def test_breast_cancer():
X, y = demos.load_breast_cancer()
assert X.shape == (569, 30)
assert y.shape == (569, )
assert isinstance(X, ww.DataTable)
assert isinstance(y, ww.DataColumn)
X, y = demos.load_breast_cancer(return_pandas=True)
assert X.shape == (569, 30)
assert y.shape == (569, )
assert isinstance(X, pd.DataFrame)
assert isinstance(y, pd.Series)
def test_graph_two_way_partial_dependence(test_pipeline):
X, y = load_breast_cancer()
go = pytest.importorskip(
'plotly.graph_objects',
reason='Skipping plotting test because plotly not installed')
clf = test_pipeline
clf.fit(X, y)
fig = graph_partial_dependence(clf,
X,
features=('mean radius', 'mean area'),
grid_resolution=20)
assert isinstance(fig, go.Figure)
fig_dict = fig.to_dict()
assert fig_dict['layout']['title'][
'text'] == "Partial Dependence of 'mean radius' vs. 'mean area'"
assert len(fig_dict['data']) == 1
assert fig_dict['data'][0]['name'] == "Partial Dependence"
part_dep_data = partial_dependence(clf,
X,
features=('mean radius', 'mean area'),
grid_resolution=20)
assert np.array_equal(fig_dict['data'][0]['x'], part_dep_data.index)
assert np.array_equal(fig_dict['data'][0]['y'], part_dep_data.columns)
assert np.array_equal(fig_dict['data'][0]['z'], part_dep_data.values)
def test_pipeline_has_classes_property(
logistic_regression_binary_pipeline_class,
logistic_regression_multiclass_pipeline_class, problem_type, use_ints):
if problem_type == "binary":
X, y = load_breast_cancer(return_pandas=True)
pipeline = logistic_regression_binary_pipeline_class(
parameters={"Logistic Regression Classifier": {
"n_jobs": 1
}})
if use_ints:
y = y.map({'malignant': 0, 'benign': 1})
answer = [0, 1]
else:
answer = ["benign", "malignant"]
elif problem_type == "multi":
X, y = load_wine(return_pandas=True)
pipeline = logistic_regression_multiclass_pipeline_class(
parameters={"Logistic Regression Classifier": {
"n_jobs": 1
}})
if use_ints:
y = y.map({"class_0": 0, "class_1": 1, "class_2": 2})
answer = [0, 1, 2]
else:
answer = ["class_0", "class_1", "class_2"]
with pytest.raises(
AttributeError,
match="Cannot access class names before fitting the pipeline."):
pipeline.classes_
pipeline.fit(X, y)
pd.testing.assert_series_equal(pd.Series(pipeline.classes_),
pd.Series(answer))
def test_partial_dependence_string_feature_name(logistic_regression_binary_pipeline_class):
X, y = load_breast_cancer()
pipeline = logistic_regression_binary_pipeline_class(parameters={"Logistic Regression Classifier": {"n_jobs": 1}})
pipeline.fit(X, y)
part_dep = partial_dependence(pipeline, X, features="mean radius", grid_resolution=20)
assert list(part_dep.columns) == ["feature_values", "partial_dependence", "class_label"]
assert len(part_dep["partial_dependence"]) == 20
assert len(part_dep["feature_values"]) == 20
assert not part_dep.isnull().any(axis=None)
def test_invalid_targets_regression_pipeline(target_type, dummy_regression_pipeline_class):
X, y = load_wine(return_pandas=True)
if target_type == "category":
y = pd.Series(y).astype("category")
if target_type == "bool":
X, y = load_breast_cancer(return_pandas=True)
y = y.map({"malignant": False, "benign": True})
mock_regression_pipeline = dummy_regression_pipeline_class(parameters={})
with pytest.raises(ValueError, match="Regression pipeline can only handle numeric target data"):
mock_regression_pipeline.fit(X, y)
def test_woodwork_classification_pipeline(
logistic_regression_binary_pipeline_class):
X, y = load_breast_cancer()
mock_pipeline = logistic_regression_binary_pipeline_class(
parameters={"Logistic Regression Classifier": {
"n_jobs": 1
}})
mock_pipeline.fit(X, y)
assert not pd.isnull(mock_pipeline.predict(X)).any()
assert not pd.isnull(mock_pipeline.predict_proba(X)).any().any()