IIS_2023_1/antonov_dmitry_lab_7/lab7.py

import numpy as np
from keras.models import Sequential
from keras.layers import Embedding, LSTM, Dense
from keras.preprocessing.text import Tokenizer
from keras_preprocessing.sequence import pad_sequences

# загрузка текста
with open('rus.txt', encoding='utf-8') as file:
    text = file.read()

tokenizer = Tokenizer()
tokenizer.fit_on_texts([text])
total_words = len(tokenizer.word_index) + 1

input_sequences = []
for line in text.split('\n'):
    token_list = tokenizer.texts_to_sequences([line])[0]
    for i in range(1, len(token_list)):
        n_gram_sequence = token_list[:i + 1]
        input_sequences.append(n_gram_sequence)

max_sequence_length = max([len(x) for x in input_sequences])
input_sequences = pad_sequences(input_sequences, maxlen=max_sequence_length, padding='pre')

predictors, labels = input_sequences[:, :-1], input_sequences[:, -1]

# создание RNN модели
model = Sequential()
model.add(Embedding(total_words, 100, input_length=max_sequence_length - 1))
model.add(LSTM(150))
model.add(Dense(total_words, activation='softmax'))

model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# тренировка модели
model.fit(predictors, labels, epochs=150, verbose=1)


# генерация текста на основе модели
def generate_text(seed_text, next_words, model, max_sequence_length):
    for _ in range(next_words):
        token_list = tokenizer.texts_to_sequences([seed_text])[0]
        token_list = pad_sequences([token_list], maxlen=max_sequence_length - 1, padding='pre')
        predicted = np.argmax(model.predict(token_list), axis=-1)
        output_word = ""
        for word, index in tokenizer.word_index.items():
            if index == predicted:
                output_word = word
                break
        seed_text += " " + output_word
    return seed_text


generated_text = generate_text("Я хочу", 50, model, max_sequence_length)
print(generated_text)