56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
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)
|