def save_model(cb_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
**kwargs):
"""
Save a CatBoost model to a path on the local file system.
:param cb_model: CatBoost model (an instance of `CatBoost`_, `CatBoostClassifier`_,
or `CatBoostRegressor`_) 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': [
'catboost==0.19.1'
]
]
}
: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.
:param kwargs: kwargs to pass to `CatBoost.save_model`_ method.
"""
import catboost as cb
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
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_path = os.path.join(path, _MODEL_BINARY_FILE_NAME)
cb_model.save_model(model_data_path, **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)
model_bin_kwargs = {_MODEL_BINARY_KEY: _MODEL_BINARY_FILE_NAME}
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.catboost",
env=conda_env_subpath,
**model_bin_kwargs,
)
flavor_conf = {
_MODEL_TYPE_KEY: cb_model.__class__.__name__,
_SAVE_FORMAT_KEY: kwargs.get("format", "cbm"),
**model_bin_kwargs,
}
mlflow_model.add_flavor(
FLAVOR_NAME,
catboost_version=cb.__version__,
**flavor_conf,
)
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(
lgb_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
):
"""
Save a LightGBM model to a path on the local file system.
:param lgb_model: LightGBM model (an instance of `lightgbm.Booster`_) to be saved.
Note that models that implement the `scikit-learn API`_ are not supported.
: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': [
'lightgbm==2.3.0'
]
]
}
: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 lightgbm as lgb
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
model_data_subpath = "model.lgb"
model_data_path = os.path.join(path, model_data_subpath)
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)
# Save a LightGBM model
lgb_model.save_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.lightgbm",
data=model_data_subpath,
env=conda_env_subpath,
)
mlflow_model.add_flavor(FLAVOR_NAME, lgb_version=lgb.__version__, data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(
pd_model,
path,
training=False,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a paddle model to a path on the local file system. Produces an MLflow Model
containing the following flavors:
- :py:mod:`mlflow.paddle`
- :py:mod:`mlflow.pyfunc`. NOTE: This flavor is only included for paddle models
that define `predict()`, since `predict()` is required for pyfunc model inference.
:param pd_model: paddle model to be saved.
:param path: Local path where the model is to be saved.
:param training: Only valid when saving a model trained using the PaddlePaddle high level API.
If set to True, the saved model supports both re-training and
inference. If set to False, it only supports inference.
:param conda_env: {{ conda_env }}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
.. code-block:: python
:caption: Example
import mlflow.paddle
import paddle
from paddle.nn import Linear
import paddle.nn.functional as F
import numpy as np
import os
import random
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
def load_data():
# dataset on boston housing prediction
X, y = load_boston(return_X_y=True)
min_max_scaler = preprocessing.MinMaxScaler()
X_min_max = min_max_scaler.fit_transform(X)
X_normalized = preprocessing.scale(X_min_max, with_std=False)
X_train, X_test, y_train, y_test = train_test_split(
X_normalized, y, test_size=0.2, random_state=42)
y_train = y_train.reshape(-1, 1)
y_test = y_test.reshape(-1, 1)
return np.concatenate(
(X_train, y_train), axis=1),np.concatenate((X_test, y_test), axis=1
)
class Regressor(paddle.nn.Layer):
def __init__(self):
super(Regressor, self).__init__()
self.fc = Linear(in_features=13, out_features=1)
@paddle.jit.to_static
def forward(self, inputs):
x = self.fc(inputs)
return x
model = Regressor()
model.train()
training_data, test_data = load_data()
opt = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())
EPOCH_NUM = 10
BATCH_SIZE = 10
for epoch_id in range(EPOCH_NUM):
np.random.shuffle(training_data)
mini_batches = [training_data[k : k + BATCH_SIZE]
for k in range(0, len(training_data), BATCH_SIZE)]
for iter_id, mini_batch in enumerate(mini_batches):
x = np.array(mini_batch[:, :-1]).astype('float32')
y = np.array(mini_batch[:, -1:]).astype('float32')
house_features = paddle.to_tensor(x)
prices = paddle.to_tensor(y)
predicts = model(house_features)
loss = F.square_error_cost(predicts, label=prices)
avg_loss = paddle.mean(loss)
if iter_id%20==0:
print("epoch: {}, iter: {}, loss is: {}".format(
epoch_id, iter_id, avg_loss.numpy()))
avg_loss.backward()
opt.step()
opt.clear_grad()
mlflow.log_param('learning_rate', 0.01)
mlflow.paddle.log_model(model, "model")
sk_path_dir = './test-out'
mlflow.paddle.save_model(model, sk_path_dir)
print("Model saved in run %s" % mlflow.active_run().info.run_uuid)
"""
import paddle
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
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"
output_path = os.path.join(path, model_data_subpath)
if isinstance(pd_model, paddle.Model):
pd_model.save(output_path, training=training)
else:
paddle.jit.save(pd_model, output_path)
# `PyFuncModel` only works for paddle models that define `predict()`.
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.paddle",
model_path=model_data_subpath,
env=_CONDA_ENV_FILE_NAME,
)
mlflow_model.add_flavor(
FLAVOR_NAME,
pickled_model=model_data_subpath,
paddle_version=paddle.__version__,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
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_explainer(
explainer,
path,
serialize_model_using_mlflow=True,
conda_env=None,
code_paths=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a SHAP explainer to a path on the local file system. Produces an MLflow Model
containing the following flavors:
- :py:mod:`mlflow.shap`
- :py:mod:`mlflow.pyfunc`
:param explainer: SHAP explainer to be saved.
