def test_infogram_iris_wrong_thresholds():
"""
Simple Iris test to check that when wrong thresholds are specified for core infogram, warnings will
be received
"""
fr = h2o.import_file(path=pyunit_utils.locate(
"smalldata/admissibleml_test/irisROriginal.csv"))
target = "Species"
fr[target] = fr[target].asfactor()
x = fr.names
x.remove(target)
with pyunit_utils.catch_warnings() as ws:
infogram_model = H2OInfogram(
seed=12345,
distribution='multinomial',
safety_index_threshold=0.2,
relevance_index_threshold=0.2,
top_n_features=len(
x)) # build infogram model with default settings
infogram_model.train(x=x, y=target, training_frame=fr)
assert len(
ws
) == 2, "Expected two warnings but received {0} warnings instead.".format(
len(ws))
assert pyunit_utils.contains_warning(
ws, 'index_threshold for core infogram runs.')
def test_infogram_personal_loan():
"""
Simple Perosnal loan test to check that when wrong thresholds are specified, warnings should be
generated.
:return:
"""
fr = h2o.import_file(path=pyunit_utils.locate(
"smalldata/admissibleml_test/Bank_Personal_Loan_Modelling.csv"))
target = "Personal Loan"
fr[target] = fr[target].asfactor()
x = [
"Experience", "Income", "Family", "CCAvg", "Education", "Mortgage",
"Securities Account", "CD Account", "Online", "CreditCard"
]
with pyunit_utils.catch_warnings() as ws:
infogram_model = H2OInfogram(seed=12345,
protected_columns=["Age", "ZIP Code"],
top_n_features=len(x),
net_information_threshold=0.2,
total_information_threshold=0.2)
infogram_model.train(x=x, y=target, training_frame=fr)
assert len(
ws
) == 2, "Expected two warnings but received {0} warnings instead.".format(
len(ws))
assert pyunit_utils.contains_warning(
ws, 'information_threshold for fair infogram runs.')
def test_binomial_response_warning():
training_data = h2o.import_file(pyunit_utils.locate("smalldata/gbm_test/titanic.csv"))
y = "survived"
features = ["name", "sex"]
expected_warning = 'We have detected that your response column has only 2 unique values (0/1). ' \
'If you wish to train a binary model instead of a regression model, ' \
'convert your target column to categorical before training.'
with pyunit_utils.catch_warnings() as ws:
model = H2OGradientBoostingEstimator(ntrees=1)
model.train(x=features, y=y, training_frame=training_data)
assert pyunit_utils.contains_warning(ws, expected_warning)
training_data[training_data[y] == 0, y] = -1
with pyunit_utils.catch_warnings() as ws:
model = H2OGradientBoostingEstimator(ntrees=1)
model.train(x=features, y=y, training_frame=training_data)
assert pyunit_utils.contains_warning(ws, expected_warning)
def test_reproducible_early_stopping_warning():
training_data = h2o.import_file(
pyunit_utils.locate("smalldata/gbm_test/BostonHousing.csv"))
with pyunit_utils.catch_warnings() as ws:
model = estimator(stopping_rounds=1, stopping_metric="mse")
model.train(x=list(range(13)), y=13, training_frame=training_data)
expected_message = 'early stopping is enabled but neither score_tree_interval or ' \
'score_each_iteration are defined. Early stopping will not be reproducible!'
assert pyunit_utils.contains_warning(ws, expected_message)
def test_lambda_warning():
training_data = h2o.import_file(pyunit_utils.locate("smalldata/gbm_test/BostonHousing.csv"))
Y = 13
X = list(range(13))
model = H2OGeneralizedLinearEstimator(family="Gaussian", lambda_search=True, Lambda=[0.01])
model.train(x=X, y=Y, training_frame=training_data)
with pyunit_utils.catch_warnings() as ws:
model = H2OGeneralizedLinearEstimator(family="Gaussian", lambda_search=True, Lambda=[0.01])
model.train(x=X, y=Y, training_frame=training_data)
assert pyunit_utils.contains_warning(ws, 'disabled when user specified any lambda value(s)')
def test_binomial_response_warning():
training_data = h2o.import_file(
pyunit_utils.locate("smalldata/gbm_test/titanic.csv"))
y = "survived"
features = ["name", "sex"]
with pyunit_utils.catch_warnings() as ws:
model = H2OGradientBoostingEstimator(ntrees=1)
model.train(x=features, y=y, training_frame=training_data)
assert pyunit_utils.contains_warning(
ws,
'Response is numeric, so the regression model will be trained. However, the cardinality is equaled to two, so if you want to train a classification model, convert the response column to categorical before training.'
)
training_data[training_data[y] == 0, y] = -1
with pyunit_utils.catch_warnings() as ws:
model = H2OGradientBoostingEstimator(ntrees=1)
model.train(x=features, y=y, training_frame=training_data)
assert pyunit_utils.contains_warning(
ws,
'Response is numeric, so the regression model will be trained. However, the cardinality is equaled to two, so if you want to train a classification model, convert the response column to categorical before training.'
)