custom_normalization.py

# Replace addresses (hhtp, email), numbers (plain, phone), money symbols
training_set['SMS'] = training_set['SMS'].str.replace(r'\b[\w\-.]+?@\w+?\.\w{2,4}\b', ' ')
training_set['SMS'] = training_set['SMS'].str.replace(r'(http[s]?\S+)|(\w+\.[A-Za-z]{2,4}\S*)', ' ')
training_set['SMS'] = training_set['SMS'].str.replace(r'£|\$', ' ')    
training_set['SMS'] = training_set['SMS'].str.replace(r'\b(\+\d{1,2}\s)?\d?[\-(.]?\d{3}\)?[\s.-]?\d{3}[\s.-]?\d{4}\b', ' ')    
training_set['SMS'] = training_set['SMS'].str.replace(r'\d+(\.\d+)?', ' ')

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

# Lowercase the entire corpus
training_set['SMS'] = training_set['SMS'].str.lower()