def test_DataLoad():
n = 10
d = 200
A = np.arange(n*d, dtype=np.float).reshape(n, d)
b = np.arange(n, dtype=np.float)
col_norm_0 = np.linalg.norm(A[:,0])
col_norm_last = np.linalg.norm(A[:,d-1])
B = np.arange(n*d, dtype=np.float).reshape(n, d)
prob = blitzl1.LassoProblem(B, b)
if prob._get_A_column_norm(0) != col_norm_0:
print "Dense data load failed (col_norm_0)"
if prob._get_A_column_norm(d-1) != col_norm_last:
print "Dense data load failed (col_norm_last)"
if prob._get_label_i(n-1) != b[n-1]:
print "Dense labels load failed"
A_float16 = np.array(A, dtype=np.float16)
b_float16 = np.array(b, dtype=np.float16)
prob = blitzl1.LassoProblem(A_float16, b_float16)
if prob._get_A_column_norm(0) != col_norm_0:
print "Dense float16 data load failed (col_norm_0)"
if prob._get_A_column_norm(d-1) != col_norm_last:
print "Dense float16 data load failed (col_norm_last)"
if prob._get_label_i(n-1) != b[n-1]:
print "Dense float16 labels load failed"
A_csc = sparse.csc_matrix(A)
prob = blitzl1.LassoProblem(A_csc, b)
if prob._get_A_column_norm(0) != col_norm_0:
print "CSC data load failed (col_norm_0)"
if prob._get_A_column_norm(d-1) != col_norm_last:
print "CSC data load failed (col_norm_last)"
if prob._get_label_i(n-1) != b[n-1]:
print "CSC labels load failed"
A_csr = sparse.csr_matrix(A)
prob = blitzl1.LassoProblem(A_csr, b)
if prob._get_A_column_norm(0) != col_norm_0:
print "CSR data load failed (col_norm_0)"
if prob._get_A_column_norm(d-1) != col_norm_last:
print "CSR data load failed (col_norm_last)"
if prob._get_label_i(n-1) != b[n-1]:
print "CSR labels load failed"
A_float16 = sparse.csr_matrix(A, dtype=np.float16)
prob = blitzl1.LassoProblem(A_float16, b)
diff = abs(prob._get_A_column_norm(d-1) - col_norm_last)
if diff > 1.0:
print "CSR float16 data load failed (col_norm_last)"
def test_SimpleLasso():
blitzl1.set_use_intercept(False)
blitzl1.set_tolerance(0.0)
blitzl1.set_verbose(False)
A = np.eye(4)
A[3, 3] = 2.0
A[2, 2] = 2.0
b = np.array([5., -2., 2., -6.])
A = sparse.csc_matrix(A)
prob = blitzl1.LassoProblem(A, b)
sol = prob.solve(1)
if not approx_equal(sol.x[0], 4.0) or not approx_equal(sol.x[3], -2.75):
print "test SimpleLasso basic failed"
blitzl1.set_use_intercept(True)
sol = prob.solve(1)
if not approx_equal(sol.intercept, -0.25):
print "test SimpleLasso intercept failed"
if not approx_equal(sol.objective_value, 9.75):
print "test SimpleLasso obj failed"
python_obj = sol.evaluate_loss(A, b) + np.linalg.norm(sol.x, ord=1)
if not approx_equal(sol.objective_value, python_obj):
print "test SimpleLasso python_obj failed"
def test_SmallLasso():
blitzl1.set_use_intercept(False)
blitzl1.set_tolerance(0.0)
blitzl1.set_verbose(False)
A = np.arange(20).reshape(5, 4)
b = np.arange(5)
A = sparse.csc_matrix(A)
prob = blitzl1.LassoProblem(A, b)
sol = prob.solve(2)
if not approx_equal(sol.objective_value, 0.4875):
print "test SmallLasso obj failed"
save_path = "/tmp/blitzl1_save_test"
sol.save(save_path)
sol2 = blitzl1.load_solution(save_path)
if not np.all(sol.x == sol2.x):
print "test SmallLasso save_x failed"
if sol.objective_value != sol2.objective_value:
print "test SmallLasso save_obj failed"
os.remove(save_path)
blitzl1.set_tolerance(0.1)
log_path = "/tmp/blitzl1_log_test/"
sol = prob.solve(5.0, log_directory=log_path)
log_point = 0
while True:
time_file = "%s/time.%d" % (log_path, log_point)
obj_file = "%s/obj.%d" % (log_path, log_point)
try:
time = float(open(time_file).read())
obj = float(open(obj_file).read())
except:
break
log_point += 1
if not approx_equal(obj, sol.objective_value):
print "test SmallLasso log_obj failed"
if time <= 0.0:
print "test SmallLasso log_time failed"
os.system("rm -r %s" % log_path)
def test_StatusMessage():
blitzl1.set_tolerance(0.0)
blitzl1.set_verbose(False)
n = 10
d = 10
A = np.arange(n*d, dtype=np.float).reshape(n, d)
b = np.arange(n, dtype=np.float)
prob = blitzl1.LassoProblem(A, b)
sol = prob.solve(2000.)
