def compute_bench(alpha, n_samples, n_features, precompute):
lasso_results = []
larslasso_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_dataset(
n_train_samples=ns, n_test_samples=n_test_samples,
n_features=nf, noise=0.1, n_informative = n_informative)
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)
larslasso_results.append(time() - tstart)
return lasso_results, larslasso_results
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_dataset(
n_train_samples=ns, n_test_samples=n_test_samples,
n_features=nf, noise=0.1, n_informative = n_informative)
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
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_train_samples': n_samples,
'n_test_samples': 2,
'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(**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
from scikits.learn.metrics import mean_square_error
from scikits.learn.datasets.samples_generator import make_regression_dataset
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_train, y_train, X_test, y_test, coef = make_regression_dataset(
n_train_samples=n_train, n_test_samples=n_test,
n_features=n_features, noise=noise)
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)
np.random.shuffle(idx)
X_train = X_train[idx]
y_train = y_train[idx]
std = X_train.std(axis=0)
mean = X_train.mean(axis=0)
from scikits.learn.datasets.samples_generator import make_regression_dataset
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_train, y_train, X_test, y_test, coef = make_regression_dataset(
n_train_samples=n_train,
n_test_samples=n_test,
n_features=n_features,
noise=noise)
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)
np.random.shuffle(idx)
X_train = X_train[idx]
y_train = y_train[idx]
std = X_train.std(axis=0)
import pylab as pl
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, X_test, Y_test, coef = make_regression_dataset(
n_train_samples=(i * step),
n_test_samples=n_test_samples,
n_features=n_features,
noise=0.1,
n_informative=n_informative)
print "benching scikit: "
scikit_results.append(bench(ScikitLasso, X, Y, X_test, Y_test, coef))
print "benching glmnet: "
glmnet_results.append(bench(GlmnetLasso, X, Y, X_test, Y_test, coef))
pl.clf()
xx = range(0, n * step, step)
pl.title('Lasso regression on sample dataset (%d features)' % n_features)
pl.plot(xx, scikit_results, 'b-', label='scikit-learn')
pl.plot(xx, glmnet_results, 'r-', label='glmnet')
pl.legend()
pl.xlabel('number of samples to classify')
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_train_samples': n_samples,
'n_test_samples': 2,
'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(**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
# Delayed import of pylab
import pylab as pl
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, X_test, Y_test, coef = make_regression_dataset(
n_train_samples=(i * step), n_test_samples=n_test_samples,
n_features=n_features, noise=0.1, n_informative=n_informative)
print "benching scikit: "
scikit_results.append(bench(ScikitLasso, X, Y, X_test, Y_test, coef))
print "benching glmnet: "
glmnet_results.append(bench(GlmnetLasso, X, Y, X_test, Y_test, coef))
pl.clf()
xx = range(0, n*step, step)
pl.title('Lasso regression on sample dataset (%d features)' % n_features)
pl.plot(xx, scikit_results, 'b-', label='scikit-learn')
pl.plot(xx, glmnet_results,'r-', label='glmnet')
pl.legend()
pl.xlabel('number of samples to classify')
pl.ylabel('time (in seconds)')
