61 lines
2.0 KiB
Python
61 lines
2.0 KiB
Python
|
import numpy as np
|
|||
|
|
import tensorflow as tf
|
|||
|
|
from keras.models import Sequential
|
|||
|
|
from keras.layers import Embedding, LSTM, Dense
|
|||
|
|
from keras.preprocessing.text import Tokenizer
|
|||
|
|
from keras.utils import pad_sequences
|
|||
|
|
|
|||
|
|
# Путь к файлу
|
|||
|
|
file_path = 'vlastelin-kolec.txt'
|
|||
|
|
|
|||
|
|
# Замените 'your_text_file.txt' на путь к вашему файлу с художественным текстом
|
|||
|
|
with open(file_path, 'r', 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')
|
|||
|
|
|
|||
|
|
X, y = input_sequences[:, :-1], input_sequences[:, -1]
|
|||
|
|
y = tf.keras.utils.to_categorical(y, num_classes=total_words)
|
|||
|
|
|
|||
|
|
model = Sequential()
|
|||
|
|
model.add(Embedding(total_words, 100, input_length=max_sequence_length-1))
|
|||
|
|
model.add(LSTM(100))
|
|||
|
|
model.add(Dense(total_words, activation='softmax'))
|
|||
|
|
|
|||
|
|
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
|
|||
|
|
|
|||
|
|
model.fit(X, y, epochs=100, verbose=1)
|
|||
|
|
|
|||
|
|
next_words = 100
|
|||
|
|
while True:
|
|||
|
|
seed_text = input('Введите текст: ')
|
|||
|
|
if seed_text == "0":
|
|||
|
|
break
|
|||
|
|
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
|
|||
|
|
|
|||
|
|
print(seed_text)
|
|||
|
|
|
|||
|
|
|
|||
|
|
|