def test_schema_enforcement_no_col_names():
class TestModel(object):
@staticmethod
def predict(pdf):
return pdf
m = Model()
input_schema = Schema([
ColSpec("double"),
ColSpec("double"),
ColSpec("double"),
])
m.signature = ModelSignature(inputs=input_schema)
pyfunc_model = PyFuncModel(model_meta=m, model_impl=TestModel())
test_data = [[1.0, 2.0, 3.0]]
# Can call with just a list
assert pyfunc_model.predict(test_data).equals(pd.DataFrame(test_data))
# Or can call with a DataFrame without column names
assert pyfunc_model.predict(pd.DataFrame(test_data)).equals(
pd.DataFrame(test_data))
# Or with column names!
pdf = pd.DataFrame(data=test_data, columns=["a", "b", "c"])
assert pyfunc_model.predict(pdf).equals(pdf)
# Must provide the right number of arguments
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict([[1.0, 2.0]])
assert "the provided input only has 2 columns." in str(ex)
# Must provide the right types
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict([[1, 2, 3]])
assert "Can not safely convert int64 to float64" in str(ex)
# Can only provide data frames or lists...
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(set([1, 2, 3]))
assert "Expected input to be DataFrame or list. Found: set" in str(ex)
def test_model_save_load():
m = Model(artifact_path="some/path",
run_id="123",
flavors={
"flavor1": {"a": 1, "b": 2},
"flavor2": {"x": 1, "y": 2},
},
signature=ModelSignature(
inputs=Schema([ColSpec("integer", "x"), ColSpec("integer", "y")]),
outputs=Schema([ColSpec(name=None, type="double")])),
saved_input_example_info={"x": 1, "y": 2})
assert m.get_input_schema() == m.signature.inputs
assert m.get_output_schema() == m.signature.outputs
x = Model(artifact_path="some/other/path", run_id="1234")
assert x.get_input_schema() is None
assert x.get_output_schema() is None
n = Model(artifact_path="some/path",
run_id="123",
flavors={
"flavor1": {"a": 1, "b": 2},
"flavor2": {"x": 1, "y": 2},
},
signature=ModelSignature(
inputs=Schema([ColSpec("integer", "x"), ColSpec("integer", "y")]),
outputs=Schema([ColSpec(name=None, type="double")])),
saved_input_example_info={"x": 1, "y": 2})
n.utc_time_created = m.utc_time_created
assert m == n
n.signature = None
assert m != n
with TempDir() as tmp:
m.save(tmp.path("model"))
o = Model.load(tmp.path("model"))
assert m == o
assert m.to_json() == o.to_json()
assert m.to_yaml() == o.to_yaml()
def save_model(pytorch_model,
path,
conda_env=None,
mlflow_model=None,
code_paths=None,
pickle_module=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
**kwargs):
"""
Save a PyTorch model to a path on the local file system.
:param pytorch_model: PyTorch model to be saved. Must accept a single ``torch.FloatTensor`` as
input and produce a single output tensor. Any code dependencies of the
model's class, including the class definition itself, should be
included in one of the following locations:
- The package(s) listed in the model's Conda environment, specified
by the ``conda_env`` parameter.
- One or more of the files specified by the ``code_paths`` parameter.
:param path: Local path where the model is to be saved.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decsribes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If ``None``, the default
:func:`get_default_conda_env()` environment is added to the model. The
following is an *example* dictionary representation of a Conda environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'pytorch=0.4.1',
'torchvision=0.2.1'
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param code_paths: A list of local filesystem paths to Python file dependencies (or directories
containing file dependencies). These files are *prepended* to the system
path when the model is loaded.
:param pickle_module: The module that PyTorch should use to serialize ("pickle") the specified
``pytorch_model``. This is passed as the ``pickle_module`` parameter
to ``torch.save()``. By default, this module is also used to
deserialize ("unpickle") the PyTorch model at load time.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
:param kwargs: kwargs to pass to ``torch.save`` method.
.. code-block:: python
:caption: Example
import torch
import mlflow
import mlflow.pytorch
# Create model and set values
pytorch_model = Model()
pytorch_model_path = ...
# train our model
for epoch in range(500):
y_pred = pytorch_model(x_data)
...
