def test_load_signatures(curated_signature, non_curated_signature):
signatures_by_uuid = load_signatures(
[curated_signature, non_curated_signature])
expected_signatures_by_uuid = {
curated_signature["signature_uuid"]: curated_signature,
non_curated_signature["signature_uuid"]: non_curated_signature,
}
assert signatures_by_uuid == expected_signatures_by_uuid
def load_data(self, curated_signatures, pairs, pairs_size):
"""Loads training data to the estimator vectors
Args:
curated_signatures (iterable): Signatures for the training
pairs (iterable): Pairs of signatures and clusters for the training
pairs_size (int): Amount of pairs
"""
signatures_by_uuid = load_signatures(curated_signatures)
self.X = np.empty((pairs_size, 2), dtype=np.object)
self.y = np.empty(pairs_size, dtype=np.int)
for i, pair in enumerate(pairs):
self.X[i, 0] = signatures_by_uuid[pair["signature_uuids"][0]]
self.X[i, 1] = signatures_by_uuid[pair["signature_uuids"][1]]
self.y[i] = 0 if pair["same_cluster"] else 1
def load_data(self, signatures, input_clusters):
"""Loads data to the estimator vectors
Args:
signatures (iterable): Signatures which should be processed
input_clusters (iterable): Input clusters built for provided signatures
see: `inspire_disambiguation.core.es.readers.get_input_clusters`
"""
signatures_by_uuid = load_signatures(signatures)
self.X = np.empty((len(signatures_by_uuid), 1), dtype=np.object)
self.y = -np.ones(len(self.X), dtype=np.int)
i = 0
for cluster in input_clusters:
for signature_uuid in cluster["signature_uuids"]:
if signature_uuid not in signatures_by_uuid:
continue # TODO figure out how this can happen
self.X[i, 0] = signatures_by_uuid[signature_uuid]
self.y[i] = cluster["cluster_id"]
i += 1