def test_max_features_dim(max_features):
clf = RandomForestClassifier(n_estimators=50, random_state=0)
transformer = SelectFromModel(estimator=clf,
max_features=max_features,
threshold=-np.inf)
X_trans = transformer.fit_transform(data, y)
assert X_trans.shape[1] == max_features
def test_threshold_and_max_features():
X, y = datasets.make_classification(
n_samples=1000, n_features=10, n_informative=3, n_redundant=0,
n_repeated=0, shuffle=False, random_state=0)
est = RandomForestClassifier(n_estimators=50, random_state=0)
transformer1 = SelectFromModel(estimator=est, max_features=3,
threshold=-np.inf)
X_new1 = transformer1.fit_transform(X, y)
transformer2 = SelectFromModel(estimator=est, threshold=0.04)
X_new2 = transformer2.fit_transform(X, y)
transformer3 = SelectFromModel(estimator=est, max_features=3,
threshold=0.04)
X_new3 = transformer3.fit_transform(X, y)
assert X_new3.shape[1] == min(X_new1.shape[1], X_new2.shape[1])
selected_indices = transformer3.transform(
np.arange(X.shape[1])[np.newaxis, :])
assert_allclose(X_new3, X[:, selected_indices[0]])
def test_max_features():
# Test max_features parameter using various values
X, y = datasets.make_classification(
n_samples=1000, n_features=10, n_informative=3, n_redundant=0,
n_repeated=0, shuffle=False, random_state=0)
max_features = X.shape[1]
est = RandomForestClassifier(n_estimators=50, random_state=0)
transformer1 = SelectFromModel(estimator=est,
threshold=-np.inf)
transformer2 = SelectFromModel(estimator=est,
max_features=max_features,
threshold=-np.inf)
X_new1 = transformer1.fit_transform(X, y)
X_new2 = transformer2.fit_transform(X, y)
assert_allclose(X_new1, X_new2)
# Test max_features against actual model.
transformer1 = SelectFromModel(estimator=Lasso(alpha=0.025,
random_state=42))
X_new1 = transformer1.fit_transform(X, y)
scores1 = np.abs(transformer1.estimator_.coef_)
candidate_indices1 = np.argsort(-scores1, kind='mergesort')
for n_features in range(1, X_new1.shape[1] + 1):
transformer2 = SelectFromModel(estimator=Lasso(alpha=0.025,
random_state=42),
max_features=n_features,
threshold=-np.inf)
X_new2 = transformer2.fit_transform(X, y)
scores2 = np.abs(transformer2.estimator_.coef_)
candidate_indices2 = np.argsort(-scores2, kind='mergesort')
assert_allclose(X[:, candidate_indices1[:n_features]],
X[:, candidate_indices2[:n_features]])
assert_allclose(transformer1.estimator_.coef_,
transformer2.estimator_.coef_)
def test_max_features_tiebreak():
# Test if max_features can break tie among feature importance
X, y = datasets.make_classification(
n_samples=1000, n_features=10, n_informative=3, n_redundant=0,
n_repeated=0, shuffle=False, random_state=0)
max_features = X.shape[1]
feature_importances = np.array([4, 4, 4, 4, 3, 3, 3, 2, 2, 1])
for n_features in range(1, max_features + 1):
transformer = SelectFromModel(
FixedImportanceEstimator(feature_importances),
max_features=n_features,
threshold=-np.inf)
X_new = transformer.fit_transform(X, y)
selected_feature_indices = np.where(transformer._get_support_mask())[0]
assert_array_equal(selected_feature_indices, np.arange(n_features))
assert X_new.shape[1] == n_features