calc_params.py

# Create two dictionaries that match each unique word with the respective probability value.
parameters_spam = {unique_word: 0 for unique_word in vocabulary}
parameters_ham = {unique_word: 0 for unique_word in vocabulary}

# Iterate over the vocabulary and for each word, calculate P(wi|Spam) and P(wi|Ham)
for unique_word in vocabulary:
    p_unique_word_spam = (spam_df[unique_word].sum() + alpha) / (n_spam + alpha * n_vocabulary)
    p_unique_word_ham = (ham_df[unique_word].sum() + alpha) / (n_ham + alpha * n_vocabulary)
    
    # Update the calculated propabilities to the dictionaries
    parameters_spam[unique_word] = p_unique_word_spam
    parameters_ham[unique_word] = p_unique_word_ham