:param path: Local path where the explainer is to be saved.
:param serialize_model_using_mlflow: When set to True, MLflow will extract the underlying
model and serialize it as an MLmodel, otherwise it
uses SHAP's internal serialization. Defaults to True.
Currently MLflow serialization is only supported for
models of 'sklearn' or 'pytorch' flavors.
:param conda_env: {{ conda_env }}
: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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import shap
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
if os.path.exists(path):
raise MlflowException(
message="Path '{}' already exists".format(path),
error_code=RESOURCE_ALREADY_EXISTS,
)
os.makedirs(path)
code_dir_subpath = _validate_and_copy_code_paths(code_paths, 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)
underlying_model_flavor = None
underlying_model_path = None
serializable_by_mlflow = False
# saving the underlying model if required
if serialize_model_using_mlflow:
underlying_model_flavor = get_underlying_model_flavor(explainer.model)
if underlying_model_flavor != _UNKNOWN_MODEL_FLAVOR:
serializable_by_mlflow = True # prevents SHAP from serializing the underlying model
underlying_model_path = os.path.join(path,
_UNDERLYING_MODEL_SUBPATH)
else:
warnings.warn(
"Unable to serialize underlying model using MLflow, will use SHAP serialization"
)
if underlying_model_flavor == mlflow.sklearn.FLAVOR_NAME:
mlflow.sklearn.save_model(explainer.model.inner_model.__self__,
underlying_model_path)
elif underlying_model_flavor == mlflow.pytorch.FLAVOR_NAME:
mlflow.pytorch.save_model(explainer.model.inner_model,
underlying_model_path)
# saving the explainer object
explainer_data_subpath = "explainer.shap"
explainer_output_path = os.path.join(path, explainer_data_subpath)
with open(explainer_output_path, "wb") as explainer_output_file_handle:
if serialize_model_using_mlflow and serializable_by_mlflow:
explainer.save(explainer_output_file_handle, model_saver=False)
else:
explainer.save(explainer_output_file_handle)
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.shap",
model_path=explainer_data_subpath,
underlying_model_flavor=underlying_model_flavor,
env=_CONDA_ENV_FILE_NAME,
code=code_dir_subpath,
)
mlflow_model.add_flavor(
FLAVOR_NAME,
shap_version=shap.__version__,
serialized_explainer=explainer_data_subpath,
underlying_model_flavor=underlying_model_flavor,
code=code_dir_subpath,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
if underlying_model_path is not None:
underlying_model_conda_env = _get_conda_env_for_underlying_model(
underlying_model_path)
conda_env = _merge_environments(conda_env, underlying_model_conda_env)
pip_requirements = _get_pip_deps(conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
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__)
# By default, Keras uses the SavedModel format -- specified by "tf"
# However, we choose to align with prior default of mlflow, HDF5
save_format = kwargs.get("save_format", "h5")
# save keras save_format to path/data/save_format.txt
with open(os.path.join(data_path, _KERAS_SAVE_FORMAT_PATH), "w") as f:
f.write(save_format)
# save keras model
# To maintain prior behavior, when the format is HDF5, we save
# with the h5 file extension. Otherwise, model_path is a directory
# where the saved_model.pb will be stored (for SavedModel format)
file_extension = ".h5" if save_format == "h5" else ""
model_subpath = os.path.join(data_subpath, _MODEL_SAVE_PATH)
model_path = os.path.join(path, model_subpath) + file_extension
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__,
save_format=save_format,
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(
h2o_model,
path,
conda_env=None,
mlflow_model=None,
settings=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save an H2O model to a path on the local file system.
:param h2o_model: H2O model to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: {{ conda_env }}
:param signature: :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: 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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
"""
import h2o
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise Exception("Path '{}' already exists".format(path))
model_data_subpath = "model.h2o"
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 h2o-model
if hasattr(h2o, "download_model"):
h2o_save_location = h2o.download_model(model=h2o_model,
path=model_data_path)
else:
warnings.warn(
"If your cluster is remote, H2O may not store the model correctly. "
"Please upgrade H2O version to a newer version")
h2o_save_location = h2o.save_model(model=h2o_model,
path=model_data_path,
force=True)
model_file = os.path.basename(h2o_save_location)
# Save h2o-settings
if settings is None:
settings = {}
settings["full_file"] = h2o_save_location
settings["model_file"] = model_file
settings["model_dir"] = model_data_path
with open(os.path.join(model_data_path, "h2o.yaml"), "w") as settings_file:
yaml.safe_dump(settings, stream=settings_file)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.h2o",
data=model_data_subpath,
env=_CONDA_ENV_FILE_NAME)
mlflow_model.add_flavor(FLAVOR_NAME,
h2o_version=h2o.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
def save_model(
keras_model,
path,
conda_env=None,
code_paths=None,
mlflow_model=None,
custom_objects=None,
keras_module=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=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: {{ conda_env }}
: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 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: :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: 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 can be a Pandas DataFrame where the given
example will be serialized to json using the Pandas split-oriented
format, or a numpy array where the example will be serialized to json
by converting it to a list. Bytes are base64-encoded.
