IIS_2023_1/basharin_sevastyan_lab_7/main.py

71 lines
2.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import numpy as np
from keras.preprocessing.sequence import pad_sequences
from keras.preprocessing.text import Tokenizer
from keras.models import Sequential
from keras.layers import Embedding, LSTM, Dense
from keras.utils import to_categorical
with open('ru.txt', "r", encoding='utf-8') as file:
text = file.read()
# Предварительная обработка текста (в зависимости от вашей задачи)
# Создание словаря для отображения слов в индексы и обратно
tokenizer = Tokenizer()
tokenizer.fit_on_texts([text])
total_words = len(tokenizer.word_index) + 1
# Подготовка данных для обучения (в зависимости от вашей задачи)
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 = to_categorical(y, num_classes=total_words)
# Определение архитектуры модели
model = Sequential()
model.add(Embedding(total_words, 50, input_length=max_sequence_length-1))
model.add(LSTM(100))
model.add(Dense(total_words, activation='softmax'))
# Компиляция модели
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# Обучение модели
model.fit(X, y, epochs=100, verbose=2)
# Генерация текста с использованием обученной 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_probs = model.predict(token_list, verbose=0)[0]
predicted_index = np.argmax(predicted_probs)
output_word = ""
for word, index in tokenizer.word_index.items():
if index == predicted_index:
output_word = word
break
seed_text += " " + output_word
return seed_text
# Пример генерации текста (замените seed_text и next_words на свои значения)
seed_text = "здесь был"
next_words = 50
generated_text = generate_text(seed_text, next_words, model, max_sequence_length)
print(generated_text)