print('단어 카운트:', token.word_counts)
print('문장 카운트:', token.document_count)
print('각 단어가 몇개의 문장에 포함되어 있는가 :', token.word_docs)
print('각 단어에 매겨진 인덱스 값 :', token.word_index)
print()
# 텍스트를 읽고 긍정 , 부정 분류 예측
docs = ['너무 재밌네요', '최고에요','참 잘만든 영화예요','추천하고 싶은 영화네요','한번 더 보고싶네요',
'글쎄요','별로네요','생각보다 지루합니다','연기가 좋지않아요','재미없어요']
import numpy as np
classes = np.array([1,1,1,1,1,0,0,0,0,0])
token = Tokenizer()
token.fit_on_texts(docs)
print(token.word_index)
model = Sequential()
model.add(Embedding(word_size,8,input_length=4))
#model.add(Flatten())
model.add(LSTM(32))
model.add(Dense(1,activation='sigmoid'))
print(model.summary())
model.compile(optimizer='adam',loss='binary_crossentropy')
def build_model(use_gpu: bool = False,
num_units: int = 64,
num_layers: int = 1,
dropout_rate: float = 0.0,
batch_size: int = 1000,
window_size: int = 10,
num_params: int = 0):
"""
Builds the RNN-Model for character prediction.
:param window_size: Sequence size
:param batch_size: {int} Size of batch
:param dropout_rate: {float} Regulating Dropout rate between layers
:param num_layers: {int} Number of layers to build
:param num_units: {int} Number of LSTM-Units to use in network
:param use_gpu: {bool} Uses Tensorflow GPU support if True, otherwise trains on CPU
:param num_params: {int} Number of control parameters
:return: Keras model
"""
# Load max 5000 entries from the dataset to build the Tokenizer / vocabulary
loader = Loader(min(batch_size, 5000), 0)
tokenizer = Tokenizer(filters='', split='°', lower=False)
for dataframe in loader:
chars = set()
for name in dataframe['name']:
chars.update(set(str(name)))
tokenizer.fit_on_texts(list(chars))
tokenizer.fit_on_texts(['pre', '<end>', 'pad'])
# Build Keras Model
model = Sequential()
for r in range(0, max(num_layers - 1, 0)):
model.add(layer=(CuDNNLSTM if use_gpu else LSTM
)(num_units,
input_shape=(window_size,
len(tokenizer.index_word) + 1 +
num_params),
return_sequences=True))
model.add(Dropout(dropout_rate))
model.add(
layer=(CuDNNLSTM if use_gpu else LSTM)(num_units,
input_shape=(
window_size,
len(tokenizer.index_word) +
1 + num_params)))
model.add(Dense(len(tokenizer.index_word) + 1, activation='softmax'))
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
# Show summary
print(model.summary())
return model, tokenizer