def test_signature_and_examples_are_saved_correctly(sklearn_knn_model,
iris_data):
data = iris_data
signature_ = infer_signature(*data)
example_ = data[0][:3, ]
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
with open(tmp.path("skmodel"), "wb") as f:
pickle.dump(sklearn_knn_model, f)
path = tmp.path("model")
kiwi.pyfunc.save_model(
path=path,
data_path=tmp.path("skmodel"),
loader_module=os.path.basename(__file__)[:-3],
code_path=[__file__],
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_signature_and_examples_are_saved_correctly(iris_data,
main_scoped_model_class):
def test_predict(sk_model, model_input):
return sk_model.predict(model_input) * 2
data = iris_data
signature_ = infer_signature(*data)
example_ = data[0][:3, ]
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.pyfunc.save_model(
path=path,
artifacts={},
python_model=main_scoped_model_class(test_predict),
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_parse_with_schema(pandas_df_with_all_types):
schema = Schema([ColSpec(c, c) for c in pandas_df_with_all_types.columns])
df = _shuffle_pdf(pandas_df_with_all_types)
json_str = json.dumps(df.to_dict(orient="split"), cls=NumpyEncoder)
df = pyfunc_scoring_server.parse_json_input(json_str,
orient="split",
schema=schema)
json_str = json.dumps(df.to_dict(orient="records"), cls=NumpyEncoder)
df = pyfunc_scoring_server.parse_json_input(json_str,
orient="records",
schema=schema)
assert schema == infer_signature(df[schema.column_names()]).inputs
# The current behavior with pandas json parse with type hints is weird. In some cases, the
# types are forced ignoting overflow and loss of precision:
bad_df = """{
"columns":["bad_integer", "bad_float", "bad_string", "bad_boolean"],
"data":[
[9007199254740991.0, 1.1, 1, 1.5],
[9007199254740992.0, 9007199254740992.0, 2, 0],
[9007199254740994.0, 3.3, 3, "some arbitrary string"]
]
}"""
schema = Schema([
ColSpec("integer", "bad_integer"),
ColSpec("float", "bad_float"),
ColSpec("float", "good_float"),
ColSpec("string", "bad_string"),
ColSpec("boolean", "bad_boolean")
])
df = pyfunc_scoring_server.parse_json_input(bad_df,
orient="split",
schema=schema)
# Unfortunately, the current behavior of pandas parse is to force numbers to int32 even if
# they don't fit:
assert df["bad_integer"].dtype == np.int32
assert all(df["bad_integer"] == [-2147483648, -2147483648, -2147483648])
# The same goes for floats:
assert df["bad_float"].dtype == np.float32
assert all(df["bad_float"] == np.array([1.1, 9007199254740992, 3.3], dtype=np.float32))\
# However bad string is recognized as int64:
assert all(df["bad_string"] == np.array([1, 2, 3], dtype=np.object))
# Boolean is forced - zero and empty string is false, everything else is true:
assert df["bad_boolean"].dtype == np.bool
assert all(df["bad_boolean"] == [True, False, True])
def test_signature_and_examples_are_saved_correctly(sequential_model, data):
model = sequential_model
signature_ = infer_signature(*data)
example_ = data[0].head(3)
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.pytorch.save_model(model, path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model, path) == example).all())
def test_signature_and_examples_are_saved_correctly(xgb_model):
model = xgb_model.model
for signature in (None, infer_signature(xgb_model.inference_dataframe)):
for example in (None, xgb_model.inference_dataframe.head(3)):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.xgboost.save_model(xgb_model=model,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_model_export_with_signature_and_examples(iris_df, spark_model_iris):
_, _, iris_spark_df = iris_df
signature_ = infer_signature(iris_spark_df)
example_ = iris_spark_df.toPandas().head(3)
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
sparkm.save_model(spark_model_iris.model, path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model, path) == example).all())
def test_signature_and_examples_are_saved_correctly(onnx_model, data, onnx_custom_env):
import kiwi.onnx
model = onnx_model
signature_ = infer_signature(*data)
example_ = data[0].head(3)
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.onnx.save_model(model, path=path, conda_env=onnx_custom_env,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model, path) == example).all())
def test_signature_and_examples_are_saved_correctly(h2o_iris_model):
model = h2o_iris_model.model
signature_ = infer_signature(h2o_iris_model.inference_data.as_data_frame())
example_ = h2o_iris_model.inference_data.as_data_frame().head(3)
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.h2o.save_model(model,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_signature_and_examples_are_saved_correctly(gluon_model, model_data):
model = gluon_model
signature_ = infer_signature(model_data[0].asnumpy())
example_ = model_data[0].asnumpy()[:3, ]
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.gluon.save_model(model,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_model_export_with_schema_and_examples(spacy_model_with_data):
spacy_model = spacy_model_with_data.model
signature_ = infer_signature(spacy_model_with_data.inference_data)
example_ = spacy_model_with_data.inference_data.head(3)
for signature in (None, signature_):
for example in (None, example_):
print(signature is None, example is None)
with TempDir() as tmp:
path = tmp.path("model")
kiwi.spacy.save_model(spacy_model,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_signature_and_examples_are_saved_correctly(sklearn_knn_model):
data = sklearn_knn_model.inference_data
model = sklearn_knn_model.model
signature_ = infer_signature(data)
example_ = data[:3, ]
for signature in (None, signature_):
for example in (None, example_):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.sklearn.save_model(model,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())
def test_schema_and_examples_are_save_correctly(saved_tf_iris_model,
model_path):
(train_x, train_y), _ = iris_data_utils.load_data()
X = pd.DataFrame(train_x)
y = pd.Series(train_y)
for signature in (None, infer_signature(X, y)):
for example in (None, X.head(3)):
with TempDir() as tmp:
path = tmp.path("model")
kiwi.tensorflow.save_model(
tf_saved_model_dir=saved_tf_iris_model.path,
tf_meta_graph_tags=saved_tf_iris_model.meta_graph_tags,
tf_signature_def_key=saved_tf_iris_model.signature_def_key,
path=path,
signature=signature,
input_example=example)
mlflow_model = Model.load(path)
assert signature == mlflow_model.signature
if example is None:
assert mlflow_model.saved_input_example_info is None
else:
assert all((_read_example(mlflow_model,
path) == example).all())