def test_number_of_subsets_of_features():
# In RFE, 'number_of_subsets_of_features'
# = the number of iterations in '_fit'
# = max(ranking_)
# = 1 + (n_features + step - n_features_to_select - 1) // step
# After optimization #4534, this number
# = 1 + np.ceil((n_features - n_features_to_select) / float(step))
# This test case is to test their equivalence, refer to #4534 and #3824
def formula1(n_features, n_features_to_select, step):
return 1 + ((n_features + step - n_features_to_select - 1) // step)
def formula2(n_features, n_features_to_select, step):
return 1 + np.ceil((n_features - n_features_to_select) / float(step))
# RFE
# Case 1, n_features - n_features_to_select is divisible by step
# Case 2, n_features - n_features_to_select is not divisible by step
n_features_list = [11, 11]
n_features_to_select_list = [3, 3]
step_list = [2, 3]
for n_features, n_features_to_select, step in zip(
n_features_list, n_features_to_select_list, step_list):
generator = check_random_state(43)
X = generator.normal(size=(100, n_features))
y = generator.rand(100).round()
rfe = RFE(estimator=SVC(kernel="linear"),
n_features_to_select=n_features_to_select,
step=step)
rfe.fit(X, y)
# this number also equals to the maximum of ranking_
assert (np.max(rfe.ranking_) == formula1(n_features,
n_features_to_select, step))
assert (np.max(rfe.ranking_) == formula2(n_features,
n_features_to_select, step))
# In RFECV, 'fit' calls 'RFE._fit'
# 'number_of_subsets_of_features' of RFE
# = the size of 'grid_scores' of RFECV
# = the number of iterations of the for loop before optimization #4534
# RFECV, n_features_to_select = 1
# Case 1, n_features - 1 is divisible by step
# Case 2, n_features - 1 is not divisible by step
n_features_to_select = 1
n_features_list = [11, 10]
step_list = [2, 2]
for n_features, step in zip(n_features_list, step_list):
generator = check_random_state(43)
X = generator.normal(size=(100, n_features))
y = generator.rand(100).round()
rfecv = RFECV(estimator=SVC(kernel="linear"), step=step)
rfecv.fit(X, y)
assert (rfecv.grid_scores_.shape[0] == formula1(
n_features, n_features_to_select, step))
assert (rfecv.grid_scores_.shape[0] == formula2(
n_features, n_features_to_select, step))
def test_rfecv_mockclassifier():
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = list(iris.target) # regression test: list should be supported
# Test using the score function
rfecv = RFECV(estimator=MockClassifier(), step=1)
rfecv.fit(X, y)
# non-regression test for missing worst feature:
assert len(rfecv.grid_scores_) == X.shape[1]
assert len(rfecv.ranking_) == X.shape[1]
def test_rfe_cv_groups():
generator = check_random_state(0)
iris = load_iris()
number_groups = 4
groups = np.floor(np.linspace(0, number_groups, len(iris.target)))
X = iris.data
y = (iris.target > 0).astype(int)
est_groups = RFECV(
estimator=RandomForestClassifier(random_state=generator),
step=1,
scoring='accuracy',
cv=GroupKFold(n_splits=2))
est_groups.fit(X, y, groups=groups)
assert est_groups.n_features_ > 0
def test_rfecv_verbose_output():
# Check verbose=1 is producing an output.
from io import StringIO
import sys
sys.stdout = StringIO()
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = list(iris.target)
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, verbose=1)
rfecv.fit(X, y)
verbose_output = sys.stdout
verbose_output.seek(0)
assert len(verbose_output.readline()) > 0
def test_rfecv_grid_scores_size():
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = list(iris.target) # regression test: list should be supported
# Non-regression test for varying combinations of step and
# min_features_to_select.
for step, min_features_to_select in [[2, 1], [2, 2], [3, 3]]:
rfecv = RFECV(estimator=MockClassifier(),
step=step,
min_features_to_select=min_features_to_select)
rfecv.fit(X, y)
score_len = np.ceil((X.shape[1] - min_features_to_select) / step) + 1
assert len(rfecv.grid_scores_) == score_len
assert len(rfecv.ranking_) == X.shape[1]
assert rfecv.n_features_ >= min_features_to_select
def test_rfe_cv_n_jobs():
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = iris.target
rfecv = RFECV(estimator=SVC(kernel='linear'))
rfecv.fit(X, y)
rfecv_ranking = rfecv.ranking_
rfecv_grid_scores = rfecv.grid_scores_
rfecv.set_params(n_jobs=2)
rfecv.fit(X, y)
assert_array_almost_equal(rfecv.ranking_, rfecv_ranking)
assert_array_almost_equal(rfecv.grid_scores_, rfecv_grid_scores)
def test_rfe_allow_nan_inf_in_x(cv):
iris = load_iris()
X = iris.data
y = iris.target
# add nan and inf value to X
X[0][0] = np.NaN
X[0][1] = np.Inf
clf = MockClassifier()
if cv is not None:
rfe = RFECV(estimator=clf, cv=cv)
else:
rfe = RFE(estimator=clf)
rfe.fit(X, y)
rfe.transform(X)
def test_rfecv():
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = list(iris.target) # regression test: list should be supported
# Test using the score function
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1)
rfecv.fit(X, y)
# non-regression test for missing worst feature:
assert len(rfecv.grid_scores_) == X.shape[1]
assert len(rfecv.ranking_) == X.shape[1]
X_r = rfecv.transform(X)
# All the noisy variable were filtered out
assert_array_equal(X_r, iris.data)
# same in sparse
rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=1)
X_sparse = sparse.csr_matrix(X)
rfecv_sparse.fit(X_sparse, y)
X_r_sparse = rfecv_sparse.transform(X_sparse)
assert_array_equal(X_r_sparse.toarray(), iris.data)
# Test using a customized loss function
scoring = make_scorer(zero_one_loss, greater_is_better=False)
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=scoring)
ignore_warnings(rfecv.fit)(X, y)
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
# Test using a scorer
scorer = get_scorer('accuracy')
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=scorer)
rfecv.fit(X, y)
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
# Test fix on grid_scores
def test_scorer(estimator, X, y):
return 1.0
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=test_scorer)
rfecv.fit(X, y)
assert_array_equal(rfecv.grid_scores_, np.ones(len(rfecv.grid_scores_)))
# In the event of cross validation score ties, the expected behavior of
# RFECV is to return the FEWEST features that maximize the CV score.
# Because test_scorer always returns 1.0 in this example, RFECV should
# reduce the dimensionality to a single feature (i.e. n_features_ = 1)
assert rfecv.n_features_ == 1
# Same as the first two tests, but with step=2
rfecv = RFECV(estimator=SVC(kernel="linear"), step=2)
rfecv.fit(X, y)
assert len(rfecv.grid_scores_) == 6
assert len(rfecv.ranking_) == X.shape[1]
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=2)
X_sparse = sparse.csr_matrix(X)
rfecv_sparse.fit(X_sparse, y)
X_r_sparse = rfecv_sparse.transform(X_sparse)
assert_array_equal(X_r_sparse.toarray(), iris.data)
# Verifying that steps < 1 don't blow up.
rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=.2)
X_sparse = sparse.csr_matrix(X)
rfecv_sparse.fit(X_sparse, y)
X_r_sparse = rfecv_sparse.transform(X_sparse)
assert_array_equal(X_r_sparse.toarray(), iris.data)