def test_select_percentile_classif_sparse():
# Test whether the relative univariate feature selection
# gets the correct items in a simple classification problem
# with the percentile heuristic
X, y = make_classification(n_samples=200,
n_features=20,
n_informative=3,
n_redundant=2,
n_repeated=0,
n_classes=8,
n_clusters_per_class=1,
flip_y=0.0,
class_sep=10,
shuffle=False,
random_state=0)
X = sparse.csr_matrix(X)
univariate_filter = SelectPercentile(f_classif, percentile=25)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='percentile',
param=25).fit(X, y).transform(X)
assert_array_equal(X_r.toarray(), X_r2.toarray())
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
X_r2inv = univariate_filter.inverse_transform(X_r2)
assert sparse.issparse(X_r2inv)
support_mask = safe_mask(X_r2inv, support)
assert X_r2inv.shape == X.shape
assert_array_equal(X_r2inv[:, support_mask].toarray(), X_r.toarray())
# Check other columns are empty
assert X_r2inv.getnnz() == X_r.getnnz()
def test_boundary_case_ch2():
# Test boundary case, and always aim to select 1 feature.
X = np.array([[10, 20], [20, 20], [20, 30]])
y = np.array([[1], [0], [0]])
scores, pvalues = chi2(X, y)
assert_array_almost_equal(scores, np.array([4., 0.71428571]))
assert_array_almost_equal(pvalues, np.array([0.04550026, 0.39802472]))
filter_fdr = SelectFdr(chi2, alpha=0.1)
filter_fdr.fit(X, y)
support_fdr = filter_fdr.get_support()
assert_array_equal(support_fdr, np.array([True, False]))
filter_kbest = SelectKBest(chi2, k=1)
filter_kbest.fit(X, y)
support_kbest = filter_kbest.get_support()
assert_array_equal(support_kbest, np.array([True, False]))
filter_percentile = SelectPercentile(chi2, percentile=50)
filter_percentile.fit(X, y)
support_percentile = filter_percentile.get_support()
assert_array_equal(support_percentile, np.array([True, False]))
filter_fpr = SelectFpr(chi2, alpha=0.1)
filter_fpr.fit(X, y)
support_fpr = filter_fpr.get_support()
assert_array_equal(support_fpr, np.array([True, False]))
filter_fwe = SelectFwe(chi2, alpha=0.1)
filter_fwe.fit(X, y)
support_fwe = filter_fwe.get_support()
assert_array_equal(support_fwe, np.array([True, False]))
def test_select_percentile_classif():
# Test whether the relative univariate feature selection
# gets the correct items in a simple classification problem
# with the percentile heuristic
X, y = make_classification(n_samples=200,
n_features=20,
n_informative=3,
n_redundant=2,
n_repeated=0,
n_classes=8,
n_clusters_per_class=1,
flip_y=0.0,
class_sep=10,
shuffle=False,
random_state=0)
univariate_filter = SelectPercentile(f_classif, percentile=25)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(f_classif, mode='percentile',
param=25).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
def test_selectpercentile_tiebreaking():
# Test if SelectPercentile selects the right n_features in case of ties.
Xs = [[0, 1, 1], [0, 0, 1], [1, 0, 0], [1, 1, 0]]
y = [1]
dummy_score = lambda X, y: (X[0], X[0])
for X in Xs:
sel = SelectPercentile(dummy_score, percentile=34)
X1 = ignore_warnings(sel.fit_transform)([X], y)
assert X1.shape[1] == 1
assert_best_scores_kept(sel)
sel = SelectPercentile(dummy_score, percentile=67)
X2 = ignore_warnings(sel.fit_transform)([X], y)
assert X2.shape[1] == 2
assert_best_scores_kept(sel)
def test_invalid_percentile():
X, y = make_regression(n_samples=10,
n_features=20,
n_informative=2,
shuffle=False,
random_state=0)
with pytest.raises(ValueError):
SelectPercentile(percentile=-1).fit(X, y)
with pytest.raises(ValueError):
SelectPercentile(percentile=101).fit(X, y)
with pytest.raises(ValueError):
GenericUnivariateSelect(mode='percentile', param=-1).fit(X, y)
with pytest.raises(ValueError):
GenericUnivariateSelect(mode='percentile', param=101).fit(X, y)
def test_mutual_info_regression():
X, y = make_regression(n_samples=100,
n_features=10,
n_informative=2,
shuffle=False,
random_state=0,
noise=10)
# Test in KBest mode.
univariate_filter = SelectKBest(mutual_info_regression, k=2)
X_r = univariate_filter.fit(X, y).transform(X)
assert_best_scores_kept(univariate_filter)
X_r2 = GenericUnivariateSelect(mutual_info_regression,
mode='k_best',
param=2).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(10)
gtruth[:2] = 1
assert_array_equal(support, gtruth)
# Test in Percentile mode.
univariate_filter = SelectPercentile(mutual_info_regression, percentile=20)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(mutual_info_regression,
mode='percentile',
param=20).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(10)
gtruth[:2] = 1
assert_array_equal(support, gtruth)
def test_mutual_info_classif():
X, y = make_classification(n_samples=100,
n_features=5,
n_informative=1,
n_redundant=1,
n_repeated=0,
n_classes=2,
n_clusters_per_class=1,
flip_y=0.0,
class_sep=10,
shuffle=False,
random_state=0)
# Test in KBest mode.
univariate_filter = SelectKBest(mutual_info_classif, k=2)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(mutual_info_classif, mode='k_best',
param=2).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(5)
gtruth[:2] = 1
assert_array_equal(support, gtruth)
# Test in Percentile mode.
univariate_filter = SelectPercentile(mutual_info_classif, percentile=40)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(mutual_info_classif,
mode='percentile',
param=40).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(5)
gtruth[:2] = 1
assert_array_equal(support, gtruth)
def test_select_percentile_regression_full():
