def train(self, texts: List[str], target: List[int]) -> None:
from tensorflow.python.keras.models import Sequential #type: ignore
from tensorflow.python.keras.layers import Embedding, Dense, LSTM, GlobalMaxPool1D #type: ignore
from tensorflow.keras.optimizers import Adam #type: ignore
from tensorflow.keras.callbacks import History #type: ignore
if self.downsampling:
texts, target = downsample(texts, target, self.downsampling_ratio)
if self.verbose:
print('1. Vectorizing texts')
NUMBER_OF_FEATURES: int = 20000
self.tokenizer = text.Tokenizer(num_words=NUMBER_OF_FEATURES)
self.tokenizer.fit_on_texts(texts)
vocabulary: Dict[str, int] = self.tokenizer.word_index
if self._max_sequence_length == 0:
self._max_sequence_length = len(max(texts, key=len))
vectorized_texts: array = self.vectorize_texts(texts)
if self.embedding_location == '':
if self.verbose:
print('2. Skip (no embeddings)')
print('3. Skip (no embeddings)')
else:
if self.verbose:
print('2. Loading word embeddings')
embedding_dictionary: Dict[
str, List[float]] = load_embedding_dictionary(
self.embedding_location)
nr_of_embedding_features: int = len(
list(embedding_dictionary.values())
[1]) # Check how many values we have for the first word
if self.verbose:
print('3. Creating embedding matrix')
embedding_matrix: array = create_embedding_matrix_for_vocabulary(
embedding_dictionary, vocabulary)
if self.verbose:
print('4. Building up model')
#Define a simple LSTM model with a pretrained embedding layer
model: Sequential = Sequential()
if self.embedding_location == '':
#Add an empty embedding layer if we have no pretrained embeddings
EMPTY_EMBEDDING_LAYER_SIZE: int = 300
model.add(
Embedding(len(vocabulary) + 1, EMPTY_EMBEDDING_LAYER_SIZE))
else:
model.add(
Embedding(input_dim=len(vocabulary) + 1,
output_dim=nr_of_embedding_features,
input_length=vectorized_texts.shape[1],
weights=[embedding_matrix],
trainable=False))
model.add(LSTM(16, return_sequences=True))
model.add(LSTM(16, return_sequences=True))
model.add(LSTM(16, return_sequences=True))
model.add(GlobalMaxPool1D())
model.add(Dense(256))
model.add(Dense(256))
model.add(Dense(1, activation='sigmoid'))
#Compile the model
optimizer: Adam = Adam(lr=self.learning_rate)
model.compile(optimizer=optimizer,
loss='binary_crossentropy',
metrics=['acc'])
if self.verbose:
print('5. training the model')
history: History = model.fit(
vectorized_texts,
target,
epochs=self.learning_epochs,
#validation_data=(test_vectors, test_target),
verbose=1, # Logs once per epoch.
batch_size=self.learning_batch_size)
self.model = model
def train(self, texts: List[str], target: List[int]) -> None:
from tensorflow.python.keras.models import Model #type: ignore
from tensorflow.python.keras.layers import Input, Embedding, GRU, Dense, Bidirectional, GlobalMaxPool1D, concatenate #type: ignore
from tensorflow.keras.optimizers import Adam #type: ignore
from tensorflow.keras.callbacks import History #type: ignore
if self.downsampling:
texts, target = downsample(texts, target, self.downsampling_ratio)
if self.verbose:
print('1. Vectorizing texts')
NUMBER_OF_FEATURES: int = 20000
self.tokenizer = text.Tokenizer(num_words=NUMBER_OF_FEATURES)
self.tokenizer.fit_on_texts(texts)
vocabulary: Dict[str, int] = self.tokenizer.word_index
if self._max_sequence_length == 0:
self._max_sequence_length = len(max(texts, key=len))
vectorized_texts: array = self.vectorize_texts(texts)
if self.include_casing_information:
casing_information: array = self.texts_to_casing_information(texts)
if self.embedding_location == '':
if self.verbose:
print('2. Skip (no embeddings)')
print('3. Skip (no embeddings)')
else:
if self.verbose:
print('2. Loading word embeddings')
embedding_dictionary: Dict[
str, List[float]] = load_embedding_dictionary(
self.embedding_location)
nr_of_embedding_features: int = len(
list(embedding_dictionary.values())
[1]) # Check how many values we have for the first word
if self.verbose:
print('3. Creating embedding matrix')
embedding_matrix: array = create_embedding_matrix_for_vocabulary(
embedding_dictionary, vocabulary)
if self.verbose:
print('4. Building up model')
#Define a simple BiGru model with a pretrained embedding layer
word_input: Input = Input(shape=(self._max_sequence_length, ))
if self.embedding_location == '':
#Add an empty embedding layer if we have no pretrained embeddings
EMPTY_EMBEDDING_LAYER_SIZE: int = 300
layers = Embedding(
len(vocabulary) + 1, EMPTY_EMBEDDING_LAYER_SIZE)(word_input)
else:
layers = Embedding(input_dim=len(vocabulary) + 1,
output_dim=nr_of_embedding_features,
input_length=vectorized_texts.shape[1],
weights=[embedding_matrix],
trainable=False)(word_input)
#Add a separate 'entrance' for the casing information
if self.include_casing_information:
word_model: Model = Model(inputs=word_input, outputs=layers)
casing_input: Input = Input(shape=(self._max_sequence_length, 1))
casing_model: Model = Model(inputs=casing_input,
outputs=casing_input)
layers = concatenate([word_model.output, casing_model.output])
if self.bidirectional:
layers = Bidirectional(
GRU(16, activation='tanh', return_sequences=True))(layers)
layers = Bidirectional(
GRU(16, activation='tanh', return_sequences=True))(layers)
else:
layers = GRU(16, activation='tanh', return_sequences=True)(layers)
layers = GRU(16, activation='tanh', return_sequences=True)(layers)
layers = GlobalMaxPool1D()(layers)
layers = Dense(256)(layers)
layers = Dense(256)(layers)
layers = Dense(1, activation='sigmoid')(layers)
if self.include_casing_information:
model: Model = Model([word_model.input, casing_model.input],
layers)
else:
model: Model = Model(word_input, layers)
#Compile the model
optimizer: Adam = Adam(lr=self.learning_rate)
model.compile(optimizer=optimizer,
loss='binary_crossentropy',
metrics=['acc'])
if self.verbose:
print('5. training the model')
if self.include_casing_information:
input = [vectorized_texts, casing_information]
else:
input = vectorized_texts
history: History = model.fit(
input,
target,
epochs=self.learning_epochs,
#validation_data=(test_vectors, test_target),
verbose=1, # Logs once per epoch.
batch_size=self.learning_batch_size)
self.model = model