24강 - 순환 신경망으로 IMDB 리뷰 분류하기

24강 - 순환 신경망으로 IMDB 리뷰 분류하기

IMDB 리뷰 데이터셋

영화 평점 소개 사이트.

리뷰 댓글을 모아 데이터로 만듦.

감성 분석.

긍정리뷰(양성샘플), 부정리뷰(음성샘플)로 25,000개씩 잘 나뉘어져 있음.

• NLP
• 말뭉치-데이터셋
• 토큰-단어
• 어휘 사전

케라스로 IMDB 데이터 불러오기

from tensorflow.keras.datasets import imdb

(train_input, train_target), (test_input, test_target) = imdb.load_data(
    num_words=500)

print(train_input.shape, test_input.shape)

#//(25000,) (25000,)

print(train_input[0])

#//[1, 14, 22, 16, 43, 2, 2, 2, 2, 65, 458, 2, 66, 2, 4, 173, 36, 256, 5, 25, 100, 43, 2, 112, 50, 2, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 2, 2, 17, 2, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2, 19, 14, 22, 4, 2, 2, 469, 4, 22, 71, 87, 12, 16, 43, 2, 38, 76, 15, 13, 2, 4, 22, 17, 2, 17, 12, 16, 2, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2, 2, 16, 480, 66, 2, 33, 4, 130, 12, 16, 38, 2, 5, 25, 124, 51, 36, 135, 48, 25, 2, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 2, 15, 256, 4, 2, 7, 2, 5, 2, 36, 71, 43, 2, 476, 26, 400, 317, 46, 7, 4, 2, 2, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2, 56, 26, 141, 6, 194, 2, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 2, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 2, 88, 12, 16, 283, 5, 16, 2, 113, 103, 32, 15, 16, 2, 19, 178, 32]

print(train_target[:20])

#//[1 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 1 1 0 1]

훈련 세트 준비

train_input, val_input, train_target, val_target = train_test_split(
    train_input, train_target, test_size=0.2, random_state=42)

lengths = np.array([len(x) for x in train_input])
print(np.mean(lengths), np.median(lengths))

#//239.00925 178.0

plt.hist(lengths)
plt.xlabel('length')
plt.ylabel('frequency')
plt.show()

시퀀스 패딩

from tensorflow.keras.preprocessing.sequence import pad_sequences

train_seq = pad_sequences(train_input, maxlen=100)

print(train_seq.shape)

#//(20000, 100)

print(train_seq[0])

#//[ 10   4  20   9   2 364 352   5  45   6   2   2  33 269   8   2 142   2
#//   5   2  17  73  17 204   5   2  19  55   2   2  92  66 104  14  20  93
#//  76   2 151  33   4  58  12 188   2 151  12 215  69 224 142  73 237   6
#//   2   7   2   2 188   2 103  14  31  10  10 451   7   2   5   2  80  91
#//   2  30   2  34  14  20 151  50  26 131  49   2  84  46  50  37  80  79
#//   6   2  46   7  14  20  10  10 470 158]

print(train_input[0][-10:])

#//[6, 2, 46, 7, 14, 20, 10, 10, 470, 158]

print(train_seq[5])

#//[  0   0   0   0   1   2 195  19  49   2   2 190   4   2 352   2 183  10
#//  10  13  82  79   4   2  36  71 269   8   2  25  19  49   7   4   2   2
#//   2   2   2  10  10  48  25  40   2  11   2   2  40   2   2   5   4   2
#//   2  95  14 238  56 129   2  10  10  21   2  94 364 352   2   2  11 190
#//  24 484   2   7  94 205 405  10  10  87   2  34  49   2   7   2   2   2
#//   2   2 290   2  46  48  64  18   4   2]

순환 신경망 모델 만들기

from tensorflow import keras

model = keras.Sequential()

model.add(keras.layers.SimpleRNN(8, input_shape=(100, 500)))
model.add(keras.layers.Dense(1, activation='sigmoid'))

원-핫 인코딩

train_oh = keras.utils.to_categorical(train_seq)

print(train_oh.shape)

#//(20000, 100, 500)

print(train_oh[0][0][:12])

#//[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0.]

print(np.sum(train_oh[0][0]))

#//1.0

val_oh = keras.utils.to_categorical(val_seq)

모델 구조 확인

model.summary()

#// Model: "sequential"
#// _________________________________________________________________
#// Layer (type)                 Output Shape              Param #   
#// =================================================================
#// simple_rnn (SimpleRNN)       (None, 8)                 4072      
#// _________________________________________________________________
#// dense (Dense)                (None, 1)                 9         
#// =================================================================
#// Total params: 4,081
#// Trainable params: 4,081
#// Non-trainable params: 0
#// _________________________________________________________________

모델 훈련

rmsprop = keras.optimizers.RMSprop(learning_rate=1e-4)
model.compile(optimizer=rmsprop, loss='binary_crossentropy', 
              metrics=['accuracy'])

checkpoint_cb = keras.callbacks.ModelCheckpoint('best-simplernn-model.h5', 
                                                save_best_only=True)
early_stopping_cb = keras.callbacks.EarlyStopping(patience=3,
                                                  restore_best_weights=True)

history = model.fit(train_oh, train_target, epochs=100, batch_size=64,
                    validation_data=(val_oh, val_target),
                    callbacks=[checkpoint_cb, early_stopping_cb])

임베딩

model2 = keras.Sequential()

model2.add(keras.layers.Embedding(500, 16, input_length=100))
model2.add(keras.layers.SimpleRNN(8))
model2.add(keras.layers.Dense(1, activation='sigmoid'))

model2.summary()

#// Model: "sequential_1"
#// _________________________________________________________________
#// Layer (type)                 Output Shape              Param #   
#// =================================================================
#// embedding (Embedding)        (None, 100, 16)           8000      
#// _________________________________________________________________
#// simple_rnn_1 (SimpleRNN)     (None, 8)                 200       
#// _________________________________________________________________
#// dense_1 (Dense)              (None, 1)                 9         
#// =================================================================
#// Total params: 8,209
#// Trainable params: 8,209
#// Non-trainable params: 0
#// _________________________________________________________________

참고자료

https://www.youtube.com/watch?v=YIrpKw04ic8&list=PLVsNizTWUw7HpqmdphX9hgyWl15nobgQX&index=24