is_dnn/labworks/LW4/lab4.ipynb

# импорт модулей
import os
os.chdir('/content/drive/MyDrive/Colab Notebooks/is_lab4')

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
import matplotlib.pyplot as plt
import numpy as np

from google.colab import drive
drive.mount('/content/drive')

import tensorflow as tf
device_name = tf.test.gpu_device_name()
if device_name != '/device:GPU:0':
  raise SystemError('GPU device not found')
print('Found GPU at: {}'.format(device_name))

# загрузка датасета
from keras.datasets import imdb

vocabulary_size = 5000
index_from = 3

(X_train, y_train), (X_test, y_test) = imdb.load_data(
    path="imdb.npz",
    num_words=vocabulary_size,
    skip_top=0,
    maxlen=None,
    seed=3,
    start_char=1,
    oov_char=2,
    index_from=index_from
    )

# вывод размерностей
print('Shape of X train:', X_train.shape)
print('Shape of y train:', y_train.shape)
print('Shape of X test:', X_test.shape)
print('Shape of y test:', y_test.shape)

# создание словаря для перевода индексов в слова
# заргузка словаря "слово:индекс"
word_to_id = imdb.get_word_index()
# уточнение словаря
word_to_id = {key:(value + index_from) for key,value in word_to_id.items()}
word_to_id["<PAD>"] = 0
word_to_id["<START>"] = 1
word_to_id["<UNK>"] = 2
word_to_id["<UNUSED>"] = 3
# создание обратного словаря "индекс:слово"
id_to_word = {value:key for key,value in word_to_id.items()}

print(X_train[26])
print('len:',len(X_train[26]))

review_as_text = ' '.join(id_to_word[id] for id in X_train[26])
print(review_as_text)
print('len:',len(review_as_text))

print('MAX Len: ',len(max(X_train, key=len)))
print('MIN Len: ',len(min(X_train, key=len)))

# предобработка данных
from tensorflow.keras.utils import pad_sequences
max_words = 500
X_train = pad_sequences(X_train, maxlen=max_words, value=0, padding='pre', truncating='post')
X_test = pad_sequences(X_test, maxlen=max_words, value=0, padding='pre', truncating='post')

print('MAX Len: ',len(max(X_train, key=len)))
print('MIN Len: ',len(min(X_train, key=len)))

print(X_train[26])
print('len:',len(X_train[26]))

review_as_text = ' '.join(id_to_word[id] for id in X_train[26])
print(review_as_text)
print('len:',len(review_as_text))

# вывод данных
print('X train: \n',X_train)
print('X train: \n',X_test)

# вывод размерностей
print('Shape of X train:', X_train.shape)
print('Shape of X test:', X_test.shape)

embed_dim = 32
lstm_units = 64

model = Sequential()
model.add(layers.Embedding(input_dim=vocabulary_size, output_dim=embed_dim, input_length=max_words, input_shape=(max_words,)))
model.add(layers.LSTM(lstm_units))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(1, activation='sigmoid'))

model.summary()

# компилируем и обучаем модель
batch_size = 64
epochs = 3
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.2)

test_loss, test_acc = model.evaluate(X_test, y_test)
print(f"\nTest accuracy: {test_acc}")

#значение метрики качества классификации на тестовых данных
print(f"\nTest accuracy: {test_acc}")

#отчет о качестве классификации тестовой выборки
y_score = model.predict(X_test)
y_pred = [1 if y_score[i,0]>=0.5 else 0 for i in range(len(y_score))]

from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred, labels = [0, 1], target_names=['Negative', 'Positive']))

#построение ROC-кривой и AUC ROC
from sklearn.metrics import roc_curve, auc

fpr, tpr, thresholds = roc_curve(y_test, y_score)
plt.plot(fpr, tpr)
plt.grid()
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC')
plt.show()
print('AUC ROC:', auc(fpr, tpr))