def test_diff_detector_serializability(config):
"""
Should play well with the gordo serializer
"""
config = yaml.load(config)
model = serializer.from_definition(config)
serializer.into_definition(model)
serialized_bytes = serializer.dumps(model)
serializer.loads(serialized_bytes)
def test_pipeline_serialization(self):
pipe = Pipeline(
[
("pca1", PCA(n_components=10)),
(
"fu",
FeatureUnion(
[
("pca2", PCA(n_components=3)),
(
"pipe",
Pipeline(
[
("minmax", MinMaxScaler()),
("truncsvd", TruncatedSVD(n_components=7)),
]
),
),
]
),
),
("ae", KerasAutoEncoder(kind="feedforward_hourglass")),
]
)
X = np.random.random(size=100).reshape(10, 10)
pipe.fit(X.copy(), X.copy())
with TemporaryDirectory() as tmp:
# Test dump
metadata = {"key": "value"}
serializer.dump(pipe, tmp, metadata=metadata)
# Test load from the serialized pipeline above
pipe_clone = serializer.load(tmp)
metadata_clone = serializer.load_metadata(tmp)
# Ensure the metadata was saved and loaded back
self.assertEqual(metadata, metadata_clone)
# Verify same state for both pipelines
y_hat_pipe1 = pipe.predict(X.copy()).flatten()
y_hat_pipe2 = pipe_clone.predict(X.copy()).flatten()
self.assertTrue(np.allclose(y_hat_pipe1, y_hat_pipe2))
# Now use dumps/loads
serialized = serializer.dumps(pipe)
pipe_clone = serializer.loads(serialized)
# Verify same state for both pipelines
y_hat_pipe1 = pipe.predict(X.copy()).flatten()
y_hat_pipe2 = pipe_clone.predict(X.copy()).flatten()
self.assertTrue(np.allclose(y_hat_pipe1, y_hat_pipe2))
def get(self):
"""
Responds with a serialized copy of the current model being served.
Returns
-------
bytes
Results from ``gordo.serializer.dumps()``
"""
serialized_model = serializer.dumps(g.model)
buff = io.BytesIO(serialized_model)
return send_file(buff, attachment_filename="model.tar.gz")