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()
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)
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 fdr heuristic
"""
X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
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 = 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)
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 compute_bench(alpha, n_samples, n_features, precompute):
lasso_results = []
lars_lasso_results = []
n_test_samples = 0
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 "- benching Lasso"
clf = Lasso(alpha=alpha, fit_intercept=False)
tstart = time()
clf.fit(X, Y, precompute=precompute)
lasso_results.append(time() - tstart)
gc.collect()
print "- benching LassoLars"
clf = LassoLars(alpha=alpha, fit_intercept=False)
tstart = time()
clf.fit(X, Y, normalize=False, precompute=precompute)
lars_lasso_results.append(time() - tstart)
return lasso_results, lars_lasso_results
from scikits.learn.metrics import mean_square_error
from scikits.learn.datasets.samples_generator import make_regression
if __name__ == "__main__":
list_n_samples = np.linspace(100, 10000, 5).astype(np.int)
list_n_features = [10, 100, 1000]
n_test = 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))
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)
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 "benching lars_path (with Gram):",
sys.stdout.flush()
tstart = time()
G = np.dot(X.T, X) # precomputed Gram matrix
Xy = np.dot(X.T, y)
lars_path(X, y, Xy=Xy, Gram=G, method='lasso')
delta = time() - tstart
print "%0.3fs" % delta
results['lars_path (with Gram)'].append(delta)
gc.collect()
print "benching lars_path (without Gram):",
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 "benching lasso_path (with Gram):",
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 "benching lasso_path (without Gram):",
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