def create_model(self, dataset: RepertoireDataset, k: int, vector_size: int, batch_size: int, model_path: Path):
model = Word2Vec(size=vector_size, min_count=1, window=5) # creates an empty model
all_kmers = KmerHelper.create_all_kmers(k=k, alphabet=EnvironmentSettings.get_sequence_alphabet())
all_kmers = [[kmer] for kmer in all_kmers]
model.build_vocab(all_kmers)
for repertoire in dataset.get_data(batch_size=batch_size):
sentences = KmerHelper.create_sentences_from_repertoire(repertoire=repertoire, k=k)
model.train(sentences=sentences, total_words=len(all_kmers), epochs=15)
model.save(str(model_path))
return model
def test_create_sentences_from_repertoire(self):
path = EnvironmentSettings.tmp_test_path / "kmer/"
PathBuilder.build(path)
rep = Repertoire.build_from_sequence_objects([ReceptorSequence(amino_acid_sequence="AACT"),
ReceptorSequence(amino_acid_sequence="ACCT"),
ReceptorSequence(amino_acid_sequence="AACT")], path, {})
sentences = KmerHelper.create_sentences_from_repertoire(rep, 3, sequence_type=SequenceType.AMINO_ACID)
self.assertEqual(3, len(sentences))
self.assertTrue(len(sentences[0]) == 2 and "AAC" in sentences[0] and "ACT" in sentences[0])
shutil.rmtree(path)