:param pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
.. 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)
"""
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
if keras_module is None:
def _is_plain_keras(model):
try:
import keras
# 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)
_validate_and_prepare_target_save_path(path)
# construct new data folder in existing path
data_subpath = "data"
data_path = os.path.join(path, data_subpath)
os.makedirs(data_path)
code_dir_subpath = _validate_and_copy_code_paths(code_paths, 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__)
# Use the SavedModel format if `save_format` is unspecified
save_format = kwargs.get("save_format", "tf")
# save keras save_format to path/data/save_format.txt
with open(os.path.join(data_path, _KERAS_SAVE_FORMAT_PATH), "w") as f:
f.write(save_format)
# save keras model
# To maintain prior behavior, when the format is HDF5, we save
# with the h5 file extension. Otherwise, model_path is a directory
# where the saved_model.pb will be stored (for SavedModel format)
file_extension = ".h5" if save_format == "h5" else ""
model_subpath = os.path.join(data_subpath, _MODEL_SAVE_PATH)
model_path = os.path.join(path, model_subpath) + file_extension
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__,
save_format=save_format,
data=data_subpath,
code=code_dir_subpath,
)
# 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_FILE_NAME,
code=code_dir_subpath,
)
# save mlflow_model to path/MLmodel
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
include_cloudpickle = custom_objects is not None
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements(
include_cloudpickle, keras_module)
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path, FLAVOR_NAME, fallback=default_reqs)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
def save_model(
spacy_model,
path,
conda_env=None,
code_paths=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=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: {{ conda_env }}
: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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import spacy
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
_validate_and_prepare_target_save_path(path)
model_data_subpath = "model.spacy"
model_data_path = os.path.join(path, model_data_subpath)
os.makedirs(model_data_path)
code_dir_subpath = _validate_and_copy_code_paths(code_paths, 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)
# 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_FILE_NAME,
code=code_dir_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,
code=code_dir_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
model_data_path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
_PythonEnv.current().to_yaml(os.path.join(path, _PYTHON_ENV_FILE_NAME))
def save_model(
h2o_model,
path,
conda_env=None,
mlflow_model=None,
settings=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save an H2O model to a path on the local file system.
:param h2o_model: H2O 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': [
'h2o==3.20.0.8'
]
]
}
: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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
"""
import h2o
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise Exception("Path '{}' already exists".format(path))
model_data_subpath = "model.h2o"
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 h2o-model
if hasattr(h2o, "download_model"):
h2o_save_location = h2o.download_model(model=h2o_model,
path=model_data_path)
else:
warnings.warn(
"If your cluster is remote, H2O may not store the model correctly. "
"Please upgrade H2O version to a newer version")
h2o_save_location = h2o.save_model(model=h2o_model,
path=model_data_path,
force=True)
model_file = os.path.basename(h2o_save_location)
# Save h2o-settings
if settings is None:
settings = {}
settings["full_file"] = h2o_save_location
settings["model_file"] = model_file
settings["model_dir"] = model_data_path
with open(os.path.join(model_data_path, "h2o.yaml"), "w") as settings_file:
yaml.safe_dump(settings, stream=settings_file)
conda_env, pip_requirements, pip_constraints = (_process_pip_requirements(
get_default_pip_requirements(),
pip_requirements,
extra_pip_requirements,
) if conda_env is None else _process_conda_env(conda_env))
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.h2o",
data=model_data_subpath,
env=_CONDA_ENV_FILE_NAME)
mlflow_model.add_flavor(FLAVOR_NAME,
h2o_version=h2o.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(
lgb_model,
path,
conda_env=None,
code_paths=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a LightGBM model to a path on the local file system.
:param lgb_model: LightGBM model (an instance of `lightgbm.Booster`_) or
models that implement the `scikit-learn API`_ to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: {{ conda_env }}
: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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import lightgbm as lgb
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
_validate_and_prepare_target_save_path(path)
model_data_subpath = "model.lgb" if isinstance(
lgb_model, lgb.Booster) else "model.pkl"
model_data_path = os.path.join(path, model_data_subpath)
code_dir_subpath = _validate_and_copy_code_paths(code_paths, 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 a LightGBM model
_save_model(lgb_model, model_data_path)
lgb_model_class = _get_fully_qualified_class_name(lgb_model)
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.lightgbm",
data=model_data_subpath,
env=_CONDA_ENV_FILE_NAME,
code=code_dir_subpath,
)
mlflow_model.add_flavor(
FLAVOR_NAME,
lgb_version=lgb.__version__,
data=model_data_subpath,
model_class=lgb_model_class,
code=code_dir_subpath,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements(
include_cloudpickle=not isinstance(lgb_model, lgb.Booster))
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
_PythonEnv.current().to_yaml(os.path.join(path, _PYTHON_ENV_FILE_NAME))
def save_model(
fonduer_model: FonduerModel,
path: str,
conn_string: str,
mlflow_model: Model = Model(),
code_paths: Optional[List[str]] = None,
parallel: Optional[int] = 1,
model_type: Optional[str] = "discriminative",
labeler: Optional[Labeler] = None,
gen_models: Optional[List[LabelModel]] = None,
featurizer: Optional[Featurizer] = None,
disc_model: Optional[Classifier] = None,
) -> None:
"""Save a custom MLflow model to a path on the local file system.
