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 single_fdr(alpha, n_informative, random_state):
X, y = make_regression(n_samples=150,
n_features=20,
n_informative=n_informative,
shuffle=False,
random_state=random_state,
noise=10)
with warnings.catch_warnings(record=True):
# Warnings can be raised when no features are selected
# (low alpha or very noisy data)
univariate_filter = SelectFdr(f_regression, alpha=alpha)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression,
mode='fdr',
param=alpha).fit(X, y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
num_false_positives = np.sum(support[n_informative:] == 1)
num_true_positives = np.sum(support[:n_informative] == 1)
if num_false_positives == 0:
return 0.
false_discovery_rate = (num_false_positives /
(num_true_positives + num_false_positives))
return false_discovery_rate
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_csr_preprocess_data():
# Test output format of _preprocess_data, when input is csr
X, y = make_regression()
X[X < 2.5] = 0.0
csr = sparse.csr_matrix(X)
csr_, y, _, _, _ = _preprocess_data(csr, y, True)
assert csr_.getformat() == 'csr'
def generate_dataset(n_train, n_test, n_features, noise=0.1, verbose=False):
"""Generate a regression dataset with the given parameters."""
if verbose:
print("generating dataset...")
X, y, coef = make_regression(n_samples=n_train + n_test,
n_features=n_features,
noise=noise,
coef=True)
random_seed = 13
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=n_train, test_size=n_test, random_state=random_seed)
X_train, y_train = shuffle(X_train, y_train, random_state=random_seed)
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)
y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train[:, None])[:, 0]
y_test = y_scaler.transform(y_test[:, None])[:, 0]
gc.collect()
if verbose:
print("ok")
return X_train, y_train, X_test, y_test
def test_f_regression():
# Test whether the F test yields meaningful results
# on a simple simulated regression problem
X, y = make_regression(n_samples=200,
n_features=20,
n_informative=5,
shuffle=False,
random_state=0)
F, pv = f_regression(X, y)
assert (F > 0).all()
assert (pv > 0).all()
assert (pv < 1).all()
assert (pv[:5] < 0.05).all()
assert (pv[5:] > 1.e-4).all()
# with centering, compare with sparse
F, pv = f_regression(X, y, center=True)
F_sparse, pv_sparse = f_regression(sparse.csr_matrix(X), y, center=True)
assert_array_almost_equal(F_sparse, F)
assert_array_almost_equal(pv_sparse, pv)
# again without centering, compare with sparse
F, pv = f_regression(X, y, center=False)
F_sparse, pv_sparse = f_regression(sparse.csr_matrix(X), y, center=False)
assert_array_almost_equal(F_sparse, F)
assert_array_almost_equal(pv_sparse, pv)
def test_linear_regression_multiple_outcome(random_state=0):
# Test multiple-outcome linear regressions
X, y = make_regression(random_state=random_state)
Y = np.vstack((y, y)).T
n_features = X.shape[1]
reg = LinearRegression()
reg.fit((X), Y)
assert reg.coef_.shape == (2, n_features)
Y_pred = reg.predict(X)
reg.fit(X, y)
y_pred = reg.predict(X)
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred, decimal=3)
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_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_preprocess_copy_data_no_checks(is_sparse, to_copy):
X, y = make_regression()
X[X < 2.5] = 0.0
if is_sparse:
X = sparse.csr_matrix(X)
X_, y_, _, _, _ = _preprocess_data(X, y, True,
copy=to_copy, check_input=False)
if to_copy and is_sparse:
assert not np.may_share_memory(X_.data, X.data)
elif to_copy:
assert not np.may_share_memory(X_, X)
elif is_sparse:
assert np.may_share_memory(X_.data, X.data)
else:
assert np.may_share_memory(X_, X)
def test_select_fwe_regression():
# Test whether the relative univariate feature selection
# gets the correct items in a simple regression problem
# with the fwe heuristic
X, y = make_regression(n_samples=200,
n_features=20,
n_informative=5,
shuffle=False,
random_state=0)
univariate_filter = SelectFwe(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, y).transform(X)
X_r2 = GenericUnivariateSelect(f_regression, mode='fwe',
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[:5], np.ones((5, ), dtype=np.bool))
assert np.sum(support[5:] == 1) < 2
def test_select_kbest_regression():
# Test whether the relative univariate feature selection
# gets the correct items in a simple regression problem
# with the k best heuristic
X, y = make_regression(n_samples=200,
n_features=20,
n_informative=5,
shuffle=False,
random_state=0,
noise=10)
univariate_filter = SelectKBest(f_regression, k=5)
X_r = univariate_filter.fit(X, y).transform(X)
assert_best_scores_kept(univariate_filter)
X_r2 = GenericUnivariateSelect(f_regression, mode='k_best',
param=5).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 compute_bench(alpha, n_samples, n_features, precompute):
lasso_results = []
lars_lasso_results = []
it = 0
for ns in n_samples:
