in words if word not in stop_words])

# Load your dataset
data = pd.read_csv('spam.csv', encoding='latin-1')
data = data[['v1', 'v2']]
data.columns = ['label', 'message']

# Convert labels to binary
data['label'] = data['label'].map({'ham': 'LABEL_0', 'spam': 'LABEL_1'})

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(data['message'], data['label'], test_size=0.2, random_state=42)

# Create a pipeline that includes preprocessing, vectorization, and classification
model_pipeline = Pipeline([
    ('vectorizer', CountVectorizer(preprocessor=preprocess)),
    ('classifier', MultinomialNB())
])

# Train the model using the pipeline
model_pipeline.fit(X_train, y_train)

# Evaluate the model
y_pred = model_pipeline.predict(X_test)
print('Accuracy:', accuracy_score(y_test, y_pred))
print('Confusion Matrix:\n', confusion_matrix(y_test, y_pred))
print('Classification Report:\n', classification_report(y_test, y_pred))

# Serialize the model pipeline
dump(model_pipeline, 'spam_classifier_pipeline.joblib')