def generic_blank_constructor():
# Train a model
airlines = h2o.import_file(
path=pyunit_utils.locate("smalldata/testng/airlines_train.csv"))
model = H2OGradientBoostingEstimator(ntrees=1)
model.train(x=["Origin", "Dest"],
y="IsDepDelayed",
training_frame=airlines)
#Save the previously created model into a temporary file
original_model_filename = tempfile.mkdtemp()
original_model_filename = model.download_mojo(original_model_filename)
# Load the model from the temporary using an empty constructor
mojo_model = H2OGenericEstimator()
mojo_model.path = original_model_filename
mojo_model.train()
assert isinstance(mojo_model, H2OGenericEstimator)
assert mojo_model._model_json["output"][
"original_model_identifier"] == "gbm"
assert mojo_model._model_json["output"][
"original_model_full_name"] == "Gradient Boosting Machine"
# Test scoring is available on the model
predictions = mojo_model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
def test(x, y, output_test, strip_part, algo_name, generic_algo_name):
airlines = h2o.import_file(
path=pyunit_utils.locate("smalldata/testng/airlines_train.csv"))
gbm = H2ODeepLearningEstimator(epochs=1)
gbm.train(x=x, y=y, training_frame=airlines, validation_frame=airlines)
print(gbm)
with Capturing() as original_output:
gbm.show()
original_model_filename = tempfile.mkdtemp()
original_model_filename = gbm.download_mojo(original_model_filename)
key = h2o.lazy_import(original_model_filename)
fr = h2o.get_frame(key[0])
generic_mojo_model = H2OGenericEstimator(model_key=fr)
generic_mojo_model.train()
compare_params(gbm, generic_mojo_model)
print(generic_mojo_model)
with Capturing() as generic_output:
generic_mojo_model.show()
output_test(str(original_output), str(generic_output), strip_part,
algo_name, generic_algo_name)
predictions = generic_mojo_model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert generic_mojo_model._model_json["output"][
"model_summary"] is not None
assert len(generic_mojo_model._model_json["output"]
["model_summary"]._cell_values) > 0
# Test constructor generating the model from existing MOJO file
generic_mojo_model_from_file = H2OGenericEstimator.from_file(
original_model_filename)
assert generic_mojo_model_from_file is not None
predictions = generic_mojo_model_from_file.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert generic_mojo_model_from_file._model_json["output"][
"model_summary"] is not None
assert len(generic_mojo_model_from_file._model_json["output"]
["model_summary"]._cell_values) > 0
generic_mojo_filename = tempfile.mkdtemp("zip", "genericMojo")
generic_mojo_filename = generic_mojo_model_from_file.download_mojo(
path=generic_mojo_filename)
assert os.path.getsize(generic_mojo_filename) == os.path.getsize(
original_model_filename)
def stackedensemble_mojo_model_test():
train = h2o.import_file(
pyunit_utils.locate("smalldata/iris/iris_train.csv"))
test = h2o.import_file(pyunit_utils.locate("smalldata/iris/iris_test.csv"))
x = train.columns
y = "species"
nfolds = 2
gbm = H2OGradientBoostingEstimator(nfolds=nfolds,
fold_assignment="Modulo",
keep_cross_validation_predictions=True)
gbm.train(x=x, y=y, training_frame=train)
rf = H2ORandomForestEstimator(nfolds=nfolds,
fold_assignment="Modulo",
keep_cross_validation_predictions=True)
rf.train(x=x, y=y, training_frame=train)
se = H2OStackedEnsembleEstimator(training_frame=train,
validation_frame=test,
base_models=[gbm.model_id, rf.model_id])
se.train(x=x, y=y, training_frame=train)
print(se)
with Capturing() as original_output:
se.show()
original_model_filename = tempfile.mkdtemp()
original_model_filename = se.download_mojo(original_model_filename)
key = h2o.lazy_import(original_model_filename)
fr = h2o.get_frame(key[0])
generic_mojo_model = H2OGenericEstimator(model_key=fr)
generic_mojo_model.train()
compare_params(se, generic_mojo_model)
predictions = generic_mojo_model.predict(test)
assert predictions is not None