# Save the model
with mlflow.start_run() as run:
mlflow.log_param("epochs", 500)
mlflow.pytorch.save_model(pytorch_model, pytorch_model_path)
"""
import torch
pickle_module = pickle_module or mlflow_pytorch_pickle_module
if not isinstance(pytorch_model, torch.nn.Module):
raise TypeError("Argument 'pytorch_model' should be a torch.nn.Module")
if code_paths is not None:
if not isinstance(code_paths, list):
raise TypeError(
'Argument code_paths should be a list, not {}'.format(
type(code_paths)))
path = os.path.abspath(path)
if os.path.exists(path):
raise RuntimeError("Path '{}' already exists".format(path))
if mlflow_model is None:
mlflow_model = Model()
os.makedirs(path)
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
model_data_subpath = "data"
model_data_path = os.path.join(path, model_data_subpath)
os.makedirs(model_data_path)
# Persist the pickle module name as a file in the model's `data` directory. This is necessary
# because the `data` directory is the only available parameter to `_load_pyfunc`, and it
# does not contain the MLmodel configuration; therefore, it is not sufficient to place
# the module name in the MLmodel
#
# TODO: Stop persisting this information to the filesystem once we have a mechanism for
# supplying the MLmodel configuration to `mlflow.pytorch._load_pyfunc`
pickle_module_path = os.path.join(model_data_path,
_PICKLE_MODULE_INFO_FILE_NAME)
with open(pickle_module_path, "w") as f:
f.write(pickle_module.__name__)
# Save pytorch model
model_path = os.path.join(model_data_path,
_SERIALIZED_TORCH_MODEL_FILE_NAME)
torch.save(pytorch_model,
model_path,
pickle_module=pickle_module,
**kwargs)
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env()
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
if code_paths is not None:
code_dir_subpath = "code"
for code_path in code_paths:
_copy_file_or_tree(src=code_path,
dst=path,
dst_dir=code_dir_subpath)
else:
code_dir_subpath = None
mlflow_model.add_flavor(FLAVOR_NAME,
model_data=model_data_subpath,
pytorch_version=torch.__version__)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.pytorch",
data=model_data_subpath,
pickle_module_name=pickle_module.__name__,
code=code_dir_subpath,
env=conda_env_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(onnx_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None):
"""
Save an ONNX model to a path on the local file system.
:param onnx_model: ONNX model to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this describes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If `None`, the default
:func:`get_default_conda_env()` environment is added to the model.
The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.6.0',
'onnx=1.4.1',
'onnxruntime=0.3.0'
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
"""
import onnx
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException(message="Path '{}' already exists".format(path),
error_code=RESOURCE_ALREADY_EXISTS)
os.makedirs(path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
model_data_subpath = "model.onnx"
model_data_path = os.path.join(path, model_data_subpath)
# Save onnx-model
onnx.save_model(onnx_model, model_data_path)
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env()
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.onnx",
data=model_data_subpath,
env=conda_env_subpath)
mlflow_model.add_flavor(FLAVOR_NAME,
onnx_version=onnx.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(sk_model,
path,
conda_env=None,
mlflow_model=None,
serialization_format=SERIALIZATION_FORMAT_CLOUDPICKLE,
signature: ModelSignature = None,
input_example: ModelInputExample = None):
"""
Save a scikit-learn model to a path on the local file system.
:param sk_model: scikit-learn model to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decsribes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If `None`, the default
:func:`get_default_conda_env()` environment is added to the model.
The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'scikit-learn=0.19.2'
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param serialization_format: The format in which to serialize the model. This should be one of
the formats listed in
``mlflow.sklearn.SUPPORTED_SERIALIZATION_FORMATS``. The Cloudpickle
format, ``mlflow.sklearn.SERIALIZATION_FORMAT_CLOUDPICKLE``,
provides better cross-system compatibility by identifying and
packaging code dependencies with the serialized model.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
.. code-block:: python
:caption: Example
import mlflow.sklearn
from sklearn.datasets import load_iris
from sklearn import tree
iris = load_iris()
sk_model = tree.DecisionTreeClassifier()
sk_model = sk_model.fit(iris.data, iris.target)
# Save the model in cloudpickle format
# set path to location for persistence
sk_path_dir_1 = ...
