def get_embeddings_per_log(data: defaultdict,
model: fasttext.FastText) -> np.ndarray:
# create embeddings per log but at first remove '\n' (newline character) from the end
embeddings = [
model.get_sentence_vector(log.rstrip()) for logs in data.values()
for log in logs
]
return np.asarray(embeddings)
def get_embeddings_per_block(data: defaultdict, model: fasttext.FastText,
with_timedelta: bool) -> List:
# create embeddings per block but at first remove '\n' (newline character) from the end
if with_timedelta:
embeddings = get_embeddings_with_timedeltas_per_block(data, model)
else:
embeddings = [
np.asarray(
[model.get_sentence_vector(log.rstrip()) for log in logs])
for logs in data.values()
]
return embeddings
def get_embeddings_with_timedeltas_per_block(data: defaultdict,
model: fasttext.FastText) -> List:
embeddings = []
for logs in data.values():
numpy_block = np.zeros(shape=(len(logs), model.get_dimension() + 1),
dtype=np.float32)
for i, log in enumerate(logs):
numpy_block[i, 1:] = model.get_sentence_vector(log.rstrip())
numpy_block[:, 0] = get_timedeltas(logs)
embeddings.append(numpy_block)
return embeddings
