def train_and_save_distance_model(ethnicity_model_path,
save_distance_model_path,
sampled_pairs_size):
"""Train the distance estimator model and save it to disk.
Args:
ethnicity_model_path (str): Full path where ethnicity model is saved.
save_distance_model_path (str): Full path where trained distance model
will be saved.
sampled_pairs_size (int): Number of pairs to be generated for the training.
Note:
Must be multiple of 12.
"""
LOGGER.info("Pulling training data from ES")
curated_signatures = get_signatures(only_curated=True)
input_clusters = get_input_clusters(curated_signatures)
LOGGER.info("Preparing %s pairs from sampled data for training.",
sampled_pairs_size)
pairs = list(
sample_signature_pairs(curated_signatures, input_clusters,
sampled_pairs_size))
ethnicity_estimator = EthnicityEstimator(ethnicity_model_path)
distance_estimator = DistanceEstimator(ethnicity_estimator)
distance_estimator.load_data(curated_signatures, pairs, sampled_pairs_size)
LOGGER.info("Training DistanceEstimator...")
distance_estimator.fit()
distance_estimator.save_model(save_distance_model_path)
def train_and_save_distance_model(ethnicity_model_path,
save_distance_model_path,
sampled_pairs_size):
"""Train the distance estimator model and save it to disk.
Args:
ethnicity_model_path (str): Full path where ethnicity model is saved.
save_distance_model_path (str): Full path where trained distance model
will be saved.
sampled_pairs_size (int): Number of pairs to be generated for the training.
Note:
Must be multiple of 12.
"""
LOGGER.info("Pulling training data from ES")
start_time = datetime.now()
curated_signatures = get_signatures(only_curated=True)
input_clusters = get_input_clusters(curated_signatures)
prepare_intput_time = datetime.now()
LOGGER.info(
"Preparing pairs from sampled data for training.",
pairs_count=sampled_pairs_size,
)
pairs = list(
sample_signature_pairs(curated_signatures, input_clusters,
sampled_pairs_size))
prepare_pairs_time = datetime.now()
ethnicity_estimator = EthnicityEstimator(ethnicity_model_path)
distance_estimator = DistanceEstimator(ethnicity_estimator)
prepare_estimators_time = datetime.now()
distance_estimator.load_data(curated_signatures, pairs, sampled_pairs_size)
load_data_to_model_time = datetime.now()
LOGGER.info("Training DistanceEstimator...")
distance_estimator.fit()
training_model_time = datetime.now()
distance_estimator.save_model(save_distance_model_path)
save_model_time = datetime.now()
LOGGER.info(
"Train distance model",
prepare_input_runtime=str(prepare_intput_time - start_time),
prepare_pairs_runtime=str(prepare_pairs_time - prepare_intput_time),
prepare_estimators_runtime=str(prepare_estimators_time -
prepare_pairs_time),
load_data_runtime=str(load_data_to_model_time -
prepare_estimators_time),
training_model_runtime=str(training_model_time -
load_data_to_model_time),
save_model_runtime=str(save_model_time - training_model_time),
total_runtime=str(save_model_time - start_time),
)
def train_and_save_distance_model(
ethnicity_model_path,
save_distance_model_path,
sampled_pairs_size,
train_to_validation_split_fraction=0.8,
):
"""Train the distance estimator model and save it to disk.
Args:
ethnicity_model_path (str): Full path where ethnicity model is saved.
save_distance_model_path (str): Full path where trained distance model
will be saved.
sampled_pairs_size (int): Number of pairs to be generated for the training.
Note:
Must be multiple of 4.
train_to_validation_split_fraction (float): fraction of the data
used for training.
"""
start_time = datetime.now()
curated_signatures = get_signatures(only_curated=True)
LOGGER.info(
"Splitting data into training and test set.",
training_set_fraction=train_to_validation_split_fraction,
)
train_signatures_dict, test_signatures_dict = train_validation_split(
curated_signatures, train_to_validation_split_fraction)
train_signatures_list = train_signatures_dict.values()
test_signatures_list = test_signatures_dict.values()
input_clusters_train = get_input_clusters(train_signatures_list)
input_clusters_test = get_input_clusters(test_signatures_list)
prepare_intput_time = datetime.now()
LOGGER.info(
"Preparing pairs from sampled data for training.",
pairs_count=sampled_pairs_size,
)
pairs_train = list(
sample_signature_pairs(train_signatures_list, input_clusters_train,
sampled_pairs_size))
prepare_pairs_time = datetime.now()
# must be multiple of 4
pair_size_test = 4 * math.ceil(
(((1 - train_to_validation_split_fraction) /
train_to_validation_split_fraction)**2 * sampled_pairs_size) / 4)
pairs_test = list(
sample_signature_pairs(test_signatures_list, input_clusters_test,
pair_size_test))
LOGGER.info(
"Pairs prepared.",
n_training_pairs=len(pairs_train),
n_test_pairs=len(pairs_test),
)
ethnicity_estimator = EthnicityEstimator(ethnicity_model_path)
distance_estimator = DistanceEstimator(ethnicity_estimator)
prepare_estimators_time = datetime.now()
distance_estimator.load_data(train_signatures_list, pairs_train,
sampled_pairs_size)
load_data_to_model_time = datetime.now()
distance_estimator.fit()
training_model_time = datetime.now()
distance_estimator.save_model(save_distance_model_path)
save_model_time = datetime.now()
distance_estimator.load_data(test_signatures_list, pairs_test,
pair_size_test)
test_score = distance_estimator.score()
LOGGER.info(
"Train distance model",
prepare_input_runtime=str(prepare_intput_time - start_time),
prepare_pairs_runtime=str(prepare_pairs_time - prepare_intput_time),
prepare_estimators_runtime=str(prepare_estimators_time -
prepare_pairs_time),
load_data_runtime=str(load_data_to_model_time -
prepare_estimators_time),
training_model_runtime=str(training_model_time -
load_data_to_model_time),
save_model_runtime=str(save_model_time - training_model_time),
total_runtime=str(save_model_time - start_time),
test_score=str(test_score),
)
return set(test_signatures_dict)