70 lines
2.4 KiB
Python
70 lines
2.4 KiB
Python
|
import numpy as np
|
||
|
|
from keras.preprocessing.text import Tokenizer
|
||
|
|
from keras.preprocessing.sequence import pad_sequences
|
||
|
|
from keras.models import Sequential
|
||
|
|
from keras.layers import LSTM, Dense, Dropout
|
||
|
|
|
||
|
|
# Чтение текста из файла
|
||
|
|
#with open('russian.txt', 'r', encoding='utf-8') as file:
|
||
|
|
# text = file.read()
|
||
|
|
with open('english.txt', 'r', encoding='utf-8') as file:
|
||
|
|
text = file.read()
|
||
|
|
|
||
|
|
# Параметры модели
|
||
|
|
seq_length = 10
|
||
|
|
|
||
|
|
# Создание экземпляра Tokenizer и обучение на тексте
|
||
|
|
tokenizer = Tokenizer(char_level=True)
|
||
|
|
tokenizer.fit_on_texts([text])
|
||
|
|
|
||
|
|
# Преобразование текста в последовательности чисел
|
||
|
|
sequences = tokenizer.texts_to_sequences([text])[0]
|
||
|
|
|
||
|
|
# Создание входных и выходных последовательностей
|
||
|
|
X_data = []
|
||
|
|
y_data = []
|
||
|
|
for i in range(seq_length, len(sequences)):
|
||
|
|
sequence = sequences[i - seq_length:i]
|
||
|
|
target = sequences[i]
|
||
|
|
X_data.append(sequence)
|
||
|
|
y_data.append(target)
|
||
|
|
|
||
|
|
# Преобразование входных и выходных данных в формат массивов numpy
|
||
|
|
X = pad_sequences(X_data, maxlen=seq_length)
|
||
|
|
y = np.array(y_data)
|
||
|
|
|
||
|
|
# Создание модели RNN
|
||
|
|
vocab_size = len(tokenizer.word_index) + 1
|
||
|
|
model = Sequential()
|
||
|
|
model.add(LSTM(256, input_shape=(seq_length, 1), return_sequences=True))
|
||
|
|
model.add(LSTM(128, input_shape=(seq_length, 1)))
|
||
|
|
model.add(Dense(vocab_size, activation='softmax'))
|
||
|
|
|
||
|
|
# Компиляция модели
|
||
|
|
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
|
||
|
|
|
||
|
|
# Обучение модели
|
||
|
|
model.fit(X, y, epochs=100, verbose=1)
|
||
|
|
|
||
|
|
|
||
|
|
# Функция для генерации текста
|
||
|
|
def generate_text(seed_text, gen_length):
|
||
|
|
generated_text = seed_text
|
||
|
|
|
||
|
|
for _ in range(gen_length):
|
||
|
|
sequence = tokenizer.texts_to_sequences([seed_text])[0]
|
||
|
|
sequence = pad_sequences([sequence], maxlen=seq_length)
|
||
|
|
prediction = model.predict(sequence)[0]
|
||
|
|
predicted_index = np.argmax(prediction)
|
||
|
|
predicted_char = tokenizer.index_word[predicted_index]
|
||
|
|
generated_text += predicted_char
|
||
|
|
seed_text += predicted_char
|
||
|
|
seed_text = seed_text[1:]
|
||
|
|
|
||
|
|
return generated_text
|
||
|
|
|
||
|
|
# Генерация текста
|
||
|
|
#seed_text = "Это было бы чудом"
|
||
|
|
seed_text = "The climate of"
|
||
|
|
generated_text = generate_text(seed_text, 250)
|
||
|
|
print(generated_text)
|