mlflow.sklearn.save_model(
sk_model, sk_path_dir_1,
serialization_format=mlflow.sklearn.SERIALIZATION_FORMAT_CLOUDPICKLE)
# save the model in pickle format
# set path to location for persistence
sk_path_dir_2 = ...
mlflow.sklearn.save_model(sk_model, sk_path_dir_2,
serialization_format=mlflow.sklearn.SERIALIZATION_FORMAT_PICKLE)
"""
import sklearn
if serialization_format not in SUPPORTED_SERIALIZATION_FORMATS:
raise MlflowException(message=(
"Unrecognized serialization format: {serialization_format}. Please specify one"
" of the following supported formats: {supported_formats}.".format(
serialization_format=serialization_format,
supported_formats=SUPPORTED_SERIALIZATION_FORMATS)),
error_code=INVALID_PARAMETER_VALUE)
if os.path.exists(path):
raise MlflowException(message="Path '{}' already exists".format(path),
error_code=RESOURCE_ALREADY_EXISTS)
os.makedirs(path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
model_data_subpath = "model.pkl"
_save_model(sk_model=sk_model,
output_path=os.path.join(path, model_data_subpath),
serialization_format=serialization_format)
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env(
include_cloudpickle=serialization_format ==
SERIALIZATION_FORMAT_CLOUDPICKLE)
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.sklearn",
model_path=model_data_subpath,
env=conda_env_subpath)
mlflow_model.add_flavor(FLAVOR_NAME,
pickled_model=model_data_subpath,
sklearn_version=sklearn.__version__,
serialization_format=serialization_format)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(path,
loader_module=None,
data_path=None,
code_path=None,
conda_env=None,
mlflow_model=None,
python_model=None,
artifacts=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
**kwargs):
"""
save_model(path, loader_module=None, data_path=None, code_path=None, conda_env=None,\
mlflow_model=Model(), python_model=None, artifacts=None)
Save a Pyfunc model with custom inference logic and optional data dependencies to a path on the
local filesystem.
For information about the workflows that this method supports, please see :ref:`"workflows for
creating custom pyfunc models" <pyfunc-create-custom-workflows>` and
:ref:`"which workflow is right for my use case?" <pyfunc-create-custom-selecting-workflow>`.
Note that the parameters for the second workflow: ``loader_module``, ``data_path`` and the
parameters for the first workflow: ``python_model``, ``artifacts``, cannot be
specified together.
:param path: The path to which to save the Python model.
:param loader_module: The name of the Python module that is used to load the model
from ``data_path``. This module must define a method with the prototype
``_load_pyfunc(data_path)``. If not ``None``, this module and its
dependencies must be included in one of the following locations:
- The MLflow library.
- Package(s) listed in the model's Conda environment, specified by
the ``conda_env`` parameter.
- One or more of the files specified by the ``code_path`` parameter.
:param data_path: Path to a file or directory containing model data.
:param code_path: A list of local filesystem paths to Python file dependencies (or directories
containing file dependencies). These files are *prepended* to the system
path before the model is loaded.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. This decsribes the environment this model should
be run in. If ``python_model`` is not ``None``, the Conda environment must
at least specify the dependencies contained in
:func:`get_default_conda_env()`. If ``None``, the default
:func:`get_default_conda_env()` environment is added to the
model. The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'cloudpickle==0.5.8'
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` configuration to which to add the
**python_function** flavor.
:param python_model: An instance of a subclass of :class:`~PythonModel`. This class is
serialized using the CloudPickle library. Any dependencies of the class
should be included in one of the following locations:
- The MLflow library.
- Package(s) listed in the model's Conda environment, specified by
the ``conda_env`` parameter.
- One or more of the files specified by the ``code_path`` parameter.
Note: If the class is imported from another module, as opposed to being
defined in the ``__main__`` scope, the defining module should also be
included in one of the listed locations.
:param artifacts: A dictionary containing ``<name, artifact_uri>`` entries. Remote artifact URIs
are resolved to absolute filesystem paths, producing a dictionary of
``<name, absolute_path>`` entries. ``python_model`` can reference these
resolved entries as the ``artifacts`` property of the ``context`` parameter
in :func:`PythonModel.load_context() <mlflow.pyfunc.PythonModel.load_context>`
and :func:`PythonModel.predict() <mlflow.pyfunc.PythonModel.predict>`.
