def test_make_upload_args(self):
self.assertTrue(hasattr(YamlHelper, 'make_upload_args'))
yg = YamlHelper(self.test_yaml_upload_good)
self.assertDictEqual(
yg.make_upload_args(),
{'local_directory': 'tests/resources/test_output_data_dir/',
's3_bucket': 'some_bucket', 's3_bucket_dir': 'some/remote/directory/',
'extra_args': {'ACL': 'public-read'}})
def test_make_embeddings_metrics_class_list(self):
self.assertTrue(hasattr(YamlHelper, 'make_embeddings_metrics_class_list'))
yh = YamlHelper("tests/resources/test_make_embeddings_metrics.yaml")
cl = yh.make_embeddings_metrics_class_list()
self.assertEqual(3, len(cl))
self.assertCountEqual(["<class 'keras.metrics.AUC'>",
"<class 'keras.metrics.Recall'>",
"<class 'keras.metrics.Precision'>"],
[str(klass.__class__) for klass in cl])
def test_make_graph_embeddings(self):
yhelp = YamlHelper(
"tests/resources/test_graph_embedding_bert_tsne.yaml")
node_embedding_args = yhelp.make_node_embeddings_args()
make_node_embeddings(**node_embedding_args)
self.assertTrue(os.path.exists(self.expected_embedding_file))
self.assertTrue(os.path.exists(self.expected_history_file))
with open(self.expected_history_file) as f:
data = f.read()
obj = json.loads(data)
self.assertListEqual(list(obj.keys()), ['loss', 'lr'])
def test_node_edge_urls_converted_to_path(self, mock_from_csv, mock_download_file):
this_yh = YamlHelper('tests/resources/test_urls_for_node_and_edge_paths.yaml')
self.assertTrue(is_url(this_yh.main_graph_args()['node_path']))
self.assertTrue(is_url(this_yh.main_graph_args()['edge_path']))
this_yh.load_graph()
self.assertFalse(is_url(this_yh.main_graph_args()['node_path']))
self.assertEqual('output_data/https___someremoteurl.com_nodes.tsv',
this_yh.main_graph_args()['node_path'])
self.assertFalse(is_url(this_yh.main_graph_args()['edge_path']))
self.assertEqual('output_data/https___someremoteurl.com_edges.tsv',
this_yh.main_graph_args()['edge_path'])
def test_pre_run_check_bad_credentials_but_no_check(
self, mock_boto_client) -> None:
mock_boto_client.side_effect = ClientError(
error_response=mock_boto_client, operation_name=mock_boto_client)
return_val = pre_run_checks(
YamlHelper('tests/resources/test_no_upload.yaml'),
check_s3_credentials=False)
# returns true if bad creds, but we don't want to check credentials
self.assertTrue(return_val)
def test_make_tsne(self):
yhelp = YamlHelper(
"tests/resources/test_graph_embedding_bert_tsne.yaml")
g = Graph.from_csv(nodes_column="id",
node_list_node_types_column="category",
default_node_type="biolink:NamedThing",
node_path=os.path.join(
yhelp.yaml['input_directory'],
yhelp.yaml['graph_data']['graph']['node_path']),
edge_path=os.path.join(
yhelp.yaml['input_directory'],
yhelp.yaml['graph_data']['graph']['edge_path']),
sources_column="subject",
destinations_column="object",
directed=False)
tsne_kwargs = yhelp.make_tsne_args(graph=g)
tsne_kwargs['embedding_file'] = 'tests/resources/test_embeddings.tsv'
make_tsne(**tsne_kwargs)
self.assertTrue(os.path.exists(self.expected_tsne_file))
def test_do_upload(self):
self.assertTrue(hasattr(YamlHelper, 'do_upload'))
yg = YamlHelper(self.test_yaml_upload_good)
self.assertTrue(yg.do_upload())
def test_do_tsne(self):
self.assertTrue(hasattr(YamlHelper, 'do_tsne'))
self.assertTrue(not self.yh.do_tsne())
