IIS_2023_1/gordeeva_anna_lab_7/laba7.py

import docx
import streamlit as st
import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Embedding

def extract_text_from_docx(file_path):
    doc = docx.Document(file_path)
    full_text = []

    for para in doc.paragraphs:
        full_text.append(para.text)

    return '\n'.join(full_text)

file_path1 = '"C:/Users/79084/Desktop/textru.doc"'
file_path2 = '"C:/Users/79084/Desktop/texten.doc"'

# Извлечение текста из файла
textru = extract_text_from_docx(file_path1)
texten = extract_text_from_docx(file_path2)

# Предобработка текста
tokenizer_russian = tf.keras.preprocessing.text.Tokenizer(char_level=True)
tokenizer_russian.fit_on_texts(textru)
tokenized_text_russian = tokenizer_russian.texts_to_sequences([textru])[0]

tokenizer_english = tf.keras.preprocessing.text.Tokenizer(char_level=True)
tokenizer_english.fit_on_texts(texten)
tokenized_text_english = tokenizer_english.texts_to_sequences([texten])[0]

# Создание последовательных последовательностей для обучения
maxlen = 40
step = 3
sentences_russian = []
next_chars_russian = []
sentences_english = []
next_chars_english = []

for i in range(0, len(tokenized_text_russian) - maxlen, step):
    sentences_russian.append(tokenized_text_russian[i: i + maxlen])
    next_chars_russian.append(tokenized_text_russian[i + maxlen])

for i in range(0, len(tokenized_text_english) - maxlen, step):
    sentences_english.append(tokenized_text_english[i: i + maxlen])
    next_chars_english.append(tokenized_text_english[i + maxlen])

# Преобразование данных в массивы numpy
x_russian = np.array(sentences_russian)
y_russian = np.array(next_chars_russian)
x_english = np.array(sentences_english)
y_english = np.array(next_chars_english)

# Создание модели для русского текста
model_russian = Sequential()
model_russian.add(Embedding(len(tokenizer_russian.word_index) + 1, 128))
model_russian.add(LSTM(128))
model_russian.add(Dense(len(tokenizer_russian.word_index) + 1, activation='softmax'))

model_russian.compile(loss='sparse_categorical_crossentropy', optimizer='adam')

# Обучение модели на русском тексте
model_russian.fit(x_russian, y_russian, batch_size=128, epochs=50)

# Создание модели для английского текста
model_english = Sequential()
model_english.add(Embedding(len(tokenizer_english.word_index) + 1, 128))
model_english.add(LSTM(128))
model_english.add(Dense(len(tokenizer_english.word_index) + 1, activation='softmax'))

model_english.compile(loss='sparse_categorical_crossentropy', optimizer='adam')

# Обучение модели на английском тексте
model_english.fit(x_english, y_english, batch_size=128, epochs=50)

# Функция для генерации текста на основе обученной модели
def generate_text(model, tokenizer, seed_text, maxlen, temperature=1.0, num_chars=400):
    generated_text = seed_text
    for _ in range(num_chars):
        encoded = tokenizer.texts_to_sequences([seed_text])[0]
        encoded = np.array(encoded)
        predicted_probs = model.predict(encoded, verbose=0)[0]
        # Используем temperature для более разнообразных предсказаний
        predicted_probs = np.log(predicted_probs) / temperature
        exp_preds = np.exp(predicted_probs)
        predicted_probs = exp_preds / np.sum(exp_preds)
        predicted = np.random.choice(len(predicted_probs), p=predicted_probs)
        next_char = tokenizer.index_word.get(predicted, '')
        generated_text += next_char
        seed_text += next_char
        seed_text = seed_text[1:]
    return generated_text

generated_russian_text = generate_text(model_russian, tokenizer_russian, 'Ты к моему', maxlen, temperature=0.5, num_chars=400)
st.write(generated_russian_text)

generated_english_text = generate_text(model_english, tokenizer_english, 'In the', maxlen, temperature=0.5, num_chars=400)
st.write(generated_english_text)