vectorization.py

# Create the corpus
corpus = training_set['SMS'].sum()

# Create the vocabulary
temp_set = set(corpus)
vocabulary = list(temp_set)

# Create a dictionary
len_training_set = len(training_set['SMS'])
word_counts_per_sms = {unique_word: [0] * len_training_set for unique_word in vocabulary}

for index, sms in enumerate(training_set['SMS']):
    for word in sms:
        word_counts_per_sms[word][index] += 1
        
# Convert to dataframe
word_counts = pd.DataFrame(word_counts_per_sms)
word_counts.head()

# Concatenate with the original training set
training_set_final = pd.concat([training_set, word_counts], axis=1)
training_set_final.head()