:param fonduer_model: the model to be saved.
:param path: the path on the local file system.
:param conn_string: the connection string.
:param mlflow_model: model configuration.
: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 parallel: the number of parallelism.
:param model_type: the model type, either "discriminative" or "generative", defaults to "discriminative".
:param labeler: a labeler, defaults to None.
:param gen_models: a list of generative models, defaults to None.
:param featurizer: a featurizer, defaults to None.
:param disc_model: a discriminative model, defaults to None.
"""
os.makedirs(path)
model_code_path = os.path.join(path, pyfunc.CODE)
os.makedirs(model_code_path)
with open(os.path.join(path, "fonduer_model.pkl"), "wb") as f:
pickle.dump(fonduer_model, f)
if model_type == "discriminative":
key_names = [key.name for key in featurizer.get_keys()]
with open(os.path.join(path, "feature_keys.pkl"), "wb") as f:
pickle.dump(key_names, f)
disc_model.save(model_file="best_model.pt", save_dir=path)
else:
for candidate_class, gen_model in zip(labeler.candidate_classes,
gen_models):
gen_model.save(
os.path.join(path, candidate_class.__name__ + ".pkl"))
key_names = [key.name for key in labeler.get_keys()]
with open(os.path.join(path, "labeler_keys.pkl"), "wb") as f:
pickle.dump(key_names, f)
_copy_file_or_tree(src=__file__, dst=model_code_path)
if code_paths is not None:
for code_path in code_paths:
_copy_file_or_tree(src=code_path, dst=model_code_path)
mlflow_model.add_flavor(
pyfunc.FLAVOR_NAME,
code=pyfunc.CODE,
loader_module=__name__,
conn_string=conn_string,
parallel=parallel,
model_type=model_type,
)
mlflow_model.save(os.path.join(path, "MLmodel"))
def save_model(
diviner_model,
path,
conda_env=None,
code_paths=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a ``Diviner`` model object to a path on the local file system.
:param diviner_model: ``Diviner`` model that has been ``fit`` on a grouped temporal
``DataFrame``.
:param path: Local path destination for the serialized model is to be saved.
:param conda_env: {{ conda_env }}
: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 mlflow_model: :py:mod:`mlflow.models.Model` the flavor that this model is being added to.
:param signature: :py:class:`Model Signature <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:: py
from mlflow.models.signature import infer_signature
model = diviner.GroupedProphet().fit(data, ("region", "state"))
predictions = model.predict(prediction_config)
signature = infer_signature(data, predictions)
:param input_example: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import diviner
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = pathlib.Path(path).absolute()
_validate_and_prepare_target_save_path(str(path))
# NB: When moving to native pathlib implementations, path encoding as string will not be needed.
code_dir_subpath = _validate_and_copy_code_paths(code_paths, str(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, str(path))
diviner_model.save(str(path.joinpath(_MODEL_BINARY_FILE_NAME)))
model_bin_kwargs = {_MODEL_BINARY_KEY: _MODEL_BINARY_FILE_NAME}
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.diviner",
env=_CONDA_ENV_FILE_NAME,
code=code_dir_subpath,
**model_bin_kwargs,
)
flavor_conf = {
_MODEL_TYPE_KEY: diviner_model.__class__.__name__,
**model_bin_kwargs
}
mlflow_model.add_flavor(FLAVOR_NAME,
diviner_version=diviner.__version__,
code=code_dir_subpath,
**flavor_conf)
mlflow_model.save(str(path.joinpath(MLMODEL_FILE_NAME)))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
inferred_reqs = mlflow.models.infer_pip_requirements(
str(path), FLAVOR_NAME, fallback=default_reqs)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs, pip_requirements, extra_pip_requirements)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with path.joinpath(_CONDA_ENV_FILE_NAME).open("w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
if pip_constraints:
write_to(str(path.joinpath(_CONSTRAINTS_FILE_NAME)),
"\n".join(pip_constraints))
write_to(str(path.joinpath(_REQUIREMENTS_FILE_NAME)),
"\n".join(pip_requirements))
def save_model(
pr_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a Prophet model to a path on the local file system.
:param pr_model: Prophet model (an instance of Prophet() forecaster that has been fit
on a temporal series.
:param path: Local path where the serialized model (as JSON) is to be saved.
:param conda_env: {{ conda_env }}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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
model = Prophet().fit(df)
train = model.history
predictions = model.predict(model.make_future_dataframe(30))
signature = infer_signature(train, predictions)
:param input_example: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import prophet
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException(f"Path '{path}' 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_path = os.path.join(path, _MODEL_BINARY_FILE_NAME)
_save_model(pr_model, model_data_path)
model_bin_kwargs = {_MODEL_BINARY_KEY: _MODEL_BINARY_FILE_NAME}
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.prophet",
env=_CONDA_ENV_FILE_NAME,
**model_bin_kwargs)
flavor_conf = {
_MODEL_TYPE_KEY: pr_model.__class__.__name__,
**model_bin_kwargs,
}
mlflow_model.add_flavor(
FLAVOR_NAME,
prophet_version=prophet.__version__,
**flavor_conf,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
# cannot use inferred requirements due to prophet's build process
# as the package installation of pystan requires Cython to be present
# in the path. Prophet's installation itself requires imports of
# existing libraries, preventing the execution of a batched pip install
# and instead using a a strictly defined list of dependencies.
# NOTE: if Prophet .whl build architecture is changed, this should be
# modified to a standard inferred approach.
default_reqs = get_default_pip_requirements()
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
def save_model(fastai_learner,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
**kwargs):
"""
Save a fastai Learner to a path on the local file system.