For example, consider the following ``artifacts`` dictionary::
{
"my_file": "s3://my-bucket/path/to/my/file"
}
In this case, the ``"my_file"`` artifact is downloaded from S3. The
``python_model`` can then refer to ``"my_file"`` as an absolute filesystem
path via ``context.artifacts["my_file"]``.
If ``None``, no artifacts are added to the model.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
"""
mlflow_model = kwargs.pop('model', mlflow_model)
if len(kwargs) > 0:
raise TypeError(
"save_model() got unexpected keyword arguments: {}".format(kwargs))
if code_path is not None:
if not isinstance(code_path, list):
raise TypeError(
'Argument code_path should be a list, not {}'.format(
type(code_path)))
first_argument_set = {
"loader_module": loader_module,
"data_path": data_path,
}
second_argument_set = {
"artifacts": artifacts,
"python_model": python_model,
}
first_argument_set_specified = any(
[item is not None for item in first_argument_set.values()])
second_argument_set_specified = any(
[item is not None for item in second_argument_set.values()])
if first_argument_set_specified and second_argument_set_specified:
raise MlflowException(message=(
"The following sets of parameters cannot be specified together: {first_set_keys}"
" and {second_set_keys}. All parameters in one set must be `None`. Instead, found"
" the following values: {first_set_entries} and {second_set_entries}"
.format(first_set_keys=first_argument_set.keys(),
second_set_keys=second_argument_set.keys(),
first_set_entries=first_argument_set,
second_set_entries=second_argument_set)),
error_code=INVALID_PARAMETER_VALUE)
elif (loader_module is None) and (python_model is None):
msg = "Either `loader_module` or `python_model` must be specified. A `loader_module` " \
"should be a python module. A `python_model` should be a subclass of PythonModel"
raise MlflowException(message=msg, error_code=INVALID_PARAMETER_VALUE)
if os.path.exists(path):
raise MlflowException(message="Path '{}' already exists".format(path),
error_code=RESOURCE_ALREADY_EXISTS)
os.makedirs(path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
if first_argument_set_specified:
return _save_model_with_loader_module_and_data_path(
path=path,
loader_module=loader_module,
data_path=data_path,
code_paths=code_path,
conda_env=conda_env,
mlflow_model=mlflow_model)
elif second_argument_set_specified:
return kiwi.pyfunc.model._save_model_with_class_artifacts_params(
path=path,
python_model=python_model,
artifacts=artifacts,
conda_env=conda_env,
code_paths=code_path,
mlflow_model=mlflow_model)
def test_schema_enforcement():
class TestModel(object):
@staticmethod
def predict(pdf):
return pdf
m = Model()
input_schema = Schema([
ColSpec("integer", "a"),
ColSpec("long", "b"),
ColSpec("float", "c"),
ColSpec("double", "d"),
ColSpec("boolean", "e"),
ColSpec("string", "g"),
ColSpec("binary", "f"),
])
m.signature = ModelSignature(inputs=input_schema)
pyfunc_model = PyFuncModel(model_meta=m, model_impl=TestModel())
pdf = pd.DataFrame(data=[[1, 2, 3, 4, True, "x",
bytes([1])]],
columns=["b", "d", "a", "c", "e", "g", "f"],
dtype=np.object)
pdf["a"] = pdf["a"].astype(np.int32)
pdf["b"] = pdf["b"].astype(np.int64)
pdf["c"] = pdf["c"].astype(np.float32)
pdf["d"] = pdf["d"].astype(np.float64)
# test that missing column raises
with pytest.raises(MlflowException) as ex:
res = pyfunc_model.predict(pdf[["b", "d", "a", "e", "g", "f"]])
assert "Model input is missing columns" in str(ex)
# test that extra column is ignored
pdf["x"] = 1
# test that columns are reordered, extra column is ignored
res = pyfunc_model.predict(pdf)
assert all((res == pdf[input_schema.column_names()]).all())
expected_types = dict(
zip(input_schema.column_names(), input_schema.pandas_types()))
actual_types = res.dtypes.to_dict()
assert expected_types == actual_types
# Test conversions
# 1. long -> integer raises
pdf["a"] = pdf["a"].astype(np.int64)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
assert "Incompatible input types" in str(ex)
pdf["a"] = pdf["a"].astype(np.int32)
# 2. integer -> long works
pdf["b"] = pdf["b"].astype(np.int32)
res = pyfunc_model.predict(pdf)
assert all((res == pdf[input_schema.column_names()]).all())
