def model_download_with_cv():
prostate = h2o.import_file(
pyunit_utils.locate("smalldata/prostate/prostate.csv"))
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate_gbm = H2OGradientBoostingEstimator(
nfolds=2, keep_cross_validation_predictions=True)
prostate_gbm.train(x=["AGE", "RACE", "PSA", "DCAPS"],
y="CAPSULE",
training_frame=prostate)
path = pyunit_utils.locate("results")
model_path = h2o.download_model(prostate_gbm,
path=path,
export_cross_validation_predictions=True)
assert os.path.isfile(
model_path
), "Expected model artifact {0} to exist, but it does not.".format(
model_path)
h2o.remove_all()
prostate_gbm_reloaded = h2o.upload_model(model_path)
assert isinstance(prostate_gbm_reloaded, H2OGradientBoostingEstimator), \
"Expected H2OGradientBoostingEstimator, but got {0}".format(prostate_gbm_reloaded)
holdout_frame_id = prostate_gbm.cross_validation_holdout_predictions(
).frame_id
assert h2o.get_frame(holdout_frame_id) is not None
def save_model(
h2o_model,
path,
conda_env=None,
mlflow_model=None,
settings=None,
signature: ModelSignature = None,
input_example: ModelInputExample = 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
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_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)
pyfunc.add_to_model(mlflow_model,
loader_module="mlflow.h2o",
data=model_data_subpath,
env=conda_env_subpath)
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(
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))
df[y] = df[y].asfactor() # h2o-3 dataset partition function splits = df.split_frame(ratios=[0.7, 0.15], seed=1) # splits outcome division into 3 new variables train, valid, test = splits print(train.nrow, valid.nrow, test.nrow) # automl estimator aml = H2OAutoML(max_models=8, max_runtime_secs=900, seed=1) aml.train(x=x, y=y, training_frame=train) # performance evaluation: leaderboard lb = aml.leaderboard print(lb.head(rows=lb.nrows)) # predict with the leader yhat = aml.leader.predict(test) auc = aml.leader.auc() conf = aml.leader.confusion_matrix() print(yhat) print(auc) print(conf) # download best model h2o.download_model(model=aml.leader, path='test/output/') h2o.cluster().shutdown()
