def get_model(model_id):
"""
Return the specified model
:param model_id: The model identification in h2o
"""
model_json = H2OConnection.get_json("Models/" + model_id)["models"][0]
model_type = model_json["output"]["model_category"]
if model_type == "Binomial":
from model.binomial import H2OBinomialModel
model = H2OBinomialModel(model_id, model_json)
elif model_type == "Clustering":
from model.clustering import H2OClusteringModel
model = H2OClusteringModel(model_id, model_json)
elif model_type == "Regression":
from model.regression import H2ORegressionModel
model = H2ORegressionModel(model_id, model_json)
elif model_type == "Multinomial":
from model.multinomial import H2OMultinomialModel
model = H2OMultinomialModel(model_id, model_json)
elif model_type == "AutoEncoder":
from model.autoencoder import H2OAutoEncoderModel
model = H2OAutoEncoderModel(model_id, model_json)
else:
print model_type
raise NotImplementedError
return model
def _resolve_model(future_model, **kwargs):
future_model.poll()
if '_rest_version' in kwargs.keys():
model_json = H2OConnection.get_json(
"Models/" + future_model.job.dest_key,
_rest_version=kwargs['_rest_version'])["models"][0]
else:
model_json = H2OConnection.get_json(
"Models/" + future_model.job.dest_key)["models"][0]
model_type = model_json["output"]["model_category"]
if model_type == "Binomial":
model = H2OBinomialModel(future_model.job.dest_key, model_json)
elif model_type == "Clustering":
model = H2OClusteringModel(future_model.job.dest_key, model_json)
elif model_type == "Regression":
model = H2ORegressionModel(future_model.job.dest_key, model_json)
elif model_type == "Multinomial":
model = H2OMultinomialModel(future_model.job.dest_key, model_json)
elif model_type == "AutoEncoder":
model = H2OAutoEncoderModel(future_model.job.dest_key, model_json)
elif model_type == "DimReduction":
model = H2ODimReductionModel(future_model.job.dest_key, model_json)
else:
raise NotImplementedError(model_type)
return model
def _model_build(x,y,validation_x,validation_y,algo_url,kwargs):
# Basic sanity checking
if algo_url == "autoencoder":
if "autoencoder" in kwargs.keys():
if kwargs["autoencoder"]:
if y:
raise ValueError("`y` should not be specified for autoencoder, remove `y` input.")
algo_url="deeplearning"
if not x: raise ValueError("Missing features")
x = _check_frame(x,y,y)
if validation_x:
validation_x = _check_frame(validation_x,validation_y,y)
# Send frame descriptions to H2O cluster
train_key = x.send_frame()
kwargs['training_frame']=train_key
if validation_x is not None:
valid_key = validation_x.send_frame()
kwargs['validation_frame']=valid_key
if y:
kwargs['response_column']=y._name
kwargs = dict([(k, kwargs[k]) for k in kwargs if kwargs[k] is not None])
# launch the job and poll
job = H2OJob(H2OConnection.post_json("ModelBuilders/"+algo_url, **kwargs), job_type=(algo_url+" Model Build")).poll()
model_json = H2OConnection.get_json("Models/"+job.dest_key)["models"][0]
model_type = model_json["output"]["model_category"]
if model_type=="Binomial":
from model.binomial import H2OBinomialModel
model = H2OBinomialModel(job.dest_key,model_json)
elif model_type=="Clustering":
from model.clustering import H2OClusteringModel
model = H2OClusteringModel(job.dest_key,model_json)
elif model_type=="Regression":
from model.regression import H2ORegressionModel
model = H2ORegressionModel(job.dest_key,model_json)
elif model_type=="Multinomial":
from model.multinomial import H2OMultinomialModel
model = H2OMultinomialModel(job.dest_key,model_json)
elif model_type=="AutoEncoder":
from model.autoencoder import H2OAutoEncoderModel
model = H2OAutoEncoderModel(job.dest_key,model_json)
else:
print model_type
raise NotImplementedError
# Cleanup
h2o.remove(train_key)
if validation_x:
h2o.remove(valid_key)
return model
def _resolve_model(future_model, **kwargs):
future_model.poll() # Wait for model-building to be complete
if '_rest_version' in kwargs.keys():
model_json = H2OConnection.get_json(
"Models/" + future_model.job.dest_key,
_rest_version=kwargs['_rest_version'])["models"][0]
else:
model_json = H2OConnection.get_json(
"Models/" + future_model.job.dest_key)["models"][0]
model_type = model_json["output"]["model_category"]
if model_type == "Binomial":
from model.binomial import H2OBinomialModel
model = H2OBinomialModel(future_model.job.dest_key, model_json)
elif model_type == "Clustering":
from model.clustering import H2OClusteringModel
model = H2OClusteringModel(future_model.job.dest_key, model_json)
elif model_type == "Regression":
from model.regression import H2ORegressionModel
model = H2ORegressionModel(future_model.job.dest_key, model_json)
elif model_type == "Multinomial":
from model.multinomial import H2OMultinomialModel
model = H2OMultinomialModel(future_model.job.dest_key, model_json)
elif model_type == "AutoEncoder":
from model.autoencoder import H2OAutoEncoderModel
model = H2OAutoEncoderModel(future_model.job.dest_key, model_json)
elif model_type == "DimReduction":
from model.dim_reduction import H2ODimReductionModel
model = H2ODimReductionModel(future_model.job.dest_key, model_json)
else:
print model_type
raise NotImplementedError
return model