def test_default():
process = BinningProcess(variable_names)
process.fit(X, y, check_input=True)
with raises(TypeError):
process.get_binned_variable(1)
with raises(ValueError):
process.get_binned_variable("new_variable")
optb = process.get_binned_variable("mean radius")
assert optb.status == "OPTIMAL"
assert optb.splits == approx([11.42500019, 12.32999992, 13.09499979,
13.70499992, 15.04500008, 16.92500019],
rel=1e-6)
optb.binning_table.build()
assert optb.binning_table.iv == approx(5.04392547, rel=1e-6)
def test_fit_params():
binning_fit_params = {"mean radius": {"max_n_bins": 4}}
process = BinningProcess(variable_names=variable_names,
binning_fit_params=binning_fit_params)
process.fit(X, y)
optb = process.get_binned_variable("mean radius")
assert optb.status == "OPTIMAL"
assert len(optb.splits) <= 4
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)
def test_default_pandas():
df = pd.DataFrame(data.data, columns=data.feature_names)
process = BinningProcess(variable_names)
with raises(TypeError):
process.fit(df.to_dict(), y, check_input=True)
process.fit(df, y, check_input=True)
optb = process.get_binned_variable("mean radius")
assert optb.status == "OPTIMAL"
assert optb.splits == approx([11.42500019, 12.32999992, 13.09499979,
13.70499992, 15.04500008, 16.92500019],
rel=1e-6)
optb.binning_table.build()
assert optb.binning_table.iv == approx(5.04392547, rel=1e-6)