def check_cv(pipeline,
X,
y=None,
n_folds=2,
groups=None,
split_start='before_transforms',
expected_metrics={},
**params):
cv = CV(pipeline)
if split_start == 'try_all':
len_pipeline = len(pipeline.nodes)
values_to_test = ['after_transforms', 'before_transforms']
values_to_test.extend(list(range(len_pipeline)))
values_to_test.extend(list(range(-len_pipeline, 0)))
for s in values_to_test:
graph_id = '_split_start={}'.format(str(s))
results = cv.fit(X,
y,
cv=n_folds,
groups=groups,
split_start=s,
graph_id=graph_id)
check_cv_results(cv._learner_type, results, n_folds,
expected_metrics)
else:
results = cv.fit(X,
y,
cv=n_folds,
groups=groups,
split_start=split_start,
**params)
check_cv_results(cv._learner_type, results, n_folds, expected_metrics)
return results
def test_unseen_classes(self):
# Create a dataset such that cv splits miss some of the classes
X = random_df()
y = random_series()
y[95:] = range(5)
msg = 'CV didn\'t raise Warning exception b/c of minority class issue'
with self.assertRaises(Warning, msg=msg):
cv = CV([FastLinearClassifier()])
cv.fit(X, y, cv=3)
def test_ensemble_supports_cv_with_user_defined_transforms(self):
path = get_dataset("airquality").as_filepath()
schema = DataSchema.read_schema(path)
data = FileDataStream(path, schema)
ind_args = {'Ozone_ind': 'Ozone', 'Solar_R_ind': 'Solar_R'}
handler_args = {'Solar_R': 'Solar_R', 'Ozone': 'Ozone'}
lgbm_args = {
'feature': ['Ozone', 'Solar_R', 'Ozone_ind', 'Solar_R_ind', 'Temp'],
'label': 'Wind',
'normalize': 'Yes'
}
ols_args = {
'feature': ['Ozone', 'Solar_R', 'Ozone_ind', 'Solar_R_ind', 'Temp'],
'label': 'Wind',
'normalize': 'Yes'
}
ogd_args = {
'feature': ['Ozone', 'Solar_R', 'Ozone_ind', 'Solar_R_ind', 'Temp'],
'label': 'Wind',
'shuffle': False,
'normalize': 'Yes'
}
for split_start in ['before_transforms', 'after_transforms']:
pipeline_steps = [
Indicator() << ind_args,
Handler(replace_with='Mean') << handler_args,
LightGbmRegressor(**lgbm_args)
]
cv_results = CV(pipeline_steps).fit(data, split_start=split_start)
l2_avg_lgbm = cv_results['metrics_summary'].loc['Average', 'L2(avg)']
r1 = OrdinaryLeastSquaresRegressor(**ols_args)
r2 = OnlineGradientDescentRegressor(**ogd_args)
r3 = LightGbmRegressor(**lgbm_args)
data = FileDataStream(path, schema)
pipeline_steps = [
Indicator() << ind_args,
Handler(replace_with='Mean') << handler_args,
VotingRegressor(estimators=[r1, r2, r3], combiner='Average')
]
cv_results = CV(pipeline_steps).fit(data, split_start=split_start)
l2_avg_ensemble = cv_results['metrics_summary'].loc['Average', 'L2(avg)']
self.assertTrue(l2_avg_ensemble < l2_avg_lgbm)
def test_unsupported_pipelines(self):
unsupported_pipelines = [OneHotVectorizer()]
for p in unsupported_pipelines:
pipeline = Pipeline([p])
msg = 'CV doesn\'t support pipeline ending with {}, but ' \
'didn\'t raise exception'.format(
pipeline._last_node_type())
with self.assertRaises(ValueError, msg=msg):
CV(pipeline)
def check_cv_with_non_defaults(self,
label_name='label',
group_id='groupid',
features='Features_1',
**params):
steps = [
ToKey(columns={
'groupid2': group_id,
'label2': label_name
}),
LightGbmRanker() << {
Role.GroupId: 'groupid2',
Role.Label: 'label2',
Role.Feature: [features]
}
]
data = self.data(label_name, group_id, features)
cv = CV(steps)
results = cv.fit(data, groups='groupid', cv=4)
check_cv_results(cv._learner_type,
results,
n_folds=4,
expected_metrics={})
def test_split_start_with_transforms_with_presteps(self):
path = get_dataset("airquality").as_filepath()
schema = DataSchema.read_schema(path)
data = FileDataStream(path, schema)
pipeline_steps = [
Indicator() << {
'Ozone_ind': 'Ozone',
'Solar_R_ind': 'Solar_R'
},
Handler(replace_with='Mean') << {
'Solar_R': 'Solar_R',
'Ozone': 'Ozone'
},
LightGbmRegressor(feature=[
'Ozone', 'Solar_R', 'Ozone_ind', 'Solar_R_ind', 'Temp'
],
label='Wind')
]
results = CV(pipeline_steps).fit(data,
split_start='after_transforms',
dry_run=True)
results = json.loads(results)
node_names = [ep['Name'] for ep in results['nodes']]
cv_node = [
ep for ep in results['nodes']
if 'Models.CrossValidator' in ep['Name']
][0]
cv_sub_node_names = [ep['Name'] for ep in cv_node['Inputs']['Nodes']]
self.assertTrue('Transforms.MissingValueHandler' in node_names)
self.assertTrue(
'Transforms.MissingValueHandler' not in cv_sub_node_names)
self.assertTrue('Transforms.ModelCombiner' in node_names)
from nimbusml.preprocessing.missing_values import Indicator, Handler
# Case 1: Default usage of CV
path = get_dataset('infert').as_filepath()
schema = DataSchema.read_schema(path, numeric_dtype=np.float32)
data = FileDataStream.read_csv(path, schema=schema)
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
LogisticRegressionClassifier(feature=['age', 'spontaneous', 'edu'],
label='induced')
])
# Do 3-fold cross-validation
cv_results = CV(pipeline).fit(data, cv=3)
# print summary statistic of metrics
print(cv_results['metrics_summary'])
# print metrics for all folds
print(cv_results['metrics'])
# print confusion matrix for fold 1
cm = cv_results['confusion_matrix']
print(cm[cm.Fold == 1])
# Case 2: Using CV with split_start option
path = get_dataset("airquality").as_filepath()
schema = DataSchema.read_schema(path)