:param fastai_learner: fastai Learner to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: {{ conda_env }}
:param mlflow_model: MLflow model config this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
:param kwargs: kwargs to pass to ``Learner.save`` method.
.. code-block:: python
:caption: Example
import os
import mlflow.fastai
# Create a fastai Learner model
model = ...
# Start MLflow session and save model to current working directory
with mlflow.start_run():
model.fit(epochs, learning_rate)
mlflow.fastai.save_model(model, 'model')
# Load saved model for inference
model_uri = "{}/{}".format(os.getcwd(), 'model')
loaded_model = mlflow.fastai.load_model(model_uri)
results = loaded_model.predict(predict_data)
"""
import fastai
from pathlib import Path
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
model_data_subpath = "model.fastai"
model_data_path = os.path.join(path, model_data_subpath)
model_data_path = Path(model_data_path)
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)
# Save an Learner
fastai_learner.export(model_data_path, **kwargs)
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.fastai",
data=model_data_subpath,
env=_CONDA_ENV_FILE_NAME,
)
mlflow_model.add_flavor(FLAVOR_NAME,
fastai_version=fastai.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
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,
requirements_file=None,
extra_files=None,
**kwargs
):
"""
Save a PyTorch model to a path on the local file system.
:param pytorch_model: PyTorch model to be saved. Can be either an eager model (subclass of
``torch.nn.Module``) or scripted model prepared via ``torch.jit.script``
or ``torch.jit.trace``.
The model accept a single ``torch.FloatTensor`` as
input and produce a single output tensor.
If saving an eager model, 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 can be a Pandas DataFrame where the given
example will be serialized to json using the Pandas split-oriented
format, or a numpy array where the example will be serialized to json
by converting it to a list. Bytes are base64-encoded.
:param requirements_file: A string containing the path to requirements file. Remote URIs
are resolved to absolute filesystem paths.
For example, consider the following ``requirements_file`` string -
requirements_file = "s3://my-bucket/path/to/my_file"
In this case, the ``"my_file"`` requirements file is downloaded from S3.
If ``None``, no requirements file is added to the model.
:param extra_files: A list containing the paths to corresponding extra files. Remote URIs
are resolved to absolute filesystem paths.
For example, consider the following ``extra_files`` list -
extra_files = ["s3://my-bucket/path/to/my_file1",
"s3://my-bucket/path/to/my_file2"]
In this case, the ``"my_file1 & my_file2"`` extra file is downloaded from S3.
If ``None``, no extra files are added to the model.
:param kwargs: kwargs to pass to ``torch.save`` method.
.. code-block:: python
:caption: Example
import os
import torch
import mlflow.pytorch
# Class defined here
class LinearNNModel(torch.nn.Module):
...
# Initialize our model, criterion and optimizer
...
# Training loop
...
# Save PyTorch models to current working directory
with mlflow.start_run() as run:
mlflow.pytorch.save_model(model, "model")
# Convert to a scripted model and save it
scripted_pytorch_model = torch.jit.script(model)
mlflow.pytorch.save_model(scripted_pytorch_model, "scripted_model")
# Load each saved model for inference
for model_path in ["model", "scripted_model"]:
model_uri = "{}/{}".format(os.getcwd(), model_path)
loaded_model = mlflow.pytorch.load_model(model_uri)
print("Loaded {}:".format(model_path))
for x in [6.0, 8.0, 12.0, 30.0]:
X = torch.Tensor([[x]])
y_pred = loaded_model(X)
print("predict X: {}, y_pred: {:.2f}".format(x, y_pred.data.item()))
print("--")
.. code-block:: text
:caption: Output
Loaded model:
predict X: 6.0, y_pred: 11.90
predict X: 8.0, y_pred: 15.92
predict X: 12.0, y_pred: 23.96
predict X: 30.0, y_pred: 60.13
--
Loaded scripted_model:
predict X: 6.0, y_pred: 11.90
predict X: 8.0, y_pred: 15.92
predict X: 12.0, y_pred: 23.96
predict X: 30.0, y_pred: 60.13
"""
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)
if isinstance(pytorch_model, torch.jit.ScriptModule):
torch.jit.ScriptModule.save(pytorch_model, model_path)
else:
torch.save(pytorch_model, model_path, pickle_module=pickle_module, **kwargs)
torchserve_artifacts_config = {}
if requirements_file:
if not isinstance(requirements_file, str):
raise TypeError("Path to requirements file should be a string")
with TempDir() as tmp_requirements_dir:
_download_artifact_from_uri(
artifact_uri=requirements_file, output_path=tmp_requirements_dir.path()
)
rel_path = os.path.basename(requirements_file)
torchserve_artifacts_config[_REQUIREMENTS_FILE_KEY] = {"path": rel_path}
shutil.move(tmp_requirements_dir.path(rel_path), path)
if extra_files:
torchserve_artifacts_config[_EXTRA_FILES_KEY] = []
if not isinstance(extra_files, list):
raise TypeError("Extra files argument should be a list")
with TempDir() as tmp_extra_files_dir:
for extra_file in extra_files:
_download_artifact_from_uri(
artifact_uri=extra_file, output_path=tmp_extra_files_dir.path()
)
rel_path = posixpath.join(_EXTRA_FILES_KEY, os.path.basename(extra_file),)
torchserve_artifacts_config[_EXTRA_FILES_KEY].append({"path": rel_path})
shutil.move(
tmp_extra_files_dir.path(), posixpath.join(path, _EXTRA_FILES_KEY),
)
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__,
**torchserve_artifacts_config,
)
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(
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,
pip_requirements=None,
extra_pip_requirements=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: {{ conda_env }}
:param signature: :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: 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 can be a Pandas DataFrame where the given
example will be serialized to json using the Pandas split-oriented
format, or a numpy array where the example will be serialized to json
by converting it to a list. Bytes are base64-encoded.
