자연어생성 (NLG, Natural Language Generation)

[13-1]LSTM 네트워크를 이용한 자연어 생성

from __future__ import print_function
from tensorflow.keras.callbacks import LambdaCallback
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import LSTM
from tensorflow.keras.optimizers import RMSprop
from tensorflow.keras.utils import get_file
import numpy as np
import random
import sys
import io

# 텍스트 파일 불러오기
fpath = get_file(
    'nietzsche.txt',
    origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt')
with io.open(fpath, encoding='utf-8') as f:
    text = f.read().lower()

# 어휘 사전 생성
chars = sorted(list(set(text)))
char2index = dict((c, i) for i, c in enumerate(chars))
index2char = dict((i, c) for i, c in enumerate(chars))

# 음절 단위 학습 데이터 생성
maxlen, step = 40, 3
sentences, next_chars = [], []
for i in range(0, len(text) - maxlen, step):
    sentences.append(text[i : i + maxlen])
    next_chars.append(text[i + maxlen])
print ('The number of sentences:', len(sentences))
x = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)

for i, sentence in enumerate(sentences):
    for t, char in enumerate(sentence):
        x[i, t, char2index[char]] = 1
    y[i, char2index[next_chars[i]]] = 1
    
# 딥러닝 모델 선언
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen, len(chars))))
model.add(Dense(len(chars), activation='softmax'))
optimizer = RMSprop(learning_rate=0.01 )
model.compile(loss='categorical_crossentropy', optimizer=optimizer)

# 입력된 확률값에 따른 다음 음절 샘플링
def sample(preds, temperature=1.0):
    preds = np.asarray(preds).astype('float64')
    preds = np.log(preds) / temperature
    exp_preds = np.exp(preds)
    preds = exp_preds / np.sum(exp_preds)
    probas = np.random.multinomial(1, preds, 1)
    return np.argmax(probas)

# 1회 (1 epoch) 학습
def on_epoch_end(epoch, _):
    print('\nEpoch: %d' % epoch)
    start_index = random.randint(0, len (text) - maxlen - 1 )
    for diversity in [0.2, 0.5, 1.0, 1.2]:
        print('\nDiversity:', diversity)
        generated = ''
        sentence = text[start_index : start_index + maxlen]
        generated += sentence
        print('Seed: %s' % sentence)
        sys.stdout.write(generated)
        for i in range (400 ):
            x_pred = np.zeros((1, maxlen, len(chars)))
            for t, char in enumerate(sentence):
                x_pred[0, t, char2index[char]] = 1.
            preds = model.predict(x_pred, verbose=0)[0]
            next_index = sample(preds, diversity)
            next_char = index2char[next_index]
            sentence = sentence[1:] + next_char
            sys.stdout.write(next_char)
            sys.stdout.flush()

print_callback = LambdaCallback(on_epoch_end=on_epoch_end)
model.fit(x, y,
          batch_size=128,
          epochs=60,
          callbacks=[print_callback])