ybt = YamlHelper(self.test_yaml_bert_tsne)
self.assertTrue(ybt.do_tsne())
def test_bad_indir(self) -> None:
with self.assertRaises(FileNotFoundError) as context:
YamlHelper("tests/resources/test_bad_indir.yaml").indir()
def test_no_indir(self) -> None:
yh = YamlHelper("tests/resources/test_no_indir.yaml")
self.assertEqual("", yh.indir())
def test_node_edge_urls_file_downloaded(self, mock_from_csv, mock_download_file):
this_yh = YamlHelper('tests/resources/test_urls_for_node_and_edge_paths.yaml')
this_yh.load_graph()
self.assertTrue(mock_download_file.called)
self.assertEqual(2, mock_download_file.call_count)
def setUp(self) -> None:
self.bad_yaml = 'tests/resources/test_bad_upload_info.yaml'
self.good_yaml = 'tests/resources/test_good_upload_info.yaml'
self.good_kwargs = YamlHelper(self.good_yaml).make_upload_args()
def test_catch_keyerror(self):
yh = YamlHelper("tests/resources/test_no_graph.yaml")
yh.pos_val_graph_args() # no assertion needed, just testing for no exception
def setUp(self) -> None:
self.upload_yaml = YamlHelper('tests/resources/test_upload_full.yaml')
def run(config: str) -> None:
"""Run a NEAT pipeline using the given YAML file [neat.yaml]
\f
Args:
config: Specify the YAML file containing instructions of what ML tasks to perform
Returns:
None.
"""
yhelp = YamlHelper(config)
# pre run checks for failing early
if not pre_run_checks(yhelp=yhelp):
raise RuntimeError("Failed pre_run_check")
# generate embeddings if config has 'embeddings' block
if yhelp.do_embeddings() and not os.path.exists(yhelp.embedding_outfile()):
node_embedding_args = yhelp.make_node_embeddings_args()
make_node_embeddings(**node_embedding_args)
if yhelp.do_tsne() and not os.path.exists(yhelp.tsne_outfile()):
graph: Graph = yhelp.load_graph()
tsne_kwargs = yhelp.make_tsne_args(graph)
make_tsne(**tsne_kwargs)
if yhelp.do_classifier():
for classifier in tqdm(yhelp.classifiers()):
model: object = None
if classifier['type'] == 'neural network':
model = MLPModel(classifier, outdir=yhelp.outdir())
elif classifier['type'] in \
['Decision Tree', 'Logistic Regression', 'Random Forest']:
model = SklearnModel(classifier, outdir=yhelp.outdir())
else:
raise NotImplementedError(f"{model} isn't implemented yet")
model.compile()
train_data, validation_data = \
model.make_link_prediction_data(yhelp.embedding_outfile(),
yhelp.main_graph_args(),
yhelp.pos_val_graph_args(),
yhelp.neg_train_graph_args(),
yhelp.neg_val_graph_args(),
yhelp.edge_embedding_method())
history_obj = model.fit(train_data, validation_data)
if yhelp.classifier_history_file_name(classifier):
with open(yhelp.classifier_history_file_name(classifier),
'w') as f: # type: ignore
json.dump(history_obj.history, f)
model.save()
if yhelp.do_upload():
upload_kwargs = yhelp.make_upload_args()
upload_dir_to_s3(**upload_kwargs)
return None
def test_classifier_history_file_name(self):
self.assertTrue(hasattr(YamlHelper, 'classifier_history_file_name'))
yg = YamlHelper(self.test_yaml)
self.assertEqual(
yg.classifier_history_file_name(yg.yaml['classifier']['classifiers'][0]),
"mlp_classifier_history.json")
def setUpClass(cls) -> None:
cls.test_yaml = "tests/resources/test.yaml"
cls.yh = YamlHelper(cls.test_yaml)
cls.embedding_args = cls.yh.make_node_embeddings_args()