import random   # library for generating random numbers
import nltk     # library for working with human language 
from nltk.tokenize import word_tokenize     # A function from NLTK for breaking words down
from nltk import ConditionalFreqDist   # A class from NLTK for representing the conditional frequency distribution of a set.
nltk.download('punkt')      # models used by word_tokenize to tokenize words.

def probs_model(text):  # takes text as input
    words = word_tokenize(text)  # split words
    bigrams = list(nltk.bigrams(words))  # pairs of consecutive words
    cond_freq_dist = ConditionalFreqDist(bigrams)  # conditional frequency of the 2 words
    return cond_freq_dist

# probs_model is the representation of the conditional probs.

def generate_sentence(model, initial_word, length):  # takes in the representation of the conditional probs, seed word, and sentence length
    sentence = [initial_word]

#Iterates to generate the next word based on the conditional probabilities until the sentence length is reached.
    for _ in range(length - 1):
        next_words = model[sentence[-1]]
        if not next_words:
            break  # If there are no next words, end the sentence
        next_word = random.choice(list(next_words))
        sentence.append(next_word)

    return ' '.join(sentence) #combine the generated words into a single string

if __name__ == '__main__':
    input_text = "In the sweet town of Candyland, there lived a marshmallow named Mallow. Mallow had a unique passion ? a love for Alan Turing's work on computers and artificial intelligence. Instead of bouncing with other candies, Mallow spent its days reading Turing's papers and dreaming of marshmallow-powered machines. Mallow's friends couldn't quite understand its fascination, but they embraced Mallow's uniqueness. One day, Mallow surprised everyone by creating a tiny marshmallow computer that could solve candy puzzles. The town marveled at Mallow's ingenuity, and Mallow's love for Turing's work became a source of inspiration for Candyland. And so, Mallow, the marshmallow with a Turing twist, continued to blend sweetness with technology, making Candyland a tastier and smarter place."

    model = probs_model(input_text)

    seed_word = "Alan"  # Select any word as the starting point
    sentence_length = 15  # desired sentence length

    generated_sentence = generate_sentence(model, seed_word, sentence_length)

    # Print the input text and the generated sentence.
    print("Input text:", input_text)
    print(f"Given seed word: '{seed_word}', Generated sentence: {generated_sentence}")