def handle_projections(exclude_key: Optional[str] = None) -> bool:
if blank_idx is None or len(project_idx) == 0:
return False
projections = []
blank_pos = self.sentence_structures[sentence_idx][blank_idx].pos
for word_idx in project_idx:
projecting_word = self.sentence_generations[sentence_idx][word_idx]
projection = projecting_word.project(word_idx, sentence_length, blank_pos,
exclude_key=exclude_key)
projections.append(projection)
# Concatenate all projections and create p-value matrix
projection_collection = MarkovWordProjectionCollection(projections)
if len(projection_collection) == 0:
return False
all_p_values = projection_collection.probability_matrix()
# We just want the p-values for the blank word
p_values = all_p_values[:, blank_idx]
# Choose an index based on the probability
choices = np.arange(len(projection_collection))
word_choice_idx = temp(p_values, temperature=MARKOV_MODEL_TEMPERATURE)
# Select the word from the database and assign it to the blank space
select_word = projection_collection.keys[word_choice_idx]
word = GeneratedWord.from_markov_word(db.select(select_word),
self.sentence_structures[sentence_idx][blank_idx].mode)
self.sentence_generations[sentence_idx][blank_idx] = word
def predict(self, num_sentences: int) -> List[PoSCapitalizationMode]:
from keras.preprocessing.sequence import pad_sequences
predictions = []
# Start the sequence with NONE / NONE
sequence = [[0]]
eos_count = 0
while eos_count < num_sentences:
padded_sequence = pad_sequences(sequence, maxlen=StructureModel.SEQUENCE_LENGTH, padding='post')
prediction = self.model.predict(padded_sequence, batch_size=1)[0]
index = temp(prediction, STRUCTURE_MODEL_TEMPERATURE)
if PoSCapitalizationMode.from_embedding(index).pos == Pos.EOS:
eos_count += 1
predictions.append(index)
sequence[0].append(index)
sequence[0] = sequence[0][-StructureModel.SEQUENCE_LENGTH:]
modes = []
for embedding_idx, embedding in enumerate(predictions):
mode = PoSCapitalizationMode.from_embedding(embedding)
modes.append(mode)
return modes
def predict(self, num_sentences: int) -> List[PoSCapitalizationMode]:
from keras.preprocessing.sequence import pad_sequences
predictions = []
# Start the sequence with NONE / NONE
sequence = [[0]]
eos_count = 0
while eos_count < num_sentences:
padded_sequence = pad_sequences(sequence, maxlen=StructureModel.SEQUENCE_LENGTH, padding='post')
prediction = self.model.predict(padded_sequence, batch_size=1)[0]
index = temp(prediction, STRUCTURE_MODEL_TEMPERATURE)
if PoSCapitalizationMode.from_embedding(index).pos == Pos.EOS:
eos_count += 1
predictions.append(index)
sequence[0].append(index)
sequence[0] = sequence[0][-StructureModel.SEQUENCE_LENGTH:]
modes = []
for embedding_idx, embedding in enumerate(predictions):
mode = PoSCapitalizationMode.from_embedding(embedding)
modes.append(mode)
return modes
def handle_projections(exclude_key: Optional[str] = None) -> bool:
if blank_idx is None or len(project_idx) == 0:
return False
projections = []
blank_pos = self.sentence_structures[sentence_idx][blank_idx].pos
for word_idx in project_idx:
projecting_word = self.sentence_generations[sentence_idx][word_idx]
projection = projecting_word.project(word_idx, sentence_length, blank_pos,
exclude_key=exclude_key)
projections.append(projection)
# Concatenate all projections and create p-value matrix
projection_collection = MarkovWordProjectionCollection(projections)
if len(projection_collection) == 0:
return False
all_p_values = projection_collection.probability_matrix()
# We just want the p-values for the blank word
p_values = all_p_values[:, blank_idx]
# Choose an index based on the probability
choices = np.arange(len(projection_collection))
word_choice_idx = temp(p_values, temperature=MARKOV_MODEL_TEMPERATURE)
# Select the word from the database and assign it to the blank space
select_word = projection_collection.keys[word_choice_idx]
word = GeneratedWord.from_markov_word(db.select(select_word),
self.sentence_structures[sentence_idx][blank_idx].mode)
self.sentence_generations[sentence_idx][blank_idx] = word