assert res.dtypes.to_dict() == expected_types
pdf["b"] = pdf["b"].astype(np.int64)
# 3. double -> float raises
pdf["c"] = pdf["c"].astype(np.float64)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
assert "Incompatible input types" in str(ex)
pdf["c"] = pdf["c"].astype(np.float32)
# 4. float -> double works
pdf["d"] = pdf["d"].astype(np.float32)
res = pyfunc_model.predict(pdf)
assert res.dtypes.to_dict() == expected_types
assert "Incompatible input types" in str(ex)
pdf["d"] = pdf["d"].astype(np.int64)
# 5. floats -> ints raises
pdf["c"] = pdf["c"].astype(np.int32)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
assert "Incompatible input types" in str(ex)
pdf["c"] = pdf["c"].astype(np.float32)
pdf["d"] = pdf["d"].astype(np.int64)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
assert "Incompatible input types" in str(ex)
pdf["d"] = pdf["d"].astype(np.float64)
# 6. ints -> floats raises
pdf["a"] = pdf["a"].astype(np.float32)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
assert "Incompatible input types" in str(ex)
pdf["a"] = pdf["a"].astype(np.int32)
pdf["b"] = pdf["b"].astype(np.float64)
with pytest.raises(MlflowException) as ex:
pyfunc_model.predict(pdf)
pdf["b"] = pdf["b"].astype(np.int64)
assert "Incompatible input types" in str(ex)
# 7. objects work
pdf["b"] = pdf["b"].astype(np.object)
pdf["d"] = pdf["d"].astype(np.object)
pdf["e"] = pdf["e"].astype(np.object)
pdf["f"] = pdf["f"].astype(np.object)
pdf["g"] = pdf["g"].astype(np.object)
res = pyfunc_model.predict(pdf)
assert res.dtypes.to_dict() == expected_types
def save_model(keras_model,
path,
conda_env=None,
mlflow_model=None,
custom_objects=None,
keras_module=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
**kwargs):
"""
Save a Keras model to a path on the local file system.
:param keras_model: Keras model to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decsribes the environment
this model should be run in. At minimum, it should specify the
dependencies contained in :func:`get_default_conda_env()`. If
``None``, the default :func:`get_default_conda_env()` environment is
added to the model. The following is an *example* dictionary
representation of a Conda environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'keras=2.2.4',
'tensorflow=1.8.0'
]
}
:param mlflow_model: MLflow model config this flavor is being added to.
:param custom_objects: A Keras ``custom_objects`` dictionary mapping names (strings) to
custom classes or functions associated with the Keras model. MLflow saves
these custom layers using CloudPickle and restores them automatically
when the model is loaded with :py:func:`mlflow.keras.load_model` and
:py:func:`mlflow.pyfunc.load_model`.
:param keras_module: Keras module to be used to save / load the model
(``keras`` or ``tf.keras``). If not provided, MLflow will
attempt to infer the Keras module based on the given model.
:param kwargs: kwargs to pass to ``keras_model.save`` method.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
.. code-block:: python
:caption: Example
import mlflow
# Build, compile, and train your model
keras_model = ...
keras_model_path = ...
keras_model.compile(optimizer="rmsprop", loss="mse", metrics=["accuracy"])
results = keras_model.fit(
x_train, y_train, epochs=20, batch_size = 128, validation_data=(x_val, y_val))
# Save the model as an MLflow Model
mlflow.keras.save_model(keras_model, keras_model_path)
"""
if keras_module is None:
def _is_plain_keras(model):
try:
# NB: Network is the first parent with save method
import keras.engine.network
return isinstance(model, keras.engine.network.Network)
except ImportError:
return False
def _is_tf_keras(model):
try:
# NB: Network is not exposed in tf.keras, we check for Model instead.
import tensorflow.keras.models
return isinstance(model, tensorflow.keras.models.Model)
except ImportError:
return False
if _is_plain_keras(keras_model):
keras_module = importlib.import_module("keras")
elif _is_tf_keras(keras_model):
keras_module = importlib.import_module("tensorflow.keras")
else:
raise MlflowException(
"Unable to infer keras module from the model, please specify "
"which keras module ('keras' or 'tensorflow.keras') is to be "
"used to save and load the model.")