if sol.status != "reached machine precision":
print "test StatusMessage machine precision failed"
blitzl1.set_tolerance(0.1)
sol = prob.solve(2000.)
if sol.status != "reached stopping tolerance":
print "test StatusMessage stopping tolerance failed"
blitzl1.set_tolerance(0.0)
blitzl1.set_max_time(0.0)
sol = prob.solve(2000.)
if sol.status != "reached time limit":
print "test StatusMessage time limit failed"
import blitzl1 import sys import os import numpy as np from scipy import sparse blitzl1.set_verbose(True) blitzl1.set_tolerance(0.0) n = 100 d = 1000 A = np.random.randn(n, d) A = sparse.csc_matrix(A) b = np.random.randn(n) prob = blitzl1.LassoProblem(A, b) lammax = prob.compute_lambda_max() print "lammax is", lammax sol = prob.solve(lammax * 0.1) from IPython import embed embed()
def set_objective(self, X, y, lmbd):
self.X, self.y, self.lmbd = X, y, lmbd
blitzl1.set_use_intercept(False)
self.problem = blitzl1.LassoProblem(self.X, self.y)
names[start:end] = [(j, k) for k in range(j, p)]
tot += Xint_sub.getnnz()
start = end
end += Xint_sub.shape[1] - 1
indices = np.hstack(indices)
indices = indices.astype('int64')
Xint = sp.csc_matrix((np.ones(tot, dtype=np.int8), indices, indptr),
dtype=np.int8,
shape=(n, p * (p + 1) / 2))
# Run blitz on SNPs data with interactions
blitzl1.set_tolerance(args.tol)
blitzl1.set_verbose(False)
blitzl1.set_use_intercept(args.useBias)
prob = blitzl1.LassoProblem(Xint, y)
# Compute lambda_max
t0_lammax = time.time()
lammax = prob.compute_lambda_max()
t1_lammax = time.time()
csv_writer_preproc.writerow([t1_lammax - t0_lammax])
file_preproc.close()
# Define the values of lambda for which the solution will be computed
lam = [
lammax * pow(10,
np.log10(args.lambdaMinRatio) * t / args.nlambda)
for t in range(1, args.nlambda + 1)
]
tol=tol,
verbose=True,
strategy=3,
min_ws_size=min_ws_size,
screening=0)
dur_a5g = time.time() - t0
print("A5G time %.4f" % (dur_a5g))
beta = np.array(a5g_res[0])
gaps = a5g_res[2]
times = a5g_res[3]
print(beta[beta != 0])
from a5g.utils import primal, dual
R = y - X_new.dot(beta)
dual_scale = max(alpha, np.max(np.abs(X_new.T.dot(R))))
p_obj = primal(R, beta, alpha)
d_obj = dual(y, R / dual_scale, alpha, (y**2).sum())
print(p_obj - d_obj)
assert (p_obj - d_obj) < tol
t0 = time.time()
prob = blitzl1.LassoProblem(X_new, y)
blitzl1.set_use_intercept(True)
blitzl1.set_tolerance(tol)
sol = prob.solve(alpha)
print("Blitz time %.3f s" % (time.time() - t0))
beta_blitz = sol.x[sol.x != 0]
R = y - X_new.dot(sol.x)
p_obj_blitz = 0.5 * (R**2).sum() + alpha * norm(sol.x, ord=1)
# parameters
j_star = np.argmax(np.abs(X.T.dot(y)))
alpha_max = np.linalg.norm(X.T.dot(y), ord=np.inf)
n_alphas = 5
eps = 1e-3
alpha_ratio = eps**(1. / (n_alphas - 1))
# alphas = np.array([alpha_max * (alpha_ratio ** i) for i in range(0, n_alphas)])
max_iter = 5000
tol = 1e-8
scg = NO_SCREENING
X = csc_matrix(X)
tic = time.time()
intercept, sp_beta, sp_gap, sp_n_iters, _ =\
sp_lasso_path(X, y.copy(), [alpha_max / 100.], eps=tol, max_iter=max_iter,
screening=scg, j_star=j_star)
print "our time = ", time.time() - tic
from sklearn import linear_model
clf = linear_model.Lasso(alpha=alpha_max / 100. / n_samples,
fit_intercept=True)
clf.fit(X, y)
import blitzl1
blitzl1.set_use_intercept(1)
prob = blitzl1.LassoProblem(X, y)
sol = prob.solve(alpha_max / 100.)
print "intercept = ", intercept, clf.intercept_, sol.intercept
def set_objective(self, X, y, lmbd, fit_intercept):
self.X, self.y, self.lmbd = X, y, lmbd
blitzl1.set_use_intercept(False)
blitzl1.set_tolerance(0)
self.problem = blitzl1.LassoProblem(self.X, self.y)