def test_summary_get_support():
data = load_breast_cancer()
variable_names = data.feature_names
X = data.data
y = data.target
process = BinningProcess(variable_names, min_iv=0.1, max_iv=0.6)
with raises(ValueError):
process.summary()
with raises(ValueError):
process.get_support()
process.fit(X, y, check_input=True)
assert isinstance(process.summary(), pd.DataFrame)
with raises(ValueError):
process.get_support(indices=True, names=True)
assert all(process.get_support() == [
False, False, False, False, False, False, False, False, False, True,
False, True, False, False, True, False, False, False, True, True,
False, False, False, False, False, False, False, False, False, True
])
assert process.get_support(indices=True) == approx([9, 11, 14, 18, 19, 29])
assert all(
process.get_support(names=True) == [
'mean fractal dimension', 'texture error', 'smoothness error',
'symmetry error', 'fractal dimension error',
'worst fractal dimension'
])
def test_summary_get_support():
data = load_breast_cancer()
variable_names = data.feature_names
X = data.data
y = data.target
selection_criteria = {"iv": {"min": 0.1, "max": 0.6,
"strategy": "highest", "top": 10}}
process = BinningProcess(variable_names=variable_names,
selection_criteria=selection_criteria)
with raises(ValueError):
process.summary()
with raises(ValueError):
process.get_support()
process.fit(X, y, check_input=True)
assert isinstance(process.summary(), pd.DataFrame)
with raises(ValueError):
process.get_support(indices=True, names=True)
assert all(process.get_support() == [
False, False, False, False, False, False, False, False, False, True,
False, True, False, False, True, False, False, False, True, True,
False, False, False, False, False, False, False, False, False, True])
assert process.get_support(indices=True) == approx([9, 11, 14, 18, 19, 29])
assert all(process.get_support(names=True) == [
'mean fractal dimension', 'texture error', 'smoothness error',
'symmetry error', 'fractal dimension error',
'worst fractal dimension'])