def test_pipeline_gridsearch():
X, y = load_boston(return_X_y=True)
pipe = Pipeline([("info", InformationFilter(columns=[11, 12])),
("model", LinearRegression())])
mod = GridSearchCV(
estimator=pipe,
param_grid={"info__columns": [[], [11], [12], [11, 12]]},
cv=2)
assert pd.DataFrame(mod.fit(X, y).cv_results_).shape[0] == 4
def test_alpha_param2():
X, y = load_boston(return_X_y=True)
df = pd.DataFrame(
X,
columns=[
"crim",
"zn",
"indus",
"chas",
"nox",
"rm",
"age",
"dis",
"rad",
"tax",
"ptratio",
"b",
"lstat",
],
)
ifilter = InformationFilter(columns=["b", "lstat"], alpha=0.0)
X_removed = df.drop(columns=["b", "lstat"]).values
assert np.isclose(ifilter.fit_transform(df), X_removed).all()
def test_output_orthogonal_general_cols():
X, y = load_boston(return_X_y=True)
cols = [
"crim",
"zn",
"indus",
"chas",
"nox",
"rm",
"age",
"dis",
"rad",
"tax",
"ptratio",
"b",
"lstat",
]
df = pd.DataFrame(X, columns=cols)
for col in cols:
X_fair = InformationFilter(columns=col).fit_transform(df)
assert all([(c * df[col]).sum() < 1e-5 for c in X_fair.T])
def test_alpha_param1():
X, y = load_boston(return_X_y=True)
ifilter = InformationFilter(columns=[11, 12], alpha=0.0)
X_removed = np.delete(X, [11, 12], axis=1)
assert np.isclose(ifilter.fit_transform(X), X_removed).all()
def test_output_orthogonal():
X, y = load_boston(return_X_y=True)
X_fair = InformationFilter(columns=[11, 12]).fit_transform(X)
assert all([(c * X[:, 11]).sum() < 1e-5 for c in X_fair.T])
assert all([(c * X[:, 12]).sum() < 1e-5 for c in X_fair.T])
def test_v_columns_orthogonal():
X, y = load_boston(return_X_y=True)
ifilter = InformationFilter(columns=[11, 12]).fit(X, y)
v_values = ifilter._make_v_vectors(X, [11, 12])
assert v_values.prod(axis=1).sum() == pytest.approx(0, abs=1e-5)
def test_estimator_checks(test_fn):
test_fn(InformationFilter.__name__, InformationFilter(columns=[]))
test_fn(InformationFilter.__name__, InformationFilter(columns=[0]))