:param pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
_validate_env_arguments(conda_env, pip_requirements, extra_pip_requirements)
_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"
model_dir_path = os.path.join(path, model_dir_subpath)
shutil.move(os.path.join(path, root_relative_path), model_dir_path)
flavor_conf = dict(
saved_model_dir=model_dir_subpath,
meta_graph_tags=tf_meta_graph_tags,
signature_def_key=tf_signature_def_key,
)
mlflow_model.add_flavor(FLAVOR_NAME, **flavor_conf)
pyfunc.add_to_model(mlflow_model, loader_module="mlflow.tensorflow", env=_CONDA_ENV_FILE_NAME)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME), "\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME), "\n".join(pip_requirements))
def _save_model_with_class_artifacts_params(path,
python_model,
artifacts=None,
conda_env=None,
code_paths=None,
mlflow_model=None):
"""
:param path: The path to which to save the Python model.
:param python_model: An instance of a subclass of :class:`~PythonModel`. ``python_model``
defines how the model loads artifacts and how it performs inference.
: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``
attribute. If ``None``, no artifacts are added to the model.
: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.
: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 before the model is loaded.
:param mlflow_model: The model configuration to which to add the ``mlflow.pyfunc`` flavor.
"""
if mlflow_model is None:
mlflow_model = Model()
custom_model_config_kwargs = {
CONFIG_KEY_CLOUDPICKLE_VERSION: cloudpickle.__version__,
}
if isinstance(python_model, PythonModel):
saved_python_model_subpath = "python_model.pkl"
with open(os.path.join(path, saved_python_model_subpath), "wb") as out:
cloudpickle.dump(python_model, out)
custom_model_config_kwargs[
CONFIG_KEY_PYTHON_MODEL] = saved_python_model_subpath
else:
raise MlflowException(
message=
("`python_model` must be a subclass of `PythonModel`. Instead, found an"
" object of type: {python_model_type}".format(
python_model_type=type(python_model))),
error_code=INVALID_PARAMETER_VALUE,
)
if artifacts:
saved_artifacts_config = {}
with TempDir() as tmp_artifacts_dir:
tmp_artifacts_config = {}
saved_artifacts_dir_subpath = "artifacts"
for artifact_name, artifact_uri in artifacts.items():
tmp_artifact_path = _download_artifact_from_uri(
artifact_uri=artifact_uri,
output_path=tmp_artifacts_dir.path())
tmp_artifacts_config[artifact_name] = tmp_artifact_path
saved_artifact_subpath = posixpath.join(
saved_artifacts_dir_subpath,
os.path.relpath(path=tmp_artifact_path,
start=tmp_artifacts_dir.path()),
)
saved_artifacts_config[artifact_name] = {
CONFIG_KEY_ARTIFACT_RELATIVE_PATH: saved_artifact_subpath,
CONFIG_KEY_ARTIFACT_URI: artifact_uri,
}
shutil.move(tmp_artifacts_dir.path(),
os.path.join(path, saved_artifacts_dir_subpath))
custom_model_config_kwargs[
CONFIG_KEY_ARTIFACTS] = saved_artifacts_config
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)
_log_pip_requirements(conda_env, path)
saved_code_subpath = None
if code_paths is not None:
saved_code_subpath = "code"
for code_path in code_paths:
_copy_file_or_tree(src=code_path,
dst=path,
dst_dir=saved_code_subpath)
mlflow.pyfunc.add_to_model(model=mlflow_model,
loader_module=__name__,
code=saved_code_subpath,
env=conda_env_subpath,
**custom_model_config_kwargs)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_explainer(
explainer,
path,
serialize_model_using_mlflow=True,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
):
"""
Save a SHAP explainer to a path on the local file system. Produces an MLflow Model
containing the following flavors:
- :py:mod:`mlflow.shap`
- :py:mod:`mlflow.pyfunc`
:param explainer: SHAP explainer to be saved.
:param path: Local path where the explainer is to be saved.
:param serialize_model_using_mlflow: When set to True, MLflow will extract the underlying
model and serialize it as an MLmodel, otherwise it
uses SHAP's internal serialization. Defaults to True.
