nlp stuff

bigrams.py

# Sample text
text = "the cat sat on the mat the dog sat on the floor"

# Tokenize the text
words = text.split()

# Build bigram model
bigrams = defaultdict(list)
for i in range(len(words) - 1):
    bigrams[words[i]].append(words[i + 1])

# Function to generate text
def generate_text(start_word, num_words):
    current_word = start_word
    result = [current_word]
    for _ in range(num_words - 1):
        if current_word in bigrams:
            next_word = random.choice(bigrams[current_word])
            result.append(next_word)
            current_word = next_word
        else:
            break
    return ' '.join(result)

# Generate text
print(generate_text("the", 5))