classify_message.py

def sms_classify(message):
    '''
    Takes in as input a new sms (w1, w2, ..., wn),
    calculates P(Spam|w1, w2, ..., wn) and P(Ham|w1, w2, ..., wn),
    compares them and outcomes whether the message is spam or not.
    '''
    
    # Replace addresses (hhtp, email), numbers (plain, phone), money symbols
    message = message.replace(r'\b[\w\-.]+?@\w+?\.\w{2,4}\b', ' ')
    message = message.replace(r'(http[s]?\S+)|(\w+\.[A-Za-z]{2,4}\S*)', ' ')
    message = message.replace(r'£|\$', ' ')    
    message = message.replace(r'\b(\+\d{1,2}\s)?\d?[\-(.]?\d{3}\)?[\s.-]?\d{3}[\s.-]?\d{4}\b', ' ')    
    message = message.replace(r'\d+(\.\d+)?', ' ')

    # Remove punctuation, collapse all whitespace (spaces, line breaks, tabs) into a single space & eliminate any leading/trailing whitespace.
    message = message.replace(r'[^\w\d\s]', ' ')
    message = message.replace(r'\s+', ' ')
    message = message.replace(r'^\s+|\s+?$', '')

    # Lowercase the entire corpus
    message = message.lower()

    # Remove stop words    
    terms = []
    for term in message.split():
        if term not in set(stop_words):
            terms.append(term)
            message = ' '.join(terms)
    
    # Lemmatization
    message = ' '.join(lemmatizer.lemmatize(term, pos='v') for term in message.split())
    
    # Stemming
    message = ' '.join(porter.stem(term) for term in message.split())
    
    # Tokenization
    message = message.split()
    
    p_spam_given_message = p_spam
    p_ham_given_message = p_ham
    
    for word in message:
        if word in parameters_spam:
            p_spam_given_message *= parameters_spam[word]
    
        if word in parameters_ham:
            p_ham_given_message *= parameters_ham[word]
    
    print('P(Spam|message):', p_spam_given_message)
    print('P(Ham|message):', p_ham_given_message)

    if p_ham_given_message > p_spam_given_message:
        print('Label: Ham')
    elif p_ham_given_message < p_spam_given_message:
        print('Label: Spam')
    else:
        print('Equal probabilities ~ Human action needed!')