def test_stacked_ensemble_is_able_to_use_imported_base_models():
import tempfile, shutil, glob
train = h2o.import_file(pu.locate("smalldata/iris/iris_train.csv"))
test = h2o.import_file(pu.locate("smalldata/iris/iris_test.csv"))
x = train.columns
y = "species"
x.remove(y)
nfolds = 2
gbm = H2OGradientBoostingEstimator(nfolds=nfolds,
fold_assignment="Modulo",
keep_cross_validation_predictions=True)
gbm.train(x=x, y=y, training_frame=train)
drf = H2ORandomForestEstimator(nfolds=nfolds,
fold_assignment="Modulo",
keep_cross_validation_predictions=True)
drf.train(x=x, y=y, training_frame=train)
se = H2OStackedEnsembleEstimator(training_frame=train,
validation_frame=test,
base_models=[gbm.model_id, drf.model_id])
se.train(x=x, y=y, training_frame=train)
assert len(se.base_models) == 2
TMP_DIR = tempfile.mkdtemp()
try:
h2o.save_model(gbm, TMP_DIR + "/gbm.model")
h2o.save_model(drf, TMP_DIR + "/drf.model")
gbm_holdout_id = gbm.cross_validation_holdout_predictions().frame_id
drf_holdout_id = drf.cross_validation_holdout_predictions().frame_id
h2o.export_file(gbm.cross_validation_holdout_predictions(), TMP_DIR + "/gbm.holdout")
h2o.export_file(drf.cross_validation_holdout_predictions(), TMP_DIR + "/drf.holdout")
h2o.remove_all()
h2o.import_file(TMP_DIR + "/gbm.holdout", gbm_holdout_id)
h2o.import_file(TMP_DIR + "/drf.holdout", drf_holdout_id)
gbm = h2o.upload_model(glob.glob(TMP_DIR + "/gbm.model/*")[0])
drf = h2o.upload_model(glob.glob(TMP_DIR + "/drf.model/*")[0])
train = h2o.import_file(pu.locate("smalldata/iris/iris_train.csv"), "some_other_name_of_training_frame")
test = h2o.import_file(pu.locate("smalldata/iris/iris_test.csv"), "some_other_name_of_test_frame")
x = train.columns
y = "species"
x.remove(y)
se_loaded = H2OStackedEnsembleEstimator(training_frame=train,
validation_frame=test,
base_models=[gbm.model_id, drf.model_id])
se_loaded.train(x=x, y=y, training_frame=train)
assert len(se_loaded.base_models) == 2
finally:
shutil.rmtree(TMP_DIR)
def download_model():
prostate = h2o.import_file(
pyunit_utils.locate("smalldata/prostate/prostate.csv"))
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
ntrees=10,
max_depth=8,
min_rows=10,
learn_rate=0.2)
prostate_gbm.train(x=["AGE", "RACE", "PSA", "VOL", "GLEASON"],
y="CAPSULE",
training_frame=prostate)
path = pyunit_utils.locate("results")
downloaded_model_path = prostate_gbm.download_model(path=path)
assert os.path.isfile(downloaded_model_path), \
"Expected load file {0} to exist, but it does not.".format(downloaded_model_path)
loaded_model = h2o.load_model(downloaded_model_path)
assert isinstance(loaded_model, H2OGradientBoostingEstimator), \
"Expected an H2OGradientBoostingEstimator, but got {0}".format(downloaded_model_path)
uploaded_model = h2o.upload_model(downloaded_model_path)
assert isinstance(uploaded_model, H2OGradientBoostingEstimator), \
"Expected an H2OGradientBoostingEstimator, but got {0}".format(downloaded_model_path)
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 _load_model(path, init=False):
import h2o
path = os.path.abspath(path)
with open(os.path.join(path, "h2o.yaml")) as f:
params = yaml.safe_load(f.read())
if init:
h2o.init(**(params["init"] if "init" in params else {}))
h2o.no_progress()
model_path = os.path.join(path, params["model_file"])
if hasattr(h2o, "upload_model"):
model = h2o.upload_model(model_path)
else:
warnings.warn(
"If your cluster is remote, H2O may not load the model correctly. "
"Please upgrade H2O version to a newer version")
model = h2o.load_model(model_path)
return model
# %% # save GLM & reupload model model_path = h2o.save_model(glm,path='../mlruns_h2o/',force=True) print(model_path) # load the model from server (if necesary) # saved_model = h2o.load_model(model_path) # download the model built above to your local machine (if necessary) # my_local_model = h2o.download_model(saved_model, path="/Users/UserName/Desktop") # upload the model that you just downloded above # to the H2O cluster uploaded_model = h2o.upload_model(model_path) # %% # Explain a model exm = uploaded_model.explain(test) # %% # PDP pdp_table = uploaded_model.partial_plot(test,cols=['CREDIT_SCORE'], nbins = 20, plot=False) # %% # shutdown h2o server h2o.cluster().shutdown(prompt=False)