for nf in n_features:
it += 1
print('==================')
print('Iteration %s of %s' % (it, max(len(n_samples),
len(n_features))))
print('==================')
n_informative = nf // 10
X, Y, coef_ = make_regression(n_samples=ns, n_features=nf,
n_informative=n_informative,
noise=0.1, coef=True)
X /= np.sqrt(np.sum(X ** 2, axis=0)) # Normalize data
gc.collect()
print("- benchmarking Lasso")
clf = Lasso(alpha=alpha, fit_intercept=False,
precompute=precompute)
tstart = time()
clf.fit(X, Y)
lasso_results.append(time() - tstart)
gc.collect()
print("- benchmarking LassoLars")
clf = LassoLars(alpha=alpha, fit_intercept=False,
normalize=False, precompute=precompute)
tstart = time()
clf.fit(X, Y)
lars_lasso_results.append(time() - tstart)
return lasso_results, lars_lasso_results
def compute_bench(samples_range, features_range):
it = 0
results = defaultdict(lambda: [])
max_it = len(samples_range) * len(features_range)
for n_samples in samples_range:
for n_features in features_range:
it += 1
print('====================')
print('Iteration %03d of %03d' % (it, max_it))
print('====================')
dataset_kwargs = {
'n_samples': n_samples,
'n_features': n_features,
'n_informative': n_features // 10,
'effective_rank': min(n_samples, n_features) / 10,
#'effective_rank': None,
'bias': 0.0,
}
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
X, y = make_regression(**dataset_kwargs)
gc.collect()
print("benchmarking lars_path (with Gram):", end='')
sys.stdout.flush()
tstart = time()
G = np.dot(X.T, X) # precomputed Gram matrix
Xy = np.dot(X.T, y)
lars_path_gram(Xy=Xy, Gram=G, n_samples=y.size, method='lasso')
delta = time() - tstart
print("%0.3fs" % delta)
results['lars_path (with Gram)'].append(delta)
gc.collect()
print("benchmarking lars_path (without Gram):", end='')
sys.stdout.flush()
tstart = time()
lars_path(X, y, method='lasso')
delta = time() - tstart
print("%0.3fs" % delta)
results['lars_path (without Gram)'].append(delta)
gc.collect()
print("benchmarking lasso_path (with Gram):", end='')
sys.stdout.flush()
tstart = time()
lasso_path(X, y, precompute=True)
delta = time() - tstart
print("%0.3fs" % delta)
results['lasso_path (with Gram)'].append(delta)
gc.collect()
print("benchmarking lasso_path (without Gram):", end='')
sys.stdout.flush()
tstart = time()
lasso_path(X, y, precompute=False)
delta = time() - tstart
print("%0.3fs" % delta)
results['lasso_path (without Gram)'].append(delta)
return results
if __name__ == "__main__":
list_n_samples = np.linspace(100, 10000, 5).astype(np.int)
list_n_features = [10, 100, 1000]
n_test = 1000
max_iter = 1000
noise = 0.1
alpha = 0.01
sgd_results = np.zeros((len(list_n_samples), len(list_n_features), 2))
elnet_results = np.zeros((len(list_n_samples), len(list_n_features), 2))
ridge_results = np.zeros((len(list_n_samples), len(list_n_features), 2))
asgd_results = np.zeros((len(list_n_samples), len(list_n_features), 2))
for i, n_train in enumerate(list_n_samples):
for j, n_features in enumerate(list_n_features):
X, y, coef = make_regression(n_samples=n_train + n_test,
n_features=n_features,
noise=noise,
coef=True)
X_train = X[:n_train]
y_train = y[:n_train]
X_test = X[n_train:]
y_test = y[n_train:]
print("=======================")
print("Round %d %d" % (i, j))
print("n_features:", n_features)
print("n_samples:", n_train)
# Shuffle data
idx = np.arange(n_train)
np.random.seed(13)
"""
print(__doc__)
from time import time
from scipy import sparse
from scipy import linalg
from mrex.datasets.samples_generator import make_regression
from mrex.linear_model import Lasso
# #############################################################################
# The two Lasso implementations on Dense data
print("--- Dense matrices")
X, y = make_regression(n_samples=200, n_features=5000, random_state=0)
X_sp = sparse.coo_matrix(X)
alpha = 1
sparse_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)
dense_lasso = Lasso(alpha=alpha, fit_intercept=False, max_iter=1000)
t0 = time()
sparse_lasso.fit(X_sp, y)
print("Sparse Lasso done in %fs" % (time() - t0))
t0 = time()
dense_lasso.fit(X, y)
print("Dense Lasso done in %fs" % (time() - t0))
print("Distance between coefficients : %s" %
scikit_results = []
glmnet_results = []
n = 20
step = 500
n_features = 1000
n_informative = n_features / 10
n_test_samples = 1000
for i in range(1, n + 1):
print('==================')
print('Iteration %s of %s' % (i, n))
print('==================')
X, Y, coef_ = make_regression(n_samples=(i * step) + n_test_samples,
n_features=n_features,
noise=0.1,
n_informative=n_informative,
coef=True)
X_test = X[-n_test_samples:]
Y_test = Y[-n_test_samples:]
X = X[:(i * step)]
Y = Y[:(i * step)]
print("benchmarking scikit-learn: ")
scikit_results.append(bench(ScikitLasso, X, Y, X_test, Y_test, coef_))
print("benchmarking glmnet: ")
glmnet_results.append(bench(GlmnetLasso, X, Y, X_test, Y_test, coef_))
plt.clf()
xx = range(0, n * step, step)