def test_default_transform():
process = BinningProcess(variable_names)
with raises(NotFittedError):
process.transform(X)
process.fit(X, y)
X_transform = process.transform(X)
optb = OptimalBinning()
x = X[:, 5]
optb.fit(x, y)
assert optb.transform(x) == approx(X_transform[:, 5], rel=1e-6)
def test_default_transform_pandas():
df = pd.DataFrame(data.data, columns=data.feature_names)
process = BinningProcess(variable_names)
process.fit(df, y)
with raises(TypeError):
X_transform = process.transform(df.to_dict(), metric="woe")
X_transform = process.transform(df, metric="woe")
optb = OptimalBinning()
x = X[:, 5]
optb.fit(x, y)
assert optb.transform(x, metric="woe") == approx(
X_transform.values[:, 5], rel=1e-6)
def test_transform_some_variables():
process = BinningProcess(variable_names)
process.fit(X, y)
with raises(TypeError):
process.transform(X, {})
with raises(ValueError):
process.transform(X, ["new_1", "new_2"])
selected_variables = [
'mean area', 'mean smoothness', 'mean compactness', 'mean concavity'
]
X_transform = process.transform(X, selected_variables)
assert X_transform.shape[1] == 4
for i in range(3, 7):
optb = OptimalBinning()
x = X[:, i]
optb.fit(x, y)
assert optb.transform(x) == approx(X_transform[:, i - 3], rel=1e-6)
def test_default_transform_multiclass():
data = load_wine()
variable_names = data.feature_names
X = data.data
y = data.target
process = BinningProcess(variable_names)
process.fit(X, y)
X_transform = process.transform(X)
optb = process.get_binned_variable(variable_names[0])
assert isinstance(optb, MulticlassOptimalBinning)
optb = MulticlassOptimalBinning()
x = X[:, 5]
optb.fit(x, y)
assert optb.transform(x) == approx(X_transform[:, 5], rel=1e-6)
def test_default_transform_continuous():
data = load_boston()
variable_names = data.feature_names
X = data.data
y = data.target
process = BinningProcess(variable_names)
process.fit(X, y)
X_transform = process.transform(X, metric="mean")
optb = process.get_binned_variable(variable_names[0])
assert isinstance(optb, ContinuousOptimalBinning)
optb = ContinuousOptimalBinning()
x = X[:, 5]
optb.fit(x, y)
assert optb.transform(x, metric="mean") == approx(
X_transform[:, 5], rel=1e-6)