elif type(keras_module) == str:
keras_module = importlib.import_module(keras_module)
# check if path exists
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
# construct new data folder in existing path
data_subpath = "data"
data_path = os.path.join(path, data_subpath)
os.makedirs(data_path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
# save custom objects if there are custom objects
if custom_objects is not None:
_save_custom_objects(data_path, custom_objects)
# save keras module spec to path/data/keras_module.txt
with open(os.path.join(data_path, _KERAS_MODULE_SPEC_PATH), "w") as f:
f.write(keras_module.__name__)
# save keras model to path/data/model.h5
model_subpath = os.path.join(data_subpath, _MODEL_SAVE_PATH)
model_path = os.path.join(path, model_subpath)
if path.startswith('/dbfs/'):
# The Databricks Filesystem uses a FUSE implementation that does not support
# random writes. It causes an error.
with tempfile.NamedTemporaryFile(suffix='.h5') as f:
keras_model.save(f.name, **kwargs)
f.flush() # force flush the data
shutil.copyfile(src=f.name, dst=model_path)
else:
keras_model.save(model_path, **kwargs)
# update flavor info to mlflow_model
mlflow_model.add_flavor(FLAVOR_NAME,
keras_module=keras_module.__name__,
keras_version=keras_module.__version__,
data=data_subpath)
# save conda.yaml info to path/conda.yml
if conda_env is None:
conda_env = get_default_conda_env(include_cloudpickle=custom_objects
is not None,
keras_module=keras_module)
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, _CONDA_ENV_SUBPATH), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# append loader_module, data and env data to mlflow_model
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.keras",
data=data_subpath,
env=_CONDA_ENV_SUBPATH)
# save mlflow_model to path/MLmodel
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(spacy_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None):
"""
Save a spaCy model to a path on the local file system.
:param spacy_model: spaCy model to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this describes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If ``None``, the default
:func:`get_default_conda_env()` environment is added to the model.
The following is an *example* dictionary representation of a Conda
environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'pip': [
'spacy==2.2.3'
]
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
"""
import spacy
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException(
"Unable to save MLflow model to {path} - path '{path}' "
"already exists".format(path=path))
model_data_subpath = "model.spacy"
model_data_path = os.path.join(path, model_data_subpath)
os.makedirs(model_data_path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
# Save spacy-model
spacy_model.to_disk(path=model_data_path)
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env()
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save the pyfunc flavor if at least one text categorizer in spaCy pipeline
if any([
isinstance(pipe_component[1], spacy.pipeline.TextCategorizer)
for pipe_component in spacy_model.pipeline
]):
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.spacy",
data=model_data_subpath,
env=conda_env_subpath)
else:
_logger.warning(
"Generating only the spacy flavor for the provided spacy model. This means the model "
"can be loaded back via `mlflow.spacy.load_model`, but cannot be loaded back using "
"pyfunc APIs like `mlflow.pyfunc.load_model` or via the `mlflow models` CLI commands. "
"MLflow will only generate the pyfunc flavor for spacy models containing a pipeline "
"component that is an instance of spacy.pipeline.TextCategorizer.")
mlflow_model.add_flavor(FLAVOR_NAME,
spacy_version=spacy.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(tf_saved_model_dir,
tf_meta_graph_tags,
tf_signature_def_key,
path,
mlflow_model=None,
conda_env=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None):
"""
Save a *serialized* collection of TensorFlow graphs and variables as an MLflow model
to a local path. This method operates on TensorFlow variables and graphs that have been
serialized in TensorFlow's ``SavedModel`` format. For more information about ``SavedModel``
format, see the TensorFlow documentation:
https://www.tensorflow.org/guide/saved_model#save_and_restore_models.
:param tf_saved_model_dir: Path to the directory containing serialized TensorFlow variables and
graphs in ``SavedModel`` format.