# Test whether the relative univariate feature selection
# selects all features when '100%' is asked.
X, y = make_regression(n_samples=200,
n_features=20,
n_informative=5,
shuffle=False,
random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=100)
X_r = univariate_filter.fit(X, y).transform(X)
assert_best_scores_kept(univariate_filter)
X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=100).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.ones(20)
assert_array_equal(support, gtruth)
def test_nans():
# Assert that SelectKBest and SelectPercentile can handle NaNs.
# First feature has zero variance to confuse f_classif (ANOVA) and
# make it return a NaN.
X = [[0, 1, 0], [0, -1, -1], [0, .5, .5]]
y = [1, 0, 1]
for select in (SelectKBest(f_classif,
2), SelectPercentile(f_classif, percentile=67)):
ignore_warnings(select.fit)(X, y)
assert_array_equal(select.get_support(indices=True), np.array([1, 2]))
def test_select_percentile_regression():
# Test whether the relative univariate feature selection
# gets the correct items in a simple regression problem
# with the percentile heuristic
X, y = make_regression(n_samples=200,
n_features=20,
n_informative=5,
shuffle=False,
random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=25)
X_r = univariate_filter.fit(X, y).transform(X)
assert_best_scores_kept(univariate_filter)
X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=25).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
gtruth = np.zeros(20)
gtruth[:5] = 1
assert_array_equal(support, gtruth)
X_2 = X.copy()
X_2[:, np.logical_not(support)] = 0
assert_array_equal(X_2, univariate_filter.inverse_transform(X_r))
# Check inverse_transform respects dtype
assert_array_equal(X_2.astype(bool),
univariate_filter.inverse_transform(X_r.astype(bool)))
def test_scorefunc_multilabel():
# Test whether k-best and percentiles works with multilabels with chi2.
X = np.array([[10000, 9999, 0], [100, 9999, 0], [1000, 99, 0]])
y = [[1, 1], [0, 1], [1, 0]]
Xt = SelectKBest(chi2, k=2).fit_transform(X, y)
assert Xt.shape == (3, 2)
assert 0 not in Xt
Xt = SelectPercentile(chi2, percentile=67).fit_transform(X, y)
assert Xt.shape == (3, 2)
assert 0 not in Xt
def test_tied_pvalues():
# Test whether k-best and percentiles work with tied pvalues from chi2.
# chi2 will return the same p-values for the following features, but it
# will return different scores.
X0 = np.array([[10000, 9999, 9998], [1, 1, 1]])
y = [0, 1]
for perm in itertools.permutations((0, 1, 2)):
X = X0[:, perm]
Xt = SelectKBest(chi2, k=2).fit_transform(X, y)
assert Xt.shape == (2, 2)
assert 9998 not in Xt
Xt = SelectPercentile(chi2, percentile=67).fit_transform(X, y)
assert Xt.shape == (2, 2)
assert 9998 not in Xt
def test_no_feature_selected():
rng = np.random.RandomState(0)
# Generate random uncorrelated data: a strict univariate test should
# rejects all the features
X = rng.rand(40, 10)
y = rng.randint(0, 4, size=40)
strict_selectors = [
SelectFwe(alpha=0.01).fit(X, y),
SelectFdr(alpha=0.01).fit(X, y),
SelectFpr(alpha=0.01).fit(X, y),
SelectPercentile(percentile=0).fit(X, y),
SelectKBest(k=0).fit(X, y),
]
for selector in strict_selectors:
assert_array_equal(selector.get_support(), np.zeros(10))
X_selected = assert_warns_message(UserWarning,
'No features were selected',
selector.transform, X)
assert X_selected.shape == (40, 0)
from mrex.model_selection import cross_val_score
from mrex.pipeline import Pipeline
from mrex.preprocessing import StandardScaler
from mrex.svm import SVC
# #############################################################################
# Import some data to play with
X, y = load_iris(return_X_y=True)
# Add non-informative features
np.random.seed(0)
X = np.hstack((X, 2 * np.random.random((X.shape[0], 36))))
# #############################################################################
# Create a feature-selection transform, a scaler and an instance of SVM that we
# combine together to have an full-blown estimator
clf = Pipeline([('anova', SelectPercentile(chi2)),
('scaler', StandardScaler()), ('svc', SVC(gamma="auto"))])
# #############################################################################
# Plot the cross-validation score as a function of percentile of features
score_means = list()
score_stds = list()
percentiles = (1, 3, 6, 10, 15, 20, 30, 40, 60, 80, 100)
for percentile in percentiles:
clf.set_params(anova__percentile=percentile)
this_scores = cross_val_score(clf, X, y)
score_means.append(this_scores.mean())
score_stds.append(this_scores.std())
plt.errorbar(percentiles, score_means, np.array(score_stds))