# Test constructor generating the model from existing MOJO file
generic_mojo_model_from_file = H2OGenericEstimator.from_file(
original_model_filename)
assert generic_mojo_model_from_file is not None
predictions = generic_mojo_model_from_file.predict(test)
assert predictions is not None
generic_mojo_filename = tempfile.mkdtemp("zip", "genericMojo")
generic_mojo_filename = generic_mojo_model_from_file.download_mojo(
path=generic_mojo_filename)
assert os.path.getsize(generic_mojo_filename) == os.path.getsize(
original_model_filename)
def test(x, y, output_test, strip_part, algo_name, generic_algo_name):
airlines = h2o.import_file(
path=pyunit_utils.locate("smalldata/testng/airlines_train.csv"))
xgb = H2OXGBoostEstimator(ntrees=1, nfolds=3)
xgb.train(x=x, y=y, training_frame=airlines, validation_frame=airlines)
print(xgb)
with Capturing() as original_output:
xgb.show()
original_model_filename = tempfile.mkdtemp()
original_model_filename = xgb.download_mojo(original_model_filename)
key = h2o.lazy_import(original_model_filename)
fr = h2o.get_frame(key[0])
model = H2OGenericEstimator(model_key=fr)
model.train()
print(model)
with Capturing() as generic_output:
model.show()
output_test(str(original_output), str(generic_output), strip_part,
algo_name, generic_algo_name)
predictions = model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert model._model_json["output"]["variable_importances"] is not None
assert len(
model._model_json["output"]["variable_importances"]._cell_values) > 0
assert model._model_json["output"]["model_summary"] is not None
assert len(model._model_json["output"]["model_summary"]._cell_values) > 0
# Test constructor generating the model from existing MOJO file
model = H2OGenericEstimator.from_file(original_model_filename)
assert model is not None
predictions = model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert model._model_json["output"]["variable_importances"] is not None
assert len(
model._model_json["output"]["variable_importances"]._cell_values) > 0
assert model._model_json["output"]["model_summary"] is not None
assert len(model._model_json["output"]["model_summary"]._cell_values) > 0
generic_mojo_filename = tempfile.mkdtemp("zip", "genericMojo")
generic_mojo_filename = model.download_mojo(path=generic_mojo_filename)
assert os.path.getsize(generic_mojo_filename) == os.path.getsize(
original_model_filename)
def mojo_model_test():
# GBM
airlines = h2o.import_file(
path=pyunit_utils.locate("smalldata/testng/airlines_train.csv"))
gbm = H2OGradientBoostingEstimator(ntrees=1)
gbm.train(x=["Origin", "Dest"], y="IsDepDelayed", training_frame=airlines)
original_model_filename = tempfile.mkdtemp()
original_model_filename = gbm.download_mojo(original_model_filename)
key = h2o.lazy_import(original_model_filename)
fr = h2o.get_frame(key[0])
model = H2OGenericEstimator(model_key=fr)
model.train()
predictions = model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert model._model_json["output"]["variable_importances"] is not None
assert len(
model._model_json["output"]["variable_importances"]._cell_values) > 0
assert model._model_json["output"]["model_summary"] is not None
assert len(model._model_json["output"]["model_summary"]._cell_values) > 0
# Test constructor generating the model from existing MOJO file
model = H2OGenericEstimator.from_file(original_model_filename)
assert model is not None
predictions = model.predict(airlines)
assert predictions is not None
assert predictions.nrows == 24421
assert model._model_json["output"]["variable_importances"] is not None
assert len(
model._model_json["output"]["variable_importances"]._cell_values) > 0
assert model._model_json["output"]["model_summary"] is not None
assert len(model._model_json["output"]["model_summary"]._cell_values) > 0
generic_mojo_filename = tempfile.mkdtemp("zip", "genericMojo")
generic_mojo_filename = model.download_mojo(path=generic_mojo_filename)
assert os.path.getsize(generic_mojo_filename) == os.path.getsize(
original_model_filename)