:param tf_meta_graph_tags: A list of tags identifying the model's metagraph within the
serialized ``SavedModel`` object. For more information, see the
``tags`` parameter of the
``tf.saved_model.builder.savedmodelbuilder`` method.
:param tf_signature_def_key: A string identifying the input/output signature associated with the
model. This is a key within the serialized ``savedmodel``
signature definition mapping. For more information, see the
``signature_def_map`` parameter of the
``tf.saved_model.builder.savedmodelbuilder`` method.
:param path: Local path where the MLflow model is to be saved.
:param mlflow_model: MLflow model configuration to which to add the ``tensorflow`` flavor.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decsribes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If ``None``, the default
:func:`get_default_conda_env()` environment is added to the model. The
following is an *example* dictionary representation of a Conda environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'tensorflow=1.8.0'
]
}
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
"""
_logger.info(
"Validating the specified TensorFlow model by attempting to load it in a new TensorFlow"
" graph...")
_validate_saved_model(tf_saved_model_dir=tf_saved_model_dir,
tf_meta_graph_tags=tf_meta_graph_tags,
tf_signature_def_key=tf_signature_def_key)
_logger.info("Validation succeeded!")
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path),
DIRECTORY_NOT_EMPTY)
os.makedirs(path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
root_relative_path = _copy_file_or_tree(src=tf_saved_model_dir,
dst=path,
dst_dir=None)
model_dir_subpath = "tfmodel"
shutil.move(os.path.join(path, root_relative_path),
os.path.join(path, model_dir_subpath))
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env()
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
mlflow_model.add_flavor(FLAVOR_NAME,
saved_model_dir=model_dir_subpath,
meta_graph_tags=tf_meta_graph_tags,
signature_def_key=tf_signature_def_key)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.tensorflow",
env=conda_env_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(gluon_model, path, mlflow_model=None, conda_env=None,
signature: ModelSignature = None, input_example: ModelInputExample = None):
"""
Save a Gluon model to a path on the local file system.
:param gluon_model: Gluon model to be saved. Must be already hybridized.
:param path: Local path where the model is to be saved.
:param mlflow_model: MLflow model config this flavor is being added to.
:param conda_env: Either a dictionary representation of a Conda environment or
the path to a Conda environment yaml file.
If provided, this decribes the environment this model should be
run in. At minimum, it should specify the dependencies
contained in :func:`get_default_conda_env()`. If ``None``, the default
:func:`mlflow.gluon.get_default_conda_env()` environment is added to
the model. The following is an *example* dictionary representation of a
Conda environment::
{
'name': 'mlflow-env',
'channels': ['defaults'],
'dependencies': [
'python=3.7.0',
'mxnet=1.5.0'
]
}
:param signature: (Experimental) :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
train = df.drop_column("target_label")
predictions = ... # compute model predictions
signature = infer_signature(train, predictions)
:param input_example: (Experimental) Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
.. code-block:: python
:caption: Example
from mxnet.gluon import Trainer
from mxnet.gluon.contrib import estimator
from mxnet.gluon.loss import SoftmaxCrossEntropyLoss
from mxnet.gluon.nn import HybridSequential
from mxnet.metric import Accuracy
import mlflow
# Build, compile, and train your model
gluon_model_path = ...
net = HybridSequential()
with net.name_scope():
...
net.hybridize()
net.collect_params().initialize()
softmax_loss = SoftmaxCrossEntropyLoss()
trainer = Trainer(net.collect_params())
est = estimator.Estimator(net=net, loss=softmax_loss, metrics=Accuracy(), trainer=trainer)
est.fit(train_data=train_data, epochs=100, val_data=validation_data)
# Save the model as an MLflow Model
mlflow.gluon.save_model(net, gluon_model_path)
"""
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
data_subpath = "data"
data_path = os.path.join(path, data_subpath)
os.makedirs(data_path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
# The epoch argument of the export method does not play any role in selecting
# a specific epoch's paramaters, and is there only for display purposes.
gluon_model.export(os.path.join(data_path, _MODEL_SAVE_PATH))
with open(os.path.join(path, "architecture.txt"), "w") as fp:
fp.write(str(gluon_model))
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = get_default_conda_env()
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
pyfunc.add_to_model(mlflow_model, loader_module="mlflow.gluon", env=conda_env_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
