def test_diff_detector_serializability(config):
"""
Should play well with the gordo serializer
"""
config = yaml.load(config)
model = serializer.pipeline_from_definition(config)
serializer.pipeline_into_definition(model)
serialized_bytes = serializer.dumps(model)
serializer.loads(serialized_bytes)
def test_download_model(gordo_ml_server_client):
"""
Test we can download a model, loadable via serializer.loads()
"""
resp = gordo_ml_server_client.get("/download-model")
serialized_model = resp.get_data()
model = serializer.loads(serialized_model)
# All models have a fit method
assert hasattr(model, "fit")
# Models MUST have either predict or transform
assert hasattr(model, "predict") or hasattr(model, "transform")
def download_model(self) -> typing.Dict[str, BaseEstimator]:
"""
Download the actual model(s) from the ML server /download-model
Returns
-------
Dict[str, BaseEstimator]
Mapping of target name to the model
"""
models = dict()
for endpoint in self.endpoints:
resp = self.session.get(f"{self.base_url + endpoint.endpoint}/download-model")
if resp.ok:
models[endpoint.name] = serializer.loads(resp.content)
else:
raise IOError(f"Failed to download model: '{repr(resp.content)}'")
return models
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)
# Assert that a dirs are created for each step in Pipeline
expected_structure = OrderedDict([
("n_step=000-class=sklearn.pipeline.Pipeline",
"metadata.json"),
(
"n_step=000-class=sklearn.pipeline.Pipeline",
OrderedDict([
(
"n_step=000-class=sklearn.decomposition.pca.PCA",
"pca1.pkl.gz",
),
(
"n_step=001-class=sklearn.pipeline.FeatureUnion",
"params.json",
),
(
"n_step=001-class=sklearn.pipeline.FeatureUnion",
OrderedDict([
(
"n_step=000-class=sklearn.decomposition.pca.PCA",
"pca2.pkl.gz",
),
(
"n_step=001-class=sklearn.pipeline.Pipeline",
OrderedDict([
(
"n_step=000-class=sklearn.preprocessing.data.MinMaxScaler",
"minmax.pkl.gz",
),
(
"n_step=001-class=sklearn.decomposition.truncated_svd.TruncatedSVD",
"truncsvd.pkl.gz",
),
]),
),
]),
),
(
"n_step=002-class=gordo_components.model.models.KerasAutoEncoder",
"model.h5",
),
(
"n_step=002-class=gordo_components.model.models.KerasAutoEncoder",
"params.json",
),
]),
),
])
self._structure_verifier(prefix_dir=tmp,
structure=expected_structure)
# 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))