Currently MLflow serialization is only supported for
models of 'sklearn' or 'pytorch' flavors.
: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=3.6.0',
'shap=0.37.0'
]
}
: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 shap
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)
underlying_model_flavor = None
underlying_model_path = None
serializable_by_mlflow = False
# saving the underlying model if required
if serialize_model_using_mlflow:
underlying_model_flavor = get_underlying_model_flavor(explainer.model)
if underlying_model_flavor != _UNKNOWN_MODEL_FLAVOR:
serializable_by_mlflow = True # prevents SHAP from serializing the underlying model
underlying_model_path = os.path.join(path,
_UNDERLYING_MODEL_SUBPATH)
else:
warnings.warn(
"Unable to serialize underlying model using MLflow, will use SHAP serialization"
)
if underlying_model_flavor == mlflow.sklearn.FLAVOR_NAME:
mlflow.sklearn.save_model(explainer.model.inner_model.__self__,
underlying_model_path)
elif underlying_model_flavor == mlflow.pytorch.FLAVOR_NAME:
mlflow.pytorch.save_model(explainer.model.inner_model,
underlying_model_path)
# saving the explainer object
explainer_data_subpath = "explainer.shap"
explainer_output_path = os.path.join(path, explainer_data_subpath)
with open(explainer_output_path, "wb") as explainer_output_file_handle:
if serialize_model_using_mlflow and serializable_by_mlflow:
explainer.save(explainer_output_file_handle, model_saver=False)
else:
explainer.save(explainer_output_file_handle)
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)
# merging the conda environment generated by serializing the underlying model
if underlying_model_path is not None:
underlying_model_conda_path = os.path.join(underlying_model_path,
"conda.yaml")
with open(underlying_model_conda_path,
"r") as underlying_model_conda_file:
underlying_model_conda_env = yaml.safe_load(
underlying_model_conda_file)
conda_env = _merge_environments(conda_env, underlying_model_conda_env)
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.shap",
model_path=explainer_data_subpath,
underlying_model_flavor=underlying_model_flavor,
env=conda_env_subpath,
)
mlflow_model.add_flavor(
FLAVOR_NAME,
shap_version=shap.__version__,
serialized_explainer=explainer_data_subpath,
underlying_model_flavor=underlying_model_flavor,
)
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,
pip_requirements=None,
extra_pip_requirements=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: {{ conda_env }}
:param signature: :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: 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 can be a Pandas DataFrame where the given
example will be serialized to json using the Pandas split-oriented
format, or a numpy array where the example will be serialized to json
by converting it to a list. Bytes are base64-encoded.
:param pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
.. 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)
"""
import mxnet as mx
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
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 parameters, and is there only for display purposes.
gluon_model.export(os.path.join(data_path, _MODEL_SAVE_PATH))
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.gluon",
env=_CONDA_ENV_FILE_NAME)
mlflow_model.add_flavor(FLAVOR_NAME, mxnet_version=mx.__version__)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
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
n.model_uuid = m.model_uuid
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(
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))
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(
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)
# `PyFuncModel` only works for sklearn models that define `predict()`.
if hasattr(sk_model, "predict"):
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(
statsmodels_model,
path,
conda_env=None,
mlflow_model=None,
remove_data: bool = False,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
):
"""
Save a statsmodels model to a path on the local file system.
:param statsmodels_model: statsmodels model (an instance of `statsmodels.base.model.Results`_)
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',
'statsmodels=0.11.1'
]
}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param remove_data: bool. If False (default), then the instance is pickled without changes.
If True, then all arrays with length nobs are set to None before
pickling. See the remove_data method.
In some cases not all arrays will be set to None.
: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 statsmodels
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
model_data_path = os.path.join(path, STATSMODELS_DATA_SUBPATH)
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)
# Save a statsmodels model
statsmodels_model.save(model_data_path, remove_data)
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.statsmodels",
data=STATSMODELS_DATA_SUBPATH,
env=conda_env_subpath,
)
mlflow_model.add_flavor(
FLAVOR_NAME, statsmodels_version=statsmodels.__version__, data=STATSMODELS_DATA_SUBPATH
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(
pmdarima_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a pmdarima ``ARIMA`` model or ``Pipeline`` object to a path on the local file system.
:param pmdarima_model: pmdarima ``ARIMA`` or ``Pipeline`` model that has been ``fit`` on a
temporal series.
:param path: Local path destination for the serialized model (in pickle format) is to be saved.
:param conda_env: {{ conda_env }}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :py:class:`Model Signature <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:: py
from mlflow.models.signature import infer_signature
model = pmdarima.auto_arima(data)
predictions = model.predict(n_periods=30, return_conf_int=False)
signature = infer_signature(data, predictions)
.. Warning:: if utilizing confidence interval generation in the ``predict``
method of a ``pmdarima`` model (``return_conf_int=True``), the signature
will not be inferred due to the complex tuple return type when using the
native ``ARIMA.predict()`` API. ``infer_schema`` will function correctly
if using the ``pyfunc`` flavor of the model, though.
