Python Bigram

bigram.py

# replace all punctuations with spaces in plain_text and store in `cleaned` variable
cleaned = re.sub(r'[^\w\s]', ' ', plain_text)

# replace all whitespace with single space in `cleaned` variable
cleaned = re.sub(r'\s+', ' ', cleaned)

# split the cleaned text into a list of words
words = cleaned.split()

# create a list to store bigrams
# iterate through words list and combine current with the next word to form bigram and append to bigrams list
bigrams = []
for i in range(len(words) - 1):
    bigrams.append(words[i] + ' ' + words[i + 1])