def test_select_percentile_regression_full():
"""
Test whether the relative univariate feature selection
selects all features when '100%' is asked.
"""
X, Y = test_dataset_reg(n_samples=50, n_features=20, k=5, seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=100)
X_r = univariate_filter.fit(X, Y).transform(X)
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_select_percentile_regression_full():
"""
Test whether the relative univariate feature selection
selects all features when '100%' is asked.
"""
X, Y = test_dataset_reg(n_samples=50, n_features=20, k=5,
seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=100)
X_r = univariate_filter.fit(X, Y).transform(X)
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_select_fdr_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the fpr heuristic
"""
X, Y = test_dataset_reg(n_samples=50, n_features=20, k=5, seed=2)
univariate_filter = SelectFdr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fdr',
param=0.01).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_select_fdr_regression():
"""
Test whether the relative univariate feature selection
gets the correct items in a simple regression problem
with the fpr heuristic
"""
X, Y = test_dataset_reg(n_samples=50, n_features=20, k=5,
seed=2)
univariate_filter = SelectFdr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fdr',
param=0.01).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_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 = test_dataset_reg(n_samples=50, n_features=20, k=5, seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
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))
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 = test_dataset_reg(n_samples=50, n_features=20, k=5,
seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
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))
