def lasso_classification(table, alpha=0.3):
'''
'''
from scikits.learn.linear_model import Lasso
X = table[:, 1:]
Y = table[:, 0]
# n_samples, n_features = 50, 200
# X = np.random.randn(n_samples, n_features)
# coef = 3*np.random.randn(n_features)
# coef[10:] = 0 # sparsify coef
# Y = np.dot(X, coef)
#
# # add noise
# Y += 0.01*np.random.normal((n_samples,))
# Split data in train set and test set
n_samples = X.shape[0]
items = np.random.permutation(n_samples)
training_items = items[:n_samples / 2]
testing_items = items[n_samples / 2:]
X_train, y_train = X[training_items], Y[training_items]
X_test, y_test = X[testing_items], Y[testing_items]
lasso = Lasso(alpha=alpha, fit_intercept=True)
lasso_fit = lasso.fit(X_train, y_train)
print lasso_fit.coef_
y_pred_lasso = lasso_fit.predict(X_test)
y_collapsed = np.zeros_like(y_pred_lasso)
collapsed_1 = y_pred_lasso >= 0.5
y_collapsed[collapsed_1] = 1
test = y_collapsed == y_test
return float(test.sum()) / test.shape[0]
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
y = np.dot(X, coef)
# add noise
y += 0.01 * np.random.normal((n_samples, ))
# Split data in train set and test set
n_samples = X.shape[0]
X_train, y_train = X[:n_samples / 2], y[:n_samples / 2]
X_test, y_test = X[n_samples / 2:], y[n_samples / 2:]
################################################################################
# Lasso
from scikits.learn.linear_model import Lasso
alpha = 0.1
lasso = Lasso(alpha=alpha)
y_pred_lasso = lasso.fit(X_train, y_train).predict(X_test)
print lasso
print "r^2 on test data : %f" % (
1 - np.linalg.norm(y_test - y_pred_lasso)**2 / np.linalg.norm(y_test)**2)
################################################################################
# ElasticNet
from scikits.learn.linear_model import ElasticNet
enet = ElasticNet(alpha=alpha, rho=0.7)
y_pred_enet = enet.fit(X_train, y_train).predict(X_test)
print enet
print "r^2 on test data : %f" % (