:param input_example: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import pmdarima
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException(f"Path '{path}' 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_path = os.path.join(path, _MODEL_BINARY_FILE_NAME)
_save_model(pmdarima_model, model_data_path)
model_bin_kwargs = {_MODEL_BINARY_KEY: _MODEL_BINARY_FILE_NAME}
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.pmdarima",
env=_CONDA_ENV_FILE_NAME,
**model_bin_kwargs)
flavor_conf = {
_MODEL_TYPE_KEY: pmdarima_model.__class__.__name__,
**model_bin_kwargs,
}
mlflow_model.add_flavor(FLAVOR_NAME,
pmdarima_version=pmdarima.__version__,
**flavor_conf)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
inferred_reqs = mlflow.models.infer_pip_requirements(
path, FLAVOR_NAME, fallback=default_reqs)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs, pip_requirements, extra_pip_requirements)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
def save_model(fastai_learner,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
**kwargs):
"""
Save a fastai Learner to a path on the local file system.
:param fastai_learner: fastai Learner 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',
'fastai=1.0.60',
]
}
:param mlflow_model: MLflow model config 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.
:param kwargs: kwargs to pass to ``Learner.save`` method.
.. code-block:: python
:caption: Example
import os
import mlflow.fastai
# Create a fastai Learner model
model = ...
# Start MLflow session and save model to current working directory
with mlflow.start_run():
model.fit(epochs, learning_rate)
mlflow.fastai.save_model(model, 'model')
# Load saved model for inference
model_uri = "{}/{}".format(os.getcwd(), 'model')
loaded_model = mlflow.fastai.load_model(model_uri)
results = loaded_model.predict(predict_data)
"""
import fastai
from pathlib import Path
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
model_data_subpath = "model.fastai"
model_data_path = os.path.join(path, model_data_subpath)
model_data_path = Path(model_data_path)
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)
# Save an Learner
fastai_learner.export(model_data_path, **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)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.fastai",
data=model_data_subpath,
env=conda_env_subpath)
mlflow_model.add_flavor(FLAVOR_NAME,
fastai_version=fastai.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
def save_model(
xgb_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save an XGBoost model to a path on the local file system.
:param xgb_model: XGBoost model (an instance of `xgboost.Booster`_) to be saved.
Note that models that implement the `scikit-learn API`_ are not supported.
:param path: Local path where the model is to be saved.
:param conda_env: {{ conda_env }}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import xgboost as xgb
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException("Path '{}' already exists".format(path))
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.xgb"
model_data_path = os.path.join(path, model_data_subpath)
# Save an XGBoost model
xgb_model.save_model(model_data_path)
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.xgboost",
data=model_data_subpath,
env=_CONDA_ENV_FILE_NAME,
)
mlflow_model.add_flavor(FLAVOR_NAME,
xgb_version=xgb.__version__,
data=model_data_subpath)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))
def save_model(
statsmodels_model,
path,
conda_env=None,
code_paths=None,
mlflow_model=None,
remove_data: bool = False,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a statsmodels model to a path on the local file system.
:param statsmodels_model: statsmodels model (an instance of `statsmodels.base.model.Results`_)
to be saved.
:param path: Local path where the model is to be saved.
:param conda_env: {{ conda_env }}
: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 mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param remove_data: bool. If False (default), then the instance is pickled without changes.
If True, then all arrays with length nobs are set to None before
pickling. See the remove_data method.
In some cases not all arrays will be set to None.
:param signature: :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: 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 pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import statsmodels
_validate_env_arguments(conda_env, pip_requirements,
extra_pip_requirements)
path = os.path.abspath(path)
_validate_and_prepare_target_save_path(path)
model_data_path = os.path.join(path, STATSMODELS_DATA_SUBPATH)
code_dir_subpath = _validate_and_copy_code_paths(code_paths, 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 a statsmodels model
statsmodels_model.save(model_data_path, remove_data)
if _save_model_called_from_autolog and not remove_data:
saved_model_size = os.path.getsize(model_data_path)
if saved_model_size >= _model_size_threshold_for_emitting_warning:
_logger.warning(
"The fitted model is larger than "
f"{_model_size_threshold_for_emitting_warning // (1024 * 1024)} MB, "
f"saving it as artifacts is time consuming.\n"
"To reduce model size, use `mlflow.statsmodels.autolog(log_models=False)` and "
"manually log model by "
'`mlflow.statsmodels.log_model(model, remove_data=True, artifact_path="model")`'
)
pyfunc.add_to_model(
mlflow_model,
loader_module="mlflow.statsmodels",
data=STATSMODELS_DATA_SUBPATH,
env=_CONDA_ENV_FILE_NAME,
code=code_dir_subpath,
)
mlflow_model.add_flavor(
FLAVOR_NAME,
statsmodels_version=statsmodels.__version__,
data=STATSMODELS_DATA_SUBPATH,
code=code_dir_subpath,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
default_reqs = get_default_pip_requirements()
# To ensure `_load_pyfunc` can successfully load the model during the dependency
# inference, `mlflow_model.save` must be called beforehand to save an MLmodel file.
inferred_reqs = mlflow.models.infer_pip_requirements(
path,
FLAVOR_NAME,
fallback=default_reqs,
)
default_reqs = sorted(set(inferred_reqs).union(default_reqs))
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(
conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
# Save `constraints.txt` if necessary
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME),
"\n".join(pip_constraints))
# Save `requirements.txt`
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME),
"\n".join(pip_requirements))