def encode(self, dataset, params: EncoderParams):
EncoderHelper.check_positive_class_label(
CompAIRRSequenceAbundanceEncoder.__name__,
params.label_config.get_label_objects())
self._prepare_sequence_presence_data(dataset, params)
encoded_dataset = self._encode_data(dataset, params)
return encoded_dataset
def encode(self, dataset, params: EncoderParams):
EncoderHelper.check_positive_class_label(
SequenceAbundanceEncoder.__name__,
params.label_config.get_label_objects())
self.comparison_data = SequenceFilterHelper.build_comparison_data(
dataset, self.context, self.comparison_attributes, params,
self.sequence_batch_size)
return self._encode_data(dataset, params)
def encode(self, dataset, params: EncoderParams):
cache_params = self._prepare_caching_params(dataset, params)
encoded_dataset = CacheHandler.memo_by_params(
cache_params, lambda: self._encode_new_dataset(dataset, params))
EncoderHelper.sync_encoder_with_cache(
cache_params, lambda: {
'model_path': self.model_path,
'scaler': self.scaler
}, self, ['model_path', 'scaler'])
return encoded_dataset
def build_comparison_data(dataset: RepertoireDataset, context: dict,
comparison_attributes: list,
params: EncoderParams, sequence_batch_size: int):
current_dataset = EncoderHelper.get_current_dataset(dataset, context)
comparison_data = CacheHandler.memo_by_params(
EncoderHelper.build_comparison_params(current_dataset,
comparison_attributes),
lambda: EncoderHelper.build_comparison_data(
current_dataset, params, comparison_attributes,
sequence_batch_size))
return comparison_data
def _prepare_sequence_presence_data(self, dataset, params):
full_dataset = EncoderHelper.get_current_dataset(dataset, self.context)
full_sequence_set = self._get_full_sequence_set(full_dataset)
sequence_presence_matrix, matrix_repertoire_ids = self._get_sequence_presence(
full_dataset, full_sequence_set, params)
self.full_sequence_set = full_sequence_set
self.sequence_presence_matrix = sequence_presence_matrix
self.matrix_repertoire_ids = matrix_repertoire_ids
def encode(self, dataset, params: EncoderParams) -> RepertoireDataset:
train_repertoire_ids = EncoderHelper.prepare_training_ids(dataset, params)
distance_matrix = self.build_distance_matrix(dataset, params, train_repertoire_ids)
labels = self.build_labels(dataset, params) if params.encode_labels else None
encoded_dataset = dataset.clone()
encoded_dataset.encoded_data = EncodedData(examples=distance_matrix, labels=labels, example_ids=distance_matrix.index.values,
encoding=DistanceEncoder.__name__)
return encoded_dataset
def encode(self, dataset, params: EncoderParams):
train_receptor_ids = EncoderHelper.prepare_training_ids(
dataset, params)
if params.learn_model:
self._build_tcr_dist_matrix(
dataset, params.label_config.get_labels_by_name())
distance_matrix = self.distance_matrix.loc[dataset.get_example_ids(),
train_receptor_ids]
labels = self._build_labels(dataset,
params) if params.encode_labels else None
encoded_dataset = dataset.clone()
encoded_dataset.encoded_data = EncodedData(
examples=distance_matrix,
labels=labels,
example_ids=distance_matrix.index.values,
encoding=TCRdistEncoder.__name__)
return encoded_dataset
def store(self, encoded_dataset, params: EncoderParams):
EncoderHelper.store(encoded_dataset, params)